High-performance sensor fusion architecture

• US 7,715,591 B2
• Filed: 04/24/2002
• Issued: 05/11/2010
• Est. Priority Date: 04/24/2002
• Status: Expired due to Fees

• Current Assignee: HRL Laboratories LLC (The Boeing Co.)
• Original Assignee: HRL Laboratories LLC (The Boeing Co.)
• Inventors: Srinivasa, Narayan, Boscolo, Riccardo, Owechko, Yuri, Medasani, Swarup
• Primary Examiner(s): PERUNGAVOOR, SATHYANARAYA V
• Application Number:
  US10/132,875
• Publication Number:
  US 20030204384A1
• Time in Patent Office: 2,939 Days
• Field of Search: 382/154, 382/104
• US Class Current: 382/104
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/20064 Wavelet transform [DWT]
• CPC Class Codes: G06T 2207/30268 Vehicle interior
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 10/431 Frequency domain transformation; Autocorrelation
• CPC Class Codes: G06V 10/809 of classification results, e.g. where the classifiers operate on the same input data
• CPC Class Codes: G06V 20/59 inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: H04N 2013/0081 Depth or disparity estimation from stereoscopic image signals
• CPC Class Codes: H04N 2013/0092 Image segmentation from stereoscopic image signals

Abstract

A vision-based system for automatically detecting the type of object within a specified area, such as the type of occupant within a vehicle is presented. The type of occupant can then be used to determine whether an airbag deployment system should be enabled or not. The system extracts different features, including wavelet features and/or a disparity map from images captured by image sensors. These features are then processed by classification algorithms to produce class confidences for various occupant types. The occupant class confidences are fused and processed to determine occupant type. In a preferred embodiment, image features from image edges, wavelet features, and disparity are used. Various classification algorithms may be implemented to classify the object. Use of the disparity map and/or wavelet features provides greater computational efficiency.

Claims

1. A computer implemented method of object detection comprising an act of causing a processor to perform operations of:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying operation is performed by at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the operation of performing data fusion comprises the operations of;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the operation of classifying image features comprises processing the image features with at least one classification algorithm; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

2. A computer implemented method of object detection comprising an act of causing a processor to perform operations of:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying operation is performed by at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the operation of performing data fusion comprises the operations of;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the operation of classifying image features comprises processing the image features with at least one classification algorithm;

wherein the operation of extracting image features comprises the operation of;

extracting wavelet coefficients of the at least one object occupying an area of the images; and

wherein the operation of classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

3. The method of claim 2, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems.

4. The method of claim 3, wherein the signals comprise airbag enable and disable signals.

5. The method of claim 4, wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

6. A computer implemented method of object detection comprising an act of causing a processor to perform operations of:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying operation is performed by at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the operation of performing data fusion comprises the operations of;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the operation of classifying image features comprises processing the image features with at least one classification algorithm;

wherein the operation of extracting image features comprises the operation of;

extracting wavelet coefficients of the at least one object occupying an area of the images; and

wherein the operation of classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein the operation of extracting image features further comprises the operations of;

detecting edges of the at least one object within the images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the operation of classifying the image features comprises processing the edge density map with at least one of the classification algorithms to produce object class confidence data.

7. The method of claim 6, wherein the operation of extracting image features further comprises the operations of:

receiving a stereoscopic pair of images of an area occupied by at least one object;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints; and

wherein the disparity constraints comprise consistency requirement constraints and local smoothness constraints, wherein the consistency requirement constraints are defined by

8. The method of claim 7, further comprising the operations of:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the operation of classifying the image features comprises processing the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

9. The method of claim 8, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems.

10. The method of claim 9, wherein the signals comprise airbag enable and disable signals.

11. The method of claim 10, wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

12. The method of claim 11, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

13. The method of claim 7, further comprising the operations of:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the operation of classifying the image features comprises processing the motion density map with at least one of the classification algorithms to produce object class confidence data.

14. The method of claim 13, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems.

15. The method of claim 14, wherein the signals comprise airbag enable and disable signals.

16. The method of claim 15, wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

17. The method of claim 16, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

18. A computer implemented method of object detection comprising an act of causing a processor to perform operations of:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying operation is performed by at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the operation of performing data fusion comprises the operations of;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as Outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the operation of classifying image features comprises processing the image features with at least one classification algorithm;

wherein the operation of extracting image features comprises the operation of;

extracting wavelet coefficients of the at least one object occupying an area of the images; and

wherein the operation of classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein the operation of extracting image features further comprises the operations of;

receiving a stereoscopic pair of images of an area occupied by at least one object;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints; and

wherein the disparity constraints comprise consistency requirement constraints and local smoothness constraints, wherein the consistency requirement constraints are defined by

19. The method of claim 18, wherein the operation of extracting image features further comprises the operations of:

detecting edges of the at least one object within the images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the operation of classifying the image features comprises processing the edge density map with at least one of the classification algorithms to produce object class confidence data.

20. The method of claim 19, further comprising the operations of:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the operation of classifying the image features comprises processing the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

21. The method of claim 20, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems.

22. The method of claim 21, wherein the signals comprise airbag enable and disable signals.

23. The method of claim 22, wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

24. The method of claim 23, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

25. The method of claim 19, further comprising the operations of:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the operation of classifying the image features comprises processing the motion density map with at least one of the classification algorithms to produce object class confidence data.

26. The method of claim 25, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems.

27. The method of claim 26, wherein the signals comprise airbag enable and disable signals.

28. The method of claim 27, wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

29. The method of claim 28, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

30. A computer implemented method of object detection comprising an act of causing a processor to perform operations of:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying operation is performed by at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the operation of performing data fusion comprises the operations of;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown

where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems;

wherein the signals comprise airbag enable and disable signals;

wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

31. A computer implemented method of object detection comprising an act of causing a processor to perform operations of:

receiving a stereoscopic pair of images of an area occupied by at least one object;

extracting image features from the images, with at least a portion of the image features being extracted by the operations of;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints;

iteratively using the subsequent estimate as the initial estimate in the operation of using the initial estimate to generate a subsequent estimate in order to generate further subsequent estimates of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using the disparity constraints until there is no change between the results of subsequent iterations, thereby generating a final estimate of the spatial disparities;

generating a disparity map of the area occupied by at least one object from the final estimate of the spatial disparities;

classifying the image features to produce object class confidence data, wherein the classifying operation is performed by at least two sub-classifiers and with at least a portion of the classifying being performed by processing the disparity map with at least one classification algorithm to produce object class confidence data; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the operation of performing data fusion comprises the operations of;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown.

32. The method of claim 31, wherein the operation of classifying image features comprises processing the image features with at least one classification algorithm.

33. The method of claim 32, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

34. The method of claim 31, wherein the operation of extracting image features further comprises the operations of:

detecting edges of the at least one object within the pair of images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the operation of classifying the image features comprises processing the edge density map with at least one of the classification algorithms to produce object class confidence data.

35. The method of claim 34, further comprising the operations of:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the operation of classifying the image features comprises processing the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

36. The method of claim 35, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems.

37. The method of claim 36, wherein the signals comprise airbag enable and disable signals.

38. The method of claim 37, wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

39. The method of claim 38, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

40. The method of claim 34, further comprising the operations of:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the operation of classifying the image features comprises processing the motion density map with at least one of the classification algorithms to produce object class confidence data.

41. The method of claim 40, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems.

42. The method of claim 41, wherein the signals comprise airbag enable and disable signals.

43. The method of claim 42, wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

44. The method of claim 43, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

45. The method of claim 31, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising an operation of processing the detected object estimate to provide signals to vehicle systems.

46. The method of claim 45, wherein the signals comprise airbag enable and disable signals.

47. The method of claim 46, wherein the method further comprises an operation of capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

48. The method of claim 47, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

49. A computer program product for object detection, the computer program product comprising means, stored on a computer readable medium, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the means for classifying image features comprises a means for processing the image features with at least one classification algorithm; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

50. A computer program product for object detection, the computer program product comprising means, stored on a computer readable medium, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the means for extracting image features comprises a means for;

extracting wavelet coefficients of the at least one object in the images; and

wherein the means for classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

51. A computer program product for object detection as set forth in claim 50, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

52. A computer program product for object detection as set forth in claim 51, wherein the signals comprise airbag enable and disable signals.

53. A computer program product for object detection as set forth in claim 52, wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

54. A computer program product for object detection, the computer program product comprising means, stored on a computer readable medium, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the means for extracting image features comprises a means for;

extracting wavelet coefficients of the at least one object in the images; and

wherein the means for classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein the means for extracting image features further comprises means for;

detecting edges of the at least one object within the images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the means for classifying the image features processes the edge density map with at least one of the classification algorithms to produce object class confidence data.

55. A computer program product for object detection as set forth in claim 54, wherein the means for extracting image features further comprises means for:

receiving a stereoscopic pair of images of an area occupied by at least one object;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints; and

wherein the disparity constraints comprise consistency requirement constraints and local smoothness constraints, wherein the consistency requirement constraints are defined by

56. A computer program product for object detection as set forth in claim 55, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

57. A computer program product for object detection as set forth in claim 56, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

58. A computer program product for object detection as set forth in claim 57, wherein the signals comprise airbag enable and disable signals.

59. A computer program product for object detection as set forth in claim 58, wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

60. A computer program product for object detection as set forth in claim 59, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

61. A computer program product for object detection as set forth in claim 54, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data.

62. A computer program product for object detection as set forth in claim 61, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

63. A computer program product for object detection as set forth in claim 62, wherein the signals comprise airbag enable and disable signals.

64. The computer program product of claim 63, wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

65. A computer program product for object detection as set forth in claim 64, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

66. A computer program product for object detection, the computer program product comprising means, stored on a computer readable medium, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the means for extracting image features comprises a means for;

extracting wavelet coefficients of the at least one object in the images; and

wherein the means for classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein the means for extracting image features further comprises means for;

receiving a stereoscopic pair of images of an area occupied by at least one object;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints; and

wherein the disparity constraints comprise consistency requirement constraints and local smoothness constraints, wherein the consistency requirement constraints are defined by

67. A computer program product for object detection as set forth in claim 66, wherein the means for extracting image features further comprises means for:

detecting edges of the at least one object within the images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the means for classifying the image features processes the edge density map with at least one of the classification algorithms to produce object class confidence data.

68. A computer program product for object detection as set forth in claim 67, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

69. A computer program product for object detection as set forth in claim 68, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

70. A computer program product for object detection as set forth in claim 69, wherein the signals comprise airbag enable and disable signals.

71. A computer program product for object detection as set forth in claim 70, wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

72. A computer program product for object detection as set forth in claim 71, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

73. A computer program product for object detection as set forth in claim 67, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data.

74. A computer program product for object detection as set forth in claim 73, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

75. A computer program product for object detection as set forth in claim 74, wherein the signals comprise airbag enable and disable signals.

76. A computer program product for object detection as set forth in claim 75, wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

77. A computer program product for object detection as set forth in claim 76, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

78. A computer program product for object detection, the computer program product comprising means, stored on a computer readable medium, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems;

wherein the signals comprise airbag enable and disable signals;

wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

79. A computer program product for object detection, the computer program product comprising means, stored on a computer readable medium, for:

receiving a stereoscopic pair of images of an area occupied by at least one object;

extracting image features from the images, with at least a portion of the image features being extracted by means for;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints;

iteratively using the subsequent estimate as the initial estimate in the means for using the initial estimate to generate a subsequent estimate in order to generate further subsequent estimates of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using the disparity constraints until there is no change between the results of subsequent iterations, thereby generating a final estimate of the spatial disparities;

generating a disparity map of the area occupied by at least one object from the final estimate of the spatial disparities;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers and with at least a portion of the classifying being performed by processing the disparity map with at least one classification algorithm to produce object class confidence data; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown.

80. A computer program product for object detection as set forth in claim 79, wherein the means for classifying image features processes the image features with at least one classification algorithm.

81. A computer program product for object detection as set forth in claim 80, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

82. A computer program product for object detection as set forth in claim 79, wherein the means for extracting image features further comprises means for:

detecting edges of the at least one object within the images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the means for classifying the image features processes the edge density map with at least one of the classification algorithms to produce object class confidence data.

83. A computer program product for object detection as set forth in claim 82, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

84. A computer program product for object detection as set forth in claim 83, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

85. A computer program product for object detection as set forth in claim 84, wherein the signals comprise airbag enable and disable signals.

86. A computer program product for object detection as set forth in claim 85, wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

87. A computer program product for object detection as set forth in claim 86, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

88. A computer program product for object detection as set forth in claim 79, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data.

89. A computer program product for object detection as set forth in claim 88, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

90. A computer program product for object detection as set forth in claim 89, wherein the signals comprise airbag enable and disable signals.

91. A computer program product for object detection as set forth in claim 90, wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

92. A computer program product for object detection as set forth in claim 91, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

93. A computer program product for object detection as set forth in claim 79, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

94. A computer program product for object detection as set forth in claim 93, wherein the signals comprise airbag enable and disable signals.

95. A computer program product for object detection as set forth in claim 94, wherein the computer program product further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

96. A computer program product for object detection as set forth in claim 95, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

97. An apparatus for object detection comprising a computer system including a processor, a memory coupled with the processor, an input coupled with the processor for receiving images, and an output coupled with the processor for outputting information based on an object estimation, wherein the computer system further comprises means, residing in its processor and memory, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein the means for classifying image features comprises a means for processing the image features with at least one classification algorithm; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

98. An apparatus for object detection comprising a computer system including a processor, a memory coupled with the processor, an input coupled with the processor for receiving images, and an output coupled with the processor for outputting information based on an object estimation, wherein the computer system further comprises means, residing in its processor and memory, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein means for extracting image features comprises a means for;

extracting wavelet coefficients of the at least one object in the images;

and wherein the means for classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

99. An apparatus for object detection as set forth in claim 98, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

100. An apparatus for object detection as set forth in claim 99, wherein the signals comprise airbag enable and disable signals.

101. An apparatus for object detection as set forth in claim 100, wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

102. An apparatus for object detection comprising a computer system including a processor, a memory coupled with the processor, an input coupled with the processor for receiving images, and an output coupled with the processor for outputting information based on an object estimation, wherein the computer system further comprises means, residing in its processor and memory, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein means for extracting image features comprises a means for;

extracting wavelet coefficients of the at least one object in the images;

and wherein the means for classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein the means for extracting image features further comprises means for;

detecting edges of the at least one object within the images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the means for classifying the image features processes the edge density map with at least one of the classification algorithms to produce object class confidence data.

103. An apparatus for object detection as set forth in claim 102, wherein the means for extracting image features further comprises means for:

receiving a stereoscopic pair of images of an area occupied by at least one object;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints; and

wherein the disparity constraints comprise consistency requirement constraints and local smoothness constraints, wherein the consistency requirement constraints are defined by

104. An apparatus for object detection as set forth in claim 103, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

105. An apparatus for object detection as set forth in claim 104, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

106. An apparatus for object detection as set forth in claim 105, wherein the signals comprise airbag enable and disable signals.

107. An apparatus for object detection as set forth in claim 106, wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

108. An apparatus for object detection as set forth in claim 107, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

109. An apparatus for object detection as set forth in claim 103, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data.

110. An apparatus for object detection as set forth in claim 109, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

111. An apparatus for object detection as set forth in claim 110, wherein the signals comprise airbag enable and disable signals.

112. An apparatus for object detection as set forth in claim 111, wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

113. An apparatus for object detection as set forth in claim 112, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

114. An apparatus for object detection comprising a computer system including a processor, a memory coupled with the processor, an input coupled with the processor for receiving images, and an output coupled with the processor for outputting information based on an object estimation, wherein the computer system further comprises means, residing in its processor and memory, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

wherein means for extracting image features comprises a means for;

extracting wavelet coefficients of the at least one object in the images;

and wherein the means for classifying the image features comprises processing the wavelet coefficients with at least one classification algorithm to produce object class confidence data; and

wherein the means for extracting image features further comprises means for;

receiving a stereoscopic pair of images of an area occupied by at least one object;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints; and

wherein the disparity constraints comprise consistency requirement constraints and local smoothness constraints, wherein the consistency requirement constraints are defined by

115. An apparatus for object detection as set forth in claim 114, wherein the means for extracting image features further comprises means for:

detecting edges of the at least one object within the images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the means for classifying the image features processes the edge density map with at least one of the classification algorithms to produce object class confidence data.

116. An apparatus for object detection as set forth in claim 115, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

117. An apparatus for object detection as set forth in claim 116, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

118. An apparatus for object detection as set forth in claim 117, wherein the signals comprise airbag enable and disable signals.

119. An apparatus for object detection as set forth in claim 118, wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

120. An apparatus for object detection as set forth in claim 119, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

121. An apparatus for object detection as set forth in claim 115, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data.

122. An apparatus for object detection as set forth in claim 121, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

123. An apparatus for object detection as set forth in claim 122, wherein the signals comprise airbag enable and disable signals.

124. An apparatus for object detection as set forth in claim 123, wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

125. An apparatus for object detection as set forth in claim 124, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

126. An apparatus for object detection comprising a computer system including a processor, a memory coupled with the processor, an input coupled with the processor for receiving images, and an output coupled with the processor for outputting information based on an object estimation, wherein the computer system further comprises means, residing in its processor and memory, for:

receiving images of an area occupied by at least one object;

extracting image features including wavelet features from the images;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown;

where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems;

wherein the signals comprise airbag enable and disable signals;

wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors; and

wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

127. An apparatus for object detection comprising a computer system including a processor, a memory coupled with the processor, an input coupled with the processor for receiving images, and an output coupled with the processor for outputting information based on an object estimation, wherein the computer system further comprises means, residing in its processor and memory, for:

receiving a stereoscopic pair of images of an area occupied by at least one object;

extracting image features from the images, with at least a portion of the image features being extracted by means for;

detecting pattern regions and non-pattern regions within each of the pair of images using a texture filter;

generating an initial estimate of spatial disparities between the pattern regions within each of the pair of images;

using the initial estimate to generate a subsequent estimate of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using disparity constraints;

iteratively using the subsequent estimate as the initial estimate in the means for using the initial estimate to generate a subsequent estimate in order to generate further subsequent estimates of the spatial disparities between the non-pattern regions based on the spatial disparities between the pattern regions using the disparity constraints until there is no change between the results of subsequent iterations, thereby generating a final estimate of the spatial disparities;

generating a disparity map of the area occupied by at least one object from the final estimate of the spatial disparities;

classifying the image features to produce object class confidence data, wherein the classifying means use at least two sub-classifiers and with at least a portion of the classifying being performed by processing the disparity map with at least one classification algorithm to produce object class confidence data; and

performing data fusion on the object class confidence data to produce a detected object estimate, wherein the means for performing data fusion comprises the means for;

initially training the sub-classifiers in a supervised way by using the image features as inputs to the sub-classifiers and by using correct decisions known a priori as outputs of the sub-classifiers;

training a fusion classifier by using confidence values generated by the trained sub-classifiers as inputs to the fusion classifier and by using correct decisions known a priori as outputs of the fusion classifier; and

using the trained sub-classifiers and trained fusion classifier to perform data fusion to produce a detected object estimate when the correct decisions are unknown.

128. An apparatus for object detection as set forth in claim 127, wherein the means for classifying image features processes the image features with at least one classification algorithm.

129. An apparatus for object detection as set forth in claim 128, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

130. An apparatus for object detection as set forth in claim 127, wherein the means for extracting image features further comprises means for:

detecting edges of the at least one object within the images;

masking the edges with a background mask to find important edges;

calculating edge pixels from the important edges; and

producing edge density maps from the important edges, the edge density map providing the image features, and wherein the means for classifying the image features processes the edge density map with at least one of the classification algorithms to produce object class confidence data.

131. An apparatus for object detection as set forth in claim 130, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data, which is used independently of the data fusion to produce an independent detected object estimate.

132. An apparatus for object detection as set forth in claim 131, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

133. An apparatus for object detection as set forth in claim 132, wherein the signals comprise airbag enable and disable signals.

134. An apparatus for object detection as set forth in claim 133, wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

135. An apparatus for object detection as set forth in claim 134, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

136. An apparatus for object detection as set forth in claim 130, further comprising means for:

detecting motion of the at least one object within the images;

calculating motion pixels from the motion; and

producing motion density maps from the motion pixels, the motion density map providing the image features; and

wherein the means for classifying the image features processes the motion density map with at least one of the classification algorithms to produce object class confidence data.

137. An apparatus for object detection as set forth in claim 136, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

138. An apparatus for object detection as set forth in claim 137, wherein the signals comprise airbag enable and disable signals.

139. An apparatus for object detection as set forth in claim 138, wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

140. An apparatus for object detection as set forth in claim 139, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.

141. An apparatus for object detection as set forth in claim 127, where the at least one object comprises a vehicle occupant and the area comprises a vehicle occupancy area, and further comprising a means for processing the detected object estimate to provide signals to vehicle systems.

142. An apparatus for object detection as set forth in claim 141, wherein the signals comprise airbag enable and disable signals.

143. An apparatus for object detection as set forth in claim 142, wherein the apparatus further comprises a means for capturing images from a sensor selected from a group consisting of CMOS vision sensors and CCD vision sensors.

144. An apparatus for object detection as set forth in claim 143, wherein at least one of the classification algorithms is selected from the group consisting of a trained C5 decision tree, a trained Nonlinear Discriminant Analysis network, and a trained Fuzzy Aggregation Network.