Apparatus and methods for performing electronic scene analysis and enhancement

• US 5,768,415 A
• Filed: 09/08/1995
• Issued: 06/16/1998
• Est. Priority Date: 09/08/1995
• Status: Expired due to Term

• Current Assignee: AT&T Corporation (AT&T, Inc.)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Jagadish, Hosagrahar Visvesvaraya, Petajan, Eric David
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Mehta, Bhavesh
• Application Number:
  US08/525,932
• Time in Patent Office: 1,012 Days
• Field of Search: 382/154, 382/285, 382/284, 382/294, 395/121, 395/122, 395/127, 395/125, 348/42, 348/43, 348/46, 348/578, 348/580, 345/452, 345/139, 345/419
• US Class Current: 382/154
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 7/55 from multiple images
• 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 2201/12 Acquisition of 3D measurements of objects
• CPC Class Codes: H04N 13/128 Adjusting depth or disparity

Abstract

Apparatus and methods are provided for analyzing and enhancing a received data signal representing one or more views of a captured scene. The received data signal includes a plurality of data points. Each view includes a plurality of image points. Ones of the plurality of data points are representative of ones of the plurality of image points. A plurality of data sets are identified wherein each one of the data sets includes ones of the plurality of data points. Ones of the identified data sets are compared with one or more standard values and, in response thereto, are enhanced selectively to generate an output signal representing a processed 3-D scene estimate.

Claims

1. An apparatus for generating an output signal representing a 3-D scene estimate, said apparatus comprising:

means for receiving at least one input signal representing a view of a scene, said view including a plurality of image points and said input signal including a plurality of data points, at least one of said data points including scene and importance information, wherein ones of said plurality of data points are representative of ones of said plurality of image points;

storage for storing said scene and importance information; and

processing means for identifying a plurality of data sets wherein each one of said plurality of data sets includes ones of said plurality of data points, ranking one or more of said plurality of identified data sets using said stored scene and importance information, and in response to said ranking, enhancing selectively one or more of said plurality of identified output data sets to generate said output signal.

2. The apparatus as set forth in claim 1 wherein said processing means includes at least one processing unit.

3. The apparatus as set forth in claim 1 further including means for storing a plurality of processing system instructions for directing said processing means to process said input signal to produce said output signal representing said 3-D scene estimate.

4. The apparatus as set forth in claim 3 wherein said processing means is further operable to retrieve and execute selected ones of said plurality of processing system instructions.

5. The apparatus as set forth in claim 1 wherein said processing means further includes means for determining an error value for one or more of said plurality of data points.

6. The apparatus as set forth in claim 5 further including means for applying selectively one or more of a plurality of records of a priori scene information to one or more of said plurality of data points to reduce said error value.

7. The apparatus as set forth in claim 5 further including means for comparing selectively one or more of a plurality of records of ranking/importance data to said error value associated with one or more of said plurality of data points.

8. The apparatus as set forth in claim 5 further including means for determining ranking/importance data associated with one or more of said plurality of data points.

9. The apparatus as set forth in claim 1 wherein said input signal is received from a single video data capturing device and said apparatus further includes means for receiving additional information which includes at least one of a focal length value representing the focal length of one or more lenses of said single video device, an aperture value representing the aperture size of one ore more lenses of said single video device, and a shutter value representing the shutter speed of said single video device.

10. The apparatus as set forth in claim 9 further including means for utilizing selectively said additional information to estimate a 3-D scene.

11. The apparatus as set forth in claim 1 further including means for estimating a 3-D scene by selectively utilizing received positional data relating to at least one of size, shape, orientation, range of depth and texture of ones of said plurality of data sets.

12. A method for generating an output signal representing a 3-D scene estimate, said method comprising the steps of:

receiving a least one input signal representing a view of a scene, said view including a plurality of image points and said input signal including a plurality of data points, wherein ones of said plurality of data points are representative of ones of said plurality of image points, at least one of said data points including scene and importance information;

identifying a plurality of data sets wherein each one of said plurality of data sets includes ones of said plurality of data points; and

comparing one or more of said plurality of identified data sets with one or more standard values, each of said identified data sets including at least one data point including scene and importance information, said scene and importance information being used to compare said identified data sets with said standard values and, in response to said comparison, enhancing selectively one or more of said plurality of identified data sets to generate said output signal.

13. The method as set forth in claim 12 wherein said comparing step further includes the step of determining an error value for one or more of said plurality of data points.

14. The method as set forth in claim 13 further including the step of applying selectively one or more of a plurality of records of a priori scene information to one or more of said plurality of data points to reduce said error value.

15. The method as set forth in claim 13 further includes the step of utilizing selectively said additional information to estimate a 3-D scene.

16. The method as set forth in claim 13 further including the step of determining ranking/importance data associated with one or more of said plurality of data points.

17. The method as set forth in claim 16 further including the step of comparing selectively one or more of a plurality of records of ranking/importance data to said error value associated with one or more of said plurality of data points.

18. The method as set forth in claim 12 wherein said input signal is produced by a single video data capturing device and said method further includes the step of receiving additional information which includes at least one of a focal length value representing the focal length of one or more lenses of said single video device, an aperture value representing the aperture size of one or more lenses of said single video device, and a shutter value representing the shutter speed of said single video device.

19. The method as set forth in claim 12 further including the step of estimating a 3-D scene by selectively utilizing received positional data relating to at least one of size, shape, orientation, range of depth and texture of ones of said plurality of data sets.

20. A method for generating an output signal representing a 3-D scene estimate, said method comprising the steps of:

receiving at least one input signal representing a view of a scene, said view including a plurality of image points and said input signal including a plurality of data points, wherein ones of said plurality of data points are representative of ones of said plurality of image points;

determining an error value for one or more of said plurality of data points;

determining ranking/importance data associated with one or more of said plurality of data points;

masking selectively ones of said plurality of data points when said ranking/importance data and said error value associated with one or more of said plurality of data points is relatively low and relatively high, respectively, to reduce said error value;

processing ones of said plurality of data points when said ranking/importance value and said error value associated with one or more of said plurality of data points are both relatively high to reduce said error value; and

generating said output signal.

21. An apparatus for generating an output signal representing a 3-D scene estimate, said apparatus comprising:

means for receiving at least one input signal representing a view of a scene, said view including a plurality of image points and said input signal including a plurality of data points, wherein ones of said plurality of data points are representative of ones of said plurality of image points;

processing means for identifying a plurality of data sets wherein each one of said plurality of data sets includes ones of said plurality of data points, ranking one or more of said plurality of identified data sets, and in response to said ranking, enhancing selectively one or more of said plurality of identified data sets to generate said output signal, said processing means further including means for determining an error value for one or more of said plurality of data points, said error value associated with said plurality of data points being relatively high, said processing means further including means for masking selectively ones of said plurality of data points to reduce said error value; and

means for determining ranking/importance data associated with one or more of said plurality of data points, said ranking/importance value associated with one or more of said plurality of data points being relatively low.

22. The apparatus as set forth in claim 21 further including means for retrieving visual masking data from a storage device.

23. An apparatus for generating an output signal representing a 3-D scene estimate, said apparatus comprising:

means for receiving at least one input signal representing a view of a scene, said view including a plurality of image points and said input signal including a plurality of data points, wherein ones of said plurality of data points are representative of ones of said plurality of image points;

processing means for identifying a plurality of data sets wherein each one of said plurality of data sets includes ones of said plurality of data points, ranking one or more of said plurality of identified data sets, and in response to said ranking, enhancing selectively one or more of said plurality of identified data sets to generate said output signal, said processing means further including means for determining an error value for one or more of said plurality of data points, said error value associated with one or more of said plurality of data points being relatively high, said processing means being operative to further process ones of said plurality of data points to reduce said error value; and

means for determining ranking/importance data associated with one or more of said plurality of data points, said ranking/importance value associated with one or more of said plurality of data points being relatively high.

24. An apparatus for generating an output signal representing a 3-D scene estimate, said apparatus comprising:

means for receiving at least one input signal representing a view of a scene, said view including a plurality of image points and said input signal including a plurality of data points, wherein ones of said plurality of data points are representative of ones of said plurality of image points;

processing means for identifying a plurality of data sets wherein each one of said plurality of data sets includes ones of said plurality of data points, ranking one or more of said plurality of identified data sets, and in response to said ranking, enhancing selectively one or more of said plurality of identified data sets to generate said output signal, said processing means further including means for determining an error value for one or more of said plurality of data points, said error value associated with one or more of said plurality of data points being relatively low, said processing means being operative to further process ones of said plurality of data points to reduce said error value; and

means for determining ranking/importance data associated with one or more of said plurality of data points.

25. A method for generating an output signal representing a 3-D scene estimate, said method comprising the steps of:

receiving at least one input signal representing a view of a scene, said view including a plurality of image points and said input signal including a plurality of data points, wherein ones of said plurality of data points are representative of ones of said plurality of image points;

identifying a plurality of data sets wherein each one of said plurality of data sets includes ones of said plurality of data points;

comparing one or more of said plurality of identified data sets with one or more standard values and, in response to said comparison, enhancing selectively one or more of said plurality of identified data sets to generate said output signal, said comparing step further including the step of determining an error value for one or more of said plurality of data points, said error value associated with one or more of said plurality of data points being relatively high;

determining ranking/importance data associated with one or more of said plurality of data points, said ranking/importance data associated with one or more of said plurality of data points being relatively low; and

masking selectively ones of said plurality of data points to reduce said error value.

26. The method as set forth in claim 25 further including the step of retrieving visual masking data from a storage device.

27. A method for generating an output signal representing a 3-D scene estimate, said method comprising the steps of:

receiving at least one input signal representing a view of a scene, said view including a plurality of image points and said input signal including a plurality of data points, wherein ones of said plurality of data points are representative of ones of said plurality of image points;

identifying a plurality of data sets wherein each one of said plurality of data sets includes ones of said plurality of data points;

comparing one or more of said plurality of identified data sets with one or more standard values and, in response to said comparison, enhancing selectively one or more of said plurality of identified data sets to generate said output signal, said comparing step further including the step of determining an error value for one or more of said plurality of data points, said error value associated with one or more of said plurality of data points being relatively high;

determining ranking/importance data associated with one or more of said plurality of data points, said ranking/importance data associated with one or more of said plurality of data points being relatively high; and

further processing ones of said plurality of data points to reduce said error value.