SYSTEM AND METHOD FOR OBJECT RECOGNITION BASED ON THREE-DIMENSIONAL ADAPTIVE FEATURE DETECTORS

• US 20110188737A1
• Filed: 02/01/2010
• Published: 08/04/2011
• Est. Priority Date: 02/01/2010
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Motor Engineering & Manufacturing North America Incorporated (Toyota Motor Corporation)
• Inventors: James, Michael R., Prokhorov, Danil V.
• Granted Patent: US 8,687,898 B2
• Time in Patent Office: Days
• US Class Current: 382/154
• CPC Class Codes: G06F 18/00 Pattern recognition

Abstract

Method and system for imaging an object in three-dimensions, binning data of the imaged object into three dimensional bins, determining a density value p of the data in each bin, and creating receptive fields of three dimensional feature maps, including processing elements O, each processing element O of a same feature map having a same adjustable parameter, weight Wc1. The density values p are processed with the processing elements O to determine an output value o for at least each three dimensional location of the imaging of the object having a density value p above a predetermined threshold value. An object is classified by processing the output values o with a committee of classifiers, and the classification of the object is communicated.

Claims

1. A method, comprising:

imaging an object in three dimensions;

binning data of the imaged object into three dimensional bins;

determining a density value p of the data in each bin;

creating receptive fields of three dimensional feature maps, including processing elements O, each processing element O of a same feature map having a same adjustable parameter, weight Wc1;

processing the density values p with the processing elements O to determine an output value o for at least each three dimensional location of the imaging of the object having a density value p above a predetermined threshold value;

classifying the object by processing the output values o with a committee of classifiers; and

communicating the classification of the object.

2. The method according to claim 1, wherein the determining the density value p of the data in each bin is based on a viewing angle of the object, an index ind.

3. The method according to claim 2, further comprising:

normalizing the density value p of the data in each bin having a same index ind.

4. The method according to claim 1, wherein the committee of classifiers includes a cascading series of weak classifiers which are trained using an AdaBoost process.

5. The method according to claim 4, wherein

the processing the density values p with the processing elements O includes ranking the output values o and selecting maximum values M and recording a location of the maximum values M in the respective feature map, and

at least one of the weak classifiers is trained using the AdaBoost process with the selected maximum values M and the recorded locations of the maximum values M.

6. A computer readable medium including computer executable instructions, which when executed by a processor, cause a computer system to perform a method, the method comprising:

imaging an object in three-dimensions;

binning data of the imaged object into three dimensional bins;

determining a density value p of the data in each bin;

creating receptive fields of three dimensional feature maps, including processing elements O, each processing element O of a same feature map having a same adjustable parameter, weight Wc1;

processing the density values p with the processing elements O to determine an output value o for at least each three dimensional location of the imaging of the object having a density value p above a predetermined threshold value;

classifying the object by processing the output values o with a committee of classifiers; and

communicating the classification of the object.

7. The computer readable medium according to claim 6, wherein the determining the density value p of the data in each bin is based on a viewing angle of the object, an index ind.

8. The computer readable medium according to claim 7, the method further comprising:

normalizing the density value p of the data in each bin having a same index ind.

9. The computer readable medium according to claim 6, wherein the committee of classifiers includes a cascading series of weak classifiers which are trained using an AdaBoost process.

10. The computer readable medium according to claim 9, wherein

the processing the density values p with the processing elements O includes ranking the output values o and selecting maximum values M and recording a location of the maximum values M in the respective feature map, and

at least one of the weak classifiers is trained using the AdaBoost process with the selected maximum values M and the recorded locations of the maximum values M.

11. A computer system, comprising:

means for imaging an object in three dimensions;

means for binning data of the imaged object into three dimensional bins;

means for determining a density value p of the data in each bin;

means for creating receptive fields of three dimensional feature maps, including processing elements O, each processing element O of a same feature map having a same adjustable parameter, weight Wc1;

means for processing the density values p with the processing elements O to determine an output value o for at least each three dimensional location of the imaging of the object having a density value p above a predetermined threshold value;

means for classifying the object by processing the output values o with a committee of classifiers; and

means for communicating the classification of the object.

12. The computer system according to claim 11, wherein the means for determining determines the density value p of the data in each bin based on a viewing angle of the object, an index ind.

13. The computer system according to claim 12, further comprising:

means for normalizing the density value p of the data in each bin having a same index ind.

14. The computer readable medium according to claim 11, wherein the committee of classifiers includes a cascading series of weak classifiers which are trained using an AdaBoost process.

15. The computer readable medium according to claim 14, wherein

the means for processing processes the density values p with the processing elements O ranks the output values o and selects maximum values M and records a location of the maximum values M in the respective feature map, and

at least one of the weak classifiers is trained using the AdaBoost process with the selected maximum values M and the recorded locations of the maximum values M.