Selective color processing for vision systems that enables optimal detection and recognition

• US 9,111,355 B1
• Filed: 03/11/2014
• Issued: 08/18/2015
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: HRL Laboratories LLC (The Boeing Co.)
• Original Assignee: HRL Laboratories LLC (The Boeing Co.)
• Inventors: Chen, Yang, Cheng, Shinko Y., Khosla, Deepak, Kim, Kyungnam, Jeong, Changsoo S., Zhang, Lei, Honda, Alexander L
• Primary Examiner(s): Tran, Phuoc
• Application Number:
  US14/205,327
• Time in Patent Office: 525 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

Described is a system for selective color processing for vision systems. The system receives a multi-band image as input. As an optional step, the multi-band image is preprocessed, and a transformation is performed to transform the multi-band image into a color space. A metric function is applied to the transformed image to generate a distance map comprising intensities which vary based on a similarity between an intensity of a pixel color and an intensity of a target color. A contrast enhancement process is applied to the distance map to normalize the distance map to a range of values. The range of values is expanded near the intensity of the target color. Finally, an output response map for the target color of interest is generated, such that the output response map has high responses in regions which are similar to the target color to aid in detection and recognition processes.

Claims

1. A system for selective color processing, the system comprising:

one or more processors and a non-transitory computer-readable medium having executable instructions encoded thereon such that when executed, the one or more processors perform operations of;

receiving a multi-band image as input;

applying a metric function to the multi-band image to generate a distance map, wherein the distance map comprises a plurality of intensities which vary based on a similarity between an intensity of a pixel color and an intensity of a target color of interest;

applying a contrast enhancement process to the distance map to normalize the distance map to a range of values;

expanding the range of values of the distance map near the intensity of the target color of interest; and

generating an output response map for the target color of interest having value ranges to aid in detection and recognition processes, wherein the output response map comprises a plurality of regions, and wherein the output response map has high responses in regions which contain colors similar to the target color of interest in the multi-band image.

2. The system as set forth in claim 1, wherein the one or more processors further perform an operation of outputting a scalar distance in the color space between each pixel color in the multi-band image and the target color of interest.

3. The system as set forth in claim 2, wherein the one or more processors further perform an operation of expanding the range of values via a tunable sensitivity parameter.

4. The system as set forth in claim 3, wherein the one or more processors further perform an operation of applying an exponential function to the distance map, such that the intensity of the target color of interest in the multi-band image maps to one, and pixel colors with a larger distance to the target color of interest map closer to zero.

5. The system as set forth in claim 4, wherein the one or more processors further perform an operation of compressing the value ranges of the output response map for regions of the multi-band image with pixel colors that are non-similar to the target color of interest and expanding the value ranges of the output response map for pixel colors that are similar to the target color of interest.

6. The system as set forth in claim 1, wherein, prior to applying the metric function, the one or more processors further perform an operation of preprocessing the multi-band image and performing a transformation to transform the multi-band image into a preferred color space, resulting in a transformed image having pixel colors, wherein the output response map has high responses in regions which contain colors similar to the target color of interest in the transformed image.

7. The system as set forth in claim 6, wherein the one or more processors further perform an operation of applying an exponential function to the distance map, such that the intensity of the target color of interest in the transformed image maps to one, and pixel colors with a larger distance to the target color of interest map closer to zero.

8. The system as set forth in claim 7, wherein the one or more processors further perform an operation of compressing the value ranges of the output response map for regions of the transformed image with pixel colors that are non-similar to the target color of interest and expanding the value ranges of the output response map for pixel colors that are similar to the target color of interest.

9. A computer-implemented method for selective color processing, comprising an act of:

causing one or more processors to execute instructions stored on a non-transitory memory such that upon execution, the one or more processors performs operations of;

receiving a multi-band image as input;

applying a metric function to the multi-band image to generate a distance map, wherein the distance map comprises a plurality of intensities which vary based on a similarity between an intensity of a pixel color and an intensity of a target color of interest;

applying a contrast enhancement process to the distance map to normalize the distance map to a range of values;

expanding the range of values of the distance map near the intensity of the target color of interest; and

generating an output response map for the target color of interest having value ranges to aid in detection and recognition processes, wherein the output response map comprises a plurality of regions, and wherein the output response map has high responses in regions which contain colors similar to the target color of interest in the multi-band image.

10. The method as set forth in claim 9, wherein the data processor further performs an operation of outputting a scalar distance in the color space between each pixel color in the multi-band image and the target color of interest.

11. The method as set forth in claim 10, wherein the data processor further performs an operation of expanding the range of values via a tunable sensitivity parameter.

12. The method as set forth in claim 11, wherein the data processor further performs an operation of applying an exponential function to the distance map, such that the intensity of the target color of interest in the multi-band image maps to one, and pixel colors with a larger distance to the target color of interest map closer to zero.

13. The method as set forth in claim 12, wherein the data processor further performs an operation of compressing the value ranges of the output response map for regions of the multi-band image with pixel colors that are non-similar to the target color of interest and expanding the value ranges of the output response map for pixel colors that are similar to the target color of interest.

14. The method as set forth in claim 9, wherein the data processor further performs an operation of preprocessing the multi-band image and performing a transformation to transform the multi-band image into a preferred color space, resulting in a transformed image having pixel colors, wherein the output response map has high responses in regions which contain colors similar to the target color of interest in the transformed image.

15. The method as set forth in claim 14, wherein the data processor further performs an operation of applying an exponential function to the distance map, such that the intensity of the target color of interest in the transformed image maps to one, and pixel colors with a larger distance to the target color of interest map closer to zero.

16. The method as set forth in claim 15, wherein the data processor further performs an operation of compressing the value ranges of the output response map for regions of the transformed image with pixel colors that are non-similar to the target color of interest and expanding the value ranges of the output response map for pixel colors that are similar to the target color of interest.

17. A computer program product for selective color processing, the computer program product comprising computer-readable instructions stored on a non-transitory computer-readable medium that are executable by a computer having a processor for causing the processor to perform operations of:

receiving a multi-band image as input;

applying a metric function to the multi-band image to generate a distance map, wherein the distance map comprises a plurality of intensities which vary based on a similarity between an intensity of a pixel color and an intensity of a target color of interest;

applying a contrast enhancement process to the distance map to normalize the distance map to a range of values;

expanding the range of values of the distance map near the intensity of the target color of interest; and

generating an output response map for the target color of interest having value ranges to aid in detection and recognition processes, wherein the output response map comprises a plurality of regions, and wherein the output response map has high responses in regions which contain colors similar to the target color of interest in the multi-band image.

18. The computer program product as set forth in claim 17, further comprising instructions for causing the processor to perform an operation of outputting a scalar distance in the color space between each pixel color in the multi-band image and the target color of interest.

19. The computer program product as set forth in claim 18, further comprising instructions for causing the processor to perform an operation of expanding the range of values via a tunable sensitivity parameter.

20. The computer program product as set forth in claim 19, further comprising instructions for causing the processor to perform an operation of applying an exponential function to the distance map, such that the intensity of the target color of interest in the multi-band image maps to one, and pixel colors with a larger distance to the target color of interest map closer to zero.

21. The computer program product as set forth in claim 20, further comprising instructions for causing the processor to perform an operation of compressing the value ranges of the output response map for regions of the multi-band image with pixel colors that are non-similar to the target color of interest and expanding the value ranges of the output response map for pixel colors that are similar to the target color of interest.

22. The computer program product as set forth in claim 17, further comprising instructions for causing the processor to perform an operation of preprocessing the multi-band image and performing a transformation to transform the multi-band image into a preferred color space, resulting in a transformed image having pixel colors, wherein the output response map has high responses in regions which contain colors similar to the target color of interest in the transformed image.

23. The computer program product as set forth in claim 22, further comprising instructions for causing the processor to perform an operation of applying an exponential function to the distance map, such that the intensity of the target color of interest in the transformed image maps to one, and pixel colors with a larger distance to the target color of interest map closer to zero.

24. The computer program product as set forth in claim 23, further comprising instructions for causing the processor to perform an operation of compressing the value ranges of the output response map for regions of the transformed image with pixel colors that are non-similar to the target color of interest and expanding the value ranges of the output response map for pixel colors that are similar to the target color of interest.