Adaptive template object classification system with a template generator

• US 20050271254A1
• Filed: 06/07/2004
• Published: 12/08/2005
• Est. Priority Date: 06/07/2004
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Hougen, Darrell
• Granted Patent: US 7,486,802 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/772 Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
• CPC Class Codes: G06V 20/182 Network patterns, e.g. roads or rivers
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

A method of performing object classification within a collision warning and countermeasure system (10) of a vehicle (12) includes the generation of an object detection signal in response to the detection of an object (52). An image detection signal is generated and includes an image representation of the object (52). The object detection signal is projected on an image plane (51) in response to the image detection signal to generate a fused image reference. A candidate template (55) is generated in response to the fused image reference. The candidate template (55) is validated. The object (52) is classified in response to the candidate template (55).

Claims

1. A method of performing object classification within a collision warning and countermeasure system of a vehicle comprising:

detecting at least one object and generating at least one object detection signal in response to said detection;

generating at least one image detection signal comprising an image representation of said at least one object;

projecting said at least one object detection signal on an image plane in response to said at least one image detection signal to generate at least one fused image reference;

generating at least one candidate template in response to said at least one fused image reference;

validating said at least one candidate template; and

classifying at least one of said at least one object in response to said at least one candidate template.

2. A method as in claim 1 further comprising:

comparing said at least one fused image reference with a plurality of validated object templates to select an approximately matching template;

determining a match level between said fused image reference and said matching template; and

adjusting a score level of said matching template in response to said at least one fused image reference.

3. A method as in claim 1 further comprising:

detecting a first object and generating a first object detection signal;

generating a first candidate template in response to said first object detection signal;

detecting a second object and generating a second object detection signal; and

classifying said second object in response to said first candidate template.

4. A method as in claim 1 further comprising refining an image location of said at least one candidate template.

5. A method as in claim 4 wherein in refining an image location comprises performing double window operations.

6. A method as in claim 5 wherein performing said double window operations comprises:

generating an inner window corresponding to the size and shape of said at least one object;

generating an outer window larger than and surrounding said inner window;

evaluating pixel intensities within said inner window to generate an inner window pixel value;

evaluating pixel intensities within said outer window to generate an outer window pixel value;

comparing said inner window pixel value with said outer window pixel value; and

adjusting image location of said at least one candidate in response to said comparison.

7. A method as in claim 1 further comprising scoring said at least one candidate template, said scoring comprising at least one of:

determining a frequency occurrence level;

comparing pixel intensity values;

comparing pixel contrasts between windows; and

comparing a candidate template with a validated template.

8. A collision warning and countermeasure system for a vehicle comprising:

at least one non-vision object detection sensor detecting at least one object and generating at least one object detection signal in response to said detection;

at least one image-generating sensor generating at least one image detection signal comprising an image representation of said at least one object;

a fusion device projecting said at least one object detection signal on an image plane in response to said at least one image detection signal to generate at least one fused image reference;

a template generator generating at least one candidate template in response to said at least one fused image reference; and

a controller validating said at least one candidate template and classifying said at least one object in response to said at least one candidate template.

9. A system as in claim 8 wherein said fusion device projects said at least one object detection signal in response to a registration model.

10. A system as in claim 9 wherein said registration model comprising a relative positions of said at least one non-vision sensor, said image-generating sensor, and ground.

11. A system as in claim 9 further comprising a template storage device storing a plurality of validated object templates.

12. A system as in claim 11 wherein said plurality of validated object templates are stored with an associated frequency occurrence level.

13. A system as in claim 11 wherein said controller periodically removes a validated object template from said template storage device when an associated frequency occurrence level is below a predetermined value.

14. A system as in claim 8 further comprising a comparator comparing said at least one fused image reference with a plurality of validated object templates to select an approximately matching template.

15. A system as in claim 14 wherein said controller increases frequency occurrence level of said matching template when a match level is greater than a predetermined level.

16. A system as in claim 8 further comprising a candidate template processor orienting said at least one candidate template at an unused fused image location within said fused image reference.

17. A system as in claim 8 further comprising a candidate template processor refining an image location of said at least one candidate template.

18. A system as in claim 17 wherein said candidate template processor in refining an image location uses double window operations.

19. A method of operating a collision warning and countermeasure system of a vehicle comprising:

detecting at least one object and generating at least one object detection signal in response to said detection;

generating at least one image detection signal comprising an image representation of said at least one object;

projecting said at least one object detection signal on an image plane in response to said at least one image detection signal and a registration model to generate at least one fused image reference;

generating at least one candidate template in response to said at least one fused image reference;

scoring said at least one candidate template;

validating said at least one candidate template in response to said score;

classifying at least one of said at least one object in response to said at least one candidate template; and

performing a countermeasure in response to said classification.

20. A method as in claim 19 further comprising:

detecting a first object and generating a first object detection signal;

generating a first candidate template in response to said first object detection signal;

detecting a second object and generating a second object detection signal; and

classifying said second object in response to said first candidate template.