SHORT-TIME STOPPING DETECTION FROM RED LIGHT CAMERA EVIDENTIARY PHOTOS

• US 20150332588A1
• Filed: 05/15/2014
• Published: 11/19/2015
• Est. Priority Date: 05/15/2014
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Bulan, Orhan, Burry, Aaron M., Loce, Robert P.
• Granted Patent: US 9,685,079 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

A method for detecting a vehicle running a stop signal includes acquiring at least two evidentiary images of a candidate violating vehicle captured from at least one camera monitoring an intersection. The method includes extracting feature points in each of the at least two evidentiary images. The method includes computing feature descriptors for each of the extracted feature points. The method includes determining a correspondence between feature points having matching feature descriptors at different locations in the at least two evidentiary images. The method includes extracting at least one attribute for each correspondence. The method includes determining if the candidate violating vehicle is in violation of running the stop signal using the extracted attribute.

Claims

1. A method to detect a vehicle running a stop signal, the method comprising:

acquiring at least two evidentiary images of a candidate violating vehicle captured from at least one camera monitoring an intersection;

extracting feature points in each of the at least two evidentiary images;

computing feature descriptors for each of the extracted feature points;

determining a correspondence between feature points having matching feature descriptors at different locations in the at least two evidentiary images;

extracting at least one attribute for each correspondence;

determining if the candidate violating vehicle is in violation of running the stop signal using the extracted attribute.

2. The method of claim 1, wherein the determining if the candidate violating vehicle is in violation of running the stop signal includes:

using the extracted attribute, determining if the each correspondence belongs to one of a spurious match and a true match;

for each correspondence belonging to a true match, comparing the attribute to a threshold; and

,

classifying the candidate violating vehicle as belonging to one of a violating vehicle and a non-violating vehicle based on the comparing.

3. The method of claim 2, wherein the classifying includes:

in response to the angle meeting and exceeding the predetermined threshold, classifying the candidate violating vehicle as belonging to a non-violating vehicle, and

in response to the angle not meeting the predetermined threshold, classifying the candidate violating vehicle as belonging to a violating vehicle.

4. The method of claim 1, wherein the attribute includes a length of a line connecting locations of the matching feature points in the at least two evidentiary images and the threshold includes a predetermined length.

5. The method of claim 4, wherein the length of the line is computed using the equation L=√

{square root over ((x₂−

x₁)²+(y₂−

y₁)²)}{square root over ((x₂−

x₁)²+(y₂−

y₁)²)}, where (x₁,y₁) is a location of a feature point in a first image and (x₂,y₂) is a location of a matching feature point in a second image.

6. The method of claim 4, further comprising:

in response to the length meeting and exceeding the predetermined threshold, classifying the candidate violating vehicle as belonging to a violating vehicle, and

in response to the length not meeting the predetermined threshold, classifying the candidate violating vehicle as belonging to a non-violating vehicle.

7. The method of claim 1, where the attribute includes an angle formed between a first line and a second line and the threshold includes a predetermined angle, the first line extending between locations of the matching feature points in the at least two evidentiary images and the second line being coincident along a road direction that the candidate violating vehicle is expected to travel through the intersection.

8. The method of claim 6, wherein the angle of the line is computed using the equation

9. The method of claim 1 further comprising:

defining a first region of interest (ROI) located before the intersection in a first of the at least two images;

determining a first location of a first one in a pair of matching points in the first image; and

,

in response to the location falling outside the first ROI, associating the correspondence as a spurious match.

10. The method of claim 9 further comprising:

defining a second ROI located after the intersection in a second of the at least two images;

determining a second location of a second one in the pair of matching feature points in the second image; and

in response to the second location falling outside the second ROI, associating the correspondence as a spurious match.

11. The method of claim 10 wherein the extracting at least one attribute for each correspondence includes:

extracting the at least one attribute for each correspondence not belonging to a spurious match and discarding the each correspondence belonging to a spurious match.

12. A system for detecting a vehicle running a stop signal, the system comprising a traffic regulation enforcement device including a memory and a processor in communication with the processor configured to:

acquire at least two evidentiary images of a candidate violating vehicle captured from at least one camera monitoring an intersection;

extract feature points in each of the at least two evidentiary images;

compute feature descriptors for each of the extracted feature points;

determine a correspondence between feature points having matching feature descriptors at different locations in the at least two evidentiary images;

extract at least one attribute for each correspondence;

determine if the candidate violating vehicle is in violation of running the stop signal using the extracted attribute.

13. The system of claim 12, wherein the processor is further configured to:

using the extracted attribute, determine if the each correspondence belongs to one of a spurious match and a true match;

for each correspondence belonging to a true match, compare the attribute to a threshold; and

,

classify the candidate violating vehicle as belonging to one of a violating vehicle and a non-violating vehicle based on the comparing.

14. The system of claim 12, wherein the attribute includes a length of a line connecting locations of the matching feature points in the at least two evidentiary images and the threshold includes a predetermined length.

15. The system of claim 14, wherein the length of the line is computed using the equation L=√

{square root over ((x₂−

x₁)²+(y₂−

y₁)²)}{square root over ((x₂−

x₁)²+(y₂−

y₁)²)}, where (x₁,y₁) is a location of a feature point in a first image and (x₂,y₂) is a location of a matching feature point in a second image.

16. The system of claim 14, wherein the processor is further configured to:

in response to the length meeting and exceeding the predetermined threshold, classify the candidate violating vehicle as belonging to a violating vehicle, and

in response to the length not meeting the predetermined threshold, classify the candidate violating vehicle as belonging to a non-violating vehicle.

17. The system of claim 12, where the attribute includes an angle formed between a first line and a second line and the threshold includes a predetermined angle, the first line extending between locations of the matching feature points in the at least two evidentiary images and the second line being coincident along a road direction that the candidate violating vehicle is expected to travel through the intersection.

18. The system of claim 17, wherein the angle of the line is computed using the equation

19. The system of claim 17, wherein the processor is further configured to:

in response to the angle meeting and exceeding the predetermined threshold, classify the candidate violating vehicle as belonging to a non-violating vehicle, and

in response to the angle not meeting the predetermined threshold, classify the candidate violating vehicle as belonging to a violating vehicle.

20. The system of claim 12, wherein the processor is further configured to:

define a first region of interest (ROI) located before the intersection in a first of the at least two images;

determine a first location of a first one in a pair of matching feature points in the first image; and

,

in response to the location falling outside the first ROI, associate the correspondence as being a spurious match.

21. The system of claim 20, wherein the processor is further configured to:

define a second ROI located after the intersection in a second of the at least two images;

determine a second location of a second one in a pair of matching feature points in the second image; and

in response to the second location falling outside the second ROI, associate the correspondence as being a spurious match.

22. The system of claim 21, wherein the processor is configured to:

extract the at least one attribute for each correspondence not belonging to a spurious match and discard the each correspondence belonging to a spurious match.