Granted Patent B2

US 9,685,079 · App. 14/278,196 · Granted Jun 20, 2017

Abstract

Claims (76)

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, the at least two evidentiary images including a first image of an intersection before a stop line and a second image of an area located within or after the 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 by 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 running the stop signal and a non-violating vehicle based on the comparing.

2. The method of claim 1 , 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.

3. 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.

4. The method of claim 3 , wherein the length of the line is computed using the equation L=√{square root over ((x 2 −x 1 ) 2 +(y 2 −y 1 ) 2 )}, where (x 1 , y 1 ) is a location of a feature point in a first image and (x 2 , y 2 ) is a location of a matching feature point in a second image.

5. The method of claim 3 , 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.

6. 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.

7. The method of claim 5 , wherein the angle of the line is computed using the equation

θ

=

atan

⁡

(

y

2

-

y

1

x

2

-

x

1

)

;

wherein (x 1 , y 1 ) is a location of a feature point in a first image and (x 2 , y 2 ) is a location of a matching feature point in a second image.

8. 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.

9. The method of claim 8 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.

10. The method of claim 9 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.

11. 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, the at least two evidentiary images including a first image of an intersection before a stop line and a second image of an area located within or after the 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 by 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 running the stop signal and a non-violating vehicle based on the comparing.

12. The system of claim 11 , 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.

13. The system of claim 12 , wherein the length of the line is computed using the equation L=√{square root over ((x 2 −x 1 ) 2 +(y 2 −y 1 ) 2 )}, where (x 1 , y 1 ) is a location of a feature point in a first image and (x 2 , y 2 ) is a location of a matching feature point in a second image.

14. The system of claim 12 , 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.

15. The system of claim 11 , 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.

16. The system of claim 15 , wherein the angle of the line is computed using the equation

θ

=

atan

⁡

(

y

2

-

y

1

x

2

-

x

1

)

;

wherein (x 1 , y 1 ) is a location of a feature point in a first image and (x 2 , y 2 ) is a location of a matching feature point in a second image.

17. The system of claim 15 , 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.

18. The system of claim 11 , 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.

19. The system of claim 18 , 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.

20. The system of claim 19 , 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.

Assignments (8)