Image processing for a traffic control system

• US 7,646,311 B2
• Filed: 08/10/2007
• Issued: 01/12/2010
• Est. Priority Date: 08/10/2007
• Status: Expired due to Fees

• Current Assignee: Asian Institute of Technology
• Original Assignee: Asian Institute of Technology
• Inventors: Afzulpurkar, Nitin, Phuong, Huynh Huu
• Primary Examiner(s): Lee; Benjamin C
• Assistant Examiner(s): Pham; Lam P
• Application Number:
  US11/837,324
• Publication Number:
  US 20090040069A1
• Time in Patent Office: 886 Days
• Field of Search: 340/435, 340/903, 340/909, 340/916, 340/932.2, 340/934, 348/143, 348148-149, 382/103, 382/104, 382/199, 382/235, 701116-118, 701/120
• US Class Current: 340/934
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

Embodiments of the invention include methods and apparatuses relation to traffic control systems. In one embodiment, a traffic condition is identified by capturing a traffic image, masking the traffic image to obtain an image portion including a traffic image object, and generating the traffic condition based on the traffic image object and the traffic image portion.

Claims

1. A vehicular traffic monitoring method comprising:

obtaining an image of a traffic location, the image of the traffic location including an image portion;

generating an image mask, the image mask being dimensionally representative of the image portion;

masking the image of the traffic location using the image mask to obtain the image portion, the image portion including at least one vehicular image object;

identifying the at least one vehicular image object from the image portion; and

determining a traffic density representative of the image portion based at least in part on the at least one vehicular image object by;

detecting an edge of the at least one vehicular image object;

drawing an image-bounding box around the edge of the at least one vehicular image object;

translating the image-bounding box from a perspective coordinate frame to a world coordinate frame;

determining an area of the image-bounding box in the world coordinate frame;

determining an area of the image portion in the world coordinate frame; and

determining the traffic density as a ratio of the area of the image-bounding box in the world coordinate frame to the area of the image portion in the world coordinate frame.

2. The traffic monitoring method of claim 1, further comprising:

enhancing the edge of the image object by applying a morphological function.

3. The traffic monitoring method of claim 1, further comprising:

determining a second traffic density for a second image portion of the image of the traffic location; and

determining a duration for a green traffic light based at least in part upon the traffic density and the second traffic density.

4. The traffic monitoring method of claim 3, further comprising:

comparing the duration for the green traffic light to a maximum green light duration; and

if the duration for the green traffic light is less than the maximum green light duration, then comparing the traffic density to a minimum traffic density; and

if the traffic density is less than the minimum traffic density, then switching the green traffic light off.

5. The traffic monitoring method of claim 4, further comprising:

if the traffic density is greater than the minimum traffic density, then obtaining a second image of the traffic location.

6. The traffic monitoring method of claim 1, wherein obtaining the image of the traffic location comprises obtaining the image of the traffic location from a remote camera.

7. The traffic monitoring method of claim 1, further comprising:

generating control signals for transmission to a traffic station for enabling traffic control.

8. The traffic monitoring method of claim 1, wherein generating the image mask comprises:

identifying a plurality of lines within the traffic image;

identifying a first line and a second line from the plurality of lines, the first line and the second line being the two longest of the plurality of lines; and

defining the image mask between the first line, the second line, and a portion of a boundary of the traffic image.

9. The traffic monitoring method of claim 8, wherein identifying the plurality of lines comprises a Hough transform.

10. A machine readable medium having stored therein a plurality of instructions that, when executed, cause the machine to monitor vehicular traffic by:

receiving an image of a traffic location, the image of the traffic location including an image portion;

generating an image mask, the image mask being dimensionally representative of the image portion;

masking the image of the traffic location using the image mask to obtain the image portion, the image portion including at least one vehicular image object;

identifying the at least one vehicular image object from the image portion; and

determining a traffic density representative of the image portion based at least in part on the at least one vehicular image object by;

detecting an edge of the at least one vehicular image object;

generating an image-bounding box around the edge of the at least one vehicular image object;

translating the image-bounding box from a perspective coordinate frame to a world coordinate frame;

determining an area of the image-bounding box in the world coordinate frame;

determining an area of the image portion in the world coordinate frame; and

determining the traffic density as a ratio of the area of the image-bounding box in the world coordinate frame to the area of the image portion in the world coordinate frame.

11. The machine readable medium of claim 10, further comprising instructions that, when executed, cause the machine to monitor vehicular traffic by:

enhancing the edge of the image object by applying a morphological function.

12. The machine readable medium of claim 10, further comprising instructions that, when executed, cause the machine to monitor vehicular traffic by:

determining a second traffic density for a second image portion of the image of the traffic location; and

determining a duration for a green traffic light based at least in part upon the traffic density and the second traffic density.

13. The machine readable medium of claim 12, further comprising instructions that, when executed, cause the machine to monitor vehicular traffic by:

comparing the duration for the green traffic light to a maximum green light duration; and

if the duration for the green traffic light is less than the maximum green light duration, then comparing the traffic density to a minimum traffic density; and

if the traffic density is less than the minimum traffic density, then generating a green traffic light off signal.

14. The machine readable medium of claim 13, further comprising instructions that, when executed, cause the machine to monitor vehicular traffic by:

if the traffic density is greater than the minimum traffic density, then receiving a second image of the traffic location.

15. The machine readable medium of claim 10, further comprising instructions that, when executed, cause the machine to monitor vehicular traffic by:

generating control signals for transmission to a traffic station for enabling traffic control.

16. The machine readable medium of claim 10, wherein generating the image mask comprises:

identifying a plurality of lines within the traffic image;

identifying a first line and a second line from the plurality of lines, the first line and the second line being the two longest of the plurality of lines; and

defining the image mask between the first line and the second line, and a portion of a boundary of the traffic image.

17. The machine readable medium of claim 16, wherein identifying the plurality of lines comprises a Hough transform.

18. An apparatus comprising:

a machine readable medium having stored therein a plurality of programming instructions that, when executed, cause the apparatus to monitor vehicular traffic by;

receiving an image of a traffic location, the image of the traffic location including an image portion;

generating an image mask, the image mask being dimensionally representative of the image portion;

masking the image of the traffic location using the image mask to obtain the image portion, the image portion including at least one vehicular image object;

identifying the at least one vehicular image object from the image portion; and

determining a traffic density representative of the image portion based at least in part on the at least one vehicular image object by;

detecting an edge of the at least one vehicular image object;

generating an image-bounding box around the edge of the at least one vehicular image object;

translating the image-bounding box from a perspective coordinate frame to a world coordinate frame;

determining an area of the image-bounding box in the world coordinate frame;

determining an area of the image portion in the world coordinate frame; and

determining the traffic density as a ratio of the area of the image-bounding box in the world coordinate frame to the area of the image portion in the world coordinate frame; and

a processor coupled to the machine readable medium to execute the programming instructions.

19. The machine readable medium of claim 18, further comprising instructions that, when executed, cause the apparatus to monitor vehicular traffic by:

enhancing the edge of the at least one vehicular image object by applying a morphological function.

20. The machine readable medium of claim 18, further comprising instructions that, when executed, cause the apparatus to monitor vehicular traffic by:

determining a second traffic density for a second image portion of the image of the traffic location; and

determining a duration for a green traffic light based at least in part upon the traffic density and the second traffic density.

21. The machine readable medium of claim 20, further comprising instructions that, when executed, cause the apparatus to monitor vehicular traffic by:

comparing the duration for the green traffic light to a maximum green light duration; and

if the duration for the green traffic light is less than the maximum green light duration, then comparing the traffic density to a minimum traffic density; and

if the traffic density is less than the minimum traffic density, then generating a green traffic light off signal.

22. The machine readable medium of claim 21, further comprising instructions that, when executed, cause the apparatus to monitor vehicular traffic by:

if the traffic density is greater than the minimum traffic density, then obtaining a second image of the traffic location.

23. The machine readable medium of claim 18, further comprising instructions that, when executed, cause the apparatus to monitor vehicular traffic by:

generating control signals for transmission to a traffic station for enabling traffic control.

24. The machine readable medium of claim 18, wherein generating the image mask comprises:

identifying a plurality of lines within the traffic image;

identifying a first line and a second line from the plurality of lines, the first line and the second line being the two longest of the plurality of lines; and

defining the image mask between the first line and the second line, and a portion of a boundary of the traffic image.

25. The machine readable medium of claim 24, wherein identifying the plurality of lines comprises of Hough transform.