Single camera system and method for range and lateral position measurement of a preceding vehicle

• US 20050244034A1
• Filed: 04/30/2004
• Published: 11/03/2005
• Est. Priority Date: 04/30/2004
• Status: Active Grant

• Current Assignee: Visteon Global Technologies Incorporated (Visteon Corporation)
• Original Assignee: Visteon Global Technologies Incorporated (Visteon Corporation)
• Inventors: Miyahara, Shunji
• Granted Patent: US 7,561,720 B2
• Time in Patent Office: Days
• US Class Current: 382/106
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

A system for determining range and lateral position of a vehicle is provided. The system includes a camera and a processor. The camera is configured to view a region of interest including the vehicle and generate an electrical image of the region. The processor is in electrical communication with the camera to receive the electrical image. The processor analyzes the image by identifying a series of windows within the image each window corresponds to features of the vehicle at a different target range. For example, from the perspective of the camera the vehicle will appear larger when it is closer to the camera than if it is further away from the camera. Accordingly, each window is sized proportional to the vehicle as it would appear at each target range. The processor evaluates characteristics in the electrical image within each window to identify the vehicle. A score is determined indicating the likelihood that certain characteristics of the electrical image actually correspond to the vehicle and also that the vehicle is at target range for that window.

Claims

1. A system for determining range of a vehicle, the system comprising:

a camera configured to view a region of interest including the vehicle and generate an electrical image of the region;

a processor in electrical communication with the camera to receive the electrical image, wherein the processor is configured to identify a plurality of windows within the electrical image, each window of the plurality of windows corresponding to a predetermined physical size at a target range from the camera, the processor being further configured to evaluate characteristics of the electrical image in relation to each window to identify the vehicle.

2. The system according to claim 1, wherein the processor is configured to determine a score indicating likelihood the vehicle is at the target range.

3. The system according to claim 2, wherein the processor is configured to determine the score based on a size ratio between each window and the characteristics of the electrical image.

4. The system according to claim 1, wherein the predetermined physical size is based on vehicle characteristics.

5. The system according to claim 4, wherein the vehicle characteristics include a width of the vehicle.

6. The system according to claim 4, wherein the vehicle characteristics include a height of the vehicle.

7. The system according to claim 1, wherein the characteristics of the electrical image include edge segments within the electrical image.

8. The system according to claim 7, wherein the edge segments are vertical edge segments.

9. The system according to claim 7, wherein the characteristics of the electrical image include a height of the edge segments.

10. The system according to claim 7, wherein the characteristics of the electrical image include a width of the edge segments.

11. The system according to claim 7, wherein the characteristics of the electrical image include objects constructed from the edge segments.

12. The system according to claim 11, wherein the characteristics of the electrical image include a height of the objects.

13. The system according to claim 11, wherein the characteristics of the electrical image include a width of the objects.

14. The system according to claim 1, wherein a position of each window is determined based on the target range.

15. The system according to claim 1, wherein the window position is determined based on an elevation angle of the camera.

16. The system according to claim 15 wherein the lower edge of each window is calculated based on the relationship Θ

₁=a tan(−

hc/r1) where hc is the height of the camera from the road surface, r1 is the range of window from the camera, and the module is [0, 2π

].

17. The system according to claim 15, wherein the upper edge of each window is calculated based on the relationship Θ

_1h=a tan((hw−

hc)/r1) where hw is a window height, hc is the height of the camera from the road surface, r1 is the range of window from the camera, and the module is [0, 2π

].

18. The system according to claim 1, wherein the position of each window is determined based on an azimuth angle of the camera.

19. The system according to claim 18, wherein the right edge of each window is calculated based on the relationship Φ

₁=a tan(−

width_w/r1)+π

/2 where window w is the distance from the center of the window to the horizontal edges, r1 is the horizontal range of the window from the camera, and the module is [0, 2π

].

20. The system according to claim 18, wherein the left edge of each window is calculated based on the relationship Φ

_1h=a tan(width_w/r1)+π

/2 where window w is the distance from the center of the window to the horizontal edges, r1 is the horizontal range of the window from the camera, and the module is [0, 2π

].

21. A method for determining range of a vehicle, the method comprising:

receiving an optical image of a region of interest onto a camera;

generating an electrical image based on the optical image;

identifying a plurality of windows within the electrical image, each window corresponding to a predetermined physical size at a target range from the camera; and

evaluating characteristics of the electrical image within each window to identify the vehicle.

22. The system according to claim 21, wherein the processor is configured to determine a score indicating likelihood the vehicle is at the target range.

23. The system according to claim 22, wherein the processor is configured to determine the score based on a size ratio between each window and the characteristics of the electrical image.

24. The system according to claim 21, wherein the predetermined physical size is based on vehicle characteristics.

25. The method according to claim 24, wherein the vehicle characteristics include a width of the vehicle.

26. The method according to claim 24, wherein the vehicle characteristics include a height of the vehicle.

27. The method according to claim 21, wherein the characteristics of the electrical image include edge segments within the electrical image.

28. The method according to claim 27, wherein the edge segments are vertical edge segments.

29. The method according to claim 27, wherein the characteristics of the electrical image include a height of the edge segments.

30. The method according to claim 27, wherein the characteristics of the electrical image include a width of the edge segments

31. The method according to claim 27, wherein the characteristics of the electrical image include objects constructed from the edge segments.

32. The method according to claim 31, wherein the characteristics of the electrical image include a height of the objects.

33. The method according to claim 31, wherein the characteristics of the electrical image include a width of the objects.

34. The method according to claim 21, wherein a position of each window is determined based on the target range.

35. The method according to claim 21, wherein the window position is determined based on an elevation angle of the camera.

36. The method according to claim 35 wherein the lower edge of each window is calculated based on the relationship Θ

₁=a tan(−

hc/r1) where hc is the height of the camera from the road surface, r1 is the range of window from the camera, and the module is [0, 2π

].

37. The method according to claim 35, wherein the upper edge of each window is calculated based on the relationship Θ

_1h=a tan((hw−

hc)/r1) where hw is a window height, hc is the height of the camera from the road surface, r1 is the range of window from the camera, and the module is [0, 2π

].

38. The method according to claim 21, wherein the position of each window is determined based on an azimuth angle of the camera.

39. The method according to claim 38, wherein the right edge of each window is calculated based on the relationship Φ

₁=a tan(−

width_w/r1)+π

/2 where window w is the distance from the center of the window to the horizontal edges, r1 is the horizontal range of the window from the camera, and the module is [0, 2π

].

40. The method according to claim 38, wherein the left edge of each window is calculated based on the relationship Φ

_1h=a tan(width_w/r1)+π

/2 where window w is the distance from the center of the window to the horizontal edges, r1 is the horizontal range of the window from the camera, and the module is [0, 2π

].

41. The method according to claim 21, wherein evaluating characteristics of the electrical image includes performing an edge enhancement algorithm to the electrical image.

42. The method according to claim 41, wherein the edge enhancement algorithm is a vertical edge enhancement algorithm.

43. The method according to claim 41, wherein evaluating characteristics of the electrical image includes extracting only the electrical image within the window.

44. The method according to claim 41, wherein evaluating characteristics of the electrical image includes binarizing the electrical image utilizing a threshold.

45. The method according to claim 41, wherein evaluating characteristics of the electrical image includes identifying segments from the binarized image.

46. The method according to claim 45, wherein evaluating characteristics of the electrical image includes constructing objects from the segments.

47. The method according to claim 46, wherein evaluating the electrical image, includes determining a score for each object based on the object width, object height position, object height, and segment width.

48. The method according to claim 47, wherein evaluating characteristics of the electrical image, further includes determining a range of the object that is based on the score of the object.