Method and apparatus for object tracking prior to imminent collision detection

• US 7,660,438 B2
• Filed: 01/22/2009
• Issued: 02/09/2010
• Est. Priority Date: 12/15/2003
• Status: Active Grant

• Current Assignee: SRI International, Inc.
• Original Assignee: Sarnoff Corporation (SRI International, Inc.)
• Inventors: Camus, Theodore Armand
• Primary Examiner(s): Ishrat, Sherali
• Application Number:
  US12/357,478
• Publication Number:
  US 20090195371A1
• Time in Patent Office: 383 Days
• Field of Search: 382/104, 382/103, 382/100, 382/106, 382/107, 382153-154, 382224-227, 348/148, 348/171, 348/149, 348/135, 348/140, 348/142, 348/143, 348/150, 348/169, 34815947- 48, 348113-119, 340/903, 340/937, 340/928, 701/23, 701/28, 701/117, 701/200, 701/300, 701/301, 701/96
• US Class Current: 382/104
• CPC Class Codes: B60R 21/013 including means for detecting collisions, impending collisions or roll-over
• CPC Class Codes: B60R 21/0134 responsive to imminent contact with an obstacle , e.g. using radar systems
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems
• 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
• CPC Class Codes: G06V 20/64 Three-dimensional objects

Abstract

A method and apparatus for performing collision detection is described. An object is detected within a first operational range of an object tracker. A classification of the object is determined using the object tracker. The object tracker tracks the object. The object is detected within a second operational range of a collision detector. A safety measure is activated based on the classification using the collision detector.

Claims

1. A method for performing collision detection, comprising:

detecting an object within a first operational range of an object tracker;

determining a classification of said object using said object tracker;

tracking said object using said object tracker;

detecting said object within a second operational range of a collision detector; and

activating a safety measure based on said classification using said collision detector, wherein said safety measure comprises at least one of a warning, providing object information, an object display and a mitigation mechanism.

2. The method of claim 1 wherein said mitigation mechanism comprises a measure to avoid a damage or injury.

3. The method of claim 1 wherein said mitigation mechanism comprises a measure to mitigate a damage or injury.

4. The method of claim 1 wherein said mitigation mechanism is reversible.

5. The method of claim 1 wherein said mitigation mechanism is non-reversible.

6. The method of claim 2 further comprising adjusting at least one threshold for said avoidance or damage or injury mitigation mechanism based on the classification of the object.

7. The method of claim 6 wherein said at least one threshold comprises parameters of a vehicle.

8. The method of claim 1 further comprising storing various templates of the objects located at various positions and depth with respect to a first sensor.

9. The method of claim 8 wherein said detecting comprises comparing the object templates to match the object.

10. The method of claim 8 further comprising receiving information regarding the object from a second sensor;

and using the information to limit a number of the stored templates that are compared to the object.

11. The method of claim 8 further comprising receiving information regarding the object from a second sensor;

and using the information to validate the match between the object and the stored object templates.

12. The method of claim 1 wherein said detected object is within a disparity image of one or more resolutions.

13. The method of claim 1 wherein said detected object is within a depth image of one or more resolutions.

14. The method of claim 1 wherein the first operational range and the second operational range are mutually exclusive.

15. The method of claim 1 wherein the first operational range and the second operational range overlap.

16. The method of claim 1 wherein the object tracker and the collision detector operate simultaneously.

17. The method of claim 1 wherein said classification is communicated from said object tracker to said collision detector by extrapolating at least one of a positional vector, a location vector, and a velocity vector.

18. The method of claim 1 further comprising communicating said classification from said object tracker to said collision detector.

19. The method of claim 18 wherein said classification is communicated during an overlap period of said first operational range and said second operational range.

20. The method of claim 18 wherein said classification is communicated by matching additional information from said object tracker and said collision detector.

21. The method of claim 20 wherein said additional information comprises at least one of range rate, closing velocity, velocity vector and collision impact point, height. width and/or length, major-axis orientation, classification, edges and/or bounding box, image statistics such as image edge density or image contrast, or depth image statistics such as depth variation or depth image density.

22. The method of claim 1 wherein the collision detector becomes operational only when a reliable classification is made.

23. A system for performing collision detection, comprising:

an object processor having at least an object tracker and a collision detector, said object processor function to detect an object within a first operational range of the object tracker and within a second operational rage of the collision detector;

said object tracker function to determine a classification of said object and to track said object;

said collision detector function to activate a safety measure based on said classification wherein said safety measure comprises at least one of a warning, providing object information, an object display and a mitigation mechanism.

24. The system of claim 23 further comprising a first sensor for sensing said object.

25. The system of claim 24 wherein said first sensor comprises at least one sensor selected from a group comprising a visible wavelength sensor, an infrared sensor, a visible wavelength and infrared sensor, a LIDAR sensor, a radar sensor, or a SONAR sensor.

26. The system of claim 24 wherein said first sensor comprises a first camera and a second camera and sensing said object comprises capturing at least one image having said object.

27. The system of claim 26 wherein said at least one image is stereo imagery.

28. The system of claim 27 further comprising an image preprocessor coupled to said first sensor and said object processor, said image preprocessor functions to process the at least one image to create at least one disparity image of one or more resolutions.

29. The system of claim 28 further comprising a depth image generator coupled to said image preprocessor for processing the at least one disparity image into at least one depth image of one or more resolutions.

30. The system of claim 24 further comprising an object template database coupled to the object processor, said database function to store various templates of the objects located at various positions and depth with respect to the first sensor.

31. The system of claim 24 further comprising a second sensor for providing information on the object, wherein said information comprise a position and a range of the object relative to a vehicle.

32. The system of claim 31 wherein the second sensor comprises at least one sensor selected from a group comprising a visible wavelength sensor, an infrared sensor, a visible wavelength and infrared sensor, a LIDAR sensor, a radar sensor, or a SONAR sensor.

33. The system of claim 24 further comprising a second sensor for confirming presence of the object.

34. The system of claim 33 wherein the second sensor comprises at least one sensor selected from a group comprising a visible wavelength sensor, an infrared sensor, a visible wavelength and infrared sensor, a LIDAR sensor, a radar sensor, or a SONAR sensor.

35. The system of claim 23 wherein said mitigation mechanism comprises a measure to avoid a damage or injury.

36. The system of claim 23 wherein said mitigation mechanism comprises a measure to mitigate a damage or injury.

37. The system of claim 23 wherein said mitigation mechanism is reversible.

38. The system of claim 23 wherein said mitigation mechanism is non-reversible.