Rear obstruction detection

• US 9,826,200 B2
• Filed: 04/30/2008
• Issued: 11/21/2017
• Est. Priority Date: 04/30/2007
• Status: Active Grant

• Current Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Original Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Inventors: Stein, Gideon
• Primary Examiner(s): Kim, Hee-Yong
• Application Number:
  US12/112,172
• Publication Number:
  US 20080266396A1
• Time in Patent Office: 3,492 Days
• Field of Search: 348148
• CPC Class Codes: B60R 2300/30 characterised by the type of image processing
• CPC Class Codes: B60R 2300/404 triggering from stand-by mode to operation mode
• CPC Class Codes: B60R 2300/806 for aiding parking
• CPC Class Codes: B60R 2300/8093 for obstacle warning
• 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: H04N 7/183 for receiving images from a single remote source

Abstract

A method is provided using a system mounted in a vehicle. The system includes a rear-viewing camera and a processor attached to the rear-viewing camera. When the driver shifts the vehicle into reverse gear, and while the vehicle is still stationary, image frames from the immediate vicinity behind the vehicle are captured. The immediate vicinity behind the vehicle is in a field of view of the rear-viewing camera. The image frames are processed and thereby the object is detected which if present in the immediate vicinity behind the vehicle would obstruct the motion of the vehicle. The processing is preferably performed in parallel for a plurality of classes of obstructing objects using a single image frame of the image frames.

Claims

1. A system mountable in a vehicle, the system comprising:

(a) a camera operable to capture a plurality of image frames from a region outside of the vehicle in a direction of motion of the vehicle, wherein the region outside of the vehicle is behind an end of the vehicle in the direction of motion in a field of view of said camera;

(b) a processor attached to said camera operable to receive the image frames and to process the image frames for detection in the region outside of the vehicle of at least one object which, if present, obstructs the motion of the vehicle; and

(c) at least one light attached to the vehicle, wherein the at least one light is capable of illuminating the region outside of the vehicle,

wherein the detection of the object is performed based on a change in illumination between one of the image frames captured before the at least one light is turned on to illuminate the region outside of the vehicle and another one of the image frames captured after the at least one light is turned on to illuminate the region outside of the vehicle.

2. The system, according to claim 1, further comprising

(c) a warning mechanism attached to said processor, wherein said warning mechanism provides a warning to a driver of the vehicle when said at least one object is detected.

3. The system, according to claim 1, wherein the processor is configured to compare the one of the image frames and the another one of the image frames to obtain the change in illumination, wherein the comparison is performed while the vehicle is stationary.

4. The system, according to claim 1, wherein said at least one object is a wall in the region outside of the vehicle,

wherein said light illuminates said wall, wherein said detection includes estimating a distance between the vehicle and said wall based on a position in image space of an illumination from said light.

5. The system, according to claim 1,

wherein said at least one light illuminates said region outside of the vehicle, wherein said detection uses a meeting point or an extrapolation point in at least one of said image frames between said at least one object and a shadow of said at least one object.

6. The system of claim 1, wherein said detection is performed using a plurality of detection algorithms corresponding respectively to a plurality of classes of obstruction objects.

7. The system of claim 6, wherein the classes are selected from the group consisting of:

pedestrians, spherical balls, vertical poles, hanging chains and upright boxes.

8. A method comprising:

(a) capturing, using a camera, a plurality of image frames from a region outside of a vehicle in a direction of motion of the vehicle, wherein the region outside of the vehicle is behind an end of the vehicle in the direction of motion in a field of view of the camera;

(b) processing the image frames to detect in the region outside of the vehicle at least one object which if present obstructs the motion of the vehicle, and

wherein the detection of the object is performed based on a change in illumination between one of the image frames captured before a light attached to the vehicle is turned on to illuminate the region outside of the vehicle and another one of the image frames captured after the light is turned on to illuminate the region outside of the vehicle.

9. The method according to claim 8, further comprising

(c) upon said detecting, warning a driver of the vehicle of a potential obstruction.

10. The method according to claim 8, further comprising comparing the one of the image frames and the another one of the image frames to obtain the change in illumination, wherein the comparing is performed while the vehicle is stationary.

11. The method according to claim 8, wherein said at least one object is a wall in the outside region of the vehicle, the method further comprising

(c) illuminating said wall by the light attached to the vehicle, wherein said processing includes estimating a distance between the vehicle and said wall based on a position in image space of an illumination from said light.

12. The method according to claim 8, the method further comprising

(c) illuminating said immediate vicinity by the light attached to the vehicle, wherein said processing uses a meeting point or extrapolation point in at least one of said image frames between said at least one object and a shadow of said at least one object.

13. A method comprising:

(a) capturing, by a rear viewing camera of a vehicle, a first image frame without illuminating an outside region of the vehicle;

(b) while illuminating the outside region of the vehicle by a light attached to the vehicle, capturing a second image frame, by the rear viewing camera; and

(c) comparing said first image frame and said second image frame, thereby detecting an object in the outside region of the vehicle based on a change in illumination between the first image frame and the second image frame.

14. The method according to claim 13, wherein said detecting is performed using a plurality of detection algorithms corresponding to a plurality of classes of obstructing objects.

15. The method according to claim 13, wherein the light attached to the vehicle is a reverse light,

wherein said capturing of said first image frame is performed prior to shifting the vehicle into reverse gear thereby turning on a reverse light attached to said vehicle, and said capturing of said second image frame is performed after said shifting and while illuminating the outside region of the vehicle with the reverse light;

said illuminating by the reverse light is performed during said capturing of the second image frame but not during said capturing of the first image frame; and

wherein said processing includes comparing said first image frame captured without illuminating the outside region of the vehicle by the reverse light and said second image frame captured while illuminating the outside region of the vehicle by the reverse light.

16. A method comprising:

capturing, by a rear viewing camera of a vehicle, a first image frame without illuminating the vicinity of the vehicle with at least one light attached to a rear of the vehicle;

after turning on the light and while illuminating a region outside of the vehicle by the light, capturing a second image frame by the rear viewing camera,

wherein the illuminating by the light is performed during the capturing of the second image frame but not during the capturing of the first image frame;

comparing the first image frame and the second image frame; and

detecting an object in the region outside of the vehicle based on a result of the comparing.

17. The method of claim 16, wherein the first image frame and the second image frame are captured while the vehicle and the object are stationary.

18. The method of claim 16, wherein the at least one light includes a reverse light and a brake light, and the illuminating is performed by the brake light and the reverse light.

19. The method of claim 16, wherein the at least one light includes a reverse light and a brake light, and capturing the second image frame includes capturing the second image frame while illuminating the region outside of the vehicle by the reverse light and without illuminating the region outside of the vehicle by the brake light.

20. The method of claim 16, wherein the result of the comparing includes a brightness change between the first image frame and the second image frame while taking into account ambient lighting.

21. The method of claim 16, wherein the at least one light includes a reverse light, and wherein the reverse light, when activated, emits a predetermined light pattern, and the method further includes using the predetermined light pattern identified in the second image frame to determine a distance to the object.

22. The method of claim 16, wherein detecting the object is performed using a plurality of detection algorithms corresponding respectively to a plurality of classes of obstruction objects.

23. The method of claim 22, wherein the classes are selected from the group consisting of:

pedestrians, spherical balls, vertical poles, hanging chains and upright boxes.

24. The method of claim 16, wherein the result of the comparing includes a change in illumination, wherein the comparing is performed while the vehicle is stationary.

25. The method of claim 16, wherein the object is a wall behind the vehicle, and the method further comprises determining a distance from the wall.

26. The method of claim 25, wherein determining the distance from the wall is based on a lighting pattern.

27. The method of claim 16, wherein detecting the object comprises detecting the object using a meeting point or an extrapolation point in at least one of the first image frame or the second image frame between the object and a shadow of the object.

28. A system mountable in a vehicle, the system comprising:

a rear viewing camera; and

a processor associated with the rear viewing camera, wherein the processor is configured to;

cause the rear review camera to capture a first image frame of a region outside of the vehicle without illuminating the region outside of the vehicle with at least one light attached to a rear of the vehicle;

cause the rear review camera to capture a second image frame after turning on the light to illuminate the region outside of the vehicle;

wherein the light illuminates an object in the region outside of the vehicle while the second image frame is being captured but not while the first image frame is being captured;

compare the first image frame and the second image frame; and

detect the object in the region outside of the vehicle based on a result of the comparison.

29. The system of claim 28, wherein detecting the object is performed using a plurality of detection algorithms corresponding respectively to a plurality of classes of obstruction objects.

30. The system of claim 29, wherein the classes are selected from the group consisting of:

pedestrians, spherical balls, vertical poles, hanging chains and upright boxes.

31. The system of claim 28, wherein the result of the comparison includes a change in illumination, wherein the comparison is performed while the vehicle is stationary.

32. The system of claim 28, wherein the object is a wall behind the vehicle, and the processor is further configured to determine a distance from the wall.

33. The system of claim 28, wherein determining the distance from the wall is based on a lighting pattern.

34. The system of claim 28, wherein detecting the object comprises detecting the object using a meeting point or an extrapolation point in at least one of the first image frame or the second image frame between the object and a shadow of the object.

35. A method comprising:

(a) capturing, by a rear viewing camera of a vehicle, a first image frame of an outside region of the vehicle while the outside region is illuminated by a brake light and a reverse light;

(b) capturing a second image frame, by the rear viewing camera, of the outside region while the outside region is illuminated by the reverse light and while the brake light is turned off; and

(c) comparing the first image frame and the second image frame to detect an object in the outside region of the vehicle based on a change in illumination between the first image frame and the second image frame.

36. A system mountable in a vehicle, the system comprising:

a rear viewing camera; and

a processor associated with the rear viewing camera, wherein the processor is configured to;

(a) capture a first image frame of an outside region of the vehicle while the outside region is illuminated by a brake light and a reverse light;

(b) capture a second image frame of the outside region while the outside region is illuminated by the reverse light and while the brake light is turned off; and

(c) compare the first image frame and the second image frame to detect an object in the outside region of the vehicle based on a change in illumination between the first image frame and the second image frame.