METHOD FOR ENHANCING VEHICLE CAMERA IMAGE QUALITY

• US 20170280061A1
• Filed: 06/12/2017
• Published: 09/28/2017
• Est. Priority Date: 09/26/2011
• Status: Active Grant

• Current Assignee: Magna Electronics Incorporated (Magna International Incorporated)
• Original Assignee: Magna Electronics Incorporated (Magna International Incorporated)
• Inventors: Kussel, Marcel
• Granted Patent: US 9,774,790 B1
• Time in Patent Office: Days
• CPC Class Codes: B60R 1/00 Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
• CPC Class Codes: B60R 2300/307 virtually distinguishing relevant parts of a scene from the background of the scene
• CPC Class Codes: B60R 2300/8053 for bad weather conditions or night vision
• CPC Class Codes: H04N 23/76 by influencing the image signals

Abstract

A method of image enhancement for a vehicle vision system includes capturing multiple frames of image data with a camera and executing a first brightness transfer function on a current frame of captured image data to generate a first enhanced image frame. At least one previously captured frame of image data is retrieved, and a second brightness transfer function is executed on the at least one previously captured frame of image data to generate a second enhanced image frame. The first and second enhanced image frames are blended to generate a blended enhanced image frame, and these steps are repeated so as to generate multiple blended enhanced image frames. The presence of an object is detected via processing of blended enhanced image frames by a processor, and an output is generated responsive to detection of the object.

Claims

1. A method of image enhancement for a vehicle vision system, said method comprising:

(a) providing a camera at a vehicle so that the camera has an exterior field of view;

(b) providing a processor operable to process image data;

(c) capturing multiple frames of image data with the camera;

(d) executing a first brightness transfer function on a current frame of image data captured by the camera to generate a first enhanced image frame;

(e) retrieving at least one previously captured frame of image data;

(f) executing a second brightness transfer function on the at least one previously captured frame of image data to generate a second enhanced image frame, wherein the second brightness transfer function is different from the first brightness transfer function;

(g) blending the first and second enhanced image frames to generate a blended enhanced image frame;

repeating steps (d)-(g) so as to generate multiple blended enhanced image frames;

(h) detecting, via processing of blended enhanced image frames by the processor, presence of an object in the field of view of the camera; and

(i) generating an output responsive to detection of the object present in the field of view of the camera.

2. The method of claim 1, wherein the step of executing the first brightness transfer function enhances contrast of the current frame of image data captured by the camera.

3. The method of claim 1, comprising executing tone mapping of multiple frames of captured image data to enhance detection of the object present in the field of view of the camera.

4. The method of claim 1, comprising classifying the detected object present in the field of view of the camera.

5. The method of claim 4, comprising generating an output responsive to classification of the detected object.

6. The method of claim 1, comprising determining a low visibility driving condition and, responsive to determination of the low visibility driving condition, increasing contrast of features in captured image data by brightening brighter areas of captured image data and dampening darker areas of captured image data.

7. The method of claim 6, comprising increasing contrast of features in captured image data over multiple successive frames of captured image data.

8. The method of claim 7, comprising tracking, via processing by the processor of multiple successive frames of captured image data during the determined low visibility driving condition, image flow caused by movement of the vehicle to enhance detection and identification of objects present in the field of view of the camera.

9. The method of claim 1, wherein the at least one previously captured frame of image data is retrieved from memory.

10. The method of claim 1, comprising determining a low visibility driving condition via processing of captured image data.

11. The method of claim 1, comprising determining that fog is present in the field of view of the camera via processing of captured image data.

12. The method of claim 1, comprising providing blended enhanced image frames of image data to a video display screen that is disposed in the vehicle at a location viewable by a driver of the vehicle when operating the vehicle.

13. The method of claim 1, wherein capturing multiple frames of image data with the camera comprises capturing multiple frames of image data with the camera at a frame rate of at least 30 frames per second.

14. The method of claim 1, wherein blending the first and second enhanced image frames comprises blending the first and second enhanced image frames to generate a blended enhanced image frame that is up to 20 percent derived from the first enhanced image frame.

15. The method of claim 1, wherein executing a second brightness transfer function on the at least one previously captured frame of image data comprises executing the second brightness transfer function on a plurality of previously captured frames of image data to generate the second enhanced image frame.

16. The method of claim 1, comprising providing the generated output to a driver assistance system of the vehicle.

17. The method of claim 16, wherein the driver assistance system of the vehicle comprises a system selected from the group consisting of a lane change assist system of the vehicle, a lane departure warning system of the vehicle, a blind spot detection system of the vehicle, an adaptive cruise control system of the vehicle, a collision avoidance system of the vehicle, a traffic sign recognition system of the vehicle, and a vehicle headlamp control system of the vehicle.

18. The method of claim 1, comprising tracking the detected object over successive frames of captured image data to determine if the detected object is an object of interest in the field of view of the camera.

19. The method of claim 1, wherein processing of captured image data by the processor is responsive at least in part to steering of the vehicle.

20. The method of claim 1, comprising distinguishing, via processing of captured image data by the processor, moving objects from non-moving objects.

21. The method of claim 20, wherein distinguishing moving objects comprises distinguishing moving objects responsive at least in part to at least one of (i) speed of the vehicle and (ii) steering of the vehicle.

22. The method of claim 1, comprising disposing the camera at a rear portion of the vehicle with an exterior field of view rearward of the vehicle, and wherein said method comprises providing a plurality of cameras at the vehicle so as to have respective exterior fields of view, and wherein the plurality of cameras comprises the camera at the rear portion of the vehicle.

23. The method of claim 22, comprising providing a display for displaying images derived, at least in part, from image data captured by the camera at the rear portion of the vehicle and derived, at least in part, from image data captured by other cameras of the plurality of cameras.

24. The method of claim 1, comprising disposing the camera at a rear portion of the vehicle with an exterior field of view rearward of the vehicle, and comprising providing a display for displaying images derived, at least in part, from image data captured by the camera during a reversing maneuver of the vehicle.

25. A method of image enhancement for a vehicle vision system, said method comprising:

(a) providing a camera at a vehicle so that the camera has an exterior field of view;

(b) providing a processor operable to process image data;

(c) capturing multiple frames of image data with the camera;

(d) executing a first brightness transfer function on a current frame of image data captured by the camera to generate a first enhanced image frame;

(e) retrieving at least one previously captured frame of image data;

(f) executing a second brightness transfer function on the at least one previously captured frame of image data to generate a second enhanced image frame, wherein the second brightness transfer function is different from the first brightness transfer function;

(g) blending the first and second enhanced image frames to generate a blended enhanced image frame;

repeating steps (d)-(g) so as to generate multiple blended enhanced image frames;

(h) detecting, via processing of blended enhanced image frames by the processor, presence of an object in the field of view of the camera;

(i) tracking the detected object over successive frames of captured image data to determine if the detected object is an object of interest in the field of view of the camera;

(j) generating an output responsive to determination of the detected object being an object of interest; and

(k) providing the generated output to a driver assistance system of the vehicle.

26. The method of claim 25, wherein the driver assistance system of the vehicle comprises a blind spot detection system of the vehicle.

27. The method of claim 25, wherein the driver assistance system of the vehicle comprises a collision avoidance system of the vehicle.

28. The method of claim 25, wherein the driver assistance system of the vehicle comprises an adaptive cruise control system of the vehicle.

29. The method of claim 25, wherein executing a second brightness transfer function on the at least one previously captured frame of image data comprises executing the second brightness transfer function on a plurality of previously captured frames of image data to generate the second enhanced image frame.

30. The method of claim 29, wherein blending the first and second enhanced image frames comprises blending the first and second enhanced image frames to generate a blended enhanced image frame that is up to 20 percent derived from the first enhanced image frame.

31. A method of image enhancement for a vehicle vision system, said method comprising:

(a) providing a camera at a rear portion of a vehicle with an exterior field of view rearward of the vehicle;

(b) providing a processor operable to process image data;

(c) capturing multiple frames of image data with the camera;

(d) executing a first brightness transfer function on a current frame of image data captured by the camera to generate a first enhanced image frame;

(e) retrieving at least one previously captured frame of image data;

(f) executing a second brightness transfer function on the at least one previously captured frame of image data to generate a second enhanced image frame, wherein the second brightness transfer function is different from the first brightness transfer function;

(g) blending the first and second enhanced image frames to generate a blended enhanced image frame;

repeating steps (d)-(g) so as to generate multiple blended enhanced image frames; and

(h) providing blended enhanced image frames of image data to a video display screen that is disposed in the vehicle at a location viewable by a driver of the vehicle when operating the vehicle.

32. The method of claim 31, comprising determining a low visibility driving condition via processing of captured image data.

33. The method of claim 32, comprising, responsive to determination of the low visibility driving condition, increasing contrast of features in captured image data by brightening brighter areas of captured image data and dampening darker areas of captured image data.

34. The method of claim 31, comprising determining that fog is present in the field of view of the camera via processing of captured image data.

35. The method of claim 31, comprising providing a plurality of cameras at the vehicle so as to have respective exterior fields of view, wherein the plurality of cameras comprises the camera at the rear portion of the vehicle, and wherein the video display screen displays images derived, at least in part, from image data captured by the camera at the rear portion of the vehicle and derived, at least in part, from image data captured by other cameras of the plurality of cameras.

36. The method of claim 35, wherein the plurality of cameras is part of a surround view multi-camera system of the vehicle, and wherein images displayed by the video display screen derived, at least in part, from image data captured by the camera at the rear portion of the vehicle and derived, at least in part, from image data captured by other cameras of the plurality of cameras comprise a bird'"'"'s-eye view.