Vehicle vision system with enhanced pedestrian detection

• US 10,095,935 B2
• Filed: 12/17/2014
• Issued: 10/09/2018
• Est. Priority Date: 12/20/2013
• Status: Active Grant

• Current Assignee: Magna Electronics Incorporated (Magna International Incorporated)
• Original Assignee: Magna Electronics Incorporated (Magna International Incorporated)
• Inventors: Gupta, Nikhil
• Primary Examiner(s): Tran, Thai
• Assistant Examiner(s): HASAN, SYED Y
• Application Number:
  US14/573,306
• Publication Number:
  US 20150178576A1
• Time in Patent Office: 1,392 Days
• Field of Search: 348148, 348 36, 382103, 382104, 701 96
• 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 2201/07 Target detection
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: H04N 23/698 for achieving an enlarged field of view, e.g. panoramic image capture

Abstract

A vision system of a vehicle includes a camera disposed at a vehicle and having a field of view that encompasses first and second regions exterior of the vehicle. The camera captures image data that includes a first set of image data representative of the first region of the field of view and a second set of image data representative of the second region of the field of view. An image processor processes the first set of image data to detect a pedestrian present in the first region based on a first predetermined orientation of a pedestrian. The image processor processes the second set of image data to detect a pedestrian present in the second region based on a second predetermined orientation of a pedestrian.

Claims

1. A vision system of a vehicle, said vision system comprising:

at least one camera disposed at a vehicle and having a field of view exterior of the vehicle, wherein the field of view encompasses a first region exterior of the vehicle and a second region exterior of the vehicle;

wherein the first region is at a side region of the field of view of said camera and the second region is at a center region of the field of view of said camera;

wherein said camera captures image data and wherein captured image data includes a first set of image data representative of the first region of the field of view and a second set of image data representative of the second region of the field of view;

wherein said camera comprises a wide angle lens and wherein distortion in captured image data is greater in the first set of image data representative of the first region of the field of view of said camera than in the second set of image data representative of the second region of the field of view of said camera;

an image processor operable to process image data captured by said camera;

wherein said image processor processes image data captured by said at least one camera to detect objects present in the field of view of said at least one camera;

wherein said image processor, responsive to processing of image data captured by said at least one camera, determines that a detected object is a pedestrian at least in part responsive to an orientation of the detected object;

wherein said image processor processes the first set of image data and determines a pedestrian present in the first region of the field of view based at least in part on determination that the orientation of an object detected present in the first region of the field of view of said at least one camera corresponds with a first predetermined orientation of a pedestrian;

wherein said image processor processes the second set of image data and determines a pedestrian present in the second region of the field of view based at least in part on determination that the orientation of an object detected present in the second region of the field of view of said at least one camera corresponds with a second predetermined orientation of a pedestrian;

wherein said second predetermined orientation of a pedestrian is different than said first predetermined orientation of a pedestrian; and

wherein the second predetermined orientation of a pedestrian is vertical, and wherein the first predetermined orientation of a pedestrian is tilted relative to the second predetermined orientation of a pedestrian.

2. The vision system of claim 1, wherein said camera comprises a camera of a surround vision system of the vehicle.

3. The vision system of claim 1, wherein said camera includes a wide angle lens and a two-dimensional array of photosensing elements.

4. The vision system of claim 1, wherein said image processor processes the first set of image data to determine a pedestrian present in the first region based on a first predetermined size of a pedestrian, and wherein said image processor processes the second set of image data to determine a pedestrian present in the second region based on a second predetermined size of a pedestrian.

5. The vision system of claim 1, wherein, responsive to processing of captured image data over multiple frames of captured image data, said image processor adjusts the first predetermined orientation of a pedestrian and adjusts the second predetermined orientation of a pedestrian.

6. The vision system of claim 5, wherein said image processor adjusts processing of the first set of image data based on the adjusted first predetermined orientation of a pedestrian, and wherein said image processor adjusts processing of the second set of image data based on the adjusted second predetermined orientation of a pedestrian.

7. The vision system of claim 1, wherein said vision system comprises a surround-view vision system and wherein said at least one camera comprises a plurality of cameras disposed at a vehicle and having respective fields of view exterior of the vehicle.

8. The vision system of claim 7, wherein said plurality of cameras includes at least (i) a rear camera disposed at a rearward portion of the vehicle and having a rearward field of view, (ii) a first side camera disposed at a first side of the vehicle and having a sideward field of view at the first side of the vehicle, and (iii) a second side camera disposed at a second side of the vehicle and having a sideward field of view at the second side of the vehicle.

9. A vision system of a vehicle, said vision system comprising:

at least one camera disposed at a vehicle and having a field of view exterior of the vehicle, wherein the field of view encompasses a first region exterior of the vehicle and a second region exterior of the vehicle;

wherein said camera captures image data and wherein captured image data includes a first set of image data representative of the first region of the field of view and a second set of image data representative of the second region of the field of view;

wherein the first region is at a side region of the field of view of said camera and the second region is at a center region of the field of view of said camera;

an image processor operable to process image data captured by said camera;

wherein said image processor processes image data captured by said at least one camera to detect objects present in the field of view of said at least one camera;

wherein said image processor, responsive to processing of image data captured by said at least one camera, determines that a detected object is a pedestrian at least in part responsive to an orientation of the detected object;

wherein said image processor processes the first set of image data and determines a pedestrian present in the first region of the field of view based at least in part on determination that the orientation of an object detected present in the first region of the field of view of said at least one camera corresponds with a first predetermined orientation of a pedestrian;

wherein said image processor processes the second set of image data and determines a pedestrian present in the second region of the field of view based at least in part on determination that the orientation of an object detected present in the second region of the field of view of said at least one camera corresponds with a second predetermined orientation of a pedestrian; and

wherein said second predetermined orientation of a pedestrian is different than said first predetermined orientation of a pedestrian, and wherein the second predetermined orientation of a pedestrian is vertical, and wherein the first predetermined orientation of a pedestrian is tilted relative to the second predetermined orientation of a pedestrian.

10. The vision system of claim 9, wherein said image processor processes the first set of image data to determine a pedestrian present in the first region based on a first predetermined size of a pedestrian, and wherein said image processor processes the second set of image data to determine a pedestrian present in the second region based on a second predetermined size of a pedestrian.

11. The vision system of claim 9, wherein, responsive to processing of captured image data over multiple frames of captured image data, said image processor adjusts the first predetermined orientation of a pedestrian and adjusts the second predetermined orientation of a pedestrian.

12. The vision system of claim 11, wherein said image processor adjusts processing of the first set of image data based on the adjusted first predetermined orientation of a pedestrian, and wherein said image processor adjusts processing of the second set of image data based on the adjusted second predetermined orientation of a pedestrian.

13. The vision system of claim 9, wherein said vision system comprises a surround-view vision system and wherein said at least one camera comprises a plurality of cameras disposed at a vehicle and having respective fields of view exterior of the vehicle, and wherein said plurality of cameras includes at least (i) a rear camera disposed at a rearward portion of the vehicle and having a rearward field of view, (ii) a first side camera disposed at a first side of the vehicle and having a sideward field of view at the first side of the vehicle, and (iii) a second side camera disposed at a second side of the vehicle and having a sideward field of view at the second side of the vehicle.

14. A vision system of a vehicle, said vision system comprising:

at least one camera disposed at a vehicle and having a field of view exterior of the vehicle, wherein the field of view encompasses a first region exterior of the vehicle and a second region exterior of the vehicle;

wherein said camera includes a wide angle lens and a two-dimensional array of photosensing elements;

wherein said camera captures image data and wherein captured image data includes a first set of image data representative of the first region of the field of view and a second set of image data representative of the second region of the field of view;

wherein the first region is at a side region of the field of view of said camera and the second region is at a center region of the field of view of said camera;

an image processor operable to process image data captured by said camera;

wherein said image processor processes image data captured by said at least one camera to detect objects present in the field of view of said at least one camera;

wherein said image processor, responsive to processing of image data captured by said at least one camera, determines that a detected object is a pedestrian at least in part responsive to an orientation of the detected object;

wherein said image processor processes the first set of image data and determines a pedestrian present in the first region of the field of view based at least in part on determination that the orientation of an object detected present in the first region of the field of view of said at least one camera corresponds with a first predetermined orientation of a pedestrian;

wherein said image processor processes the second set of image data and determines a pedestrian present in the second region of the field of view based at least in part on determination that the orientation of an object detected present in the second region of the field of view of said at least one camera corresponds with a second predetermined orientation of a pedestrian;

wherein the second predetermined orientation of a pedestrian is vertical, and wherein the first predetermined orientation of a pedestrian is tilted relative to the second predetermined orientation of a pedestrian;

wherein, responsive to processing of captured image data over multiple frames of captured image data, said image processor adjusts the first predetermined orientation of a pedestrian and adjusts the second predetermined orientation of a pedestrian; and

wherein said image processor adjusts processing of the first set of image data based on the adjusted first predetermined orientation of a pedestrian, and wherein said image processor adjusts processing of the second set of image data based on the adjusted second predetermined orientation of a pedestrian.

15. The vision system of claim 14, wherein said image processor processes the first set of image data to determine a pedestrian present in the first region based on a first predetermined size of a pedestrian, and wherein said image processor processes the second set of image data to determine a pedestrian present in the second region based on a second predetermined size of a pedestrian.

16. The vision system of claim 14, wherein said vision system comprises a surround-view vision system and wherein said at least one camera comprises a plurality of cameras disposed at a vehicle and having respective fields of view exterior of the vehicle.

17. The vision system of claim 16, wherein said plurality of cameras includes at least (i) a rear camera disposed at a rearward portion of the vehicle and having a rearward field of view, (ii) a first side camera disposed at a first side of the vehicle and having a sideward field of view at the first side of the vehicle, and (iii) a second side camera disposed at a second side of the vehicle and having a sideward field of view at the second side of the vehicle.