Vehicle vision system with enhanced pedestrian detection
First Claim
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.
1 Assignment
0 Petitions
Accused Products
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.
-
Citations
17 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
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. - View Dependent Claims (10, 11, 12, 13)
-
-
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. - View Dependent Claims (15, 16, 17)
-
Specification