Method for determining alignment of vehicular cameras
First Claim
1. A method for determining alignment of cameras at a vehicle relative to one another, said method comprising:
- mounting a first camera at a vehicle so as to have a first field of view encompassing a road surface of a road along which the vehicle is traveling;
mounting a second camera at the vehicle so as to have a second field of view encompassing the road surface of the road along which the vehicle is traveling;
wherein the first and second fields of view of the first and second cameras overlap partially;
providing an image processor at the vehicle;
while the vehicle is moving along the road, capturing first image data via the first camera;
while the vehicle is moving along the road, capturing second image data via the second camera;
providing first image data captured by the first camera to the image processor;
providing second image data captured by the second camera to the image processor;
processing, via the image processor, first image data captured by the first camera;
processing, via the image processor, second image data captured by the second camera;
dewarping the first image data and the second image data;
while the vehicle is moving along the road, determining, via processing of first image data captured by the first camera, movement of a road feature present in first image data captured by the first camera;
while the vehicle is moving along the road, determining, via processing of second image data captured by the second camera, movement of the road feature when the road feature is present in second image data captured by the second camera;
comparing the determined movement of the road feature in first image data captured by the first camera to the determined movement of the road feature in second image data captured by the second camera while the vehicle is moving along the road;
determining, via comparing the determined movements of the road feature, a rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle; and
responsive to determination of the rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle, remapping the first and second image data based at least in part on the determined rotational and translational offset to at least partially accommodate misalignment of the second camera relative to the first camera.
0 Assignments
0 Petitions
Accused Products
Abstract
A method for determining alignment of cameras at a vehicle includes mounting first and second cameras at a vehicle and providing an image processor at the vehicle. While the vehicle is moving along the road, first image data captured via the first camera is processed to determine movement of a road feature and second image data captured by the second camera is processed to determine movement of the road feature when the road feature is present in the second image data. The determined movement of the road feature in first image data is compared to the determined movement of the road feature in second image data, and an offset of the second camera relative to the first camera is determined, with the offset caused by a rotational or translational change in position of the first or second camera relative to the other.
582 Citations
18 Claims
-
1. A method for determining alignment of cameras at a vehicle relative to one another, said method comprising:
-
mounting a first camera at a vehicle so as to have a first field of view encompassing a road surface of a road along which the vehicle is traveling; mounting a second camera at the vehicle so as to have a second field of view encompassing the road surface of the road along which the vehicle is traveling; wherein the first and second fields of view of the first and second cameras overlap partially; providing an image processor at the vehicle; while the vehicle is moving along the road, capturing first image data via the first camera; while the vehicle is moving along the road, capturing second image data via the second camera; providing first image data captured by the first camera to the image processor; providing second image data captured by the second camera to the image processor; processing, via the image processor, first image data captured by the first camera; processing, via the image processor, second image data captured by the second camera; dewarping the first image data and the second image data; while the vehicle is moving along the road, determining, via processing of first image data captured by the first camera, movement of a road feature present in first image data captured by the first camera; while the vehicle is moving along the road, determining, via processing of second image data captured by the second camera, movement of the road feature when the road feature is present in second image data captured by the second camera; comparing the determined movement of the road feature in first image data captured by the first camera to the determined movement of the road feature in second image data captured by the second camera while the vehicle is moving along the road; determining, via comparing the determined movements of the road feature, a rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle; and responsive to determination of the rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle, remapping the first and second image data based at least in part on the determined rotational and translational offset to at least partially accommodate misalignment of the second camera relative to the first camera. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A method for determining alignment of cameras at a vehicle relative to one another, said method comprising:
-
mounting a first camera at a vehicle so as to have a first field of view encompassing a road surface of a road along which the vehicle is traveling; mounting a second camera at the vehicle so as to have a second field of view encompassing the road surface of the road along which the vehicle is traveling; wherein the first camera is mounted at the vehicle so as to have a sideward field of view, and wherein the second camera is mounted at the vehicle so as to have a rearward field of view; wherein the first and second fields of view of the first and second cameras overlap partially; providing an image processor at the vehicle; while the vehicle is moving along the road, capturing first image data via the first camera; while the vehicle is moving along the road, capturing second image data via the second camera; providing first image data captured by the first camera to the image processor; providing second image data captured by the second camera to the image processor; processing, via the image processor, first image data captured by the first camera; processing, via the image processor, second image data captured by the second camera; dewarping the first image data and the second image data; while the vehicle is moving along the road, determining, via processing of first image data captured by the first camera, movement of a road feature present in first image data captured by the first camera; while the vehicle is moving along the road, determining, via processing of second image data captured by the second camera, movement of the road feature when the road feature is present in second image data captured by the second camera; comparing the determined movement of the road feature in first image data captured by the first camera to the determined movement of the road feature in second image data captured by the second camera while the vehicle is moving along the road; determining, via comparing the determined movements of the road feature, a rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle; responsive to determination of the rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle, remapping the first and second image data based at least in part on the determined rotational and translational offset to at least partially accommodate misalignment of the second camera relative to the first camera; and displaying video images derived from image data captured by the first and second cameras. - View Dependent Claims (11, 12, 13)
-
-
14. A method for determining alignment of cameras at a vehicle relative to one another, said method comprising:
-
mounting a first camera at a vehicle so as to have a first field of view encompassing a road surface of a road along which the vehicle is traveling; mounting a second camera at the vehicle so as to have a second field of view encompassing the road surface of the road along which the vehicle is traveling; wherein the first camera is mounted at the vehicle so as to have a forward field of view, and wherein the second camera is mounted at the vehicle so as to have a sideward field of view; wherein the first and second fields of view of the first and second cameras overlap partially; providing an image processor at the vehicle; while the vehicle is moving along the road, capturing first image data via the first camera; while the vehicle is moving along the road, capturing second image data via the second camera; providing first image data captured by the first camera to the image processor; providing second image data captured by the second camera to the image processor; processing, via the image processor, first image data captured by the first camera; processing, via the image processor, second image data captured by the second camera; dewarping the first image data and the second image data; while the vehicle is moving along the road, determining, via processing of first image data captured by the first camera, movement of a road feature present in first image data captured by the first camera; while the vehicle is moving along the road, determining, via processing of second image data captured by the second camera, movement of the road feature when the road feature is present in second image data captured by the second camera; comparing the determined movement of the road feature in first image data captured by the first camera to the determined movement of the road feature in second image data captured by the second camera while the vehicle is moving along the road; determining, via comparing the determined movements of the road feature, a rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle; wherein determining the rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle comprises determining, via comparing the determined movements of the road feature, a rotation of the road feature while the vehicle is moving along the road; responsive to determination of the rotational and translational offset of the second camera at the vehicle relative to the first camera at the vehicle, remapping the first and second image data based at least in part on the determined rotational and translational offset to at least partially accommodate misalignment of the second camera relative to the first camera; and displaying video images derived from image data captured by the first and second cameras. - View Dependent Claims (15, 16, 17, 18)
-
Specification