Determining yaw error from map data, lasers, and cameras
The present disclosure relates to methods and systems that facilitate determination of a pose of a vehicle based on various combinations of map data and sensor data received from light detection and ranging (LIDAR) devices and/or camera devices. An example method includes receiving point cloud data from a (LIDAR) device and transforming the point cloud data to provide a top-down image. The method also includes comparing the top-down image to a reference image and determining, based on the comparison, a yaw error. An alternative method includes receiving camera image data from a camera and transforming the camera image data to provide a top-down image. The method also includes comparing the top-down image to a reference image and determining, based on the comparison, a yaw error.
1. A method comprising:
capturing point cloud data using a light detection and ranging (LIDAR) device, wherein the point cloud data comprises information indicative of objects in an environment around a vehicle;
transforming the point cloud data to provide a top-down image;
comparing the top-down image to a reference image; and
determining, based on the comparison, a yaw error.
2. The method of claim 1 , wherein comparing the top-down image to the reference image comprises performing normalized cross-correlation, grayscale matching, gradient matching, histogram matching, edge detection, scale-invariant feature transform (SIFT), or speeded-up robust features (SURF).
3. The method of claim 1 , wherein the top-down image comprises a flattened two-dimensional image of the environment around the vehicle.
4. The method of claim 1 , further comprising:
providing an adjustment signal to a pose estimator of a vehicle based on the determined yaw error.
5. The method of claim 4 , further comprising:
determining, with the pose estimator, a yaw orientation of the vehicle; and
determining a refined yaw orientation based on the adjustment signal and the determined yaw orientation.
6. The method of claim 1 , wherein the reference image comprises at least a portion of map data.
7. The method of claim 1 , wherein the reference image comprises at least a portion of at least one of: one or more prior camera images, a LIDAR point cloud, RADAR data, satellite imagery, or other overhead imagery.
8. A method comprising:
capturing camera image data using a camera, wherein the camera image data comprises information indicative of an environment around a vehicle;
transforming the camera image data to provide a top-down image;
adjusting the top-down image by removing temporally varying objects;
comparing the top-down image to a reference image; and
determining, based on the comparison, a yaw error.
9. The method of claim 8 , wherein comparing the top-down image to the reference image comprises performing normalized cross-correlation, grayscale matching, gradient matching, histogram matching, edge detection, scale-invariant feature transform (SIFT), or speeded-up robust features (SURF).
10. The method of claim 8 , wherein the top-down image comprises a flattened two-dimensional image of the environment around the vehicle.
11. The method of claim 8 , further comprising:
providing an adjustment signal to a pose estimator of a vehicle based on the determined yaw error.
12. The method of claim 11 , further comprising:
determining, with the pose estimator, a yaw orientation of the vehicle; and
determining a refined yaw orientation based on the adjustment signal and the determined yaw orientation.
13. The method of claim 8 , wherein the reference image comprises at least a portion of map data.
14. The method of claim 8 , wherein the reference image comprises at least a portion of at least one of: one or more prior camera images, a LIDAR point cloud, RADAR data, satellite imagery, or other overhead imagery.
15. A method comprising:
receiving reference data, wherein the reference data comprises information indicative of an overhead perspective of a scene;
transforming the reference data so as to correspond to a field of view of a camera;
capturing camera image data using the camera, wherein the camera image data comprises information indicative of an environment around a vehicle;
comparing the transformed reference data to the camera image data; and
determining, based on the comparison, a yaw error.
16. The method of claim 15 , wherein the camera image data comprises a flattened two-dimensional image of the environment around the vehicle.
17. The method of claim 15 , further comprising:
providing an adjustment signal to a pose estimator of a vehicle based on the determined yaw error.
18. The method of claim 15 , wherein the camera image data corresponds to at least a portion of the transformed reference data.
19. The method of claim 15 , wherein the reference data comprises at least a portion of at least one of: one or more prior camera images, a LIDAR point cloud, RADAR data, satellite imagery, or other overhead imagery.
20. The method of claim 15 , wherein at least one of: the reference data or the camera image data are processed with at least one of: an image difference algorithm, an image homography algorithm, or an image rectification algorithm.