Detection and recalibration for a camera system using lidar data
Systems and method are provided for calibrating a camera system of an autonomous vehicle. In one embodiment, a method includes: identifying, by the processor, a planar object from sensor data generated by a sensor of the autonomous vehicle while the autonomous vehicle is operating; identifying, by the processor, a pattern of the planar object; selecting, by the processor, planar points from the pattern of the planar object; and calibrating, by the processor, the camera system, while the autonomous vehicle is operating, based on the planar points.
1. A computer implemented method of calibrating a camera system of an autonomous vehicle, comprising:
identifying, by a processor, a planar object from sensor data generated by a sensor of the autonomous vehicle while the autonomous vehicle is operating;
identifying, by the processor, a grid-like pattern presented by the planar object based on gradient values computed from the sensor data;
selecting, by the processor, planar points from the pattern of the planar object; and
calibrating, by the processor, the camera system, while the autonomous vehicle is operating, based on the planar points.
2. The method of claim 1 , wherein the sensor data includes lidar data.
3. The method of claim 2 , wherein the identifying the pattern is based on gradient values computed from points of the lidar data.
4. The method of claim 1 , wherein the sensor data includes image data.
5. The method of claim 4 , further comprising:
computing gradient values for pixels in the image data; and
selecting the planar points based on gradient values in the image data.
6. The method of claim 1 , wherein the identifying the pattern is based on gradient values computed from points of lidar data and image data.
7. The method of claim 1 , further comprising filling holes of the pattern based on at least one data enhancing technique.
8. The method of claim 7 , wherein the data enhancing technique includes anti-aliasing.
9. The method of claim 7 , wherein the data enhancing technique is based on a predefined three dimensional map.
10. A computer implemented system for calibrating a camera system of an autonomous vehicle, comprising:
a first non-transitory module that, by a processor, identifies a planar object from sensor data generated by a sensor of the autonomous vehicle while the autonomous vehicle is operating;
a second non-transitory module that, by the processor, identifies a grid-like pattern presented by the planar object based on gradient values computed from the sensor data, and selects planar points from the pattern of the planar object; and
a third non-transitory module that, by the processor, calibrates the camera system, while the autonomous vehicle is operating, based on the planar points.
11. The system of claim 10 , wherein the sensor data includes lidar data.
12. The system of claim 11 , wherein the second non-transitory module identifies the pattern based on gradient values computed from points of the lidar data.
13. The system of claim 10 , wherein the sensor data includes image data and lidar data.
14. The system of claim 13 , wherein the second non-transitory module computes gradient values for pixels in the image data, and selects the planar points based on the gradient values in the image data.
15. The system of claim 10 , wherein the second non-transitory module identifies the pattern is based on gradient values computed from points of lidar data.
16. The system of claim 10 , the second non-transitory module fills holes of the pattern based on at least one data enhancing technique.
17. The system of claim 16 , wherein the data enhancing technique includes anti-aliasing.
18. The system of claim 16 , wherein the data enhancing technique is based on a predefined three dimensional map of the world.
19. A vehicle, comprising:
a lidar system;
a camera system; and
a controller configured to, by a processor, identify a planar object from sensor data generated by the lidar system of the autonomous vehicle while the autonomous vehicle is operating, identify a grid-like pattern presented by the planar object based on gradient values computed from the sensor data, select planar points from the pattern of the planar object, and calibrate the camera system, while the autonomous vehicle is operating, based on the planar points.