System and method for calibrating on-board vehicle cameras
Provided herein are methods for calibrating a camera. The method may include capturing an image that includes at least a traffic sign. The location of the traffic sign using the image may then be determined, which may include taking as input the location and direction of the vehicle and the location and the direction of the camera relative to the vehicle. The method may also include obtaining an actual location of the traffic sign. The camera may be determined to require recalibration if the determined location is different from the actual location.
1. A method for recalibrating a camera installed on a vehicle, the method comprising:
capturing, with the camera, an image including a traffic sign;
determining a location of the traffic sign based on the image, a location and an orientation of the vehicle, and a location and an orientation of the camera relative to the vehicle;
obtaining an actual location of the traffic sign at a same time that the location of the traffic sign is determined;
determining that the camera requires a recalibration in response to a difference between the determined location and the actual location exceeding a threshold;
correcting at least one of the location or the orientation of the camera relative to the vehicle such that the determined location of the traffic sign matches the actual location of the traffic sign; and
adjusting a rate of determining whether to perform the recalibration on the camera based on a historical rate of recalibrations on the camera.
2. The method of claim 1 , wherein the traffic sign is selected from a group comprising at least one of a traffic light, a stop sign, or a street sign.
3. The method of claim 2 , wherein the traffic sign is a traffic light.
4. The method of claim 3 , wherein two or more traffic lights are captured in the image and used for the recalibration.
5. The method of claim 1 , wherein the actual location of the traffic sign is obtained from a GPS map.
6. The method of claim 1 , wherein the actual location of the traffic sign is obtained by one or more other cameras on the vehicle.
7. The method of claim 1 , wherein the actual location of the traffic sign is obtained by a LiDAR unit on the vehicle.
8. The method of claim 1 , wherein the location and the orientation of the vehicle are determined by a GPS unit in the vehicle.
9. A system comprising:
at least one processor;
a camera; and
memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:
capturing, with the camera, an image including a traffic sign;
determining a location of the traffic sign based on the image, a location and an orientation of the vehicle, and a location and an orientation of the camera relative to the vehicle;
obtaining an actual location of the traffic sign at a same time that the location of the traffic sign is determined;
determining that the camera requires a recalibration in response to a difference between the determined location and the actual location exceeding a threshold;
correcting at least one of the location or the orientation of the camera relative to the vehicle such that the determined location of the traffic sign matches the actual location of the traffic sign; and
adjusting a rate of determining whether to perform the recalibration on the camera based on a historical rate of recalibrations on the camera.
10. The system of claim 9 , wherein the traffic sign is selected from a group comprising at least one of a traffic light, a stop sign, or a street sign.
11. The method system of claim 10 , wherein the traffic sign is a traffic light.
12. The system of claim 11 , wherein two or more traffic lights are captured in the image and used for the recalibration.
13. The system of claim 9 , wherein the actual location of the traffic sign is obtained from a GPS map.
14. The system of claim 9 , wherein the actual location of the traffic sign is obtained by one or more other cameras on the vehicle.
15. The system of claim 9 , wherein the actual location of the traffic sign is obtained by a LiDAR unit on the vehicle.
16. The system of claim 9 , wherein the location and the orientation of the vehicle is determined by a GPS unit in the vehicle.
17. The method of claim 1 , wherein determining the location of the traffic sign based on the image comprises:
determining a projected position of the traffic sign from the image based on an angle view of traffic sign in the image; and
comparing the projected position with other projected positions of the traffic sign in other images captured by one or more other cameras on the vehicle, wherein the projected position of the traffic sign includes at least one of a front view, a back view, a left-side view, a right-side view, or a bottom view of the traffic sign.
18. The system of claim 9 , wherein determining the actual location comprises:
determining a distance between the traffic sign and the camera by calculating a propagation time of a LiDAR pulse reflected from the traffic sign; and
determining the actual location based on the determined distance and the location and the orientation of the vehicle.