Systems and methods for vehicle signal light detection

1. A method for analyzing vehicle signal lights in order to operate an autonomous vehicle, comprising:

receiving, by one or more processors, an image from a camera regarding a vehicle proximate to the autonomous vehicle;

using, by the one or more processors, data from a lidar sensor regarding the proximate vehicle to determine object geometry and position information for identifying a subsection within the camera image, wherein the identified subsection corresponds to an area of the proximate vehicle containing one or more vehicle signals; and

locating, by the one or more processors, one or more vehicle signal lights of the proximate vehicle by using the identified camera image subsection as an area of focus;

wherein tracking of the proximate vehicle is based upon the located one or more vehicle signal lights of the proximate vehicle.

2. The method of claim 1 , wherein the data from the lidar sensor provides object depth and distance information;

wherein the lidar sensor and camera are calibrated so that depth can be assigned to the camera image.

3. The method of claim 1 , wherein behavior of the proximate vehicle is predicted based upon the located proximate vehicle signal lights.

4. The method of claim 1 , wherein the locating of the one or more vehicle signal lights by using the identified camera image subsection results in filtering out false positives.

5. The method of claim 1 , wherein the locating of the one or more vehicle signal lights includes using lane information and velocity of the proximate vehicle to differentiate between front of the proximate vehicle and back of the proximate vehicle.

6. The method of claim 1 , wherein the camera image is from a fixed exposure camera.

7. The method of claim 1 , wherein the one or more vehicle signal lights include turn signals, hazard lights, and brake lights.

8. The method of claim 1 , wherein the identifying of the subsection of the camera image includes determining whether the camera image includes rear of the proximate vehicle or front of the proximate vehicle, wherein the identifying of the subsection of the camera image is based upon sizes of signal lights expected to be located within the camera image.

9. The method of claim 1 , wherein the identifying of the subsection of the camera image eliminates other lights that are not vehicle signal lights, thereby reducing processing cycles by avoiding analysis of non-relevant portions of the camera image.

10. The method of claim 1 , wherein the proximate vehicle is in front of the autonomous vehicle or to the side of the autonomous vehicle.

11. A system for analyzing vehicle signal lights in order to operate an autonomous vehicle, the system comprising:

a storage device for storing instructions for performing safety analysis of autonomous vehicle operation; and

one or more data processors configured to execute the instructions to:

receive an image from a camera regarding a vehicle proximate to the autonomous vehicle;

use data from a lidar sensor regarding the proximate vehicle to determine object geometry and position information for identifying a subsection within the camera image, wherein the identified subsection corresponds to an area of the proximate vehicle containing one or more vehicle signals; and

locate one or more vehicle signal lights of the proximate vehicle by using the identified camera image subsection as an area of focus;

wherein tracking of the proximate vehicle is based upon the located one or more vehicle signal lights of the proximate vehicle.

12. The system of claim 11 , wherein the data from the lidar sensor provides object depth and distance information;

wherein the lidar sensor and camera are calibrated so that depth can be assigned to the camera image.

13. The system of claim 11 , wherein behavior of the proximate vehicle is predicted based upon the located proximate vehicle signal lights.

14. The system of claim 11 , wherein the locating of the one or more vehicle signal lights by using the identified camera image subsection results in filtering out false positives.

15. The system of claim 11 , wherein the locating of the one or more vehicle signal lights includes using lane information and velocity of the proximate vehicle to differentiate between front of the proximate vehicle and back of the proximate vehicle.

16. The system of claim 11 , wherein the camera image is from a fixed exposure camera.

17. The system of claim 11 , wherein the one or more vehicle signal lights include turn signals, hazard lights, and brake lights.

18. The system of claim 11 , wherein the identifying of the subsection of the camera image includes determining whether the camera image includes rear of the proximate vehicle or front of the proximate vehicle, wherein the identifying of the subsection of the camera image is based upon sizes of signal lights expected to be located within the camera image.

19. The system of claim 11 , wherein the identifying of the subsection of the camera image eliminates other lights that are not vehicle signal lights, thereby reducing processing cycles by avoiding analysis of non-relevant portions of the camera image, wherein the proximate vehicle is in front of the autonomous vehicle or to the side of the autonomous vehicle.

20. An autonomous vehicle comprising:

at least a camera and lidar sensor that provides sensor data; and

a controller that, by a processor and based on the sensor data:

receives an image from the camera regarding a vehicle proximate to the autonomous vehicle;

uses data from the lidar sensor regarding the proximate vehicle to determine object geometry and position information for identifying a subsection within the camera image, wherein the identified subsection corresponds to an area of the proximate vehicle containing one or more vehicle signals; and

locates one or more vehicle signal lights of the proximate vehicle by using the identified camera image subsection as an area of focus;

wherein tracking of the proximate vehicle is based upon the located one or more vehicle signal lights of the proximate vehicle.