Measurements incorporating brake light detection
Systems, methods, and non-transitory computer readable media may be configured to calibrate sensor measurements based on detection of brake light. Acceleration information of a first vehicle may be obtained. The acceleration information may define an acceleration probability distribution of the first vehicle. Image information may be obtained. The image information may define an image of the first vehicle. Whether a brake light of the first vehicle is on or off may be determined based on the image of the first vehicle. Based on a determination that the brake light of the first vehicle is on, a calibrated acceleration probability distribution of the first vehicle may be generated based on the acceleration probability distribution of the first vehicle and a braking-calibration curve.
1. A system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the system to perform:
obtaining acceleration information of a first vehicle, the acceleration information defining an acceleration probability distribution of the first vehicle;
obtaining image information of the first vehicle, the image information defining an image of the first vehicle;
determining whether a brake light of the first vehicle is on or off based on the image of the first vehicle;
upon a determination that the brake light of the first vehicle is on, determining a location of the first vehicle based on the acceleration probability distribution and a braking-calibration curve;
generating, based on the determined location of the first vehicle, navigation instructions for a second vehicle; and
populating the generated navigation instructions on a display.
2. The system of claim 1 , wherein the acceleration information is determined based on a LIDAR sensor or a radar sensor.
3. The system of claim 2 , wherein the acceleration information is determined based on distance values and speed values of the first vehicle detected by the LIDAR sensor or the radar sensor.
4. The system of claim 3 , wherein the LIDAR sensor or the radar sensor is carried by the second vehicle behind the first vehicle.
5. The system of claim 4 , wherein the image information is generated by an image capture device of the second vehicle.
6. The system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to perform:
generating, based on the determination that the brake light of the first vehicle is on, a calibrated acceleration probability distribution of the first vehicle based on the acceleration probability distribution of the first vehicle and the braking-calibration curve, wherein generating the calibrated acceleration probability distribution of the first vehicle includes multiplying the acceleration probability distribution of the first vehicle by the braking-calibration curve.
7. The system of claim 6 , wherein generating the calibrated acceleration probability distribution of the first vehicle further includes scaling a product of the acceleration probability distribution and the braking-calibration curve such that probabilities of the calibrated acceleration probability distribution sum to one.
8. The system of claim 6 , wherein the location or a speed of the first vehicle is determined based on the calibrated acceleration probability distribution of the first vehicle.
9. The system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the system to perform:
generating, based on a determination that the brake light of the first vehicle is off, a calibrated acceleration probability distribution of the first vehicle based on the acceleration probability distribution of the first vehicle and a non-braking-calibration curve.
10. A method implemented by a computing system including one or more processors and storage media storing machine-readable instructions, wherein the method is performed using the one or more processors, the method comprising:
obtaining acceleration information of a first vehicle, the acceleration information defining an acceleration probability distribution of the first vehicle;
obtaining image information of the first vehicle, the image information defining an image of the first vehicle;
determining whether a brake light of the first vehicle is on or off based on the image of the first vehicle;
upon a determination that the brake light of the first vehicle is on, determining a location of the first vehicle based on the acceleration probability distribution and a braking-calibration curve;
generating, based on the determined location of the first vehicle, navigation instructions for a second vehicle; and populating the generated navigation instructions on a display.
11. The method of claim 10 , wherein the acceleration information is determined based on a LIDAR sensor or a radar sensor.
12. The method of claim 11 , wherein the acceleration information is determined based on distance values and speed values of the first vehicle detected by the LIDAR sensor or the radar sensor.
13. The method of claim 12 , wherein the LIDAR sensor or the radar sensor is carried by the second vehicle behind the first vehicle.
14. The method of claim 13 , wherein the image information is generated by an image capture device of the second vehicle.
15. The method of claim 10 , further comprising:
generating, based on the determination that the brake light of the first vehicle is on, a calibrated acceleration probability distribution of the first vehicle based on the acceleration probability distribution of the first vehicle and the braking-calibration curve, wherein generating the calibrated acceleration probability distribution of the first vehicle includes multiplying the acceleration probability distribution of the first vehicle by the braking-calibration curve.
16. The method of claim 15 , wherein generating the calibrated acceleration probability distribution of the first vehicle further includes scaling a product of the acceleration probability distribution and the braking-calibration curve such that probabilities of the calibrated acceleration probability distribution sum to one.
17. The method of claim 15 , wherein the location or a speed of the first vehicle is determined based on the calibrated acceleration probability distribution of the first vehicle.
18. The method of claim 10 , further comprising:
generating, based on a determination that the brake light of the first vehicle is off, a the calibrated acceleration probability distribution of the first vehicle based on the acceleration probability distribution of the first vehicle and a non-braking-calibration curve.
19. A non-transitory computer readable medium comprising instructions that, when executed, cause one or more processors to perform:
obtaining acceleration information of a first vehicle, the acceleration information defining an acceleration probability distribution of the first vehicle;
obtaining image information of the first vehicle, the image information defining an image of the first vehicle;
determining whether a brake light of the first vehicle is on or off based on the image of the first vehicle;
upon a determination that the brake light of the first vehicle is on, determining a location of the first vehicle based on the acceleration probability distribution and a braking-calibration curve;
generating, based on the determined location of the first vehicle, navigation instructions for a second vehicle; and populating the generated navigation instructions on a display.
20. The non-transitory computer readable medium of claim 19 , further comprising:
generating, based on the determination that the brake light of the first vehicle is on, a calibrated acceleration probability distribution of the first vehicle based on the acceleration probability distribution of the first vehicle and the braking-calibration curve, wherein generating the calibrated acceleration probability distribution of the first vehicle includes multiplying the acceleration probability distribution of the first vehicle by the braking-calibration curve.