US 12,266,192 B2
Traffic light detection and classification for autonomous driving vehicles
Jeong Ho Lyu, Sunnyvale, CA (US); and Lingchang Li, Beijing (CN)
Assigned to Baidu USA LLC, Sunnyvale, CA (US); and Baidu.com Times Technology (Beijing) Co., Ltd., Beijing (CN)
Appl. No. 17/294,877
Filed by Baidu USA LLC, Sunnyvale, CA (US); and Baidu.com Times Technology (Beijing) Co., Ltd., Beijing (CN)
PCT Filed Apr. 20, 2021, PCT No. PCT/CN2021/088379
§ 371(c)(1), (2) Date May 18, 2021,
PCT Pub. No. WO2022/222028, PCT Pub. Date Oct. 27, 2022.
Prior Publication US 2024/0020988 A1, Jan. 18, 2024
Int. Cl. G06V 20/58 (2022.01); B60W 60/00 (2020.01); G06V 10/56 (2022.01); H04N 23/73 (2023.01)
CPC G06V 20/584 (2022.01) [B60W 60/001 (2020.02); G06V 10/56 (2022.01); H04N 23/73 (2023.01); B60W 2420/403 (2013.01); B60W 2555/60 (2020.02)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method for operating an autonomous driving vehicle (ADV), the method comprising:
perceiving a driving environment based on sensor data obtained from a plurality of sensors mounted on the ADV, the perceiving including detecting a traffic light, the plurality of sensors including an image sensor;
applying a first sensor setting to the image sensor to capture a set of first frames, the first sensor setting including at least one of a first exposure time or a first gain;
alternately applying a second sensor setting to the image sensor to capture a set of second frames, the second sensor setting including at least one of a second exposure time or a second gain, the second sensor setting further including a red light intensity below a red light intensity saturation threshold, wherein at least one of:
the second exposure time is less than the first exposure time, or
the second gain is less than the first gain;
determining a presence of the traffic light based on the set of first frames;
determining a color of the traffic light based on the set of second frames; and
controlling the ADV to drive autonomously according to the determined color of the traffic light and the perceived driving environment.