US 11,908,200 B2
System and method in the prediction of target vehicle behavior based on image frame and normalization
Kilsoo Kim, Hermosa Beach, CA (US); Jongmoo Choi, Gardena, CA (US); Mayukh Sattiraju, Redondo Beach, CA (US); and Siddharth Agarwal, Torrance, CA (US)
Assigned to Canoo Technologies Inc., Torrance, CA (US)
Filed by Canoo Technologies Inc., Torrance, CA (US)
Filed on Jul. 13, 2021, as Appl. No. 17/305,701.
Prior Publication US 2023/0015357 A1, Jan. 19, 2023
Int. Cl. G06V 20/58 (2022.01); G06V 10/75 (2022.01); G06V 20/56 (2022.01)
CPC G06V 20/58 (2022.01) [G06V 10/751 (2022.01); G06V 20/588 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
capturing a series of image frames for traffic lanes in front of an ego vehicle using at least one camera, wherein each of the series of image frames is captured at a different one of a plurality of times, and wherein the traffic lanes include an ego traffic lane occupied by the ego vehicle and an adjacent traffic lane for traffic traveling in a same direction as traffic within the ego traffic lane;
processing each of the image frames to detect a target vehicle in the adjacent traffic lane within the respective image frame at a time corresponding to capture of the respective image frame;
determining, using pixel measurements extracted from the image frames, a predicted time to line crossing for the detected target vehicle to cross into the ego traffic lane from the adjacent traffic lane;
determining a rate of arrival R(k) of the target vehicle from the ratio Ln(k) at time k and the ratio Ln(k−1) at time k−1; and
controlling the ego vehicle based on the predicted time to line crossing by the target vehicle into the ego traffic lane from the adjacent traffic lane.