| CPC B60W 30/0956 (2013.01) [B60W 40/04 (2013.01); B60W 2420/408 (2024.01); B60W 2554/4041 (2020.02); G06T 2207/30261 (2013.01)] | 20 Claims |
|
1. An obstacle tracking method, comprising:
obtaining two frames of laser point clouds acquired by an unmanned driving device as a first point cloud and a second point cloud;
determining an obstacle aggregation region in the first point cloud according to position information of each obstacle in the first point cloud;
determining, according to a position of the obstacle aggregation region, at least one obstacle in the second point cloud within the obstacle aggregation region as at least one aggregated obstacle, and at least one another obstacle, except the at least one aggregated obstacle, in the second point cloud as at least one non-aggregated obstacle; and
for each of the at least one aggregated obstacle,
determining matching parameter values between the aggregated obstacle and each obstacle in the first point cloud by using a group matching rule, and
determining a matching result of the aggregated obstacle according to the matching parameter values between the aggregated obstacle and each obstacle in the first point cloud;
for each of the at least one non-aggregated obstacle,
determining matching parameter values between the non-aggregated obstacle and each obstacle in the first point cloud by using a non-group matching rule, and
determining a matching result of the non-aggregated obstacle according to the matching parameter values between the non-aggregated obstacle and each obstacle in the first point cloud, wherein a constraint condition of the group matching rule is stronger than a constraint condition of the non-group matching rule; and
determining an obstacle tracking result according to the matching result of each of the at least one aggregated obstacle and the matching result of each of the at least one non-aggregated obstacle.
|