Motion direction change-based candidate seed point cloud single target tracking method

Abstract

The invention discloses a motion direction change-based candidate seed point cloud single target tracking method, which comprises a training module and a test module, and is characterized in that the training module firstly preprocesses point cloud to obtain template point cloud, then uses Gaussian sampling to obtain candidate point cloud, and then inputs the template point cloud and the candidate point cloud into an encoder for encoding, a corresponding feature vector is obtained, a distance loss function and a direction loss function are calculated, and the whole model is trained. The test module firstly uses a pre-trained PointRcnn model to carry out target detection, then carries out candidate area sampling, then inputs sampled candidate point cloud and tracking target point cloud of a previous frame into the trained model to carry out coding, and finally carries out target tracking on a coded feature vector by using cosine similarity comparison. According to the method, the single-target tracking precision can be improved, and a wrong tracking phenomenon can be effectively prevented.

Description

technical field [0001] The invention relates to a point cloud single-target tracking method, in particular to a point cloud single-target tracking method based on candidate seeds whose motion direction changes, and belongs to the field of 3D point cloud target tracking. Background technique [0002] At present, target tracking at home and abroad is mainly concentrated in the direction of computer vision and lidar. Computer vision mainly refers to obtaining information in images and videos. Since the obtained information is easily affected by changes in weather, light and target rigidity, if encountered In extreme weather conditions or when the point cloud of the tracking target is occluded and truncated, it is difficult to obtain the target information comprehensively by computer vision methods alone, so there are phenomena such as wrong tracking and missing tracking, which make the target tracking effect not good. The 3D point cloud information obtained by lidar has the adv...

AI Technical Summary

Problems solved by technology

[0004] At present, most algorithms are dedicated to point cloud multi-target tracking and few algorithms are used for point target tracking. The existing single target tracking algorithms have two problems: 1. During the tracking training process, only the distance of the target is concerned and the direction of motion of the target is ignored. , resulting in low single-target tracking accuracy; 2. During the implementation process, the target point cloud is compared with the global candidate point cloud, and the similarity between the candidate point cloud and the tracking target point cloud that often appears in a farther position is higher than the actual target point. The similarity between the cloud and the tracking target point cloud is prone to error tracking

Images