Target tracking method and device, and storage medium

Abstract

The embodiment of the invention provides a target tracking method and a device, and a storage medium. The method comprises the steps of performing density clustering on current frame point cloud datato obtain at least one point cloud cluster; matching the point cloud cluster with at least one current target by adopting at least one matching mode to obtain a matching result, and marking a target corresponding to the point cloud cluster according to the matching result; wherein the matching result indicates that no current target is matched with the point cloud cluster, and the target corresponding to the point cloud cluster is a new target, or the matching result indicates the point cloud cluster matched with the current target one by one, and the target corresponding to the point cloud cluster is the current target indicated by the matching result; wherein the at least one matching mode comprises feature matching, space matching and matching according to a weighting result. The targettracking method of the invention can improve the accuracy of target tracking.

Description

technical field [0001] The embodiments of this specification relate to the technical field of object tracking, and in particular, to an object tracking method, device, and storage medium. Background technique [0002] With the continuous improvement of the computing power of processors and other hardware and the rapid development of software algorithms, the implementation of target tracking has developed from traditional target tracking based on image processing technology to target tracking based on point cloud data. [0003] Target tracking schemes based on point cloud data generally segment and cluster point cloud data, extract local or global feature descriptor operators, and then match with reference descriptor operators to establish associations to achieve target tracking. [0004] If the same or similar feature descriptor operators are extracted, the matching may be inaccurate, resulting in an association error. For example, the extracted feature descriptor operators...

AI Technical Summary

Problems solved by technology

[0004] If the same or similar feature descriptor operators are extracted, the matching may be inaccurate, resulting in an association error

For example, the extracted feature descriptor operators A and B are the same, and their corresponding targets should be A' and B', but when matching with the reference descriptor operator, A and B may be mistakenly associated with the target A' The corresponding reference descriptor operator matches

Images