Target tracking method, device and equipment based on mutual supervision twin network

Abstract

The invention relates to the technical field of computers, in particular to a target tracking method, device and equipment based on a mutual supervision twin network. The method comprises the following steps: acquiring a first twinning network similarity response graph in a twinning A network; obtaining a 90-degree rotation twinning network similarity response graph in the twinning B network, andthen performing reverse 90-degree rotation to obtain a second twinning network similarity response graph; performing network training on the obtained first and second twin network similarity responsegraphs to obtain an optimal network model; obtaining a fusion response graph from the first twin network similarity response graph and the second twin network similarity response graph through a meanvalue fusion method; according to the method, more visual information can be better fused from multiple perspectives of a homologous image, the problem of rotation invariance of a convolutional neuralnetwork can be effectively solved, the tracking robustness of a tracker in target rotation is improved, and the tracking precision of the tracker in target rotation is improved. And meanwhile, the problems of tracking drift and tracking failure caused by tracking error accumulation and tracking target rotation can be solved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a target tracking method, device and equipment based on mutual supervision twin network. Background technique [0002] The tracking method of a single moving target based on information such as images and videos has extremely wide applications in intelligent robot control, computer-human interaction, UAV visual navigation, automatic / assisted driving, and smart city security monitoring. [0003] At present, the commonly used target tracking methods mainly include two types. One is the target tracking method based on the accumulated information of adjacent frames. A tracker that can be iteratively updated online locates the target to be tracked in the search area of ​​each frame. To a certain extent, it can effectively supplement the change information of the target to be tracked, and can effectively obtain dynamic information such as color change, shape change and attitu...

AI Technical Summary

Problems solved by technology

[0005] Based on this, the present invention aims at the above problems and provides a target tracking method based on mutual supervision twin network, which aims to solve the problem that existing target tracking methods cannot solve complex problems such as target rotation, color change, shape change and attitude change in the real environment. Reasonable handling of the problem leads to technical problems that the existing target tracking methods are difficult to use effectively in reality

Images