Multi-scale correlation filtering target tracking method and device based on response discrimination

Abstract

The invention discloses a multi-scale correlation filtering target tracking method and a multi-scale correlation filtering target tracking device based on response discrimination. The method specifically comprises the steps of determining an initial target position and an initial target size of a current frame image; determining a tracking window size according to the initial target size; extracting a sampling image block in the current frame image based on the initial target position and the tracking window size; performing target detection on the sampling image block, obtaining a response graph corresponding to the sampling image block, and extracting a maximum response peak value of the response graph as a first maximum response peak value; determining a final target position and a final target size in the current frame image according to the first maximum response peak value in response to the fact that the first maximum response peak value is greater than or equal to the first threshold value; according to the method, multi-scale detection does not need to be carried out on each frame of image, so that the calculation amount of target tracking in the video sequence is reduced,the calculation time is shortened, and real-time tracking of the video sequence is realized.

Description

technical field [0001] The invention belongs to the technical field of target tracking, and in particular relates to a multi-scale correlation filtering target tracking method and device based on response discrimination. Background technique [0002] Target tracking is an important research direction of computer vision. It is to accurately find information such as the position and trajectory of the target of interest in the video sequence. It is widely used in security monitoring, military guidance, human-computer interaction, medical diagnosis, virtual reality, and intelligent transportation. and visual navigation. In actual tracking applications, the change of the target scale in the video sequence is a frequent occurrence. Whether the scale of the target tracking template is accurate has an important impact on the performance of the tracking. As the scale error continues to spread and accumulate, it will eventually cause It will fail badly in target tracking. [0003] A...

AI Technical Summary

Problems solved by technology

In actual tracking applications, the change of the target scale in the video sequence is a frequent occurrence. Whether the scale of the target tracking template is accurate has an important impact on the performance of the tracking. As the scale error continues to spread and accumulate, it will eventually cause Will target tracking fail badly

[0003] At present, in the tracking method, feature extraction and response value calculation will bring a large amount of calculation burden. The more scales, the greater the calculation load of target tracking, which leads to longer calculation time, and it is difficult to achieve real-time tracking of targets.

Images