Video target tracking method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of video tracking, and particularly discloses a video target tracking method and device, electronic equipment and a storage medium, and the method comprises the following steps: obtaining video information; setting initial tracking target information according to the video information; acquiring scale change information of the video information according to the initial tracking target information on the basis of a tracking algorithm which has a scale change tracking characteristic and performs tracking by using an L-K optical flow method under the condition of not performing target position tracking; respectively adjusting the position and the scale of the initial tracking target information according to the position change information and the scale change information so as to track the target in the video information; according to the method, accurate tracking including scale and position parameters can be rapidly carried out on the target in the video information.

Description

technical field [0001] The present application relates to the technical field of video tracking, and in particular, to a video object tracking method, device, electronic equipment, and storage medium. Background technique [0002] Video target tracking technology is the technology of locating targets in continuous frames of video. [0003] Video object tracking is widely used in various fields, such as intelligent video surveillance, visual navigation, medical diagnosis, virtual reality, etc. [0004] In the prior art, video target tracking generally uses one of Boosting, MIL, KCF, TLD, Median Flow, GOTURN, MOSSE and CSRT algorithms for tracking; these algorithms have different functions, principles, effects, and speeds, and the tracking operation speed is fast The tracking algorithm cannot obtain the feature of the target size change in the video (ie, the scale feature), and the tracking algorithm that can obtain the feature of the target size change in the video has a fas...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, video target tracking generally uses one of Boosting, MIL, KCF, TLD, Median Flow, GOTURN, MOSSE and CSRT algorithms for tracking; these algorithms have different functions, principles, effects, and speeds, and the tracking operation speed is fast The tracking algorithm can not obtain the target size change feature in the video (that is, the scale feature), and the tracking algorithm that can obtain the target size change feature in the video has a fast operation speed and a low speed.

[0005] For the above problems, there is no effective technical solution

Images