Object scale self-adaption tracking method based on spatial-temporal model

Abstract

The invention discloses an object scale self-adaption tracking method based on a spatial-temporal model, and the method comprises the following steps: beginning a video, reading in a first frame of image, manually assigning the rectangle position of a tracked object; then based on context airspace, initializing the spatial-temporal model and a multiscale history object template library; next reading in a next frame of image, building the spatial-temporal model by iteration, calculating a confidence map, and estimating an object center position; then according to the history object template library, judging a template optimal scale, determining the rectangle position of the object, completing tracking of the current frame of object, and updating scale parameters of the spatial-temporal model and the multiscale history object template library; finally detecting whether the video is finished or not, continuously reading in a next frame if the video is not finished, or completing tracking. By adopting the object scale self-adaption tracking method, the object appearance scale change is effectively coped with under the conditions of illumination change, partial blocking and swift moving, and the robust tracking is realized.

Description

Technical field: [0001] The invention belongs to the field of machine vision, and in particular relates to an adaptive tracking method of target scale based on a spatio-temporal model. Background technique: [0002] Target tracking is a high-level visual processing in the video surveillance system, that is, using computer vision, image and video processing and other related technologies to describe, process and analyze the targets in the image sequence captured by the camera without human intervention, to achieve Detect, track and identify moving objects in dynamic scenes, and then obtain the trajectory of interest based on the processed and analyzed object characteristics. Moving target tracking and detection is an important research content in the field of video surveillance. The effect of target tracking and detection in video images directly affects the accuracy of advanced processing such as target behavior detection, event understanding and analysis in the subsequent v...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem of the decrease of tracking accuracy caused by the change of target scale, the present invention introduces a multi-scale historical target template library constructed by borrowing the idea of ​​clustering, proposes a target scale adaptive tracking algorithm based on a spatio-temporal model, and realizes the real-time target robustness of scale change. stick track

Images