Target Scale Adaptive Tracking Method Based on Spatiotemporal Model

Abstract

The invention discloses a target scale adaptive tracking method based on a spatio-temporal model, which comprises the following steps: start the video, read in the first frame image, and manually specify the rectangular position of the tracking target; then, based on the context space, initialize the spatio-temporal model and multi-scale history Target template library; then read in the next frame of image, iteratively construct the space-time model, calculate the confidence map, and estimate the center position of the target; then judge the optimal scale of the template according to the historical target template library, determine the position of the target rectangle, and complete the current frame target tracking. And update the spatio-temporal model scale parameters and the multi-scale historical target template library; finally check whether the video is over, and continue to read the next frame if it is not over, otherwise end the tracking. The invention effectively copes with the change of the appearance scale of the target and realizes robust tracking when the target suffers from disturbances such as illumination changes, local occlusion and fast movement.

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