Video tracking method based on local background learning

Abstract

The invention provides a video tracking method based on local background learning. The video tracking method includes the steps that the time-space relationship between a target to be tracked and the local background of the target is modeled through the Bayes frame, a plurality of multi-dimensional images of the target are simultaneously collected through the time-space relationship between the modeled target and the local background, and dimensions of the collected multi-dimensional images of the target are reduced through a random sensing matrix meeting compressed sensing conditions to obtain feature vectors of the multiple multi-dimensional images; according to the feature vectors of the multiple multi-dimensional images, the multi-dimensional images with the dimensions reduced are classified through a naive Bayes classifier, and the position where the target appears is estimated according to a likelihood confidence image of the target position; based on target structure constraint conditions, a collector outputs the target with the maximum degree of overlapping with the previous frame target tracked successfully as the final tracking target. The video tracking method is suitable for video target tracking under complex conditions, and is high in discernment capacity and tracking accuracy.

Description

technical field [0001] The invention belongs to the technical field of computer vision tracking, and relates to a video tracking method, in particular to a video tracking method based on local background learning. Background technique [0002] At present, video tracking algorithms are mainly divided into two categories according to different application models: tracking algorithms based on generative models and tracking algorithms based on discriminative models. The representative methods of the former tracking algorithm include the tracking algorithm based on template matching, etc. This type of method realizes tracking by searching the sub-region that best matches the given template in the image, and it ignores the background information around the target. The representative methods of the latter tracking algorithm include detection learning tracking (TLD) and compressed sensing tracking (CT). This type of method regards tracking as a binary classification problem, and fin...

AI Technical Summary

Problems solved by technology

[0006] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a video tracking method based on local background learning, which is used to solve the problem that the video tracking method in the prior art cannot guarantee the accuracy of tracking and the real-time nature of tracking. Problems with object tracking performance

Images