Target tracking algorithm based on image set

Abstract

The invention discloses a target tracking algorithm based on an image set. The target tracking algorithm based on the image set comprises an initialization stage, a training stage used for building a target model, a test stage used for testing the central position of a specific target object according to the built target model and an updating stage. According to the target tracking algorithm based on the image set, the image set serves as a basic unit of a training sample and a test sample in the target tracking process, the target tracking problem is considered as a multi-class classification problem under the framework of the kernel partial least square method, and therefore the problem of drifting of a tracker can be effectively relieved.

Description

technical field [0001] The invention relates to the fields of computer vision and pattern recognition in the field of information technology, in particular to an image set-based target tracking algorithm. Background technique [0002] It is not difficult to see from the increasing number of surveillance cameras in public places, streets and lanes that video surveillance has become a conventional means of security surveillance. However, traditional video surveillance is only a tool for recording and replaying historical events, and cannot play a good early warning role. Its "control" function is useless and requires manual "monitoring". With the rapid expansion of the network scale of video surveillance, the number of terminals required to be monitored is increasing day by day. Manual monitoring alone is far from meeting the rapid growth of application requirements. Video surveillance urgently needs to use intelligent means to greatly improve monitoring efficiency and reduce ...

AI Technical Summary

Problems solved by technology

Although this method solves the uncertainty problem of positive sample labeling in the training phase and the updating phase to a certain extent, the method does not make full use of the target object contained in multiple images from different image frames in the training phase. information, and at the testing stage, the method did not make full use of the information contained in multiple image patches containing the target object

Images