Online multi-object tracking method based on unified object motion perception and re-identification network

A multi-target tracking and motion perception technology, applied in the field of online multi-target tracking, can solve the problems of frequent conversion of identity recognition and inability to associate, and achieve the effect of adding re-identification branches, improving performance, and enhancing anti-occlusion ability
CN113313736BActive Publication Date: 2022-05-17XIAMEN UNIV
6 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Patent Type
Patents(China)
Current Assignee / Owner
XIAMEN UNIV
Publication Date
2022-05-17

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

An online multi-object tracking method that unifies object motion perception and re-identification networks, involving computer vision technology. A. Input the current frame image and the previous frame image into the backbone network to obtain the feature maps of the two frames of images; B. Send the heat map of the previous frame image and the two feature maps of step A into the detection and tracking branch to calculate Current frame detection result and target tracking offset; C. Send the feature maps of the two frames of images in step A to the re-identification branch to obtain embedded feature vectors and store them in the re-identification feature vector pool; D. According to the tracking offset, Match the detection results obtained in step B for the first time, and assign the identification of the corresponding target to the matched detection; E. Perform a second match on the unmatched detection results obtained in step D, and match the unmatched detection results with step C The obtained embedded feature vectors are calculated one by one for similarity, and according to the set threshold, different detection results are assigned identity recognition, that is, the final tracking result of the current frame is obtained.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to computer vision technology, in particular to an online multi-target tracking method that unifies target motion perception and re-identification networks. Background technique

[0002] The visual system is a very important way for humans to obtain external information. It can provide humans with rich resource information. As a basic task in the field of computer vision, multi-target tracking aims to estimate the trajectory of a specific category in a sequence. In recent years, research on multi-target tracking algorithms has received more and more attention. However, in dense crowds or low frame rate videos, the targets are prone to large motion offsets, mutual occlusion, overlapping, etc., resulting in limited tracking performance. Therefore, it is of great significance to study the target motion information and construct a simple and effective re-identification network for online multi-target tracking methods.

[0003] The e...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More