Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-target tracking method

A multi-target tracking and target technology, applied in neural learning methods, image data processing, image enhancement and other directions, can solve problems such as changes in the number of targets, improve tracking performance, improve multi-target tracking accuracy and multi-target tracking accuracy Effect

Pending Publication Date: 2020-05-08
BEIJING JIAOTONG UNIV
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the performance upgrade of the graphics computing platform, the performance of the target detection algorithm continues to improve, which can solve the problem of the number of targets changing during the tracking process

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-target tracking method
  • Multi-target tracking method
  • Multi-target tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] like figure 1 As shown, the multi-target tracking method based on LSTM network includes the following steps:

[0054] (1) Use the MASK-R-CNN target detector to detect each frame of image in the video to be tested, and output the detection result, and set the detection result of the t-th frame image as a set is the i-th detection result of the t-th frame image, N is the total number of detections; output the appearance feature map of the detected target; simultaneously detect and output the segmentation features for targets whose confidence is lower than the tracking threshold.

[0055] (2) if Figure II As shown, a nonlinear motion model based on the LSTM network is constructed, and a multi-target tracker is established by classifying the detected N targets. The LSTM network involved in this application contains three types of multi-target trackers, which are motor vehicle trackers non-motor vehicle tracker pedestrian tracker

[0056] (3) Input the coordinat...

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

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of computer vision, and particularly relates to a multi-target tracking method. The shielding and appearance similarity problems in multi-target tracking still limit the performance of a visual multi-target tracking algorithm. The invention provides a multi-target tracking method. The method includes: detecting each frame of image in the video; outputting a detection result and constructing a nonlinear motion model based on an LSTM network; and constructing a multi-target tracker, outputting a prediction result of the multi-target tracker, constructing a data association module based on a Hungary algorithm, inputting a tracking target prediction position and a feature vector matrix, outputting an allocation probability vector to obtain a targetdetection result with the maximum matching probability, and taking the target detection result as a tracking result of the ith target. The problems of inaccurate tracking and identity switching aftershielding in an existing visual multi-target tracking algorithm are solved, and the tracking performance is greatly improved.

Description

technical field [0001] The present application belongs to the technical field of computer vision, and in particular relates to a multi-target tracking method. Background technique [0002] Visual multi-target tracking is a hot issue in the field of computer vision, with many applications, such as: motion correction, unmanned driving, security monitoring, etc. Due to frequent occlusions in the multi-target tracking process, when the target is occluded during the tracking process, the number of detected targets changes, and the occluded track of the tracked target cannot match the detection target of the current frame, and it is impossible to determine whether the track is due to occlusion Temporarily disappear or leave the detection area to stop tracking, causing a part of the covered track to stop tracking due to misjudgment. After the target occlusion ends, the originally tracked target reappears in the detection area. If the original tracking track has stopped tracking, t...

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/246G06N3/04G06N3/08
CPCG06T7/246G06N3/084G06T2207/10004G06T2207/20081G06T2207/20084G06N3/045Y02T10/40
Inventor 王忠立蔡伯根蔡余钰王剑陆德彪
Owner BEIJING JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com