Supercharge Your Innovation With Domain-Expert AI Agents!

Track confidence coefficient based multi-object tracking method

A multi-target tracking and confidence level technology, applied in the field of image processing, can solve the problems of low target tracking accuracy, unsatisfactory tracking effect of large-density crowds, and unfulfilled requirements for applications with high time requirements

Inactive Publication Date: 2016-07-27
SYSU CMU SHUNDE INT JOINT RES INST +1
View PDF4 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are some defects in the above-mentioned algorithms, which mainly include: (1) slow calculation speed. Most of these methods determine the target trajectory in the entire video set, which requires a long calculation time, and cannot meet the requirements for some applications with high time requirements; (2) ) The target tracking accuracy rate is not high, generally the color feature information is not fully utilized, and the tracking effect on large-density crowds is not ideal

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
  • Track confidence coefficient based multi-object tracking method
  • Track confidence coefficient based multi-object tracking method
  • Track confidence coefficient based multi-object tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] A multi-target tracking method based on trajectory confidence, comprising the following steps:

[0043] S1: Detect the moving target in each frame of the video, and save the detected detection accuracy of each detected moving target;

[0044] S2: Extract the detection accuracy of each moving target in each frame of the video and the continuity of the moving track of the moving target in the video, and calculate the confidence of the moving target's moving track;

[0045] S3: Set a confidence threshold. For a moving target whose trajectory confidence is greater than the threshold, its trajectory is judged as a high-confidence trajectory, otherwise it is a low-confidence trajectory;

[0046] S4: First make a local correlation between the moving target of the high-confidence trajectory and the current frame, and then globally correlate the moving target of the low-confidence trajectory with the current frame;

[0047] S5: Steps S1-S4 are repeated until the end of the vide...

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 provides a track confidence coefficient based multi-object tracking method. According to the invention, the moving object detection accuracy and the track continuity are adopted for indicating the confidence of a track. A multi-object tracking problem is solved through the track confidence. Based on the moving object track confidence, different correlation method is adopted for tracks with confidence in different ranges. The moving object track links current detection object frame by frame. Track fragment can be correlated to the movement track without iteration and high-cost correlation, so that calculation amount is reduced. Since the track confidence contains moving object multiple information and different processing methods are adopted for tracks with different confidence, the object tracking accuracy is improved.

Description

technical field [0001] The invention relates to the field of image processing, and more specifically, to a multi-target tracking method based on trajectory confidence. Background technique [0002] Multi-target tracking technology has been widely used in many fields such as video surveillance, intelligent transportation systems, and robots. However, the accuracy of tracking results in complex environments still needs to be improved, and the calculation and processing time needs to be shortened. Since the algorithm for single-frame picture target detection is relatively mature, and the detection accuracy is getting higher and higher, most of the existing research directly uses the detection results of single-frame pictures, focusing on the correlation algorithm between targets to determine the target trajectory. The existing multi-target tracking methods include: multi-target tracking based on the target pair model, looking for target pairs from pictures, and then finding the...

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
IPC IPC(8): G06T7/20
CPCG06T2207/10016G06T2207/10024G06T2207/30241
Inventor 胡海峰潘瑜曹向前肖翔张伟
Owner SYSU CMU SHUNDE INT JOINT RES INST
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com