Anti-blocking target tracking method

A target tracking and anti-occlusion technology, applied in the field of computer vision, can solve the problems of drift, change, complex background environment, etc., achieve the effect of lasting stable tracking and improve the suppression ability

Active Publication Date: 2017-02-15
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Video tracking still faces many problems in practical applications: such as: changes in illumination, changes in the attitude of the target, and complex background environments. Long-term target tracking is a challenging task. The difficulty lies in dealing with cumulative errors and drift. on issues such as occlusion
However, in the process of persistent target tracking, occlusion and target attitude changes are unavoidable, which will lead to drift problems

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
  • Anti-blocking target tracking method
  • Anti-blocking target tracking method
  • Anti-blocking target tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0037] Such as figure 1 As shown, an anti-occlusion target tracking method includes the following steps:

[0038] Step 1: According to the initial image frame, determine the target area, initialize the tracker parameters, the tracker forms the initial target template through the target area, and use the target template and background template to sparsely represent the candidate target:

[0039]

[0040] In formula (1), is a candidate target, T t represents the target template, is the coefficient of the target template, I represents the background template, is the coefficient of the background template, the subscript t indicates the tth frame, the superscript i=1, 2,..., N, and N is the total number of candidate targets.

[0041] Step 2: Initialize the cascade detector.

[0042] The cascade detector is composed of variance classifi...

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 discloses an anti-blocking target tracking method comprising the following steps: first, the area of a target is determined according to initial image frames, and a tracker forms an initial target template according to the target area; second, the parameters of a cascaded detector are initialized; third, a blocking detection mechanism is added, and the threshold is updated in real time; fourth, the tracking confidence and detection confidence of the tracker and the detector to the target are calculated respectively; and finally, the tracking result is integrated according to the confidence, the tracker is initialized by use of the detection result if the tracker fails to track the target, and the tracking result is input to a learning module in order to update the corresponding parameters of the detector. By adding the blocking detection mechanism, the drift inhibition ability of the tracking algorithm is improved, and lasting and sound tracking is realized.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to an anti-occlusion target tracking method. Background technique [0002] In recent years, video target tracking, as a key technology in the field of computer vision research, has been widely used in various fields of national defense and civilian use, such as medical diagnosis, intelligent monitoring, human-computer interaction, navigation guidance, etc. Video tracking still faces many problems in practical applications: such as: changes in illumination, changes in the attitude of the target, and complex background environments. Long-term target tracking is a challenging task. The difficulty lies in dealing with cumulative errors and drift. occlusion etc. [0003] There are several commonly used target tracking algorithms in the field of video target detection and tracking at home and abroad: tracking algorithms based on target motion characteristics, such as:...

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): G06T7/223G06T7/246G06K9/62
CPCG06T2207/20081G06T2207/20004G06T2207/10016G06F18/24
Inventor 杨欣张鹏张芹兰周大可刘冬雪高菊
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap