TLD target tracking method based on circle projection matching algorithm

A target tracking and matching algorithm technology, applied in the field of target tracking, can solve the problems of three-layer classifiers, such as complex calculation, affecting engineering practice effect, and poor real-time performance, and achieve the effect of small calculation, improved real-time performance, and simple algorithm

Active Publication Date: 2017-10-13
XIDIAN UNIV
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But when the target rotates at a large angle, it is easy to cause the target to be lost
Moreover, the three-tier classifier of the traditional TLD tracking algorithm detection module has complex calculations and poor real-time performance. Among them, the random fern classifier is particularly time-consuming, which affects the effect of engineering practice.
[0005] Therefore, improving the anti-rotation performance of the TLD target tracking algorithm is still a very challenging subject.

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
  • TLD target tracking method based on circle projection matching algorithm
  • TLD target tracking method based on circle projection matching algorithm
  • TLD target tracking method based on circle projection matching algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] See figure 1 , figure 1 A schematic flow chart of a TLD target tracking method based on a circular projection matching algorithm provided by an embodiment of the present invention; wherein, the target tracking method includes: a tracking module, a detection module, and a learning module, and the method includes:

[0041] (a) Initially select the target area from the first frame image, and obtain the target area information;

[0042] (b) The tracking module predicts and determines the target tracking result according to the target area information in the previous frame image;

[0043] (c) The detection module performs global traversal on the current frame image to obtain a target to be selected;

[0044] (d) The detection module uses a circular projection matching algorithm to screen the candidate target to form a target detection result;

[0045] (e) determining a target tracking area according to the target tracking result and the target detection result;

[0046] ...

Embodiment 2

[0070] See figure 2 , figure 2 A schematic diagram of the working principle of a circular projection matching algorithm provided for the embodiment of the present invention; this embodiment provides a TLD target tracking method based on the circular projection matching algorithm on the basis of the above-mentioned embodiments, combined with the workflow of the TLD algorithm , focusing on the improvement of the detection module. The detection module mainly makes the following improvements: remove the random fern classifier, and improve the nearest neighbor classifier matching algorithm for the TLD detection module.

[0071] The working process of the TLD target tracking method of the circle projection matching algorithm in this embodiment is as follows:

[0072] S01: Select the position and size of the target in the starting frame; at the starting frame of the video (or picture sequence), manually determine a rectangle containing the target through the mouse to obtain the t...

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 relates to a TLD target tracking method based on a circle projection matching algorithm. A tracking module, a detection module and a learning module are comprised. The method comprises steps that initialization selection of a target zone from a first image is carried out, and the target zone information is acquired; the target tracking result is determined by the tracking module according to target zone information prediction of a previous image; global traversal of the present image is carried out by the detection module to acquire to-be-selected targets; the circle projection matching algorithm is employed by the detection module to screen the to-be-selected targets to acquire the target detection result; a target tracking zone is determined according to the target tracking result and the target detection result; the target tracking zone is inputted to the learning module for learning. The method is advantaged in that rotation resistance is greatly improved, calculation amount is relatively small, the algorithm is simple, and timeliness of the TLD algorithm is further improved.

Description

technical field [0001] The invention belongs to the technical field of target tracking, and in particular relates to a TLD target tracking method based on a circular projection matching algorithm. Background technique [0002] Target tracking has a wide range of applications in both military and civilian fields. With the rapid development of modern aerospace technology, various navigation speeds and maneuverability are getting higher and higher, and higher and higher requirements are put forward for target tracking. Target tracking is an organic combination of automatic control, image processing, and information science to form a technology that can automatically identify targets, extract and predict target position information, and automatically track target motion from image signals in real time. [0003] As a single target tracking algorithm based on online learning detection, TLD (Tracking-Learning-Detection, TLD for short) tracking algorithm has received extensive atte...

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): G06T7/269G06T7/246G06K9/62
CPCG06T7/248G06T7/269G06T2207/20081G06T2207/10016G06F18/24147G06F18/24
Inventor 刘杰涛袁胜春张策俱青
Owner XIDIAN UNIV
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