United target tracking method based on local sparse representation and system thereof

A target tracking and local sparse technology, applied in the field of intelligent video, can solve problems such as failure to track successfully, changes in appearance features, and occlusion of target images

Active Publication Date: 2014-01-29
HEFEI UNIV OF TECH
View PDF3 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the defect that the video tracking technology in the prior art cannot track successfully when it encounters target image occlusion and appearance feature changes, and provides a joint target tracking method and system based on local sparse representation to solve the above 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
  • United target tracking method based on local sparse representation and system thereof
  • United target tracking method based on local sparse representation and system thereof
  • United target tracking method based on local sparse representation and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] In order to have a further understanding and understanding of the structural features of the present invention and the achieved effects, the preferred embodiments and accompanying drawings are used for a detailed description, as follows:

[0068] like figure 1 As shown, a joint target tracking method based on local sparse representation of the present invention comprises the following steps:

[0069] The first step is to initialize the target appearance feature template, initialize the video target position through the first frame image of the video, construct the feature template obtained from the sparse coding histogram, construct the classifier model obtained from the local sparse coefficient, and use the feature template and the classifier The models form a joint object tracking template. Both the feature template and the classifier model will be used as the basic data for the comparison of the second frame of images, so as to determine the target image. In this co...

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 united target tracking method based on local sparse representation and a system thereof. Compared with the prior art, the united target tracking method based on the local sparse representation and the system thereof overcome the defects that tracking cannot succeed when target images are shielded and the appearance characteristics change in the video tracking technology. The united target tracking method based on the local sparse representation comprises the following steps of initializing a template of the appearance characteristics of a target, tracking images of the target, updating a tracking template of a united target, and checking whether reading of a video is finished or not. The united target tracking method based on the local sparse representation and the system thereof improve the precision and efficiency of target tracking in complex scenes, and improve the application degree of the target tracking technology in various scenes. The effect that accurate tracking can be achieved when target images are shielded is achieved through classifier models in the comparing process and by adopting the self-learning technology in the tracking technology.

Description

technical field [0001] The invention relates to the field of intelligent video technology, in particular to a joint target tracking method and system based on local sparse representation. Background technique [0002] Object tracking in video is an important research direction in the field of computer vision, and plays a vital role in many practical applications, such as video surveillance, video scene understanding, interactive video processing, etc. At this stage, researchers have proposed different tracking algorithms and achieved certain success in different application scenarios. However, when the tracked target has experienced a long video sequence, the occlusion, the shape of the target appearance, the lighting of the environment, etc. will all change, resulting in the target tracking cannot be completed smoothly. At the same time, after the target image passes through a long video sequence, the tracking fails after a large change in the appearance characteristics. 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
IPC IPC(8): G06K9/00G06K9/62
Inventor 檀结庆谢成军何蕾阿里霍星刘奎白天姚焱刚
Owner HEFEI UNIV OF TECH
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