Object tracking method for intensive scene based on multi-module sparse projection

A technique of sparse projection and target tracking, applied in the field of computer vision

Inactive Publication Date: 2012-07-18
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF2 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims at the problem that the movement track of any single target cannot be correctly detected in dense scenes with random motion, and proposes a dense scene target tracking method based on multi-module sparse projection to realize the automatic target tracking method of crowd-intensive scenes in public places

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
  • Object tracking method for intensive scene based on multi-module sparse projection
  • Object tracking method for intensive scene based on multi-module sparse projection
  • Object tracking method for intensive scene based on multi-module sparse projection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] Since the sparse projection method can characterize target features more effectively and accurately, it is applied to target tracking in dense passenger flow scenes. Aiming at the severe mutual occlusion problem in dense scenes, a reconstruction matrix based on multi-module kernel color histogram is designed. Based on this, the corresponding target matching and updating algorithms are designed.

[0019] sparse representation ：

[0020] Assuming that there is a sufficient training sample set for the i-th object class, , then for any test sample belonging to the same class , which can be represented by a linear weighted sum of training samples, namely: , (1)

[0021] However, because the class of the test sample is unknown, the redefinition matrix T consists of n training samples of k object classes, namely: (2)

[0022] Therefore, x can be represented by a linear combination of all training samples, that is: (3)

[0023] where T is called the reco...

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 an object tracking method for an intensive scene based on multi-module sparse projection. The object characteristic is characterized by a sparse projection method; and for solving the serious mutual shield problem in an intensive scene, a reconstruction matrix based on a multi-module core color histogram is designed and further a corresponding object matching and updating algorithm is designed. According to the object tracking method, the automatic tracking of objects in the people stream intensive scene in a public place is realized; and meanwhile, the solution to the problem of serious mutual shield in the intensive scene is provided.

Description

Technical field [0001] The invention involves a computer vision field, which specializes in a dense scene target tracking method based on multi -module sparse projection. Background technique [0002] With the rapid development of the economy, the degree of urbanization of society is getting higher and higher, the population density of the city is getting greater and greater, and the management of crowds in public places has become increasingly prominent.Out of the demand for security, most public places are installed with closed -circuit TV monitoring systems (CCTV), especially at densely intensive places such as subway and airports, which can achieve large -scale real -time image collection.However, most collected images must rely on manual surveillance or be stored only as data records, and there is no effect that can achieve real -time intelligent monitoring. [0003] Target detection and tracking are the basic methods of computer vision, and new solutions have also been prop...

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): G06K9/62
Inventor 邵洁
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
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