Video target tracking method based on dynamic sparse projection

A technology of sparse projection and target tracking, which is applied in the field of video target tracking based on dynamic sparse projection, and can solve problems such as poor robustness

Inactive Publication Date: 2013-11-27
NORTHWESTERN POLYTECHNICAL UNIV
View PDF1 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of poor robustness of the existing fixed sparse projection matrix t

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
  • Video target tracking method based on dynamic sparse projection
  • Video target tracking method based on dynamic sparse projection
  • Video target tracking method based on dynamic sparse projection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The specific steps of the video target tracking method based on dynamic sparse projection of the present invention are as follows:

[0039] Step 1. Generate a sparse projection matrix The constituent element r of the sparse projection matrix R ij Obtained by random sampling, defined as follows.

[0040]

[0041] In the formula, s=2 or s=3.

[0042] In order to improve the robustness of the algorithm and the real-time performance of the calculation, 10 sparse projection matrices are generated at a time, and the dimension of the matrix is ​​generated between 0 and 100 by uniform random sampling.

[0043] Step 2, using the image coordinate position l of the tracking result of the previous frame t-1 , to generate a set of positive samples D α ={z|||l(z)-l t-1 ||β,ζ ={z|βt-1 ||<ζ}, define α=4 to generate 45 positive samples; define ζ=8, β=30, in a large number of generated negative samples, randomly select 50 as negative samples.

[0044] Define a set of multiscale...

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 a video target tracking method based on dynamic sparse projection. The method is used for solving the technical problem that an existing fixed sparse projection matrix tracking method is poor in robustness. According to the technical scheme, different low-dimensional image feature information is obtained from a high-dimensional image by utilizing a series of sparse projection matrixes with different dimensions, and corresponding classified samples are respectively obtained through a naive Bayes classifier on this basis; the weight information of each classified sample is obtained by calculating the character contrast ratio of each classified sample and a previous frame of sample, the image similarity degree of each classified sample and the initial frame of sample and the comparison result of the pixel distribution difference degree of the current frame of target and a background, the sparse projection matrix with a weight value smaller than a threshold value is dynamically updated, and the classified sample with optimal weight is selected as the final target tracking result. The accuracy rate of the tracking result reaches more than 85%.

Description

technical field [0001] The invention relates to a video target tracking method, in particular to a video target tracking method based on dynamic sparse projection. Background technique [0002] It is of great significance to convert the high-dimensional image space information into low-dimensional feature space information by using the projection matrix, and realize fast and robust video target tracking by calculating the low-dimensional feature space information. The existing video tracking methods mainly include: video tracking methods based on offline learning and video tracking methods based on online learning. [0003] The document "Real-time compressive tracking. ECCV, 20:866–879, 2012." discloses a video tracking method based on online learning. This method uses a sparse projection matrix to obtain low-dimensional image feature space information, and then uses a naive Bayesian classifier to classify the feature information of all samples to obtain the optimal classif...

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): G06K9/62G06T7/20
Inventor 张艳宁杨涛陈挺
Owner NORTHWESTERN POLYTECHNICAL 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