Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Video Object Tracking Method under Scale Variation and Occlusion

A technology of scale change and target tracking, which is applied in the field of image processing and can solve the problems of unsatisfactory tracking effect of LBP tracking algorithm.

Inactive Publication Date: 2016-02-03
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of unsatisfactory tracking effect of the LBP tracking algorithm in the case of scale change and occlusion, and provide a video target tracking method in the case of scale change and occlusion

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
  • A Video Object Tracking Method under Scale Variation and Occlusion
  • A Video Object Tracking Method under Scale Variation and Occlusion
  • A Video Object Tracking Method under Scale Variation and Occlusion

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0030] Specific implementation mode one: the following combination figure 1 Describe this embodiment, a video object tracking method under the condition of scale change and occlusion in this embodiment is to use the size invariance of the image normalized moment of inertia and the prediction function of Kalman filter to perform the target size change and the target Tracking during occlusion, the method includes the following steps:

[0031] Step 1, preprocessing the current frame image of the video, such as smoothing filtering, etc.; setting the size of the target template, the size of the search area, and the initial state of Kalman filtering;

[0032] Step 2, judging whether the target template needs to be reselected in the current frame image;

[0033] If it is not necessary to reselect the target template, perform step 3; if it is necessary to reselect the target template, select a new target template and reinitialize the target template to obtain the LBP operator of the ...

specific Embodiment approach 2

[0054] Specific implementation mode two: the following combination figure 2 Describe this embodiment, this embodiment will further explain Embodiment 1. In step 3, the center position of the target template in the previous frame image is used as the center to establish the search area of ​​the current frame image, traverse the search area in the search area, and find the search area The process of the LBP module and the NMI module is:

[0055] Establish the search area of ​​the current frame image centered on the center position of the target template in the previous frame image,

[0056] The center position coordinates of the target template in the previous frame image are (TemplateCenterX, TemplateCenterY), the length of the target template is TemplateHeight, and the width is TemplateWidth,

[0057] Then establish the center position coordinates of the search area of ​​the current frame image as (TemplateCenterX, TemplateCenterY), length is 2×TemplateHeight, width is 2×Tem...

specific Embodiment approach 3

[0062] Specific implementation mode three: this implementation mode further explains implementation mode one, the LBP operator of the LBP module in step three by formula

[0063] LBP P , R r i u 2 = Σ i = 0 P - 1 S ( g i - g c ) ...

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 video target tracking method under the circumstance of scale change and shielding and belongs to the field of image processing. The invention aims at solving the problem of non-ideal tracking effect under the circumstance of the scale change and shielding of an LBP (local binary pattern) tracking algorithm. The invention provides an optimization objective tracking method based on combining the LBP algorithm, NMI (normalized moment of inertia) features and kalman filtering. The NMI features are used for determining an update strategy of a module and solving the problem of target loss caused by target rotation, scale change and the like. The kalman filtering is used for overcoming the defect that a target is easy to lose under the circumstance of shielding.

Description

technical field [0001] The invention relates to a video target tracking method under the condition of scale change and occlusion, and belongs to the field of image processing. Background technique [0002] Video-based target tracking is to use the method of digital image processing to process the video obtained by video information acquisition equipment such as cameras, and lock the specified target position. The image target tracking algorithm involves various processes such as image data preprocessing, target detection, image segmentation, feature extraction, motion analysis and target tracking, among which image segmentation, feature extraction and target tracking are the key processes. The current popular target algorithms mainly include MeanShift algorithm, Camshift algorithm, SURF algorithm and particle filter algorithm. [0003] The Local Binary Pattern (LBP, LocalBinaryPattern) algorithm describing local image texture features was proposed by T.Ojala et al. Compared...

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 Patents(China)
IPC IPC(8): G06T7/20
Inventor 宋华军王玉霞任鹏胡勤振周林刘超王震俞其伟
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com