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

A Stable Feature Mining and Object Tracking Method Based on Clustering Subregion Association

A target tracking and sub-region technology, which is applied in the field of video image processing, can solve the problems of update errors, inconsistent change rules of color centroid positions, etc., and achieve the goals of reducing time consumption, improving clustering efficiency and adaptability, and suppressing calculation errors Effect

Active Publication Date: 2019-01-22
南京雷斯克电子信息科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, changes in the target's appearance scale and attitude may cause inconsistencies in the change of the position of some color centroids, causing update errors

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 Stable Feature Mining and Object Tracking Method Based on Clustering Subregion Association
  • A Stable Feature Mining and Object Tracking Method Based on Clustering Subregion Association
  • A Stable Feature Mining and Object Tracking Method Based on Clustering Subregion Association

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with the accompanying drawings.

[0028] Such as figure 1 As shown, the stable feature mining and target tracking method based on clustering sub-region association, the specific implementation steps are as follows:

[0029] Step 1: Use the threshold and background update adaptive background difference algorithm to detect the target moving area; according to the peak profile, candidate peak, regional peak and residual peak energy of the V color component histogram of the target moving area, adaptively obtain the number of clusters. The specific steps to calculate the number of clusters are as follows:

[0030] 1a. Extracting the V color component histogram peak profile of the target motion detection area;

[0031] 1b. Use a median filter with a window length of n=2, n∈[2,5] to smooth the peak profile to highlight the main peak Where l1=1,2..., L1 is the number of the main peak;

[0032] 1c. will be g...

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 stable feature mining and target tracking method based on clustering sub-area association. Residual peak energy to obtain the number of clusters; b) construct the S and V component sample grayscale matrix of the target motion area, and perform class-adaptive K-means clustering; c) label and establish the class-based connected sub-regions Sub-region template, observation model and incremental model description; d) Establish the correlation between the target template and the current observation model sub-region, and mine the "template-observation" stable sub-region feature pair and template feature change rate; e) Weighted fusion template for each stable Sub-area displacement, target detection area center and previous frame trajectory to locate the target current trajectory, and update target template frame by frame according to the weighted average increment of stable features and their rate of change.

Description

technical field [0001] The invention relates to a stable feature mining and target tracking method based on clustering sub-region association, and belongs to the technical field of video image processing. Background technique [0002] Object visual feature modeling is one of the key technologies in the field of object recognition and tracking. At present, scholars at home and abroad are mainly concerned with the improvement of the robustness and accuracy of the target feature model under the conditions of target pose and scale changes, scene illumination changes and scene interference. [0003] Since the feature description method based on the target content information was reported, there have been continuous patent reports on improving this route at home and abroad, which can be summarized into three categories: 1. Improvement of the description method based on the target’s own spatial feature information; 2. Fusion of the target’s own spatial feature and The description ...

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): G06K9/00G06K9/46
CPCG06V20/46G06V20/41G06V10/56
Inventor 路红李宏胜刘大伟汤皓宗成成
Owner 南京雷斯克电子信息科技有限公司
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