Video tracking method based on important region identifying and matching

An important area and video tracking technology, applied in the field of computer vision, can solve problems such as not bad, and achieve the effect of improving sampling quality, improving quality, and high sampling quality

Active Publication Date: 2018-01-09
SOUTH CHINA AGRI UNIV
View PDF9 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The tracking based on the important area recognition method has a good effect when the target object is occluded or deformed.

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 tracking method based on important region identifying and matching
  • Video tracking method based on important region identifying and matching
  • Video tracking method based on important region identifying and matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] like figure 1 As shown, the present embodiment is based on the video tracking method of important region identification and matching, comprising the following steps:

[0051] (1) Target template construction stage: First, take the initial target area as the center, expand 5 pixels 6 times in the four directions of up, down, left, and right respectively, and obtain a total of 4 7 An extended region; then, identify the important regions of the extended region and extract the largest connected region based on the 4-neighborhood. Next, calculate the coincidence degree of the connected area and the initial target area, the coincidence degree D=0.2×D 1 +0.8×D 2 ,D 1 =|M h -N h |+|M w -N w |, D. 1 Indicates the sum of the absolute values ​​of the corresponding length and width differences between the initial target region M and the connected region N, D 2 Indicates the center coordinates of M (P mx ,P my ) and the central coordinates of the connected area N (P nx...

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 tracking method based on important region identifying and matching, which includes the following steps: first, identifying an important region of an initial target based on the minimum spanning tree theory to get a target important region, and constructing a target template; then, identifying an important region of the subsequent frame target expansion region, taking the region as a sampling region, and collecting samples; next, calculating the shape similarity value, the color similarity value and the Pearson correlation coefficient value between each sample and the target template, and carrying out weighted calculation on the three values to get the matching degree between each sample and the target plate; and finally, updating the target template based ona threshold comparison method to support follow-up tracking until the end of tracking. Through the method, a target object in a dynamically changing tracking scene can be better described based on important region identification. Through sample collection in the important region of a target, the sampling quality is improved. The accuracy and stability of tracking are enhanced.

Description

technical field [0001] The present invention relates to the field of computer vision, more specifically, to a video tracking method based on identification and matching of important regions. Background technique [0002] Video tracking can realize real-time monitoring, behavior analysis and motion estimation of targets by tracking moving objects. It is a research hotspot in the field of computer vision and has attracted widespread attention in recent years. This technology has broad application prospects and plays an important role in many fields, such as security monitoring, human-computer interaction, medical diagnosis and vehicle flow monitoring and so on. Although a large number of video tracking methods have been proposed, these methods often cannot provide ideal tracking results and cannot track the target object when the shape of the object changes greatly or there is serious occlusion. Therefore, proposing an effective object tracking method has important applicatio...

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 Applications(China)
IPC IPC(8): G06T7/246G06K9/62
Inventor 梁云王美华胡月明陈湘骥刘汉兴
Owner SOUTH CHINA AGRI 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