Video group character motion trail tracking method based on feature association

A motion trajectory and feature association technology, applied in the cross field, can solve problems such as insufficient matching accuracy of characters between frames, tracking errors, etc.

Inactive Publication Date: 2020-05-05
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Purpose of the invention: The technical problem to be solved by the invention is that the accuracy of character matching between frames is insufficient. The traditional character matching uses a single position information as the matching principle, but in the scene of group characters, there are a large number of collective behavior interactions, and the pure use of position information Tracking the trajectory of a person can easi

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 group character motion trail tracking method based on feature association
  • Video group character motion trail tracking method based on feature association

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings.

[0034] figure 1It is a process of a method for tracking motion trajectories of people in video groups based on feature association. First input a video, in order to facilitate the processing of subsequent tracking operations, normalize the size of all video frames in the video sequence, set the standard video frame size, and use double lines for video frames that do not meet the standard video frame size specification Image scaling with interpolation algorithm.

[0035] Considering the serious mutual occlusion of group figures and complex lighting changes, the Mask-RCNN network using high-low fusion features is used for character detection to reduce the impact of environmental factors on subsequent tracking operations and obtain accurate character position and feature descriptions. Computational cost, transforming feature descriptions into feature masks that are easy...

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 group character motion trail tracking method based on feature association. The method comprises the following steps: firstly, detecting group characters appearing in avideo, and obtaining position information and feature masks of the group characters; detecting a newly added person, selecting a current tracking person, and calculating the association similarity between the current tracking person and the person in the adjacent video frame frame by frame; and finally, determining the inter-frame dynamic state of the current tracked person in combination with theassociation similarity, updating the motion clue of the current tracked person, and traversing the video sequence to complete motion trail tracking of the video group person. According to the method,the motion characteristics of the group characters are utilized, in the inter-frame character association matching process, the influences of the position relation and the motion form are comprehensively considered, the accuracy of group character motion trail tracking can be effectively improved, and the method has good implementation performance and robustness.

Description

technical field [0001] The invention relates to a method for tracking motion trajectories of video group figures based on feature association, and belongs to the cross technical fields of computer vision, pattern recognition and the like. Facing massive amounts of video data, researchers in the field of computer vision began to explore how to automatically and efficiently extract the movement trajectories of group figures in videos. Tracking the trajectory of people in video groups has great application prospects and use value, and has a wide range of applications in video surveillance, sports analysis, human-computer interaction and other fields. Background technique [0002] Tracking the trajectory of people in video crowds is an important research topic in the field of computer vision, which has important theoretical significance and application value. [0003] The so-called group figure movement refers to the interactive movement with collective characteristics among mu...

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): G06T7/246G06K9/00
CPCG06T7/246G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30196G06T2207/30241G06V20/53
Inventor 陈志掌静岳文静周传陈璐刘玲任杰周松颖江婧
Owner NANJING UNIV OF POSTS & TELECOMM
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