Real-time tracking method for certain person in video

A real-time tracking, person-specific technology for computer vision

Inactive Publication Date: 2018-08-03
南京云思创智信息科技有限公司
View PDF3 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

That is to propose a new solution, but also solve the problems of the existing practice mentioned before

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
  • Real-time tracking method for certain person in video
  • Real-time tracking method for certain person in video
  • Real-time tracking method for certain person in video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] In order to facilitate the understanding of those skilled in the art, the present invention will be further described below in conjunction with the embodiments and accompanying drawings.

[0091] The basic idea of ​​this method is to use the tracking algorithm to manage the prediction results of the object detection algorithm and the face recognition algorithm, so as to make up for the shortcomings of the latter two and reduce the amount of calculation. The object detection algorithm will not be affected by the situation where the camera is facing away from the camera and part of the face is displayed when detecting people, but it will be affected by obstacles. The present invention uses a tracking algorithm, organizes the detection results of each frame into a tracking track, and uses the Kalman filter method to effectively predict the tracking track even when the object is blocked. Therefore, the tracking algorithm can continue to track the specific person when the sp...

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 real-time tracking method for a certain person in a video. The method is characterized by comprising the following steps that step one, an input video is cut into images, andeach image corresponds to a frame; step two, a detecting algorithm is performed on the images, and persons are detected from the images; step three, a detecting result is input to a tracking algorithm, the tracking algorithm constructs a new tracking path according to conditions, an existing tracking path is upgraded, and tracking paths are deleted; step four, the tracking algorithm calls a faceidentification algorithm to name the paths which do not acquire names, and the naming is determined by the paths which acquire names; step five, if the residual frames in the video are not processed,the process returns to the step two; otherwise, the processed frames are made into a video for output. The method can greatly reduce the calculated amount of a full connection neural network, improvethe calculating speed, reserve space information better, and improve the generalization capability and predicting accuracy of a model.

Description

technical field [0001] The invention belongs to the technical field of computer vision, in particular to a method for real-time tracking of a specific person in a video. Background technique [0002] Specific person tracking refers to the task of detecting and tracking a specific person appearing in a video. That is, in a video, each frame is marked with bounding boxes to mark the position of a specific person, and at the same time, the tracking trajectory of the specific person is given according to the information of the current frame and the previous frame. It is understood that the existing technology will give a specific person in the video a rectangular box mark (bounding boxes) and the corresponding name by combining the two algorithms of object detection and face recognition algorithms, and through the rectangular box of the current frame and the previous frame The bounding boxes give the tracking trajectory of a particular person. The specific method is: [0003]...

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): G06K9/00G06N3/04
CPCG06V40/167G06V40/172G06V40/168G06V20/40G06N3/045
Inventor 凌志辉俞旸徐中恒
Owner 南京云思创智信息科技有限公司
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