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

Face recognition and movement track judging methods under high noise

A face recognition and motion trajectory technology, applied in the field of face recognition, can solve problems such as misjudgment of face recognition technology, and achieve the effect of reducing the possibility of misjudgment

Inactive Publication Date: 2017-09-12
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF14 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In real scenes, due to the existence of factors such as angle, light and shade, posture and matching errors, face recognition technology inevitably has misjudgment

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] A face recognition method for high noise, including,

[0028] Image acquisition step: Obtain multi-frame images decoded from the video stream. There are multiple video streams; in this step, the system processes each camera independently. The system decodes the video stream sent by the camera and converts the decoded data For pictures encoded in jpg format, the optimal way to acquire multi-frame pictures is at intervals. For example, for one of the cameras, assuming that it sends out 25 frames of images per second, we can acquire 5 of them per second. The picture of the frame, that is, n takes 5. Because in one second, the difference between the decoded pictures of each frame is not big, especially the difference between adjacent pictures is even smaller. For each video stream, the system acquires decoded pictures at intervals, which can reduce the processing from 25 frames per second to n frames per second. If n is less than 25, the system needs to process fewer pictu...

Embodiment 2

[0042] A high-noise-oriented motion trajectory discrimination method, comprising identifying a suspect using the face recognition method of Embodiment 1, after the identity of the suspect is confirmed, recording the suspect id, the camera where the suspect is, and where the suspect appears according to the suspect id. The timestamp of the camera. The tracking module tracks the suspect through the coordinates of the face frame and facial features. When the suspect leaves the camera, the timestamp of when the suspect leaves the camera is recorded. Here we can get a suspect in a certain camera. The time of appearance and departure of the suspect can be obtained, and the location information and real-time trajectory of the suspect can be accurately fed back. When the tracking module tracks the suspect of a certain camera, other cameras will judge whether there are other suspects in parallel through the method of embodiment 1. If there is another suspect, the tracking module will tr...

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 face recognition and movement track judging methods under high noise. The face recognition method comprises an image acquisition step, a feature extraction step, a feature comparison step, and a judgment step. In the image acquisition step, images of a video stream are acquired at intervals. In the feature comparison step, extracted features are compared with features stored in a face library, corresponding result vectors <id1, id2,...,idk > and <score1, score2,...,scorek> (respectively representing the IDs of most similar k persons in the face library and the similarity thereof) of faces are obtained, and two m*k matrixes are obtained for each image, wherein m is the number of persons in the frame of image. In the judgment step, a candidate person set is obtained according to images decoded from the same video stream and the number of times each ID appears in the comparison results, and a suspect ID is determined according to the number of times each ID in the candidate person set appears in images decoded from different video streams and the similarity. The method is of high detection reliability and low misjudgment rate under the condition of high noise.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a high noise-oriented face recognition and motion trajectory discrimination method. Background technique [0002] With the development of the city and the improvement of security awareness, the cameras arranged in various places are becoming more and more dense. In order to find specific targets among the many cameras, intelligent monitoring technology has emerged as the times require. Face recognition is a kind of biometric recognition technology based on human facial feature information for identification. A series of related technologies that use a video camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then perform facial recognition on the detected faces. [0003] The face feature recognition method obtains the face frame by detecting the face of the picture, and then extracts the feature...

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): G06K9/00
CPCG06V40/166G06V20/41
Inventor 段翰聪赵子天文慧梁君健张帆
Owner UNIV OF ELECTRONIC SCI & TECH OF 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