Person recognition method based on multiple poses

A person identification, multi-pose technology, applied in the field of information security, to achieve the effect of strong practicability, improve use efficiency, and improve personnel recognition rate

Inactive Publication Date: 2018-09-28
CHANGZHOU UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the current problem of using human behavior characteristics to identify people, the present invention uses the built-in acceleration sensor of the mobile phone to solve these problems

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
  • Person recognition method based on multiple poses
  • Person recognition method based on multiple poses
  • Person recognition method based on multiple poses

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Firstly, a division method is proposed according to the change characteristics of personnel walking acceleration, which divides the personnel walking acceleration into two parts: relative dynamic and steady state, and extracts the standard deviation, mean value, energy and other characteristics from the two regions respectively. Then, according to different walking speeds, select these features and the slope of the peak point connection line to form a new feature set. Finally, the recognition accuracy is obtained by combining classifiers.

[0035] specific plan:

[0036] The user carries a mobile phone to carry out four daily behaviors, which are fast walking, slow walking, going upstairs and downstairs. The smartphone was fixed on the right thigh of the experimenter, and the specific position was as follows: figure 1 As shown, in the process of data collection, users need to walk for a period of time according to their own walking habits in order to obtain stable dat...

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 person recognition method based on multiple poses. According to the method, a mobile phone is utilized to collect acceleration data of a person in the walking process, in order to further mine acceleration information, refine feature vectors and explore the acceleration change rate, an information segmentation method is proposed, and according to the change size of the acceleration data, the acceleration data is divided into a dynamic part and a steady part; features are extracted from the two regions respectively to form a dynamic feature set and a static feature set, a ReliefF algorithm is adopted to select features from the two sets, a new feature set is formed in combination with the slope of a peak point connecting line, and the person recognition rate is increased; and finally a classifier combination method is adopted to perform person recognition. By utilizing the mobile phone to perform person recognition, the instantaneity of recognition is improved,and cost is low.

Description

technical field [0001] The invention belongs to the field of information security, and in particular relates to a method for identifying people based on multiple gestures. Background technique [0002] With the improvement of the performance of electronic equipment and the development of social informatization, the use of portable electronic equipment such as mobile phones and PDAs is becoming more and more extensive, and it is developing towards the direction of integrating electronic payment functions and identity authentication functions, so its security issues are becoming more and more serious. are getting more and more attention. Many identification systems, such as fingerprints, password verification, face, etc., have been put into application, which can authenticate the user's identity during the boot stage, but are not suitable for continuous identity authentication during use. In addition, these methods require the active cooperation of users, and too much verific...

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): G06K9/00G06K9/62
CPCG06V40/103G06F18/241
Inventor 郇战李晨万彩艳陈学杰申佳华
Owner CHANGZHOU 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