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

Accurate passenger flow statistics system and method based on human face and human shape, and device thereof

A statistical method, human-shaped technology, applied in the field of image recognition, can solve difficult problems such as face recognition

Pending Publication Date: 2021-03-09
上海悠络客电子科技股份有限公司
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The current mainstream face passenger flow statistics based on face detection and recognition, there are missing statistics for face occlusion, and it is difficult to accurately recognize faces due to the profile of faces and poses.

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
  • Accurate passenger flow statistics system and method based on human face and human shape, and device thereof
  • Accurate passenger flow statistics system and method based on human face and human shape, and device thereof
  • Accurate passenger flow statistics system and method based on human face and human shape, and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] A method for accurate passenger flow statistics based on human faces and human figures, the steps are as follows:

[0056] Step 1: Simultaneously detect human faces and human bodies in the video, and then perform human body posture analysis on human body detection to associate human faces with human figures; effectively solve the problem of accurate matching between human faces and human figures in multiple face frames in human figure frames; the same person The trajectory number personID is associated with the person-related face trajectory number faceID and humanoid trajectory number bodyID; by establishing the management of the person trajectory sequence, it can effectively avoid some face pictures that are not conducive to recognition during the change of the face posture.

[0057] Step 2: By analyzing the trajectory of the doll and its body posture, judge whether the person enters the store or passes through the store; captures the doll who enters the store; facilit...

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 provides an accurate passenger flow statistics system and method based on human face and human shape, and a device thereof, and the method comprises the following steps: 1, detecting a human face and a human body in a video at the same time, carrying out the human body posture analysis of human body detection, and associating the human face with the human shape; acheiving accurate matching of faces and human shapes of a plurality of face frames in the human-shaped frame effectively, wherein the track number personID of the same person is associated with the human face track number face ID and the human shape track number body ID related to the person; 2, judging whether a person enters a store or passes the store or not by analyzing the track of the human shape and the posture of the human body; capturing the figure of the person entering the store; identifying the body weight of the shop assistant; removing the captured face at the store gate; 3, performing face recognition and human body recognition on the captured face and human shape data; removing shop assistants, and repeatedly removing the duplication of the shop assistants within a period of time.

Description

technical field [0001] The invention belongs to the field of image recognition, and in particular relates to an accurate passenger flow statistics method based on the combination of face detection and human figure detection and its tracking algorithm. The method of counting the number of people at the entrance and exit. Background technique [0002] The KPI assessment of traditional stores relies on the floor efficiency, that is, the average turnover per square meter of the store, and the overall operation status of the store is examined in this way. This simple and rude method has its own advantages due to historical factors, but when it is really used as a KPI assessment for store staff or overall operations, its shortcomings are quickly highlighted. [0003] The key factor affecting the sales per square meter is actually the location. The store is located in a location with different flow of people, and the corresponding difference in the sales per square meter is more o...

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): G06K9/00G06Q10/06G06Q30/02
CPCG06Q10/06393G06Q30/0201G06V40/10G06V40/172G06V20/53
Inventor 刘东海沈修平
Owner 上海悠络客电子科技股份有限公司
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