Method and system for pedestrian monitoring and behavior recognition

A behavioral and pedestrian technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of limited application scenarios, few types of recognized actions, and inability to be divided by multiple people, so as to ensure safety, convenient and flexible installation. Effect

Active Publication Date: 2016-07-20
HAOYUN TECH CO LTD
View PDF5 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the deficiencies of the existing technology, the present invention provides a method and system for pedestrian monitoring and behavior recognition, which solves the problems in the prior art of limited application scenarios, fewer types of recognition actions, and inseparability of multi-person occlusion

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
  • Method and system for pedestrian monitoring and behavior recognition
  • Method and system for pedestrian monitoring and behavior recognition
  • Method and system for pedestrian monitoring and behavior recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to facilitate the understanding of those skilled in the art, the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0026] A method for pedestrian monitoring and behavior recognition, comprising the steps of:

[0027] (S1) Collect video from the somatosensory video device, and obtain the corresponding depth image data stream and color image data stream;

[0028] (S2) Calculate the system space coordinate-ground coordinate transformation matrix, perform ground projection on the depth information, effectively segment a single human body when multiple people block the entry, and exclude non-human targets according to the ground projection;

[0029] (S3) Obtain the three-dimensional depth information of the target individual, and locate the three-dimensional coordinates of the 15 joints of the human body according to the depth information;

[0030] (S4) Establishing a three-dimensional model of the hu...

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 relates to the related technical field of behavior analysis simulation, and discloses a method of pedestrian monitoring and behavior recognition. The method comprises the following steps: S1, video acquisition is carried out on a somatosensory video device, and a corresponding depth image data stream and a color image data stream are acquired; S2, a system spatial coordinate-ground coordinate conversion matrix is calculated, ground projection is carried out on the depth information, a single human body is effectively segmented in the case of occlusion entering of multiple bodies, and non-human body targets are eliminated according to the ground projection; S3, three-dimensional depth information of a target body is acquired, and three-dimensional coordinates of 15 joints of the human body are positioned according to the depth information; S4, a human body three-dimensional model is built; S5, motion parameters of the human body are acquired; and S6, behavior features of the human body are acquired, and a processing result is fed back. The method and the system of the invention have the beneficial effects that the mounting is convenient and flexible; the pedestrian in-out conditions in a specified area is monitored and detected in a real time mode; and tracking and behavior recognition is carried out on a pedestrian entering.

Description

technical field [0001] The invention relates to the technical field of behavior analysis and simulation, in particular to an Xtion-based method and system for pedestrian monitoring and behavior identification in a bank lobby. Background technique [0002] At present, with the expansion of banking business, people are more and more concerned about the safety measures and protection in the bank. How to effectively prevent and avoid emergencies in the bank lobby is an urgent problem to be solved. Most of the current video surveillance in banks does not have intelligent analysis functions, cannot respond to emergencies, and cannot be quickly checked after an event occurs, which has caused great trouble to the security of the bank. [0003] Compared with color cameras, somatosensory cameras can obtain more useful information and expand two-dimensional plane images to three-dimensional. The somatosensory camera was first applied to the game field, using the movements of the body ...

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): G06K9/00G08B25/10
CPCG08B25/08G06V40/20G06V20/44G06V20/40
Inventor 曹江中周雷李彦志茅庆江龙中胜
Owner HAOYUN TECH CO LTD
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