Check patentability & draft patents in minutes with Patsnap Eureka AI!

Escalator flow monitoring method and system based on human skeleton information and multi-target tracking

A multi-target tracking and human skeleton technology, applied in the field of escalator flow monitoring, can solve the problems of lack of efficient and stable escalator flow monitoring technology, and achieve the effects of maintaining accuracy, improving accuracy, and assisting on-site management

Active Publication Date: 2020-04-24
HANGZHOU ANMAISHENG INTELLIGENT TECH CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: the problem of the current lack of efficient and stable escalator flow monitoring technology

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
  • Escalator flow monitoring method and system based on human skeleton information and multi-target tracking
  • Escalator flow monitoring method and system based on human skeleton information and multi-target tracking
  • Escalator flow monitoring method and system based on human skeleton information and multi-target tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Escalator flow monitoring method based on human skeleton information and multi-target tracking, such as figure 1 As shown, this embodiment includes the following steps: S100: Obtain a surveillance video image of the escalator area through a camera; the surveillance video image of the escalator area includes an escalator entrance image and an escalator exit image, respectively image 3 , Figure 4 Shown.

[0025] S200. Use the OpenPose deep learning network model to extract the human skeleton from the current frame image; the OpenPose deep learning network model is specifically: BODY_25, COCO or MPI.

[0026] S300. Collect misdetection and real passenger skeleton information, and label them accordingly to construct a positive and negative sample of normal pedestrian skeleton and misdetection skeleton data.

[0027] S400. Use the SVM classifier to construct a classification model.

[0028] S500: Classify the real-time skeleton information, retain the correct skeleton information, ...

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 technical field of computers, in particular to an escalator flow monitoring method and a system based on human skeleton information and multi-target tracking, and the method comprises the following steps: obtaining an escalator area monitoring image; extracting human skeleton information; establishing a classification model of the skeleton information; classifying thereal-time skeleton information; selecting human skeleton key points; obtaining an external rectangle of a selected human skeleton key point; intercepting a pixel region corresponding to the circumscribed rectangle, newly adding a tracking object, and tracking the newly added tracking object to obtain a motion trail of the tracking object; if the tracking object enters the escalator entrance, adding 1 to the escalator monitoring number of people, and if the tracking object enters the escalator exit, subtracting 1 from the escalator monitoring number of people; when the escalator monitors that the number of people exceeds the standard, performing on-site sound alarm. The escalator flow monitoring system has the substantive effects that through the image recognition technology, the deploymentcost is reduced, and the escalator flow monitoring efficiency is improved; and the safety of passengers taking the escalator is improved.

Description

Technical field [0001] The invention relates to the field of computer technology, in particular to an escalator flow monitoring method and system based on human skeleton information and multi-target tracking. Background technique [0002] An escalator is also called an escalator, hereinafter referred to as an escalator. It is a transportation device similar to an inclined conveyor belt, which mainly completes the task of transporting passengers and goods, especially the former. As people continue to pursue a fast lifestyle, the use of escalators has become more and more common, such as subway stations, railway stations, buildings and other public places. With the large-scale use of escalators, some safety issues and smooth running issues of escalators have attracted more and more attention, especially the location of escalator openings, including whether the escalator opening is congested, whether passengers fall, whether there are large objects stranded, etc. . On the one hand...

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): G06K9/00G06K9/62
CPCG06V40/10G06F18/217G06F18/2411Y02B50/00
Inventor 胡芬
Owner HANGZHOU ANMAISHENG INTELLIGENT TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More