Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and system for detecting escalator out-of-bounds behavior based on Gaussian mixture model

A technology of Gaussian mixture model and detection method, applied in character and pattern recognition, instrument, image data processing, etc., can solve problems such as real-time care and intelligent alarm of escalators

Active Publication Date: 2021-05-11
HANGZHOU ANMAISHENG INTELLIGENT TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problem that the existing technology cannot realize the real-time care and intelligent alarm of the escalator in operation, and provides a method and system for detecting the escalator's out-of-bounds behavior based on the Gaussian mixture model

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
  • A method and system for detecting escalator out-of-bounds behavior based on Gaussian mixture model
  • A method and system for detecting escalator out-of-bounds behavior based on Gaussian mixture model
  • A method and system for detecting escalator out-of-bounds behavior based on Gaussian mixture model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Embodiment one, a kind of escalator cross-border behavior detection method based on Gaussian mixture model, such as figure 1 shown, including steps:

[0046] A) Obtain the monitoring video image of the escalator area through the camera, and the monitoring video image of the escalator area includes the image of the entrance of the escalator and the image of the exit of the escalator, such as image 3 Shown is the original video image of the entrance and exit of the escalator in an unmanned state according to the embodiment of the present invention. Such as Figure 4 As shown, the OpenPose deep learning network model is used to extract the human skeleton from the video image. The OpenPose deep learning network model uses the MPI model. The MPI model includes 18 key points of the human skeleton, namely the right shoulder, right elbow, right wrist, left shoulder, and left elbow. , left wrist, right hip, right knee, right ankle, left knee, right hip, left ankle, top of hea...

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 present invention relates to the technical field of escalator safety monitoring, and discloses a Gaussian mixture model-based escalator cross-border behavior detection method and system, including the steps: A) using the OpenPose deep learning network model to extract a human skeleton from a video image; B) using SVM Classifier to build a classification model; C) Build a Gaussian mixture model; D) Preprocess the moving target image to obtain the moving image in the passenger cross-border detection area on both sides of the escalator handrail; E) Screen out the smallest circumscribed rectangle area greater than the area threshold The contour of the moving target; F) Obtain the minimum distance from the center point of the smallest circumscribed rectangle to the key point of the skeleton; G) Alarm for the escalator out of bounds. The invention reduces false detections, improves the accuracy of boundary-crossing detection, and establishes a Gaussian mixture model to detect and real-time alarm the boundary-crossing behavior of passengers when they ride the escalator, and has high detection accuracy of boundary-crossing behavior.

Description

technical field [0001] The invention relates to the technical field of escalator safety monitoring, in particular to a Gaussian mixture model-based detection method and system for escalator out-of-boundary behavior. Background technique [0002] An escalator is a transportation device similar to an inclined conveyor belt, which mainly completes the task of transporting passengers and goods. With people's continuous pursuit of a fast lifestyle, the use of escalators is becoming more and more common. Escalators are often seen in public places such as subway stations, railway stations and various buildings. With the extensive use of escalators, some safety issues and smooth operation of escalators have attracted more and more attention. It is difficult to monitor the passenger flow and its behavior during the use of the escalator by choosing the method of manual care of the escalator. Take countermeasures at the first time. Therefore, it is necessary to develop a more intelli...

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 Patents(China)
IPC IPC(8): G08B13/196G06K9/00G06T7/254G06T7/62
CPCG08B13/19602G06T7/254G06T7/62G06V40/10
Inventor 胡芬陈南西楼阳冰
Owner HANGZHOU ANMAISHENG INTELLIGENT TECH CO LTD