Elevator trapped person detection method based on computer vision

A computer vision and detection method technology, applied to elevators, lifts, transportation and packaging in buildings, etc., can solve problems such as call button damage, untimely call alarm response, etc., to reduce the incidence, avoid heavy workload and Fatigue problem, the effect of improving accuracy

Active Publication Date: 2021-03-30
成都睿瞳科技有限责任公司
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the uncertain factors of the elevator call alarm in the current market, the problem that the call button is destroyed and the call alarm response is not timely, and proposes a computer vision-based elevator trapped person detection method

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
  • Elevator trapped person detection method based on computer vision
  • Elevator trapped person detection method based on computer vision
  • Elevator trapped person detection method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0049] Such as figure 1 As shown, the present invention provides a kind of elevator sleepy person detection method based on computer vision, comprises the following steps:

[0050] S1: Use the camera of the elevator car to collect the scene video of the elevator;

[0051] S2: Determine whether the elevator door of the elevator car is closed and whether the closing time exceeds the set threshold, if so, enter step S3, otherwise return to step S1;

[0052] S3: Build a convolutional neural network model for the elevator scene video;

[0053] S4: Use the convolutional neural network model to identify the number of people in the video of the elevator scene, and feed back the result of the number of people in the elevator car to the monitoring center to complete the detection of people trapped in the elevator.

[0054] In the embodiment of the present inven...

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 an elevator trapped person detection method based on computer vision. The method comprises the following steps that S1, an elevator scene video is collected through a camera ofan elevator car; S2, whether closing duration of an elevator door of the elevator car exceeds a set threshold value or not is judged, if yes, the step S3 is executed, and if not, the step S1 is executed again; S3, a convolutional neural network model for the elevator scene video is constructed; and S4, the number of people in the elevator scene video is identified by using the convolutional neural network model, and a number result of people in the elevator car is fed back to a monitoring center. According to the elevator trapped person detection method based on the computer vision, the elevator trapped situation can be found in time, so that elevator safety and passenger satisfaction are improved, and the elevator taking safety is guaranteed; compared with a traditional method, the elevator trapped person detection method has the advantages that the two models are constructed to effectively recognize door opening and closing of the elevator car and the number of people in an elevator, more accurate elevator information can be provided, and a better reference effect is achieved for maintenance personnel and the monitoring center.

Description

technical field [0001] The invention belongs to the technical field of elevator monitoring, and in particular relates to a method for detecting a person trapped in an elevator based on computer vision. Background technique [0002] With the development of society, the rhythm of people's work and life is constantly accelerating, and the elevator, which is a tool that people must use in daily life, is also gradually developing at a high speed. The main components of the elevator are composed of the following: traction system, guidance system, car, door system, weight balance system, electric drive system, electrical control system and safety protection system. [0003] In the elevators that are usually used, there will be a call for help alarm button inside the elevator. If a passenger is trapped inside the elevator, you can press the call button to call the police. For normal calls, there are false alarms in this calling method. In the process of our daily elevator ride, som...

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): B66B3/00B66B5/00B66B13/00
CPCB66B3/002B66B5/0012B66B13/00
Inventor 周旭东黄剑张记复
Owner 成都睿瞳科技有限责任公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap