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

Elevator door opening and closing state recognition method and device based on deep learning

A deep learning, elevator door technology, applied in the field of image recognition, can solve the problems of low background accuracy, motion blur, inaccuracy, etc., to achieve the effect of reducing deployment, strengthening generalization, and high recognition accuracy

Pending Publication Date: 2021-11-12
LIAONING SINODOM SECURITY TECH
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional computer vision algorithm process is separated, and the accuracy rate is not high when encountering complex backgrounds. The deep learning algorithm can solve this problem and can realize end-to-end mapping. At present, the combination of computer vision and deep learning has achieved remarkable results. progress
[0003] Elevator door opening and closing state monitoring based on computer vision is beneficial to cost savings. At present, the elevator door opening and closing state recognition methods mainly use traditional optical flow algorithms and algorithms based on deep learning target detection, which are inaccurate and time-consuming due to motion blur. question

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 door opening and closing state recognition method and device based on deep learning
  • Elevator door opening and closing state recognition method and device based on deep learning
  • Elevator door opening and closing state recognition method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] see figure 1 , figure 1 It is a schematic flowchart of a deep learning-based method for identifying the state of opening and closing of elevator doors disclosed in the embodiment of the present application. Such as figure 1 As shown, a deep learning-based elevator door opening and closing state recognition method according to the embodiment of the present application, the method includes:

[0044] Obtain the first video data in the elevator, and when the pixel change in the elevator door area in the first video data is greater than the first threshold, transmit the first video data to a deep learning recognition model, and the deep learning recognition model outputs The first elevator door status.

[0045] In the embodiment of the present invention, the first video data in the elevator is sent to the deep learning recognition model for classification and recognition, and the state of the elevator door can be quickly obtained. Among them, when the pixels in the eleva...

Embodiment 2

[0066] see figure 2 , figure 2 It is a schematic structural diagram of an elevator door opening and closing state recognition device based on deep learning disclosed in the embodiment of this application. Such as figure 2 As shown, an elevator door opening and closing state recognition device based on deep learning in the embodiment of the present application, the device includes an acquisition module, a transmission module, a deep learning recognition module, and an output module; wherein,

[0067] The obtaining module is used to obtain the first video data in the elevator;

[0068] The transmission module is configured to transmit the first video data to a deep learning identification module when the pixel change in the elevator door area in the first video data is greater than a first threshold,

[0069] The deep learning identification model is used to identify the first video data and output the first elevator door state.

[0070] For the specific functions of the ...

Embodiment 3

[0072] see image 3 , image 3 It is an electronic device disclosed in the embodiment of this application, and the device includes:

[0073] a memory storing executable program code;

[0074] a processor coupled to the memory;

[0075] The processor invokes the executable program code stored in the memory to execute the deep learning-based elevator door opening and closing state recognition method as described in Embodiment 1.

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 door opening and closing state recognition method and device based on deep learning, electronic equipment and a computer storage medium. The method comprises the steps that first video data in an elevator are obtained, when the pixel change condition of an elevator door area in the first video data is larger than a first threshold value, the first video data are transmitted to a deep learning recognition model, and the deep learning recognition model outputs a first elevator door state. According to the scheme, the elevator door opening and closing state is monitored through the computer vision technology, the cost is effectively reduced, training data of the deep learning recognition model comprises enough scenes, higher generalization is achieved, and the recognition accuracy is high.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a deep learning-based recognition method, device, electronic equipment and computer storage medium for opening and closing states of elevator doors. Background technique [0002] With the continuous improvement of the computer industry level, computer vision systems and artificial intelligence are gradually becoming practical. Thanks to the massive data brought by the rise of the Internet and the wide application of machine learning methods, computer vision is developing rapidly and is being widely used in Various fields related to computers are getting closer to life and are closely related to us. Computer vision uses images as input to realize the correct expression of the environment, study the feature organization of images, perform target detection or scene recognition, and then give scientific explanations to events. Deep learning technology is the develo...

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): G06K9/00G06K9/62G06N3/04
CPCG06N3/045G06F18/214
Inventor 丁武林琳李林
Owner LIAONING SINODOM SECURITY TECH