Elevator human sensing recognition method based on artificial intelligence similarity comparison

A technology of artificial intelligence and recognition method, which is applied in the field of human sensory recognition, can solve the problems of increased detection cost, detection error, recognition error, etc., and achieve the effect of ensuring safe and efficient management and improving the accuracy rate

Pending Publication Date: 2021-05-11
揭阳市聆讯软件有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The use of infrared sensors will increase the cost of detection, and infrared sensors are prone to false alarms in the detection of human bodies. At the same time, infrared sensors are easily interfered by electromagnetic waves from electrical equipment, resulting in detection errors; The recognition rate of the detection software is not high, resulting in recognition errors, which is even more detrimental to the safety management of the elevator

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 human sensing recognition method based on artificial intelligence similarity comparison
  • Elevator human sensing recognition method based on artificial intelligence similarity comparison

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0016]Example 1, referencefigure 1 A elevator man-sensitizer based on artificial intelligence similarity alignment, including the following steps:

[0017]S11. First use the camera in the elevator to capture the elevator in the unmanned state, and save it as a background image.

[0018]S12. Calculate the average structure similarity between the real-time image collected from the elevator in the elevator and the background image. If the average structure similarity is greater than a certain threshold, the image is determined as a background image, that is, it is determined that the elevator is unattended. Otherwise, enter the next step.

[0019]S13. If the average structure similarity between the real-time image and the background image in step S12 is not greater than a certain threshold, the object detection model is called in a lower threshold, and a number of suspected human region coordinates are obtained.

[0020]S14. Calculation of a few suspected human region coordinates obtained in step ...

Embodiment 2

[0022]Example 2, referencefigure 2A elevator man-sensitizer based on artificial intelligence similarity alignment, including the following steps:

[0023]Step S10. Average the real-time image collected by the elevator inner camera first calculates, if the average gradation value is below a certain threshold, it is judged that the elevator is turned off, and it is judged that the elevator is unattended, if an average The grayscale value is not less than the threshold, then proceges into steps S11 to S14.

[0024]S11. First use the camera in the elevator to capture the elevator in the unmanned state, and save it as a background image.

[0025]S12. Calculate the average structure similarity between the real-time image collected from the elevator in the elevator and the background image. If the average structure similarity is greater than a certain threshold, the image is determined as a background image, that is, it is determined that the elevator is unattended. Otherwise, enter the next step.

[...

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 elevator safety management, in particular to an elevator human sensing recognition method based on artificial intelligence similarity comparison. According to the technical scheme adopted by the invention, the method comprises: calculating the average structural similarity of a real-time image and a background image, carrying out the preliminary screening, carrying out the preliminary detection of a human body region of an image which does not exceed a threshold value through an object detection model, and obtaining a suspected human body region coordinate; and finally, calculating the average structural similarity of the preliminarily detected suspected human body area coordinates and the corresponding background image again, and carrying out secondary screening so as to determine whether a person is in the elevator or not. The method has the advantages that infrared sensor equipment does not need to be additionally arranged for human sensing recognition, human sensing recognition can be conducted through the images collected by the camera, the correct rate of human sensing recognition can be effectively improved, and safe and efficient management of an elevator is ensured.

Description

Technical field[0001]The present invention relates to the field of human sense identification, and more particularly to an elevator man-sensing method based on artificial intelligence similarity alignment.Background technique[0002]With the popularity of elevators, people's attention to elevators is also higher and higher. The camera is installed in the elevator car, which is used to monitor the monitor in the elevator car, and will use the camera in the elevator to monitor whether there is anyone in the elevator to prevent the elevator. Currently using elevators in the elevator, there are some people in the elevator, generally adopt an increase in infrared sensor for human infrared detection, or use a conventional human body identification detection software to perform human identification. The use of an infrared sensor will increase the detection cost, and the infrared sensor is prone to the human body. At the same time, the infrared sensor is easily interfered with electromagnetic...

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
CPCG06V40/10G06F18/22
Inventor 林浩恩林康伟周东姚威威吴江涛刘捷
Owner 揭阳市聆讯软件有限公司
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