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

Detection method of abnormal behavior in elevator car based on computer vision

A computer vision and elevator car technology, applied in the field of detection of abnormal behavior in the elevator car, can solve problems such as being easily affected by light and relying on the accuracy of background modeling methods

Active Publication Date: 2022-07-15
CHANGSHU INSTITUTE OF TECHNOLOGY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The accuracy of the background modeling method depends on the process of establishing the background model and is easily affected by light

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
  • Detection method of abnormal behavior in elevator car based on computer vision
  • Detection method of abnormal behavior in elevator car based on computer vision
  • Detection method of abnormal behavior in elevator car based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0134] like figure 1 As shown, the present invention proposes a method for detecting abnormal behavior in an elevator car based on computer vision. Firstly, the ViBe algorithm combined with the inter-frame difference method and the convolutional neural network YOLOv3 are used to detect the moving objects in the video surveillance scene. The outer contour of the moving target is obtained by the ViBe algorithm combined with the frame difference method, and the height-width ratio information of the passenger body entering the car is obtained on the basis of the outer contour; Detect and obtain the position information of the human head target. According to the number of heads detected by the YOLOv3 neural network, the abnormal behavior detection in the elevator is divided into two scenarios: single person, two people and more. In the case of a single person, the present invention utilizes the change of the height-width ratio of the passenger's body contour and the vertical move...

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 a method for detecting abnormal behavior in an elevator car based on computer vision. The outer contour of a moving target is obtained by combining the ViBe algorithm of the frame difference method, and the height of the body of a passenger in the car is obtained on the basis of the outer contour. Width ratio information; the number and position of human heads in the car are detected through the YOLOv3 neural network. According to the number of heads detected by the YOLOv3 neural network, the abnormal behavior detection in the car is divided into two scenarios: single person, two people and more. In the single-person scenario, the change of the aspect ratio of the passenger's body contour and the vertical movement distance of the passenger's head are used to detect the fall behavior. In the case of two or more people, on the basis of the target contour obtained by the ViBe algorithm of the inter-frame difference method, the pyramid LK optical flow algorithm is used to calculate the average kinetic energy of the passengers to realize the detection of violent violations. In the present invention, video input and detection are performed at the same time to achieve the effect of real-time detection.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a computer vision-based detection method for abnormal behavior in an elevator car. Background technique [0002] The video-based automatic abnormal behavior detection system can automatically judge the abnormal behavior of passengers in the car and send out signals according to the detection results. Abnormal behavior: harmful behavior in the elevator car, in the present invention, it refers to two behaviors of falling and violent assault. Due to the large number of video surveillance in a certain area, manual monitoring is not only time-consuming and inefficient, but also cannot detect threats to passenger safety in time. Therefore, behavior recognition technology based on computer vision is the main research direction of abnormal behavior detection in recent years. [0003] At present, abnormal behavior detection methods can be roughly divided into three categories, name...

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): G06V10/774G06V10/75G06V20/40G06K9/62G06T7/149G06T7/246
CPCG06T7/149G06T7/246G06V20/20G06V20/46G06F18/214G06V20/52G06V10/82G06F18/24133
Inventor 徐本连孙振施健鲁明丽从金亮
Owner CHANGSHU INSTITUTE OF TECHNOLOGY