Elevator passenger abnormal behavior detection method and system, terminal equipment and storage medium

Abstract

The invention discloses an elevator passenger abnormal behavior detection method and system, terminal equipment and a storage medium. The method comprises the steps that a video frame image in an elevator is obtained; converting the video frame image into an HSV color space image; carrying out ROI region segmentation on a human body in the HSV color space image to obtain human body key points; identifying the human body key points to obtain key point connection data and key point coordinate data of the corresponding passengers; and based on the key point connection data and the key point coordinate data, carrying out classification identification on the behavior of the passenger, and based on a classification identification result, determining whether the behavior of the passenger is an abnormal behavior. According to the method, the calculation efficiency is improved, meanwhile, recognition errors caused by environmental factors are eliminated, the recognition accuracy of the abnormal behaviors in the elevator is improved, and the detection requirement is met.

Description

technical field [0001] The present invention relates to the technical field of elevator safety, in particular to a method, system, terminal equipment and storage medium for detecting abnormal behavior of elevator passengers based on AI and image processing. Background technique [0002] In recent years, with the increase of high-rise buildings, people have become more and more dependent on elevators. However, the space of the elevator car is narrow, closed and opaque, and it is usually difficult for the outside world to find in time the abnormal human behaviors such as robbery, fighting, infringement, and door opening in the elevator car. Therefore, it is particularly important to monitor the behavior of elevator passengers. Dangerous behaviors of passengers, such as jumping, door opening, etc., are likely to cause accidents such as elevator falling, threatening the lives and property safety of passengers, and taking timely and effective measures can greatly Avoid or save l...

AI Technical Summary

Problems solved by technology

[0004] At present, the most direct way to detect the dangerous behavior of elevator passengers is to perform image processing on the elevator monitoring video, but most of the existing technologies only directly use deep learning technology to recognize passenger behavior without preprocessing the image, which will lead to Environmental factors have a great influence on the recognition accuracy, which reduces the accuracy of abnormal behavior recognition. At the same time, the existing technology fails to consider the calculation efficiency and cannot meet the detection requirements.

Images