Intelligent monitoring method for comprehensive safety of elevator occupants based on machine vision

Abstract

The invention provides a comprehensive safety intelligent monitoring method, which can quickly and effectively determine whether abnormal activities such as trapped people, falls, violent events, etc. occur in the car, thereby timely and accurately issuing alarms, and effectively reducing the burden of monitoring personnel. Specifically: the image captured by the camera at a fixed position is used as the background model, and the difference image is obtained by subtracting the background from the current video frame and the background model, and the difference image is binarized according to the binarization formula, and then through morphological filtering Algorithm denoising, and finally perform regional connectivity analysis on the denoised results; use the Canny operator to extract the edge contour of the binarized image; use the template matching algorithm to compare the extracted foreground contour with the human body image template library, Determine whether there is only one person or many people in the car, determine whether abnormal activities have occurred, and trigger an alarm.

Description

technical field [0001] The invention relates to an intelligent monitoring method for abnormal activities in elevators based on machine vision. Background technique [0002] While elevators bring convenience and convenience to people, they also challenge people's safety. Since the elevator is a relatively closed public place, on the one hand, it provides an excellent place for criminals to carry out illegal activities, and incidents such as fights and robberies in the elevator car occur frequently; on the other hand, when a person takes the elevator alone, especially It is the elderly who may have a sudden illness and fall in the elevator. If they are not discovered in time, it may be life-threatening. In order to build a safe living environment, video monitoring devices are installed in the elevator cars of many high-rise residential areas, hotels, and buildings. However, the current video surveillance systems installed in elevator cars, like most of the video surveillance...

AI Technical Summary

Problems solved by technology

[0021] In order to solve the problems existing in the current elevator safety monitoring and processing method based on machine vision, such as complicated information collection, large amount of data processing, and difficulty in popularization and application in residential communities, the present invention provides a comprehensive safety intelligent monitoring method, which uses lightweight data collection and Algorithm processing can quickly and effectively determine whether there are abnormal activities such as trapped people, falls, and violent incidents in the car, so as to issue alarms in a timely and accurate manner, effectively reducing the burden on monitoring personnel

Images