Elevator door state detection method based on video image

Abstract

The invention relates to an elevator door state detection method based on a video image. The elevator door state detection method comprises the steps of: S1, collecting the video image containing an elevator door area through a camera arranged in an elevator; S2, setting an elevator door label area in the video image; S3, extracting a label area image when the elevator door is closed, and performing feature extraction and storage on the label area image; S4, performing image similarity comparison on the label area image stored in the step S3 and the elevator door label area image acquired in real time; and S5, if the similarity comparison result in the step S4 is higher than a set threshold value, outputting that the current elevator door is in a closed state, and if the similarity comparison result in the step S4 is lower than the set threshold value, outputting that the current elevator door is in an open state. The method provided by the invention is not interfered by external factors, and has better accuracy and stability. Meanwhile, according to the method, detection is carried out in a mode of combining a simple first algorithm and a complex second algorithm, and meanwhile, the requirements of accurate detection result and high detection speed are met.

Description

technical field [0001] The invention belongs to the technical field of elevator safety, in particular to an elevator door state detection method based on video images. Background technique [0002] At present, elevators are a very popular public facility, widely used in shopping malls, office areas, residential areas and other scenarios, bringing great convenience to people's daily life. However, due to improper use, untimely maintenance and other factors, elevators occasionally break down. Elevator door failure is the most frequent failure among many elevator failures, and there are many types of door failures. The sudden opening of the door during operation may cause passengers to fall, and failure to open the door may lead to trapped people. Therefore, accurate and real-time detection of the state of the elevator door is a very critical link in the safety detection of elevator passengers. [0003] In the prior art, there is an elevator door state detection based on a 3D...

AI Technical Summary

Problems solved by technology

[0005] The disadvantages of this scheme are as follows: the method of extracting the straight line boundary of the elevator door is susceptible to external interference, which affects the accuracy and stability of the elevator door state detection. The main influencing factors are the influence of ambient light, background information outside the elevator, and passengers blocking the edge of the elevator door. Cannot detect perfectly straight lines

Images