Passenger fall detection method for escalator based on deep learning

Abstract

The invention discloses a deep learning-based detection method for passengers falling down in an escalator, comprising the steps of: 1) collecting video images of passengers taking the escalator; 2) detecting the faces of passengers by using FHOG descriptors and SVM classifiers; 3) Use KCF to track passengers' faces, and create a new passenger track list based on passenger face information; 4) Use transfer learning to retrain the yolo2 algorithm model to detect passengers' bodies; 5) Match passengers' faces and passengers' bodies, and add personal information to the track list ; 6) Use the openpose deep learning algorithm to extract the passenger skeleton joint point sequence; 7) Match the passenger's body and the passenger skeleton joint point sequence, and add the skeleton joint point information to the trajectory list; 8) Analyze the skeleton joint point information in the trajectory list, Detect passenger falls. Through the method of the invention, the falling behavior of passengers on the escalator can be detected, and when the falling behavior is found, an emergency plan can be started in time to minimize safety hazards.

Description

technical field [0001] The invention relates to the technical field of image processing and behavior recognition, in particular to a deep learning-based detection method for passengers falling down in an escalator. Background technique [0002] With the continuous advancement of my country's modernization process and the continuous improvement of people's economic living standards, more and more public facilities appear in public places to facilitate people's daily production and life. As a public facility that facilitates passengers to travel, escalators are used in shopping malls. It can be seen everywhere in public places such as office buildings, subway stations, etc. However, the convenience of travel has caused a series of safety problems, such as passenger congestion on the escalator, passengers going backwards, passengers running, passengers falling, etc., these Behaviors, especially passenger falls, will cause serious safety accidents. It is necessary to monitor and d...

AI Technical Summary

Problems solved by technology

[0002] With the continuous advancement of my country's modernization process and the continuous improvement of people's economic living standards, more and more public facilities appear in public places to facilitate people's daily production and life. As a public facility that facilitates passengers to travel, escalators are used in shopping malls. It can be seen everywhere in public places such as office buildings, subway stations, etc. However, the convenience of travel has caused a series of safety problems, such as passenger congestion on the escalator, passengers going backwards, passengers running, passengers falling, etc., these Behaviors, especially passenger falls, will cause serious safety accidents. It is necessary to monitor and discover safety problems in time and issue warnings or stop the escalator. At present, the safety problems of escalators are mainly prevented by manually monitoring the escalator area. , but now the labor cost is getting higher and higher, and the repetitive and boring monitoring work is easy to make the staff slack and fail to deal with sudden security incidents in time

Images