Recognition of Abnormal Human Behavior in Elevators based on CNN

Abstract

This study explores a CNN based model to identify abnormal behavior in elevator cabs, which I have named S-LRCN ( S-Long-term Recurrent Convolutional Network). It starts with the detection of key points of the human skeleton by using the Openpose method, then further detects and tracks the human body through the CenterNet and DeepSort methods, and finally integrates the Long Short Term Memory Network (LSTM) and Convolutional Neural Network (CNN) to form a deep learning model. In this study, a large dataset (500 video clips) collected from real elevator cabs with different backgrounds has been applied to ensure the robustness and generalizability of the proposed model. At last, this study applies the two mainstream dangerous human behaviors, i.e., door blocking and door picking as case studies to test and evaluate the usability and availability. Experimental results show that the model has a 85% recognition rate of abnormal behavior.