A Review of Abnormal Personnel Behavior Detection Based on Deep Learning
计算机科学
人工智能
作者
Jinfei Shi,Tianqi Zhang,He Guanghong,Fei Hao
标识
DOI:10.1109/m2vip58386.2023.10413442
摘要
With the increasing demand for intelligent security on various occasions, the detection of personnel behavior in a variety of environments has become a current research hotspot through new detection methods. Based on the recent popular deep learning techniques, this paper gives a detailed review of abnormal behavior detection. First, abnormal behavior detection based on machine vision is the focus of this review and divide the research progress of deep learning on this basis into two categories, convolutional neural network and autoencoder network. According to the characteristics of detection methods and applicable environment, the research methods of different categories are described and analyzed. Next, in the light of the situation of person gathering in different environments, some commonly used public datasets are listed, and the experiment results of various detection methods on each dataset are compared and analyzed. Finally, abnormal behavior detection trends are analyzed and prospected.