The study of video anomaly detection involves the methods such as probabilistic statistics,machine learning and deep learning.The purpose of this paper is to synthesize the research results of the author's group and other advanced researches with a focus on deep learning-based video anomaly detection methods,comprehensively discussing the background,challenges and solutions in this field.Most relevant papers in the field are synthesized and systematically analyzed to provide the scholars with a fundamental understanding of the current research progress.The deep learning-based video anomaly detection methods are classified and analyzed.The network model selection for different methods is summarized.The commonly used datasets and performance evaluation indexes are introduced in detail.The advantages of various methods are highlighted by the performance comparison,and the future research directions and application scenarios in the field of video anomaly detection are deeply explored and forecasted.
关键词
视频异常检测/深度学习/伪异常/卷积神经网络/多示例学习
Key words
Video Anomaly Detection/Deep Learning/Pseudo Anomaly/Convolutional Neural Net-work/Multiple Instance Learning
维普
万方数据