文章基本信息

标题：ABNORMAL BEHAVIOR DETECTION IN AUTOMATED SURVEILLANCE VIDEOS: A REVIEW
本地全文：下载
作者：AHLAM AL-DHAMARI ; RUBITA SUDIRMAN ; NASRUL HUMAIMI MAHMOOD 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：19
页码：5245
出版社：Journal of Theoretical and Applied
摘要：Abnormal detection refers to infrequent data instances that come from a diverse cluster or distribution than the majority normal instances. Owing to the increasing demand for safety and security, discovery abnormalities from video streams has attracted significant research interest during recent years. By automatically finding abnormal actions, it significantly decreases the cost to label and annotate the videos of a huge number of hours. The current advancements in computer vision and machine learning have a remarkable role in enabling such intelligent frameworks. Different algorithms that are specially designed for building smart vision frameworks seek to scene understanding and building correct semantic inference from observed dynamic motions caused by moving targets. Unfortunately, although there are many algorithms have been proposed in this interesting topic, the research in this area still lacks strongly to two important things: comparative general assessment and public-accessible datasets. This study addresses these inadequacies by presenting an overview of most recent research algorithms that concentrate significantly on abnormal behavior detection in surveillance applications. This study extensively presents state-of-the-art algorithms in a way that enables those interested to know all the key issues and challenges relevant to the abnormal behavior detection topic and their applications as well as their specific features. Additionally, there are five important evaluation benchmarks from 2007 to 2017. The performance and limitations of those benchmarks are discussed, which will help largely research in this area.
关键词：Video Surveillance; Abnormal Detection; Feature Extraction; Learning Methods; Clustering; Spatio-temporal Compositions; Sparsity