Abnormal behavior recognition for intelligent video surveillance systems : a review
智能视频监控系统中异常行为识别综述
Expert Systems with Applications, In press, accepted manuscript, Available online 11 September 2017
Amira Ben Mabrouk, Ezzeddine Zagrouba
Abstract:With the increasing number of surveillance cameras in both indoor and outdoor locations, there is a grown demand for an intelligent system that detects abnormal events. Although human action recognition is a highly reached topic in computer vision, abnormal behavior detection is lately attracting more research attention. Indeed, several systems are proposed in order to ensure human safety. In this paper, we are interested in the study of the two main steps composing a video surveillance system which are the behavior representation and the behavior modeling. Techniques related to feature extraction and description for behavior representation are reviewed. Classification methods and frameworks for behavior modeling are also provided. Moreover, available datasets and metrics for performance evaluation are presented. Finally, examples of existing video surveillance systems used in real world are described.
Graph formulation of video activities for abnormal activity recognition
基于视频活动图构的异常活动识别方法
Pattern Recognition, Volume 65, May 2017, Pages 265-272
Dinesh Singh, C. Krishna Mohan
Abstract:Abnormal activity recognition is a challenging task in surveillance videos. In this paper, we propose an approach for abnormal activity recognition based on graph formulation of video activities and graph kernel support vector machine. The interaction of the entities in a video is formulated as a graph of geometric relations among space–time interest points. The vertices of the graph are spatio-temporal interest points and an edge represents the relation between appearance and dynamics around the interest points. Once the activity is represented using a graph, then for classification of the activities into normal or abnormal classes, we use binary support vector machine with graph kernel. These graph kernels provide robustness to slight topological deformations in comparing two graphs, which may occur due to the presence of noise in data. We demonstrate the efficacy of the proposed method on the publicly available standard datasets viz. UCSDped1, UCSDped2 and UMN. Our experiments demonstrate high rate of recognition and outperform the state-of-the-art algorithms.
A Review on Crowd Behavior Analysis Methods for Video Surveillance
视频监控中群体行为分析方法综述
Saurabh Maheshwari, Surbhi Heda
March 2016 ICTCS '16: Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies
ABSTRACT: Abnormal Crowd Detection has become the most viral and active research topic in computer vision. There is need of automated tracking of the abnormalities in surveillance video sequence for the detection of abnormal events. These systems are mainly used for supervising and security purpose. This automated system can alarm for abnormality in fairs, temples. It can also be used for the traffic monitoring etc. Crowd is a group of individuals belonging to a community or society. In the crowd, there exist many behavior abnormalities. Crowd density estimation, crowd motion detection, crowd tracking and crowd behavior recognition are multiple techniques for detecting abnormalities. Computer based crowd analysis algorithm can be divided into three groups; people counting, people tracking and crowd behavior analysis. In this paper, we will discuss multiple techniques of abnormal crowd detection background subtraction, optical flow, 3D Convolutional neural network, hydrodynamics lens. Once detected, a moving object could be classified as a human being using shape-based texture-based or motion-based features. Comparison of available techniques for detecting abnormal crowd in surveillance videos has also been done in this paper.
Online Weighted Clustering for Real-time Abnormal Event Detection in Video Surveillance
视频监控中实时异常事件检测的在线加权聚类
Hanhe Lin, Jeremiah D. Deng, Brendon J. Woodford, Ahmad Shahi
October 2016 MM '16: Proceedings of the 2016 ACM on Multimedia Conference
ABSTRACT:Detecting abnormal events in video surveillance is a challenging problem due to the large scale, stream fashion video data as well as the real-time constraint. In this paper, we present an online, adaptive, and real-time framework to address this problem. The spatial locations in a frame is partitioned into grids, in each grid the proposed Adaptive Multi-scale Histogram Optical Flow (AMHOF) features are extracted and modelled by an Online Weighted Clustering (OWC) algorithm. The AMHOFs which cannot be fit to a cluster with large weight are regarded as abnormal events. The OWC algorithm is simple to implement and computational efficient. In addition, we improve the detection performance by a Multiple Target Tracking (MTT) algorithm. Experimental results demonstrate our approach outperforms the state-of-the-art approaches in pixel-level rate of detection at a processing speed of 30 FPS.
