Motion anomaly detection and trajectory analysis in visual surveillance

Abstract

Motion anomaly detection through video analysis is important for delivering autonomous situation awareness in public places. Surveillance scene segmentation and representation is the preliminary step to implementation anomaly detection. Surveillance scene can be represented using Region Association Graph (RAG), where nodes represent regions and edges denote connectivity among the regions. Existing RAG-based analysis algorithms assume simple anomalies such as moving objects visit statistically unimportant or abandoned regions. However, complex anomalies such as an object encircles within a particular region (Type-I) or within a set of regions (Type-II). In this paper, we extract statistical features from a given set of object trajectories and train multi-class support vector machines (SVM) to deal with each type of anomaly. In the testing phase, a given test trajectory is categorized as normal or anomalous with respect to the trained models. Performance evaluation of the proposed algorithm has been carried out on public as well as our own datasets. We have recorded sensitivity as high as 86% and fallout rate as low as 9% in experimental evaluation of the proposed technique. We have carried out comparative analysis with state-of-the-art techniques to benchmark the method. It has been observed that the proposed model is consistent and highly accurate across challenging datasets.

MA-GeSAN: Motion-Appearance Stream-Based Generative Self-Annotation Network Guided Self-Supervised Abnormal Event Detection in Videos

“…In the last decade variety of methods have been proposed to identify and locate abnormal or prohibited events. The proposed methods can be broadly classified into three major categories i.e., (i) Classical methods [17], [22], [25], [26], [27], [28], (ii) Deep learning methods [4], [6], [7], [8], [29], [30], and (iii) Hybrid methods [13], [21], [31]. A significant research effort has been dedicated towards the manual feature extraction followed by well-established classifiers like one-class support vector machine (OC-SVM) [28], [9], clustering mechanisms like K-nearest neighbor (KNN) [21] and a hardware-friendly classifier KUGDA proposed in [32].…”

User-Centered Pipeline for Synthetic Augmentation of Anomaly Detection Datasets

“…Current state-of-the-art research on anomaly detection commonly uses existing datasets to train and evaluate their models [5,25,26]. Common datasets include UCSD Ped2 [27], CUHK Avenue [14], and ShanghaiTech [15].…”

On the nature and types of anomalies: a review of deviations in data

“…Two anomalies with regard to the trajectories of moving entities are presented in [ 118 , cf. 146 , 147 ], namely the positional outlier , which is positioned in a low-density area of the trajectory space, and the angular outlier , which has a direction different from regular trajectories. The subfield of graph mining has also acknowledged several specific classes of anomalies, with anomalous vertices , edges, and subgraphs being the basic forms [ 18 , 20 , 112 , 113 , 148 , 149 ].…”