Contextual Information Based Anomaly Detection for a Multi-Scene UAV Aerial Videos

TL;DR

This paper introduces a novel multi-scene UAV video anomaly detection system that leverages contextual, temporal, and appearance features, along with a new dataset and inference strategy, to improve detection accuracy in complex surveillance scenarios.

Contribution

It develops a comprehensive anomaly detection framework for multi-scene UAV videos, including a new annotated dataset and a novel inference method utilizing few anomalous samples.

Findings

Performed competitively against state-of-the-art methods

Developed a new UAV multi-scene anomaly dataset with annotations

Utilized contextual, temporal, and appearance features for detection

Abstract

UAV based surveillance is gaining much interest worldwide due to its extensive applications in monitoring wildlife, urban planning, disaster management, campus security, etc. These videos are analyzed for strange/odd/anomalous patterns which are essential aspects of surveillance. But manual analysis of these videos is tedious and laborious. Hence, the development of computer-aided systems for the analysis of UAV based surveillance videos is crucial. Despite this interest, in literature, several computer aided systems are developed focusing only on CCTV based surveillance videos. These methods are designed for single scene scenarios and lack contextual knowledge which is required for multi-scene scenarios. Furthermore, the lack of standard UAV based anomaly detection datasets limits the development of these systems. In this regard, the present work aims at the development of a Computer Aided Decision support system to analyse UAV based surveillance videos. A new UAV based multi-scene anomaly detection dataset is developed with frame-level annotations for the development of computer aided systems. It holistically uses contextual, temporal and appearance features for accurate detection of anomalies. Furthermore, a new inference strategy is proposed that utilizes few anomalous samples along with normal samples to identify better decision boundaries. The proposed method is extensively evaluated on the UAV based anomaly detection dataset and performed competitively with respect to state-of-the-art methods.