Automatic Event Detection for Signal-based Surveillance

TL;DR

This paper reviews automatic event detection techniques in signal-based surveillance systems like CCTV, discussing challenges and emphasizing the need for multidisciplinary research to enable real-world deployment.

Contribution

It provides an overview of current detection methods, highlights challenges in practical implementation, and advocates for integrated multidisciplinary approaches.

Findings

Detection techniques face significant real-world challenges

Data collection and evaluation protocols are critical issues

Multidisciplinary research is essential for progress

Abstract

Signal-based Surveillance systems such as Closed Circuits Televisions (CCTV) have been widely installed in public places. Those systems are normally used to find the events with security interest, and play a significant role in public safety. Though such systems are still heavily reliant on human labour to monitor the captured information, there have been a number of automatic techniques proposed to analysing the data. This article provides an overview of automatic surveillance event detection techniques . Despite it's popularity in research, it is still too challenging a problem to be realised in a real world deployment. The challenges come from not only the detection techniques such as signal processing and machine learning, but also the experimental design with factors such as data collection, evaluation protocols, and ground-truth annotation. Finally, this article propose that multi-disciplinary research is the path towards a solution to this problem.