Artificial Intelligence in Video Surveillance

Abstract

Surveillance is an essential component of security, and e-surveillance is one of the primary goals of the Indian Government's Digital India development initiative. Video surveillance offers a wide range of applications to reduce ecological and economic losses and becomes one of the most effective means of ensuring security. This chapter addresses the problem of how artificial intelligence is powering video surveillance. There is a significant research focus on video analytics but comparatively less effort has been taken for surveillance videos. However, there is little evidence that researchers have approached the issue of intelligent video surveillance in terms of suspicious action detection, crime scene description, face detection, crowd counting, and the like. Most AI-powered surveillance is based on deep neural networks and deep learning techniques using analysis of video frames as images. Consequently, this chapter aims to provide an overview and significance of how artificial intelligence techniques are employed in video surveillance and image processing.