A comprehensive review on intelligent surveillance systems

Abstract

Intelligent surveillance system (ISS) has received growing attention due to the increasing demand on security and safety. ISS is able to automatically analyze image, video, audio or other type of surveillance data without or with limited human intervention. The recent developments in sensor devices, computer vision, and machine learning have an important role in enabling such intelligent system. This paper aims to provide general overview of intelligent surveillance system and discuss some possible sensor modalities and their fusion scenarios such as visible camera (CCTV), infrared camera, thermal camera and radar. This paper also discusses main processing steps in ISS: background-foreground segmentation, object detection and classification, tracking, and behavioral analysis.

Sensor Fusion Approach for Multiple Human Motion Detection for Indoor Surveillance Use-Case

“…Similarly important, securing a house and working environment with the purpose of preventing any kind of theft or robbery has become more imperative than in the past. Available surveillance systems are often manually controlled and require human supervision, which is a tedious and time-consuming task, with their efficacy prone to being affected by human mistakes and neglects [3,4]. In this sense, automating this surveillance task by tracking people and/or recognizing any noticeable, unwanted, or illegal activity/object appears to be crucial for improving security, deterring criminals with alarms, or calling security forces promptly.…”

“…Recent advancements in computer vision, namely with the aid of deep learning algorithms, are dramatically changing the trend of video surveillance. Despite the great deal of work done in the past decades on human action recognition with computer vision algorithms, recent state-ofthe-art deep learning algorithms and advanced cameras have created a huge opportunity towards improving intelligent surveillance systems, increasing their applicability, and making them more efficient and accurate [3]. Surveillance systems typically use conventional RGB cameras to capture the outside scene and, less often, use infrared cameras for night vision inspection.…”

Revolutionizing Perimeter Intrusion Detection: A Machine Learning-Driven Approach With Curated Dataset Generation for Enhanced Security

“…However, as security threats become increasingly sophisticated and diverse, traditional PIDS methods often struggle to keep pace, resulting in false alarms, missed detections, and compromised security [1,2]. The development of vision-based technologies has advanced significantly during the past two centuries [3].…”

Perimeter Intrusion Detection by Video Surveillance: A Survey

“…In the last two decades, we have seen tremendous innovation in vision-based systems [1]. The massive installations of cameras in almost all essential sites, from banks to supermarkets and in prominent streets, have further helped in developing and testing these systems.…”