Guest Editorial: Special issue on intelligent video surveillance for public security and personal privacy

O VER the past decade, video surveillance has rapidly become a widespread tool for public security. However, with the increasing volume of surveillance data, traditional manual monitoring suffers from human errors and potentially considerable delays in decision making. Moreover, there is an increasing concern of invasion of personal privacy as people's whereabouts and activities are recorded and stored by video surveillance systems. To address the concerns of public security and privacy, it is desirable to design new cloud and distributed computing systems for data recording, archival, indexing, and manipulation that enable achieving the potentially contradicting goals of effective surveillance and preservation of the privacy of individuals. Driven by such a vision, the intelligent video surveillance (IVS) technology is the core of the emerging next-generation video surveillance system. Recent advances in computer vision have shown good potential for many tasks, such as object detection, human identification , tracking, and behavior understanding. The success of these technologies promotes the fast growth of applied industrial IVS systems in diverse security applications for crime prevention and counterterrorism. In addition, research on security and privacy issues in video surveillance has been growing in recent years. New interdisciplinary technologies that integrate computer vision, data hiding, and stenography have been developed to address privacy protection concerns. The codevelop-ment of security technology and privacy protection is essential to the healthy growth of intelligent video surveillance, and its acceptance by the general public. This Special Issue offers an overview of ongoing research on IVS techniques, and brings together cutting-edge research work on security and privacy problems with respect to technological, behavioral, legal, and cultural aspects. We received 34 submissions and each submission was rigorously reviewed by at least two experts in the related fields based on the criteria of originality , significance, quality, and clarity. Eventually, 12 papers were accepted for the Special Issue, spanning a variety of topics including privacy protection, background modeling, tracking, action/activity analysis, and crowd behavior perception. In IVS, two key factors which hinder scalability are the time spent in decompressing the input video streams and the limited computational power of the processing unit. The contribution by Popa et al. (" Hardware Acceleration of Background Mod-eling in the Compressed Domain ") demonstrates how a combination of algorithmic and hardware techniques can overcome these limitations, and significantly increase the number of simultaneous streams. The work explores the effects of reducing the number of coefficients in the …