VIDEO SURVEILLANCE Edited by Weiyao Lin Video Surveillance Edited by Weiyao Lin Published by InTech Janeza Trdine 9, 51000 Rijeka, Croatia Copyright © 2011 InTech All chapters are Open Access articles distributed under the Creative Commons Non Commercial Share Alike Attribution 3.0 license, which permits to copy, distribute, transmit, and adapt the work in any medium, so long as the original work is properly cited. After this work has been published by InTech, authors have the right to republish it, in whole or part, in any publication of which they are the author, and to make other personal use of the work. Any republication, referencing or personal use of the work must explicitly identify the original source. Statements and opinions expressed in the chapters are these of the individual contributors and not necessarily those of the editors or publisher. No responsibility is accepted for the accuracy of information contained in the published articles. The publisher assumes no responsibility for any damage or injury to persons or property arising out of the use of any materials, instructions, methods or ideas contained in the book. Publishing Process Manager Ivana Lorkovic Technical Editor Teodora Smiljanic Cover Designer Martina Sirotic Image Copyright bogdan ionescu, 2010. Used under license from Shutterstock.com First published February, 2011 Printed in India A free online edition of this book is available at www.intechopen.com Additional hard copies can be obtained from orders@intechweb.org Video Surveillance, Edited by Weiyao Lin p. cm. ISBN 978-953-307-436-8 free online editions of InTech Books and Journals can be found at www.intechopen.com Part 1 Chapter 1 Chapter 2 Chapter 3 Part 2 Chapter 4 Chapter 5 Chapter 6 Chapter 7 Preface IX Overview 1 Information Management and Video Analytics: the Future of Intelligent Video Surveillance 3 Bennie Coetzer, Jaco van der Merwe and Bradley Josephs Efficient Video Surveillance: Performance Evaluation in Distributed Video Surveillance Systems 17 Aleksandra Karimaa Federalism, Privacy Rights, and Intergovernmental Management of Surveillance: Legal and Policy Issues 27 Michael W. Hail Video Surveillance Systems, Frameworks, and Structures 35 Video Surveillance of Today: Compressed Domain Object Detection, ONVIF Web Services Based System Component Communication and Standardized Data Storage and Export using VSAF – a Walkthrough 37 Houari Sabirin and Gero Bäse Realizing Video-Surveillance on Wireless Mesh Networks: Implementation Issues and Performance Evaluation 55 Giovanni Schembra An Application of Quantum Networks for Secure Video Surveillance 73 Alan Mink, Lijun Ma, Barry Hershman and Xiao Tang Cooperative Visual Surveillance Network with Embedded Content Analysis Engine 99 Shao-Yi Chien and Wei-Kai Chan Contents Contents VI SuperVision: Video Content Analysis Engine for Videosurveillance Applications 125 Lisa Usai, Francesco Pantisano, Leonardo G. Vaccaro and Franco Selvaggi Multi-Stage Video Analysis Framework 147 Andrzej Czyżewski, Grzegorz Szwoch, Piotr Dalka, Piotr Szczuko, Andrzej Ciarkowski, Damian Ellwart, Tomasz Merta, Kuba Łopatka, Łukasz Kulasek and Jędrzej Wolski Object Segmentation, Detection, and Tracking 173 Background Subtraction and Lane Occupancy Analysis 175 Erhan A. Ince, Nima S. Naraghi and Saameh G. Ebrahimi Block Matching-Based Background Generation and Non-Rigid Shape Tracking for Video Surveillance 193 Taekyung Kim and Joonki Paik Integrating Color and Gradient into Real-Time Curve Tracking and Feature Extraction for Video Surveillance 217 Huiqiong Chen and Qigang Gao Targets Tracking in the Crowd 231 Cheng-Chang Lien Measurement of Pedestrian Traffic Using Feature-based Regression in the Spatiotemporal Domain 247 Gwang-Gook Lee and Whoi-Yul Kim The Management of a Multicamera Tracking System for Videosurveillance by Using an Agent Based Approach 263 Bethel Atohoun and Cina Motamed Content Analysis and Event Detection for Video Surveillance 277 A Survey on Behaviour Analysis in Video Surveillance Applications 279 Teddy Ko Automatic Detection of Unexpected Events in Dense Areas for Videosurveillance Applications 295 Bertrand Luvison, Thierry Chateau, Jean-Thierry Lapreste, Patrick Sayd and Quoc Cuong Pham Chapter 8 Chapter 9 Part 3 Chapter 10 Chapter 11 Chapter 12 Chapter 13 Chapter 14 Chapter 15 Part 4 Chapter 16 Chapter 17 Contents VII Automatic Scenario Recognition for Visual-Surveillance by Combining Probabilistic Graphical Approaches 321 Ahmed Ziani and Cina Motamed A Parallel Non-Linear Surveillance Video Synopsis System with Operator Eye-Gaze Input 335 Ulas Vural and Yusuf Sinan Akgul Video Surveillance for Fall Detection 357 Caroline Rougier, Alain St-Arnaud, Jacqueline Rousseau and Jean Meunier Uncertainty Control for Reliable Video Understanding on Complex Environments 383 Marcos Zúñiga, François Brémond and Monique Thonnat Advanced Topics 409 Animal Eyes and Video Imagery 411 Tomasz P. Jannson and Ranjit Pradhan Hot Topics in Video Fire Surveillance 443 Verstockt Steven, Van Hoecke Sofie, Tilley Nele, Merci Bart, Sette Bart, Lambert Peter, Hollemeersch Charles-Frederik and Van De Walle Rik Camera Placement for Surveillance Applications 459 Indu Sreedevi, Nikhil R Mittal, Santanu Chaudhury and Asok Bhattacharyya Real-time Stereo Disparity Map for Continuous Distance Sensing Applications - A Method of Sparse Correspondence 475 Kunio Takaya Chapter 18 Chapter 19 Chapter 20 Chapter 21 Part 5 Chapter 22 Chapter 23 Chapter 24 Chapter 25 Pref ac e Video surveillance is becoming increasingly important in many applications, includ- ing traffi c control, urban surveillance, home security, environmental monitoring, and healthcare. With the rapid growth of demand for ubiquitous sensing and security, great challenges have been raised for designing, transmi ing, and processing over video surveillance systems. As such, evolution is changing from the tedious manual surveillance to the effi cient automatic and intelligent surveillance. And this evolu- tion, in turn, is issuing new challenges in front of us, including system designing, data analysis and processing, resource scheduling, and data streaming. This requires bet- ter understanding of the implications of communication, compression, data mining, content-based video retrieval, machine learning, and pa ern recognition. The goal of this book is to consolidate and highlight the latest achievements and de- velopments in the fi eld of video surveillance. The papers selected for this book com- prise a cross-section of topics that refl ect a variety of perspectives and disciplinary backgrounds. Besides the introduction of new achievements in video surveillance, this book also presents some good overviews of the state-of-the-art technologies as well as some interesting advanced topics related to video surveillance. I believe the 25 chap- ters presented in this book can provide a clear picture of the current research status in the area of video surveillance. This book contains a total of fi ve major parts that cover the following directions: over- view of the current developments in video surveillance; new designs and frameworks for video surveillance systems; novel algorithms for object extraction and tracking; new methods for video content analysis and event detection; and some advanced top- ics related to video surveillance. The brief outline of the book is as follows: Part I presents tutorials, surveys and comparative studies of several new trends and developments in video surveillance. Chapter 1 is a tutorial on video analysis and infor- mation management techniques used for video surveillance applications. These two parts are normally indentifi ed as the key factors for future intelligent video surveil- lance systems. Chapter 2 gives an overview of the techniques about performance eval- uation in distributed video surveillance systems. By discussing the evaluation metrics for various parts including data acquisition, system intelligence, system architecture, user-interface, and user-oriented functionality, this chapter also provides a clear view on where and how to improve the effi ciency of a video surveillance system. Chapter 3 X Preface describes the legal and policy issues for surveillance applications. While surveillance applications are o en weighed against the civil rights of individuals being observed, this chapter gives a very good discussion on this complex rights-and-security balance issue. Thus, it can serve as a good reference during the practical usage of surveillance systems. Part II comprising six chapters is devoted to the design of video surveillance systems, frameworks, and structures. Here the readers can fi nd a wide variety of surveillance systems and frameworks for diff erent applications. Chapter 4 provides a walkthrough to the ONVIF (Open Network Video Interface Forum) video surveillance system, from the camera through analysis and storage right up to display and export. In addition, this chapter also illustrates the general trend towards processing increasing amounts of data in real-time automatically by avoiding completely the task of decoding the vid- eo prior analysis. Chapter 5 describes a real experience of a wireless video-surveillance system, illustrating the overall architecture and the structure of each component block. Specifi cally, video sources use rate-control to emit a constant bit-rate fl ow, while the ac- cess network is a WMN (Wireless Mesh Networks) implementing a multipath routing algorithm to minimize delay and intrusions. Furthermore, analysis is also carried out against the emission bit rate, and quality perceived at destination is evaluated with an objective parameter. Chapter 6 discusses the QKD (Quantum Key Distribution) proto- col and its potential to secure video surveillance applications. This chapter shows ex- amples of a QKD implementation along with reference to other implementations as well as some innovations that can reduce QKD costs, limit some of the side channel a acks and provide hardware support to off load CPU processing. In addition it also touched on the need for integration with existing network infrastructure, providing services necessary for deployment and an on-going standards eff ort that is needed by both cus- tomers and developers. Chapter 7 discusses the data abstraction hierarchy and the sys- tem confi guration of the next-generation surveillance systems. A conclusion has been made that each camera should be embedded with content analysis ability to become a smart camera instead of just an IP camera. Furthermore, two examples of cooperative surveillance systems are also provided for diff erent scenarios. Chapter 8 describes a video analysis engine called SuperVision system that can analyze video streams from diff erent types of camera, in particular omnidirectional, and to set alarms when pre- confi gured events are detected. The types of events detected are numerous, and can be composed according to the context and needs of applications. Chapter 9 proposes a multi-stage video analysis framework which is a fl exible and effi cient solution for automatic analysis of camera images in the monitoring systems. Part III comprises six chapters and deals with new methods and techniques for object segmentation, detection, and tracking in videos. Chapter 10 summarizes the existing techniques for background subtraction and its application in lane occupancy analy- sis. By comparing diff erent background subtraction methods, this chapter provides a good insight into the usability and eff ectiveness for various background subtraction algorithms. Chapter 11 presents a combined shape and feature-based object tracking method. The proposed method adaptively generates background, which serves as a fundamental building block for robust tracking by resolving inherent problems of existing block-matching algorithm. A er generating background, the shape tracking module in the proposed algorithm determines object’s moving region based on shape control points. Experimental results demonstrate the eff eictiveness of the this method. [...]... on the use of Video Analytics to achieve the various objectives as defined, but, as will be seen in the paragraph on Intelligent Information management, Video Analytics is merely a part of the complete system 2 Video analytics 2.1 Basics of video analytics The role of Video Analytics can be described in a number of ways and consist primarily of the following: 4 Video Surveillance 2.1.1 Video enhancement... surveillance videos under the supervision of an surveillance operator The system employs an eyegaze tracker that returns the focus points of the surveillance operator The resulting video summary is an integration of the actions observed in the surveillance video and the video sections where the operator pays most attention or overlooks The unique combination of the eye-gaze positions with the non-linear video. .. proposes a new generic video understanding approach able to extract and learn valuable information from noisy video scenes for real-time applications This approach is able to estimate the reliability of the information associated to the objects tracked in the scene, in order to properly control XI XII Preface the uncertainty of data due to noisy videos and many other difficulties present in video applications... an object over time In video analysis this would translate to the following of a detected object in between successive frames in video or in more advanced instances between different videos Before we jump into an explanation of how tracking works let us look at an example; Fig 2 shows a sequence of images containing some tracked objects The images are a few frames taken from video sequence, showing... Intelligence ExtracƟon Video AnalyƟcs Apriori InformaƟon (Databases) Local Storage Threat DetecƟon Threat ClassificaƟon Assessment Human Scenario Analysis (Visual Display) Machine Scenario Analysis SituaƟonal Awareness System Decision Support ExecuƟon Post Event Analysis Fig 5 Information Management Process Video AnalyƟcs Information Management and Video Analytics: the Future of Intelligent Video Surveillance... in public transport, and (Lipton et al., 2004) presents video content analysis tools deployment for forensics application Despite of the fact the video content analysis is well popularized and widely researched, the deployment of the video analytics is considered as one of the most risky areas in surveillance business It is worth to mention that video content analysis tools should not only have positive... the following block diagram to explain the slightly more complex algorithm: Fig 1 Algorithm block diagram for the Foreground Object Detection from Videos Containing Complex Background Information Management and Video Analytics: the Future of Intelligent Video Surveillance 7 The algorithm consists of four parts: change detection, change classification, foreground object segmentation, and background... from false-negative detections (i.e not detecting objects it should have) especially in monochrome video such a thermal images But used in a less critical general monitoring environment this algorithm performs very well with constant detection results Fig 2 Video sequence containing a few tracked objects 8 Video Surveillance In comparison the Mixture of Gaussian Modelling and the Complex background both... discusses some interesting advanced topics related to video surveillance Chapter 22 discusses an interesting interdisciplinary problem: the relationships between animal eyes and relevant human engineering (HE), in the context of video surveillance It purposely use engineering language rather than biologic one in order to make those relationships more familiar to video imagery scientists and engineers Based... was left to humans but, modern video analytic tools promise automation of this The event is thus analysed such that benign movement such as scene clutter, movement outside regions of interest (ROI), moving trees, busy roads, etc are ignored and those movements or events that matter are considered Information Management and Video Analytics: the Future of Intelligent Video Surveillance 9 Fig 3 Examples . 8 Chapter 9 Part 3 Chapter 10 Chapter 11 Chapter 12 Chapter 13 Chapter 14 Chapter 15 Part 4 Chapter 16 Chapter 17 Contents VII Automatic Scenario Recognition for Visual -Surveillance by Combining. 2. Video analytics 2 .1 Basics of video analytics The role of Video Analytics can be described in a number of ways and consist primarily of the following: Video Surveillance 4 2 .1. 1 Video. VIDEO SURVEILLANCE Edited by Weiyao Lin Video Surveillance Edited by Weiyao Lin Published by InTech Janeza Trdine 9, 510 00 Rijeka, Croatia Copyright © 2 011 InTech All chapters