RECENTDEVELOPMENTS INVIDEOSURVEILLANCE EditedbyHazemEl‐Alfy Recent Developments in Video Surveillance Edited by Hazem El-Alfy Published by InTech Janeza Trdine 9, 51000 Rijeka, Croatia Copyright © 2012 InTech All chapters are Open Access distributed under the Creative Commons Attribution 3.0 license, which allows users to download, copy and build upon published articles even for commercial purposes, as long as the author and publisher are properly credited, which ensures maximum dissemination and a wider impact of our publications. 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. As for readers, this license allows users to download, copy and build upon published chapters even for commercial purposes, as long as the author and publisher are properly credited, which ensures maximum dissemination and a wider impact of our publications. Notice 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 chapters. 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 Marija Radja Technical Editor Teodora Smiljanic Cover Designer InTech Design Team First published April, 2012 Printed in Croatia A free online edition of this book is available at www.intechopen.com Additional hard copies can be obtained from orders@intechopen.com Recent Developments in Video Surveillance, Edited by Hazem El-Alfy p. cm. ISBN 978-953-51-0468-1 Contents Preface VII Chapter 1 Compressive Sensing in Visual Tracking 3 Garrett Warnell and Rama Chellappa Chapter 2 A Construction Method for Automatic Human Tracking System with Mobile Agent Technology 17 Hiroto Kakiuchi, Kozo Tanigawa, Takao Kawamura and Kazunori Sugahara Chapter 3 Appearance-Based Retrieval for Tracked Objects in Surveillance Videos 39 Thi-Lan Le, Monique Thonnat and Alain Boucher Chapter 4 Quality Assessment in Video Surveillance 57 Mikołaj Leszczuk, Piotr Romaniak and Lucjan Janowski Chapter 5 Intelligent Surveillance System Based on Stereo Vision for Level Crossings Safety Applications 75 Nizar Fakhfakh, Louahdi Khoudour, Jean-Luc Bruyelle and El-Miloudi El-Koursi Chapter 6 Behavior Recognition Using any Feature Space Representation of Motion Trajectories 101 Shehzad Khalid Preface Surveillancesystemshavebecomeanessentialpartinmostestablishmentsnowadays. Therearemanyusestothesesystemsinnationalsecurity,safetyinpublicareas,flow control in crowded scenes, private safety and in providing special care for the aged and disabled. At the heart ofany surveillance system are video cam eras which have had their numbers significantly multiply over the last decade,thanks to advances in digitalnetworks andautomated videoprocessing.This hasresulted inan abundance ofavailablesurveillancevideowhichmadetheprocessofmonitoringthembyhuman operatorsnotonlyoutdatedbutalsopracticallyinfeasible.Severalmethodshavebeen develope dtoautomatethedetectionandreportingofscenes,eventsandsubjectsthat satisfyapplicationspecificrequirements. The purpose of this book is to collect recent advances in select areas of video surveillance. Research in that area usually combines results from machine learning, artificial intelligence, software engineering, stochastic model ing, signal processing in additiontopattern recognitionanddigital image/videoprocessing.Solvingproblems related to video surveillance often requires the reconciliation between several contradicting objectives. This makes it a challenging task and also an open research areawherenovelsolutionsarecontinuallypresentedtoovercomeearliershortcomings butstillwithoutreachingafi nalsolution. Thebookisorganizedintosixchaptersoutlinedasfollows: Chapter 1 addresses the challenges that face surveillance applications due to the increased availability ofvisual datato beprocessed. Asa casestudy, the problemof visual trackingis presented, its classicaltechniques are described and the difficulties thatthesetechniqueshavetodealwithduetoincreasedvisualdataareillustrated.The emerging theory of compressive sensing is then introduced as a solution to these challenges, applying it to the successive stages of object tracking. Unlike the mathematical oriented approach used earlier, Chapter 2 presents a software engineering approach to the problem of tracking. In p articular, the technology of mobileagentsisappliedto theproblemoftrackingobjectsas theymovebetweenthe fields of view of several cameras. The challenge here is to recover and maintain the identitiesoftargets lostby thesy stem.Neighborhoodnodedetermination techniques areintroduced,analyzedandcompared. VIII Preface Chapter 3 surveys most recent advances in the area of indexing surveillance video. The challenges in the retrieval of tracked objects from video are presented. Then, existingand suggestedsolutionsare evaluated.Thisbrings ustoan importantaspect ofvideosurveillance:thedifficultyincomparingandevaluatingresultsduetothela ck ofstandards.Subjective assessmentofthe qualityof surveillancevideois yetanother emergingarea presentedinthis bookand isthe topicof Chapter4. Itis comparedto earlier qualitative assessment approaches such asʺuser satisfactionʺ or other quantitative measures of quality deterioration versus frame per seco nd rates. In contrast,thesuggested assessmentmethodfocusesonrecognitionanddiscrimination taskswhichfitvideosurveillanceneedsmoreadequately. Chapter5presentsanimportantapplicationofvideosurveillanceintheareaofpublic safety, namely at railroad crossings. Current safety settings include sensor triggered devices that detect objects crossing rail tracks when a train is approaching (danger zone). The su ggested approach, however, uses stereo color surveillance cameras to accurately detect, in 3D, obstacles that are either moving or stopped in the danger zone. A novel background subtraction technique that uses color information is developed and, in addition, the chapter contains a clear presentation of a wealth of classical topics in computer vision, such as stereo matching, segmentation and tracking.ThebookconcludesinChapter6withanapplicationineventunderstanding (event modeling) which lies at the edge between machine learning and computer vision.Ithighlightsthe commonchallengewithin thecomputervisioncommunityof choosinganappropriatedatarepresentation.Asuitablerepresentationresultsinmore efficientandaccuratedataprocessing.Thisisillustratedinthechapterusingafeature space representation for motion trajectories. Clustering of trajectories is then performedmoreefficientlyandis usedtodetectoutlierswhicharetypicallyreported assuspiciousactivity. Thechaptersof thisbook comprisemultipleareasofvideosurveillanceranging from classical computer vision areas of video segmentation, stereo matching, anomaly detection and video indexing to recently emerging areas such as quality assessment and compressive sensing. Recent developments in those areas are presented along withpractica lreal lifeapplications.Still, eachchapter containsa clearpresentation of theareaitcoverswithreferencestoearlierrelatedwork.Thismakesthebookavailable for awide range of readers.Academicresearchers willfind a reliablecompilation of relevant literature in addition to timely pointers to current advances in the field of video surveillance. Industry practitioners will find useful hints about state‐of‐the‐art applications. The book also provides directions for open problems where further advancescanbepursued. Acknowledgements I am indebted tomany people who assisted me in the different processing stages of this book. In particular, I would lik e to acknowledge the editorial staff for their professionalism and patience. I also extend special thanks to Behjat Siddiquie, PhD Preface IX (Computer Scientist at SRI International, USA) and Vlad I. Morariu, PhD (Research Associate at the University of Maryland, USA) for reviewing several chapters and providinghelpfulcomments. April2012 HazemEl‐Alfy Dept.ofEngineeringMathematicsandPhysics FacultyofEngineering,AlexandriaUniversity Alexandria, EGYPT