Bhanu / Ravishankar / Roy-Chowdhury Distributed Video Sensor Networks

1. Auflage 2011
ISBN: 978-0-85729-127-1
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 485 Seiten

Large-scale video networks are of increasing importance in a wide range of applications. However, the development of automated techniques for aggregating and interpreting information from multiple video streams in real-life scenarios is a challenging area of research. Collecting the work of leading researchers from a broad range of disciplines, this timely text/reference offers an in-depth survey of the state of the art in distributed camera networks. The book addresses a broad spectrum of critical issues in this highly interdisciplinary field: current challenges and future directions; video processing and video understanding; simulation, graphics, cognition and video networks; wireless video sensor networks, communications and control; embedded cameras and real-time video analysis; applications of distributed video networks; and educational opportunities and curriculum-development. Topics and features: presents an overview of research in areas of motion analysis, invariants, multiple cameras for detection, object tracking and recognition, and activities in video networks; provides real-world applications of distributed video networks, including force protection, wide area activities, port security, and recognition in night-time environments; describes the challenges in graphics and simulation, covering virtual vision, network security, human activities, cognitive architecture, and displays; examines issues of multimedia networks, registration, control of cameras (in simulations and real networks), localization and bounds on tracking; discusses system aspects of video networks, with chapters on providing testbed environments, data collection on activities, new integrated sensors for airborne sensors, face recognition, and building sentient spaces; investigates educational opportunities and curriculum development from the perspective of computer science and electrical engineering. This unique text will be of great interest to researchers and graduate students of computer vision and pattern recognition, computer graphics and simulation, image processing and embedded systems, and communications, networks and controls. The large number of example applications will also appeal to application engineers.

Autoren/Hrsg.

Bhanu, Bir

Ravishankar, Chinya V.

Roy-Chowdhury, Amit K.

Aghajan, Hamid

Terzopoulos, Demetri

Inhaltsverzeichnis

1;Preface;5
2;Contents;7
3;Introduction;11
4;Distributed Video Sensor Networks and Research Challenges;18
4.1;Report on NSF/ARO/ONR Workshop on Distributed Camera Networks: Research Challenges and Future Directions;19
4.1.1;1 Introduction;20
4.1.2;2 Workshop Recommendations;20
4.1.3;3 Suggested Major Research Topics;28
4.1.4;Appendix 1: List of Attendees in Alphabetical Order;29
4.1.5;Appendix 2: Groups and Group Leaders;34
4.1.6;Appendix 3: Talks with Titles and Presenters;37
5;Video Processing and Understanding;40
5.1;Motion Analysis: Past, Present and Future;41
5.1.1;1 Introduction to Motion: An Early History;42
5.1.2;2 Motion: Highlights from Philosophy, Psychology and Neurobiology;43
5.1.3;3 Motion in Computer Vision: The Beginnings;44
5.1.4;4 Optical Flow-Based Motion Detection;46
5.1.5;5 Human Actions and Activities;48
5.1.6;6 Motion: Future;49
5.1.7;References;51
5.2;Projective Joint Invariants for Matching Curves in Camera Networks;54
5.2.1;1 Introduction;54
5.2.2;2 Problem Formulation and Preliminaries;57
5.2.3;3 Joint-Invariant Signatures;60
5.2.4;4 Toward Local Signatures;61
5.2.5;5 Matching Performance;65
5.2.6;6 Discussion;66
5.2.7;References;66
5.3;Multiple-View Object Recognition in Smart Camera Networks;68
5.3.1;1 Introduction;69
5.3.2;2 Encoding Multiple-View Features via Sparse Representation;70
5.3.3;3 System Implementation;76
5.3.4;4 Experiment;78
5.3.5;5 Conclusion and Discussion;80
5.3.6;References;80
5.4;A Comparison of Techniques for Camera Selection and Hand- Off in a Video Network;82
5.4.1;1 Introduction;82
5.4.2;2 RelatedWork and Contributions;83
5.4.3;3 Theoretical Comparison;86
5.4.4;4 Experimental Results;90
5.4.5;5 Conclusions and Future Work;94
5.4.6;References;95
5.5;Distributed Sensing and Processing for Multi- Camera Networks;97
5.5.1;1 Introduction;97
5.5.2;2 Statistical Inference for Tracking;99
5.5.3;3 Efficient Particle Filtering;102
5.5.4;4 Compressive Sensing;107
5.5.5;5 Conclusions and Future Directions;111
5.5.6;References;112
5.6;Tracking of Multiple Objects over Camera Networks with Overlapping and Non- overlapping Views;114
5.6.1;1 Introduction;114
5.6.2;2 RelatedWork;116
5.6.3;3 Tracking within a Single Camera;117
5.6.4;4 Tracking Across Multiple Cameras;121
5.6.5;5 Experimental Results;124
5.6.6;6 Conclusion;127
5.6.7;References;127
5.7;Toward Robust Online Visual Tracking;129
5.7.1;1 Introduction;129
5.7.2;2 Appearance Modeling for Visual Tracking;130
5.7.3;3 Learning Detectors Online for Visual Tracking;135
5.7.4;4 Conclusions;143
5.7.5;References;143
5.8;Modeling Patterns of Activity and Detecting Abnormal Events with Low- Level Co- occurrences;147
5.8.1;1 Introduction;148
5.8.2;2 Context, Overview and Notations;148
5.8.3;3 OurMethod;151
5.8.4;4 Experimental Results;154
5.8.5;5 Conclusion;156
5.8.6;References;158
5.9;Use of Context in Video Processing;159
5.9.1;1 Introduction;159
5.9.2;2 Case Study: Environment Discovery;161
5.9.3;3 Conclusion;169
5.9.4;References;170
6;Simulation, Graphics, Cognition and Video Networks;171
6.1;Virtual Vision;172
6.1.1;1 Introduction;173
6.1.2;2 The Case for Virtual Vision;174
6.1.3;3 RelatedWork;177
6.1.4;4 Smart Camera Nodes;178
6.1.5;5 Surveillance Systems;183
6.1.6;6 Conclusions;184
6.1.7;References;186
6.2;Virtualization and Programming Support for Video Sensor Networks with Application toWireless and Physical Security;187
6.2.1;1 Motivation;188
6.2.2;2 RelatedWork;189
6.2.3;3 SNBench Overview;191
6.2.4;4 EnablingWireless Monitoring;192
6.2.5;5 Deployment Environment;194
6.2.6;6 Service Programming Primer;195
6.2.7;7 Wireless Security Services;196
6.2.8;8 Future Work and Conclusions;198
6.2.9;References;199
6.3;Simulating Human Activities for Synthetic Inputs to Sensor Systems;201
6.3.1;1 Overview;201
6.3.2;2 The CAROSA System;202
6.3.3;3 RelatedWork;203
6.3.4;4 Parameterized Representations;204
6.3.5;5 Resource Management;206
6.3.6;6 Roles and Groups;206
6.3.7;7 Scenario Authoring;208
6.3.8;8 Example Simulation;209
6.3.9;9 CAROSA Summary;210
6.3.10;10 Input to Distributed Sensor Networks;211
6.3.11;11 Summary;211
6.3.12;References;212
6.4;Cognitive Sensor Networks;214
6.4.1;1 Introduction;214
6.4.2;2 Cognition;215
6.4.3;3 Symmetry Theory in Signal Processing;218
6.4.4;4 Conclusion;219
6.4.5;References;219
6.5;Ubiquitous Displays: A Distributed Network of Active Displays;221
6.5.1;1 Introduction;221
6.5.2;2 Initial Progress;226
6.5.3;3 Conclusion;235
6.5.4;References;235
7;Wireless Video Sensor Networks, Communications and Control;237
7.1;Research Challenges forWireless Multimedia Sensor Networks;238
7.1.1;1 Introduction;238
7.1.2;2 Applications of Wireless Multimedia Sensor Networks;239
7.1.3;3 Network Architecture;240
7.1.4;4 Factors Influencing the Design of Multimedia Sensor Networks;241
7.1.5;5 Application Layer;243
7.1.6;6 Transport Layer Protocols;246
7.1.7;7 Network Layer;248
7.1.8;8 MAC Layer;248
7.1.9;9 Physical Layer;249
7.1.10;10 Conclusions;250
7.1.11;References;250
7.2;Camera Control and Geo-Registration for Video Sensor Networks;252
7.2.1;1 Introduction;252
7.2.2;2 RelatedWork;253
7.2.3;3 PTZ Camera Viewspace Control Model;254
7.2.4;4 Scene-Based Camera Geo-Registration and Mapping;257
7.2.5;5 Operational Interface;260
7.2.6;6 Summary;260
7.2.7;References;261
7.3;Persistent Observation of Dynamic Scenes in an Active Camera Network;263
7.3.1;1 Introduction;264
7.3.2;2 Technical Rationale;264
7.3.3;3 Cooperative Target Acquisition Using Game Theory;266
7.3.4;4 Experimental Results;271
7.3.5;5 Conclusion;274
7.3.6;References;274
7.4;Proactive PTZ Camera Control;276
7.4.1;1 Introduction;276
7.4.2;2 Proactive Camera Control;279
7.4.3;3 Results;285
7.4.4;4 Conclusions and Future Work;288
7.4.5;References;289
7.5;Distributed Consensus Algorithms for Image- Based Localization in Camera Sensor Networks;291
7.5.1;1 Introduction;291
7.5.2;2 Review of Average-Consensus Algorithms;293
7.5.3;3 Distributed Object Localization;294
7.5.4;4 Distributed CSN Localization;297
7.5.5;5 Conclusion;302
7.5.6;References;303
7.6;Conditional Posterior Cramér–Rao Lower Bound and its Applications in Adaptive Sensor Management;305
7.6.1;1 Introduction;306
7.6.2;2 Conditional PCRLB for Recursive Nonlinear Filtering;309
7.6.3;3 C-PCRLB-Based Sensor Management;312
7.6.4;4 Applications in Camera Network Management;315
7.6.5;References;317
8;Distributed Embedded Cameras and Real- Time Video Analysis;320
8.1;VideoWeb: Optimizing aWireless Camera Network for Real- time Surveillance;321
8.1.1;1 Introduction;321
8.1.2;2 RelatedWork and Contributions;322
8.1.3;3 Building the Camera Network;322
8.1.4;4 The VideoWebWireless Camera Network;326
8.1.5;5 Experiments for Performance Characterization and Optimization of the Video Network;328
8.1.6;6 Conclusions;333
8.1.7;References;333
8.2;VideoWeb Dataset for Multi-camera Activities and Non- verbal Communication;335
8.2.1;1 Introduction;336
8.2.2;2 Data Collection;336
8.2.3;3 Conclusions;347
8.2.4;References;347
8.3;Wide-Area Persistent Airborne Video: Architecture and Challenges;348
8.3.1;1 Introduction;349
8.3.2;2 Spatio-temporal Reflectance Variations;353
8.3.3;3 Wide Aperture Imaging Model of Camera Arrays;358
8.3.4;4 Accommodating Dynamic Variations in Operational Camera Arrays Using Pose Information;364
8.3.5;5 Summary and Conclusions;366
8.3.6;References;368
8.4;Collaborative Face Recognition Using a Network of Embedded Cameras;371
8.4.1;1 Introduction;371
8.4.2;2 RelatedWork;373
8.4.3;3 Experimental Setup;374
8.4.4;4 System Performance;379
8.4.5;5 Conclusions and Future Work;382
8.4.6;References;384
8.5;SATware: A Semantic Approach for Building Sentient Spaces;386
8.5.1;1 Introduction;386
8.5.2;2 SATware: An Middleware Framework for Sentient Spaces;389
8.5.3;3 A Programming Model for Pervasive Applications;389
8.5.4;4 Supporting Scalability through Semantic Scheduling;394
8.5.5;5 Supporting Robustness through Sensor Recalibration;396
8.5.6;6 Conclusions;397
8.5.7;References;398
9;Applications of Distributed Video Networks;400
9.1;Video Analytics for Force Protection;401
9.1.1;1 Aerial Video Analysis;403
9.1.2;2 Tracking from Fixed Ground Based Cameras;406
9.1.3;3 Person Detection from Moving Platforms;410
9.1.4;4 Biometrics at a Distance;412
9.1.5;5 Facial Analysis;416
9.1.6;6 Summary;418
9.1.7;References;419
9.2;Recognizing Activity Structures in Massive Numbers of Simple Events Over Large Areas;422
9.2.1;1 Introduction;422
9.2.2;2 Spatial Structure;424
9.2.3;3 Temporal Structure;426
9.2.4;4 Event-Linkage Structure;427
9.2.5;5 Short Event-Sequence Structure;427
9.2.6;6 Network Structure;430
9.2.7;7 Summary;432
9.2.8;References;432
9.3;Distributed Sensor Networks for Visual Surveillance;433
9.3.1;1 Introduction;434
9.3.2;2 Technical Challenges in Large Sensor Networks;434
9.3.3;3 System Design and Components;435
9.3.4;4 Results;440
9.3.5;References;443
9.4;Ascertaining Human Identity in Night Environments;444
9.4.1;1 Introduction;445
9.4.2;2 Color-NIR Cross-Spectral Iris Matching;446
9.4.3;3 Short Wave Infrared Face Verification;449
9.4.4;4 Gait Curves for Human Recognition in a Night-Time Environment;454
9.4.5;5 Soft Biometrics—Body Measurement;457
9.4.6;6 Summary;459
9.4.7;References;459
10;Educational Opportunities and Curriculum Development;461
10.1;Educational Opportunities in Video Sensor Networks;462
10.1.1;1 Introduction;462
10.1.2;2 Computational Sensor Networks;464
10.1.3;3 Engineering Background for Video Sensor Networks;465
10.1.4;4 Course Organization;465
10.1.5;5 Support Technology for Instruction;466
10.1.6;6 Conclusion;466
10.1.7;Appendix 1: Recommended Courses and Topics;468
10.1.8;References;469
11;Index;470