Automated Multi-Camera Surveillance: Algorithms and Practice

Front Cover
Springer Science & Business Media, Dec 16, 2008 - Computers - 110 pages
0 Reviews

The deployment of surveillance systems has captured the interest of both the research and the industrial worlds in recent years. The aim of this effort is to increase security and safety in several application domains such as national security, home and bank safety, traffic monitoring and navigation, tourism, and military applications. The video surveillance systems currently in use share one feature: A human operator must monitor them at all times, thus limiting the number of cameras and the area under surveillance and increasing cost. A more advantageous system would have continuous active warning capabilities, able to alert security officials during or even before the happening of a crime.

Existing automated surveillance systems can be classified into categories according to:

  • The environment they are primarily designed to observe;
  • The number of sensors that the automated surveillance system can handle;
  • The mobility of sensor.

The primary concern of this book is surveillance in an outdoor urban setting, where it is not possible for a single camera to observe the complete area of interest. Multiple cameras are required to observe such large environments. This book discusses and proposes techniques for development of an automated multi-camera surveillance system for outdoor environments, while identifying the important issues that a system needs to cope with in realistic surveillance scenarios. The goal of the research presented in this book is to build systems that can deal effectively with these realistic surveillance needs.

 

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

AUTOMATED VIDEO SURVEILLANCE
1
12 Automated Systems for Video Surveillance
2
13 Automated Surveillance System Tasks and Related Technical Challenges
4
133 Tracking Across Cameras
5
134 General Challenges
6
15 Book Organization
9
IDENTIFYING REGIONS OF INTEREST IN IMAGE SEQUENCES
11
22 General Problems in Background Subtraction
12
421 Feature Point Tracking Methods
46
422 Region Tracking Methods
47
423 Methods to Track People
48
43 Problems in Tracking 2D silhouettes of People
49
431 Occlusion
50
442 Object Tracker
51
45 Results
52
46 Discussion
54

23 Related Work
13
231 Background Subtraction using Color as a Feature
14
232 Background Subtraction using Multiple Features
16
233 Finite State Space Based Background Subtraction
17
241 Assumptions
18
243 Region Level Processing
21
244 FrameLevel Processing
22
26 Discussion
24
OBJECT DETECTION AND CATEGORIZATION
29
32 Problems in Object Categorization
30
332 Object Categorization using Supervised Classifiers
31
333 Object Categorization using Weakly Supervised Classifiers
32
34 Overview of the proposed categorization approach
33
35 Feature Selection and Base Classifiers
34
36 The CoTraining Framework
36
361 Online Learning
37
37 CoTraining Ability Measurement
39
39 Concluding Remarks
42
OBJECT TRACKING IN A SINGLE CAMERA
45
TRACKING IN MULTIPLE CAMERAS WITH DISJOINT VIEWS
59
52 Related Work
61
53 Formulation of the MultiCamera Tracking Problem
64
54 Learning InterCamera SpaceTime Probabilities
66
55 Estimating Change in Appearances across Cameras
67
551 The Space of Brightness Transfer Functions
68
552 Estimation of InterCamera BTFs and their Subspace
71
553 Computing Object Color Similarity Across Cameras Using the BTF Subspace
72
57 Results
74
58 Conclusions
81
KNIGHT SURVEILLANCE SYSTEM DEPLOYMENT
85
63 Knight in Action
86
64 Conclusion
89
CONCLUDING REMARKS
90
712 Understanding Complex Human Interaction Activities
92
References
95
Index
102
Copyright

Other editions - View all

Common terms and phrases