Skip to main content

2003 | Buch

Multisensor Surveillance Systems

The Fusion Perspective

herausgegeben von: Gian Luca Foresti, Carlo S. Regazzoni, Pramod K. Varshney

Verlag: Springer US

insite
SUCHEN

Über dieses Buch

Monitoring of public and private sites is increasingly becoming a very important and critical issue, especially after the recent flurry of terrorist attacks including the one on the Word Trade Center in September 2001. It is, therefore, imperative that effective multisensor surveillance systems be developed to protect the society from similar attacks in the future. The new generation of surveillance systems to be developed have a specific requirement: they must be able to automatically identify criminal and terrorist activity without sacrificing individual privacy to the extent possible. Privacy laws concerning monitoring and surveillance systems vary from country to country but, in general, they try to protect the privacy of their citizens. Monitoring and visual surveillance has numerous other applications. It can be employed to help invalids or handicapped and to monitor the activities of elderly people. It can be used to monitor large events such as sporting events, as well. Nowadays, monitoring is employ~d in several different contexts including transport applications, such as monitoring of railway stations and airports, dangerous environments like nuclear facilities or traffic flows on roads and bridges. The latest generation of surveillance systems mainly rely on hybrid analog-digital, or completely digital video communications and processing methods and take advantage of the greater of flexibility offered by video processing algorithms that are capable focusing a human operator's attention on a set of interesting situations.

Inhaltsverzeichnis

Frontmatter

Multisensor Fusion in Surveillance Systems

Frontmatter
Chapter 1. A Distributed Sensor Network for Video Surveillance of Outdoors
Abstract
New generation surveillance systems [1], [2], [3] require to manage large amounts of visual data (optical, infrared, etc.). Recently, the development of sensor technology and computer networks has contributed to increase the interest in Distributed Sensor Networks (DSNs) for real-time information fusion [4], [5], [6].
G. L. Foresti, L. Snidaro
Chapter 2. Distributed Metadata Extraction Strategies in a Multi-Resolution Dual Camera System
Abstract
Several advanced video-surveillance systems based on video processing and understanding techniques have been recently developed [1, 2]. The principal aim of such systems is to recognize and classify potentially dangerous situations and consequentially generate some kind of alarm to raise the attention of a human operator. The use of automatic scene understanding systems is becoming more and more frequent in modern society: in particular, video-surveillance systems can be used for transport monitoring [3, 4], urban and building security [5], tourism [6], and bank protection [7, 8], even if their use was originally restricted to a military related field [9, 10]. Fast improvements in computing capabilities, cheap sensors and advanced image processing algorithms can be considered as the enabling technologies for the development of real-time video surveillance and monitoring systems. In particular, aspects related to the distribution of intelligence in cooperative systems need to be considered for the development of third-generation surveillance systems. A multiple sensors setup can be useful for satisfying several requirements on the system functionalities: a system using several video sensors without overlapped fields of view can be useful when a large area needs to be guarded.
L. Marcenaro, L. Marchesotti, C. S. Regazzoni
Chapter 3. Automatic Target Acquisition and Tracking with Cooperative Fixed and PTZ Video Cameras
Abstract
This chapter presents an overview of an automated video tracking and location system under development at the University of Tennessee’s Imaging, Robotics and Intelligent Systems (IRIS) Laboratory in Knoxville, Tennessee. Utilization of this system in any situation where detection of “wrong way” motion with subsequent video tracking would be beneficial is feasible. Examples of these situations include federal buildings, court houses, large office buildings, military bases, and national laboratories. Guidance of a robot arm employing dynamic imaging and motion trajectory analysis of workers in hazardous environments are also potential applications of the system’s tracking aspect. The University of Tennessee is initially developing this system for potential use as a security tool in commercial airports.
B. Abidi, A. Koschan, S. Kang, M. Mitckes, M. Abidi
Chapter 4. Learning the Fusion of Video Data Streams
Automatic Calibration and Registration of Surveillance Cameras
Abstract
Visual surveillance cameras pose two major problems: on one hand they must be installed and calibrated, on the other hand camera views must be combined if the final goal is to generate some natural language description of the dynamic evolution of a scene3 4 5 7 8 9. The work presented in this paper provides a semi automated solution to both problems.
J. Renno, P. Remagnino, G. A. Jones
Chapter 5. Image Fusion Using the Expectation-Maximization Algorithm and a Gaussian Mixture Model
Abstract
Image fusion refers the process of combining multiple images of a scene to obtain a single composite image [14]. The different images to be fused can come from different sensors of the same basic type or they may come from different types of sensors. The composite image should contain a more useful description of the scene than provided by any of the individual source images. This fused image should be more useful for human visual or machine perception. In recent years, image fusion has become an important and useful technique for image analysis, computer vision [47], concealed weapon detection (CWD) [8,9], and autonomous landing guidance (ALG) [1011].
Rick S. Blum, Jinzhong Yang
Chapter 6. Video-Based Surveillance for Chem-Bio Protection of Buildings
Abstract
In the wake of recent global events the threat of a chemical and biological (chem-bio) attacks became very real. The community of technology and policy experts has recognized this threat way ahead of its time and a very extensive treatise of the matter can be found at [1]. There are various scenarios that the terrorists may follow to stage a chem-bio attack. One such scenario by testimony of one terrorist is to attack through the air-intakes of commercial or Government buildings. In July 2001, the terrorist Ahmed Ressam described in his court testimony how the training he and many others received in Al-Qaeda camps included attacking buildings with chemical agents ([2]). In particular, he detailed how he was trained to use cyanide and sulfuric acid to create deadly fumes and how to inject these fumes into building air-intakes. The targeting of air-intakas meant to maximize the number of deaths in the building without creating a risk for the attacker.
Ioannis Pavlidis, Christos Stathopoulos, Tony Faltesek

Detection, Tracking and Recognition

Frontmatter
Chapter 7. Second Generation Prefiltering for Video Compression and Analysis in Multisensor Surveillance Systems
Abstract
Large digital surveillance networks that are deployed on buildings, highways, cities, train and metro stations, integrate an increasing number of cameras and sensors. Human operators cannot monitor all the available visual data without reliable and automatic detection systems. This is why object detection and tracking techniques, that are the first important steps towards higher level of scene understanding and analysis, become critical in video surveillance scenarios.
Francesco Ziliani, Julien Reichel
Chapter 8. Acquiring Multi-View Video with an Active Camera System
Abstract
For applications in human identification, activity recognition, 3D reconstruction, entertainment and sports, it is often desirable to capture a set of synchronized video sequences of a person from multiple camera viewpoints (see Figure 8-1). One way to achieve this is to set up a ring of cameras all statically aimed at a single point in space, and to have an actor perform at this fixation point while the video footage is shot. This is the method used to create spectacular special effects in the movie The Matrix, where playing back frames from a single time step, across all cameras, yields the appearance of freezing the action in time while a virtual camera flies around the scene. However, in surveillance or sports applications it is not possible to predict beforehand the precise location where an interesting activity will occur, and therefore it is necessary to dynamically adjust the fixation point of multiple camera views. We have developed a system that tracks a person in real-time and adjusts the pan, tilt, zoom and focus of each camera to acquire synchronized multi-view video of a person moving through the scene.
Robert T. Collins, Omead Amidi, Takeo Kanade
Chapter 9. A Computational Framework for Simultaneous Real-Time High-Level Video Representation
Extraction of moving objects and related events
Abstract
Because of the ever-increasing needs for video content accessibility, developing automated and effective frameworks for content-oriented video representation have become an active field of research.
Aishy Amer
Chapter 10. Multi-Camera Surveillance
Objec-Based Summarization Approach
Abstract
Most of the current indoor surveillance applications have single-camera single-room architecture where the cameras are stationary. Typically, each camera is assignee to a dedicated video recorder that can store the streaming video in either time-lapsed or event-based mode. These events are often limited to simple motion detection mechanisms. Considering the huge amount of the video data a multi-camera system may produces over a short time period, more sophisticated tools for control, representation, and content analysis became an urgent need. The nature of surveillance applications demands automatic and accurate detection of object of interest, intra-camera tracking, fusion of multiple modalities to solve inter-camera correspondence problem, easy access and retrieving video data, capability to make semantic query, and abstraction of video content.
Fatih Porikli
Chapter 11. Detecting Dangerous Behaviors of Mobile Objects in Parking Areas
Abstract
In the last decade video-surveillance systems have been developed for monitoring remote environments in order to detect and prevent dangerous situations. Until few years ago, surveillance was performed entirely by human operators, who interpreted the visual information presented to them on one or more monitors.
Gian Luca Foresti, Giorgio Giacinto, Fabio Roli

Biometrics in Surveillance Systems

Frontmatter
Chapter 12. Biometric Feature Extraction in a Multi-Camera Surveillance System
Abstract
Advanced, multi-camera surveillance systems present a practical and effective means of automatically detecting, tracking, and characterizing various people, events, activities, and situations. Recently, considerable focus has been placed on the tracking and analysis of human motion and, specifically, on the measurement of diverse biometrics for authentication and identification [1]. In this article we concentrate on the use of gait as a biometric and provide an introduction to a unique system for its robust tracking, extraction, and subsequent analysis.
Shiloh L. Dockstader, A. Murat Tekalp
Chapter 13. Fusion of Face Recognition Algorithms for Video-Based Surveillance Systems
Abstract
It is widely acknowledged that face recognition could play an important role in advanced video-based surveillance systems, mainly because it is non intrusive and does not require people cooperation [12]. Unfortunately, face recognition algorithms showed to suffer a lot from the high variability of environmental conditions. As an example, the effectiveness of face recognition strongly depends on lighting conditions and on variations in the subject’s pose and expression in front of the camera. This obviously limits their application to real video-surveillance tasks. On the other hand, face is considered a very good biometric. People recognize each other through the face, the acquisition process is non-intrusive, and does not require the collaboration of the subject to be recognized. Therefore, face recognition is a very active research field with many applications. For the purposes of this chapter, the face recognition applications can be subdivided in two types: applications in controlled and uncontrolled environments. One of the main applications of the first type is the so called “identity authentication”. A person submits to the automatic identity verification system its face (frontal and/or profile view) and declares her/his identity. The system matches the acquired face with the “template” stored in its data base, and classifies the person as a “genuine” (i.e., the claimed identity is accepted) or an “impostor”.
Gian Luca Marcialis, Fabio Roli
Chapter 14. Information Theory Based Face Tracking
Abstract
Automatic detection and tracking of human body parts (e.g. face, arms) is a challenging research topic with applications in many domains such as human computer interaction, surveillance, face recognition and human joint audio and video localization systems.
Evangelos Loutas, Christophoros Nikou, Ioannis Pitas
Chapter 15. Optimum Fusion Rules for Multimodal Biometric Systems
Abstract
“Biometrics is the automated use of physiological or behavioral characteristics to determine or verify identity”. The first modern commercial biometric device was introduced over 25 years ago when a machine that measured finger length was installed for maintaining employee time records at Shearson Hamil on Wall Street. In the ensuing years, hundreds of these hand geometry devices have been installed for security purposes at facilities operated by Western Electric and Naval Intelligence. In the US today, biometric security systems may be found in the Oakland International Airport (face recognition), Chicago O'Hare International (fingerprint), and Navy Consolidated Building (Iris recognition) [1]. With the demand for better security technology increasing, a variety of pilot projects have been completed recently in the area of access control [2]. These projects highlight the need to improve biometric verification accuracy.
Lisa Osadciw, Pramod Varshney, Kalyan Veeramachaneni
Backmatter
Metadaten
Titel
Multisensor Surveillance Systems
herausgegeben von
Gian Luca Foresti
Carlo S. Regazzoni
Pramod K. Varshney
Copyright-Jahr
2003
Verlag
Springer US
Electronic ISBN
978-1-4615-0371-2
Print ISBN
978-1-4613-5043-9
DOI
https://doi.org/10.1007/978-1-4615-0371-2