Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2019 | Book

Introduction Read chapter Read first chapter

Introduction to Intelligent Surveillance

Surveillance Data Capture, Transmission, and Analytics

Author: Dr. Wei Qi Yan

Publisher: Springer International Publishing

Book Series : Texts in Computer Science

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

This practically-oriented textbook introduces the fundamentals of designing digital surveillance systems powered by intelligent computing techniques. The text offers comprehensive coverage of each aspect of the system, from camera calibration and data capture, to the secure transmission of surveillance data, in addition to the detection and recognition of individual biometric features and objects. The coverage concludes with the development of a complete system for the automated observation of the full lifecycle of a surveillance event, enhanced by the use of artificial intelligence and supercomputing technology.

This updated third edition presents an expanded focus on human behavior analysis and privacy preservation, as well as deep learning methods.

Topics and features: contains review questions and exercises in every chapter, together with a glossary; describes the essentials of implementing an intelligent surveillance system and analyzing surveillance data, including a range of biometric characteristics; examines the importance of network security and digital forensics in the communication of surveillance data, as well as issues of issues of privacy and ethics; discusses the Viola-Jones object detection method, and the HOG algorithm for pedestrian and human behavior recognition; reviews the use of artificial intelligence for automated monitoring of surveillance events, and decision-making approaches to determine the need for human intervention; presents a case study on a system that triggers an alarm when a vehicle fails to stop at a red light, and identifies the vehicle’s license plate number; investigates the use of cutting-edge supercomputing technologies for digital surveillance, such as FPGA, GPU and parallel computing.

This concise and accessible work serves as a classroom-tested textbook for graduate-level courses on intelligent surveillance. Researchers and engineers interested in entering this area will also find the book suitable as a helpful self-study reference.

Table of Contents

Frontmatter
Chapter 1. Introduction
Abstract
This chapter covers the fundamentals in intelligent surveillance, i.e., what intelligent surveillance is, what elements should be included in a surveillance system, and how such a surveillance system will be implemented. There are three main phases, each of them shows the evolution in this field. Substantially, sensor deployment and calibration will be stressed in the second half of this chapter, networked camera settings, multisensor calibration Collins et al. (Proc IEEE 89(10):1456–1475, 2001), image distortion and its corrections, etc. will be covered Collins et al. (Proc IEEE 89(10):1456–1475, 2001). Automated calibration of multiple sensors Zhang (IEEE PAMI 22(11):1330–1334, 2000) will be formatted mathematically. In this chapter, we will overview the core issues and demonstrate an advanced understanding of the state-of-the-art theories and technologies in intelligent surveillance.
Wei Qi Yan
Chapter 2. Surveillance Data Capturing and Compression
Abstract
In this chapter, we will introduce surveillance data capturing using finite state machine (FSM) and critically evaluate the major technology of surveillance data compression. FSM has been used in the case of transmissions between different states within a system. It is important to study FSM in intelligent surveillance because it is an approach to bridge the gap between our real world and semantic space by using events. Moreover, a surveillance system records monitoring data all day long to effectively tackle the input data of surveillance systems; technologies of data compression are indispensable which will be detailed at the second half of this chapter.
Wei Qi Yan
Chapter 3. Surveillance Data Secure Transmissions
Abstract
In this chapter, we will introduce fundamental knowledge of network communications including the infrastructure of computer networks as well as network security, monitoring, and forensics; we also analyze scrambling and descrambling techniques in data security; finally, we will review the technologies of data secure transmissions over the Internet and Intranet. By the end of this chapter, we hope the major components of surveillance data transmission could be critically compared and evaluated.
Wei Qi Yan
Chapter 4. Surveillance Data Analytics
Abstract
In surveillance, object analysis refers to treat an object as a whole, while object analytics means taking each object into multiple parts and analyzing the components from various aspects. In this chapter, we mainly discuss those computable features of a visual object and how to use them for visual object analysis which includes object segmentation, detection and recognition, classification, tracking Murray and Basu (IEEE Trans Pattern Anal Mach Intell 16(5):449–459, 1994), annotation, labeling and ontology, search or retrieval, etc. Bimbo (1999); Hampapur et al. (IEEE Signal Process 22(2):38–51, 2005). We also will introduce deep learning-based visual object analysis in this chapter Goodfellow et al. (2016); LeCun and Bengio (255–258, 1995); LeCun et al. (Nature 521:436–444, 2015).
Wei Qi Yan
Chapter 5. Biometrics for Surveillance
Abstract
Our human always bring biometric information such as face, fingerprints, palms, and iris; no matter where we are, but biometric is discriminative from one to another which has essential and unique characteristics. In this chapter, we will introduce algorithms of surveillance data analytics, especially using biometric features, and critically compare and evaluate the major algorithms of biometrics for digital surveillance. At the end of this chapter, human privacy and ethics issues will be taken into consideration Adams, Ferryman (Secur J 28(3):272–289, 2012), Bowyer (IEEE Technol Soc 23(1):9–19, 2004).
Wei Qi Yan
Chapter 6. Visual Event Computing I
Abstract
In surveillance, we need present a story of a moving object. This story is called event which is the best way to describe the motion of this object. In this chapter, we will critically compare and evaluate the major components of a surveillance event, understand the event as a basic semantic unit of intelligent surveillance. We will introduce the algorithms how to detect and recognize an event.
Wei Qi Yan
Chapter 7. Visual Event Computing II
Abstract
In this chapter, we will continue event computing within the life cycle, we will emphasize it from the aspect of artificial intelligence in observation, learning, presentation and reasoning. We will critically evaluate the relevant computable algorithms for the purpose of intelligent surveillance.
Wei Qi Yan
Chapter 8. Surveillance Alarm Making
Abstract
Surveillance systems are monitoring human behaviors (walking, running, jumping, etc.) as well as natural disasters of this world (wide fire, flooding, tsunami, earthquake on earth, etc.) for the sake of safety and security. Correspondingly, alarming of surveillance systems should be set at everywhere in any time. Particularly, well-designed algorithms will trigger alarms and reduce the annoying false alarms. In this chapter, we will critically review and justify surveillance alarming algorithms using decision-making approaches so as to save security staff’s workload.
Wei Qi Yan
Chapter 9. Surveillance Computing
Abstract
Modern computing has to face the hardware bottleneck at present. Nowadays, supercomputing including multithread, multicore, GPU, and FPGA technologies (Kilts, Advanced FPGA design. Wiley, Hoboken, 2007; Stallings, Operating systems: internals and design principles. Pearson Education Limited, New Jersey, 2015) are alleged for resolving the problems and overcoming the technical barriers (Sanders, Kandrot, CUDA by examples: an introduction to general-purpose GPU programming. Addison-Wesley, Upper Saddle River, 2011). In this chapter, we will dwell on how to use these cutting-edge technologies in digital surveillance and make intelligent computing much faster. There are several criteria in evaluating or choosing parallel programming models (Rauber, Runger, Parallel programming: for multicore and cluster systems. Springer, Berlin, 2010), a few well-known parallel programming models such as OpenMP, UPC, and CUDA have been adopted in practice (Sanders, Kandrot, CUDA by examples: an introduction to general-purpose GPU programming. Addison-Wesley, Upper Saddle River, 2011).
Wei Qi Yan
Backmatter
Metadata
Title
Introduction to Intelligent Surveillance
Author
Dr. Wei Qi Yan
Copyright Year
2019
Electronic ISBN
978-3-030-10713-0
Print ISBN
978-3-030-10712-3
DOI
https://doi.org/10.1007/978-3-030-10713-0

Premium Partner

    Image Credits