Visual Information Processing in Wireless Sensor Networks: Technology, Trends and Applications

Top

Description

Wireless sensor networks (WSNs) have many applications ranging from environmental monitoring, security management, and medical applications to smart homes.

Visual Information Processing in Wireless Sensor Networks: Technology, Trends and Applications provides a central source of reference on visual information processing in wireless sensor network environments and its technology, application, and society issues. This book is an important resource for researchers and academics working in the interdisciplinary domains of wireless sensor network technology and multimedia technology and its related areas, which include image processing, pervasive computing, embedded systems, and computer networks.

Top

Preface

The combination of image sensors with wireless sensor network (WSN) technology has resulted in a new network technology called a visual sensor network (VSN). The use of image sensors in VSNs increases the range of potential applications because compared to scalar sensors, image sensors are able to provide more information which can be used for visual processing tasks such as detection, identification, and tracking. On the one hand, VSNs can be seen as an extension of traditional WSNs where image sensors have replaced scalar sensors. On the other hand, the use of image sensors in VSNs brings with it a whole different set of practical and research challenges. The successful development of VSNs will require research contributions from different disciplines such as visual information processing, wireless networks, hardware and embedded systems, and power engineering.

The objective of this book is to assemble together the technology, trends, and applications for research on VSNs to serve as a comprehensive source of reference and to play an influential role in setting the scopes and directions of this emerging field of research. It contains open-solicited and invited chapters written by leading academics, researchers, and practitioners in the field. The target audience would be researchers, professionals, and students in engineering and Information Technology that engage with visual information processing and wireless systems. While there are other books on wireless sensor networks, few provide a primary focus for discussing the specific challenges for visual information processing in wireless sensor network environments.

This book contains 16 chapters including an opening chapter to introduce the reader to this area. It is structured into four sections which are: foundations of visual information processing in wireless sensor networks, energy efficient information processing and transmission in VSN, collaborative information processing in VSN, and hardware technology and applications for VSN. The first section on foundations of visual information processing in wireless sensor networks contains an introductory chapter. Chapter 1 by Li-minn Ang and Kah Phooi Seng, presents an introduction to VSN technology and its applications. The authors provide an overview of research issues and trends. Issues related to energy efficient processing, collaborative processing, and hardware technology will be highlighted. This chapter will also give a brief introduction to the other chapters in the book with a focus on showing how the topics covered in each chapter relate to the overall picture of visual information processing in wireless sensor network environments.

Section 2 is devoted to energy efficient information processing and transmission in VSNs. Image sensors generate a very high amount of data that would have to be processed and transmitted within the network. There is a trade-off between the energy required for processing and the energy required for transmission. To save energy in transmission, image and video compression algorithms can be applied to reduce the amount of data to be transmitted. However, the implementation of compression algorithms would require higher computational complexity, leading to higher energy consumption for processing. For energy efficient implementation in VSNs, the algorithms would need to have low computational and memory complexity. This section contains six chapters.

The first four chapters in the section present various approaches for energy efficient compression techniques to reduce the data. The techniques range from current standards like JPEG, MPEG-x and H.26x to newer techniques using distributed video coding and compressive sensing. Chapter 2 by Yinhao Ding and Cheng-Chew Lim, presents compressive sampling techniques to achieve information compression in VSNs. The authors focus on energy-efficiency and reliability issues such as the relationships between sparsity control and compression ratio, the effect of block-based sampling on reconstruction quality, the complexity consideration of the reconstruction process for real-time applications, and the compensation for packets missing in network flows. The effectiveness of the approach on recovered image quality is evaluated using Euclidean distance and variance analysis. The next chapter by A. Elamin, Varun Jeoti and Samir Belhouari, describes the use of distributed video coding for VSNs. The authors review important developments such as the Stanford Wyner-Ziv coding architecture and discuss the latest research trends highlighting a Region-Based-Wyner-Ziv video codec that enables low-complexity encoding while achieving high compression efficiency.

The fourth chapter by Mammeri Abdelhamid, Brahim Hadjou, Ahmed Khoumsi and Djemel Ziou, presents the design of wavelet filters for use in power constrained VSNs. While designing a wavelet-based coder (WBC) in the context of VSN, engineers and designers must respect the strict constraint on power consumption. The authors evaluate and select the best set of wavelet filters. Their results provide a good reference for designers of WBC for power-constrained applications such as VSN. Chapter 5 by Ruth Aguilar-Ponce, J. Luis Tecpanecatl-Xihuitl, and Alfonso Alba-Cadena, presents approaches for low level representation in VSNs. The authors introduce algorithms for data encoding and data filtering. Data encoding is performed by means of predictive video encoding using a phase-only correlation function for motion estimation. Data filtering is performed in three phases: pixel classification, background update, and detection. The algorithms involved in each phase are low in terms of complexity and memory resources.

The remaining two chapters in the section present various approaches for energy efficient transmission in VSNs. Visual information requires higher bandwidth and lower delay and delay jitter to provide the required Quality of Service (QoS) for multimedia transmission. Chapter 6 by Nalin Sharda, presents an overview of the evolution of WSNs and discusses factors for multimedia transmission in such networks such as bandwidth, delay and delay jitter and how these influence the QoS in the delivery of multimedia information. The author explores various transmission issues and limitations, such as limited energy, computational power, and bandwidth. The final chapter in the section by S. Mehta and K. S. Kwak, presents the use of energy-efficient backoff algorithms in MAC protocols. The authors present a study of various backoff algorithms and propose an improved backoff (IB) algorithm for an energy efficient MAC protocol in WSNs. Their results show that the IB algorithm gives improvements in throughput, channel access delay, and energy efficiency under varying traffic conditions over the widely used binary exponential backoff based algorithm.

Section 3 is devoted to collaborative information processing in VSNs. To realize the full potential of the VSN, the visual nodes can collaborate with each other to achieve the goals of the application. The issues for collaborative processing are similar to that involving multi-camera networks. Typical visual processing tasks to be performed collaboratively are to detect, track, and recognize objects in the scene. Object detection refers to a visual processing task to locate a certain class of objects in the image frame (for example, faces and vehicles). The goal of object tracking is to associate target objects in different video frames. Object recognition refers to a visual processing task where the general class of the object is known and the objective is to recognize an object’s exact identity. This section contains four chapters.

Chapter 8 by Yi Zhou, Hichem Snoussi, Shibao Zheng and Fethi Smach, presents an approach in wireless camera networks for visual human tracking. The authors exploit the use of distinctive and fast to compute local features to represent the non-rigid targets. Transmission of feature descriptors between cameras is done without any calibration. They show that their proposed local features succeed to re-identify and relocate the target among the distributed cameras and also propose an efficient interest point detection and matching scheme for the visual tracking under real-time constraints. The next chapter by Shung Han Cho, Yunyoung Nam and Sangjin Hong, presents an object association method through multiple cameras collaboration for a large-scale surveillance system. The objects association is achieved by locally generating homographic lines on targets in collaborating cameras. Their proposed method is verified with real video sequences. The simulation result demonstrates that the proposed method is robust against false association because it considers all the possible pairing cases of occluded targets.

Chapter 10 by Juan Gómez-Romero, Jesús García, Miguel A. Patricio, José M. Molina, and James Llinas, presents an approach for high-level fusion in VSNs. Information fusion techniques combine data from multiple sensors, along with additional information and knowledge, to obtain better estimates of the observed scenario than could be achieved by the use of single sensors or information sources alone. The authors study the architectural and functional issues of applying context information to improve high-level fusion procedures, with a particular focus on visual data applications. The next chapter by Majdi Mansouri, Hichem Snoussi, Jing Teng, Ouachani Ilham, and Cédric Richard, describes a technique using quantized bayesian filtering in WSNs. The focus of the chapter is to study the Bayesian inference problem in distributed WSNs with particular emphasis on the trade-off between estimation precision and energy-awareness. The authors propose a variational approach to approximate the particle distribution to a single Gaussian distribution, while respecting the communication constraints of WSNs. Simulation results demonstrate the significantly improved performance of the approach.

The final section (Section 4) of the book deals with the hardware technology and applications for VSNs. This section contains five chapters. Important issues for the hardware technology are related to the image sensor, processor hardware and power considerations. The authors in Chapters 11 and 12 present approaches using line scan cameras in place of two-dimensional cameras to reduce data during the acquisition process. Chapter 12 by Jiang Yu Zheng, describes the use of line sensors for monitoring and surveillance in VSNs using linear CCD sensors. It reads temporal data from a CCD array continuously and stores them to form a 2D image profile. The method delivers more information such as color, shape, and event of a flowing scene. It abstracts passing objects in the profile without heavy computation and transmits much less data than a video from normal cameras. This chapter focuses on several unsolved issues of line sensors in capturing targets in the 3D space such as sensor setting, shape analysis, robust object extraction, and real time background adapting to ensure long-term sensing and visual data collection via networks.

Chapter 13 by Mangesh Chitnis, Claudio Salvadori, Matteo Petracca, Paolo Pagano, Giuseppe Lipari, and Luca Santinelli, present an innovative technique of using line sensor based image capturing and processing in order to detect moving objects such as vehicles. The authors show that line sensor techniques may achieve faster processing results with less storage and bandwidth requirements while conserving node energy. Their solution presents itself as a low-cost candidate for Intelligent Transport Systems (ITS) to monitor and control urban traffic. The next chapter by Wai Chong Chia, Christopher Ngau, Lee Seng Yeong, Li Wern Chew, Li-minn Ang, and Kah Phooi Seng, presents hardware technology for VSNs using field programmable gate array technology (FPGA). The authors propose a FPGA implementation of a low-complexity and strip-based microprocessor architecture for image processing. The captured image data is processed in a strip-by-strip manner to reduce the local memory requirement. This allows an image with higher resolution to be captured and processed with the limited hardware resources. The approach is illustrated with a visual saliency application.

The remaining two chapters are concerned with applications for VSNs. Chapter 15 by Johannes Karlsson, Tim Wark, Keni Ren, Karin Fahlquist, and Haibo Li, presents a practical application of VSNs – the Digital Zoo. The authors describe their work to set up a large scale VSN in a Swedish zoo. It is located close to the Arctic Circle making the environment very hard for this type of deployment. To reach this goal the sensed data will be processed and semantic information will be used to support interaction design, which is a key component to provide a new type of experience for the visitors. The final chapter by Julien Sebastien Jainsky, and Deepa Kundur, presents a security application for VSNs. In particular, attention is brought to steganographic security and how it can be discouraged without challenging the primary objectives of the network. Preventative steganalysis aims at discouraging any potential steganographic attacks by processing the collected data such that the possibility of steganography becomes very small and the steganalysis leads to high rate of success. The authors motivate the development and implementation of more lightweight steganalytic solutions that take into account the resources made available by the network’s deployment and its application in order to minimize the steganalysis impact on the workload.

We would like to express our deepest appreciation to the authors of this book and to the reviewers for their tremendous service by critically reviewing the chapters and offering useful suggestions. Most of the authors of chapters included in this book also served as referees for chapters written by other authors. We hope that the reader will share our enthusiasm to present this volume and will find it useful.

Li-minn Ang and Kah Phooi Seng
Editors

Top

Author(s)/Editor(s) Biography

Li-Minn Ang
Li-Minn Ang received his PhD and Bachelor degrees from Edith Cowan University, Australia in 2001 and 1996 respectively. He is currently an Associate Professor at the University of Nottingham Malaysia Campus. His research interests are in the fields of visual information processing, intelligent processing techniques, hardware architectures, reconfigurable computing and engineering education. He has authored or coauthored a number of journal and conference papers in these areas. Currently he leads the research activities at the Visual Information Engineering Research Group at the University of Nottingham Malaysia Campus. He has received research grants from the Malaysian government and industry for his research activities and has served as a reviewer and committee member for a number of journals and conferences. Dr. Ang is a Senior Member of the IEEE and a Fellow of the Higher Education Academy (UK).

Kah Phooi Seng
Kah Phooi Seng received her PhD and Bachelor degrees from the University of Tasmania, Australia in 2001 and 1997 respectively. She is currently an Associate Professor at the University of Nottingham Malaysia Campus. Her research interests are in the fields of intelligent visual processing, biometrics and multi-biometrics, artificial intelligence and signal processing. She has authored or coauthored a number of journal and conference papers in these areas. Dr. Seng is involved with research activities at the Visual Information Engineering Research Group at the University of Nottingham Malaysia Campus. She has received research grants from the Malaysian government and industry for her research activities and has served as a reviewer for journals and conferences.

Top

Reviews and Testimonials

"While there are other books on wireless sensor networks, few provide a primary focus for discussing the specific challenges for visual information processing in wireless sensor network environments. This book contains 16 chapters including an opening chapter to introduce the reader to this area."

- Dr. Li-minn Ang and Dr. Kah Phooi Seng, University of Nottingham, Malaysia