Distributed low-power image processing in wireless sensor networks for intelligent video surveillance applications

Distributed Wireless Smart Camera (DWSC) network is a special type of Wireless Sensor Network (WSN) that processes captured images in a distributed manner. While image processing on DWSCs sees a great potential for growth, with its applications possessing a vast practical application domain such as security surveillance and health care, it suffers from tremendous constraints. In addition to the limitations of conventional WSNs, image processing on DWSCs requires more computational power, bandwidth and energy that presents significant challenges for large scale deployments. This dissertation has developed a number of algorithms that are highly scalable, portable, energy efficient and performance efficient, with considerations of practical constraints imposed by the hardware and the nature of WSN. More specifically, these algorithms tackle the problems of multi-object tracking and localisation in distributed wireless smart camera net- works and optimal camera configuration determination. Addressing the first problem of multi-object tracking and localisation requires solving a large array of sub-problems. The sub-problems that are discussed in this dissertation are calibration of internal parameters, multi-camera calibration for localisation and object handover for tracking. These topics have been covered extensively in computer vision literatures, however new algorithms must be invented to accommodate the various constraints introduced and required by the DWSC platform. A technique has been developed for the automatic calibration of low-cost cameras which are assumed to be restricted in their freedom of movement to either pan or tilt movements. Camera internal parameters, including focal length, principal point, lens distortion parameter and the angle and axis of rotation, can be recovered from a minimum set of two images of the camera, provided that the axis of rotation between the two images goes through the camera's optical centre and is parallel to either the vertical (panning) or horizontal (tilting) axis of the image. For object localisation, a novel approach has been developed for the calibration of a network of non-overlapping DWSCs in terms of their ground plane homographies, which can then be used for localising objects. In the proposed approach, a robot travels through the camera network while updating its position in a global coordinate frame, which it broadcasts to the cameras. The cameras use this, along with the image plane location of the robot, to compute a mapping from their image planes to the global coordinate frame. This is combined with an occupancy map generated by the robot during the mapping process to localised objects moving within the network. In addition, to deal with the problem of object handover between DWSCs of non-overlapping fields of view, a highly-scalable, distributed protocol has been designed. Cameras that follow the proposed protocol transmit object descriptions to a selected set of neighbours that are determined using a predictive forwarding strategy. The received descriptions are then matched at the subsequent camera on the object's path using a probability maximisation process with locally generated descriptions. The second problem of camera placement emerges naturally when these pervasive devices are put into real use. The locations, orientations, lens types etc. of the cameras must be chosen in a way that the utility of the network is maximised (e.g. maximum coverage) while user requirements are met. To deal with this, a statistical formulation of the problem of determining optimal camera configurations has been introduced and a Trans-Dimensional Simulated Annealing (TDSA) algorithm has been proposed to effectively solve the problem.

Design and evaluation of an image analysis platform for low-power, low-bandwidth camera networks

We describe the design and evaluation of a platform for networks of cameras in low-bandwidth, low-power sensor networks. In our work to date we have investigated two different DSP hardware/software platforms for undertaking the tasks of compression and object detection and tracking. We compare the relative merits of each of the hardware and software platforms in terms of both performance and energy consumption. Finally we discuss what we believe are the ongoing research questions for image processing in WSNs.

Mapping of indoor environments by robots using low-cost vision sensors

For robots to operate in human environments they must be able to make their own maps because it is unrealistic to expect a user to enter a map into the robot’s memory; existing floorplans are often incorrect; and human environments tend to change. Traditionally robots have used sonar, infra-red or laser range finders to perform the mapping task. Digital cameras have become very cheap in recent years and they have opened up new possibilities as a sensor for robot perception. Any robot that must interact with humans can reasonably be expected to have a camera for tasks such as face recognition, so it makes sense to also use the camera for navigation. Cameras have advantages over other sensors such as colour information (not available with any other sensor), better immunity to noise (compared to sonar), and not being restricted to operating in a plane (like laser range finders). However, there are disadvantages too, with the principal one being the effect of perspective. This research investigated ways to use a single colour camera as a range sensor to guide an autonomous robot and allow it to build a map of its environment, a process referred to as Simultaneous Localization and Mapping (SLAM). An experimental system was built using a robot controlled via a wireless network connection. Using the on-board camera as the only sensor, the robot successfully explored and mapped indoor office environments. The quality of the resulting maps is comparable to those that have been reported in the literature for sonar or infra-red sensors. Although the maps are not as accurate as ones created with a laser range finder, the solution using a camera is significantly cheaper and is more appropriate for toys and early domestic robots.

Propagation of low power low divergence Gaussian fields in unbiased self-defocusing photorefractive media and their interactions

Many optical networks are limited in speed and processing capability due to the necessity for the optical signal to be converted to an electrical signal and back again. In addition, electronically manipulated interconnects in an otherwise optical network lead to overly complicated systems. Optical spatial solitons are optical beams that propagate without spatial divergence. They are capable of phase dependent interactions, and have therefore been extensively researched as suitable all optical interconnects for over 20 years. However, they require additional external components, initially high voltage power sources were required, several years later, high power background illumination had replaced the high voltage. However, these additional components have always remained as the greatest hurdle in realising the applications of the interactions of spatial optical solitons as all optical interconnects. Recently however, self-focusing was observed in an otherwise self-defocusing photorefractive crystal. This observation raises the possibility of the formation of soliton-like fields in unbiased self-defocusing media, without the need for an applied electrical field or background illumination. This thesis will present an examination of the possibility of the formation of soliton-like low divergence fields in unbiased self-defocusing photorefractive media. The optimal incident beam and photorefractive media parameters for the formation of these fields will be presented, together with an analytical and numerical study of the effect of these parameters. In addition, preliminary examination of the interactions of two of these fields will be presented. In order to complete an analytical examination of the field propagating through the photorefractive medium, the spatial profile of the beam after propagation through the medium was determined. For a low power solution, it was found that an incident Gaussian field maintains its Gaussian profile as it propagates. This allowed the beam at all times to be described by an individual complex beam parameter, while also allowing simple analytical solutions to the appropriate wave equation. An analytical model was developed to describe the effect of the photorefractive medium on the Gaussian beam. Using this model, expressions for the required intensity dependent change in both the real and imaginary components of the refractive index were found. Numerical investigation showed that under certain conditions, a low powered Gaussian field could propagate in self-defocusing photorefractive media with divergence of approximately 0.1 % per metre. An investigation into the parameters of a Ce:BaTiO3 crystal showed that the intensity dependent absorption is wavelength dependent, and can in fact transition to intensity dependent transparency. Thus, with careful wavelength selection, the required intensity dependent change in both the real and imaginary components of the refractive index for the formation of a low divergence Gaussian field are physically realisable. A theoretical model incorporating the dependence of the change in real and imaginary components of the refractive index on propagation distance was developed. Analytical and numerical results from this model are congruent with the results from the previous model, showing low divergence fields with divergence less than 0.003 % over the propagation length of the photorefractive medium. In addition, this approach also confirmed the previously mentioned self-focusing effect of the self-defocusing media, and provided an analogy to a negative index GRIN lens with an intensity dependent focal length. Experimental results supported the findings of the numerical analysis. Two low divergence fields were found to possess the ability to interact in a Ce:BaTiO3 crystal in a soliton-like fashion. The strength of these interactions was found to be dependent on the degree of divergence of the individual beams. This research found that low-divergence fields are possible in unbiased self-defocusing photorefractive media, and that soliton-like interactions between two of these fields are possible. However, in order for these types of fields to be used in future all optical interconnects, the manipulation of these interactions, together with the ability for these fields to guide a second beam at a different wavelength, must be investigated.

A novel CDVM based high-voltage converter using low power solid-state switches and a tuned resonant circuit designed for pulsed power applications

A novel concept of producing high dc voltage for pulsed-power applications is proposed in this paper. The topology consists of an LC resonant circuit supplied through a tuned alternating waveform that is produced by an inverter. The control scheme is based on the detection of variations in the resonant frequency and adjustment of the switching signal patterns for the inverter to produce a square waveform with exactly the same frequencies. Therefore the capacitor voltage oscillates divergently with an increasing amplitude. A simple one-stage capacitor-diode voltage multiplier (CDVM) connected to the resonant capacitor then rectifies the alternating voltage and gives a dc level equal to twice the input voltage amplitude. The produced high voltage appears then in the form of high-voltage pulses across the load. A basic model is simulated by Simulink platform of MATLAB and the results are included in the paper.

Low-cost flight control system for a small autonomous helicopter

In this paper we describe a low-cost flight control system for a small (60 class) helicopter which is part of a larger project to develop an autonomous flying vehicle. Our approach differs from that of others in not using an expensive inertial/GPS sensing system. The primary sensors for vehicle stabilization are a low-cost inertial sensor and a pair of CMOS cameras. We describe the architecture of our flight control system, the inertial and visual sensing subsystems and present some flight control results.

A comparison of two commercially available motion capture systems for gait analysis : high end vs low-cost

In 1999 Richards compared the accuracy of commercially available motion capture systems commonly used in biomechanics. Richards identified that in static tests the optical motion capture systems generally produced RMS errors of less than 1.0 mm. During dynamic tests, the RMS error increased to up to 4.2 mm in some systems. In the last 12 years motion capture systems have continued to evolve and now include high-resolution CCD or CMOS image sensors, wireless communication, and high full frame sampling frequencies. In addition to hardware advances, there have also been a number of advances in software, which includes improved calibration and tracking algorithms, real time data streaming, and the introduction of the c3d standard. These advances have allowed the system manufactures to maintain a high retail price in the name of advancement. In areas such as gait analysis and ergonomics many of the advanced features such as high resolution image sensors and high sampling frequencies are not required due to the nature of the task often investigated. Recently Natural Point introduced low cost cameras, which on face value appear to be suitable as at very least a high quality teaching tool in biomechanics and possibly even a research tool when coupled with the correct calibration and tracking software. The aim of the study was therefore to compare both the linear accuracy and quality of angular kinematics from a typical high end motion capture system and a low cost system during a simple task.

The exploration of consumer power in online brand communities : a comparison case study in Australia and China

Aided by the development of information technology, the balance of power in the market place is rapidly shifting from marketers towards consumers and nowhere is this more obvious than in the online environment (Denegri-Knott, Zwick, & Schroeder, 2006; Moynagh & Worsley, 2002; Newcomer, 2000; Samli, 2001). From the inception and continuous development of the Internet, consumers are becoming more empowered. They can choose what they want to click on the Internet, they can shop and transact payments, watch and download video, chat with others, be it friends or even total strangers. Especially in online communities, like-minded consumers share and exchange information, ideas and opinions. One form of online community is the online brand community, which gathers specific brand lovers. As with any social unit, people form different roles in the community and exert different effects on each other. Their interaction online can greatly influence the brand and marketers. A comprehensive understanding of the operation of this special group form is essential to advancing marketing thought and practice (Kozinets, 1999). While online communities have strongly shifted the balance of power from marketers to consumers, the current marketing literature is sparse on power theory (Merlo, Whitwell, & Lukas, 2004). Some studies have been conducted from an economic point of view (Smith, 1987), however their application to marketing has been limited. Denegri-Knott (2006) explored power based on the struggle between consumers and marketers online and identified consumer power formats such as control over the relationship, information, aggregation and participation. Her study has built a foundation for future power studies in the online environment. This research project bridges the limited marketing literature on power theory with the growing recognition of online communities among marketing academics and practitioners. Specifically, this study extends and redefines consumer power by exploring the concept of power in online brand communities, in order to better understand power structure and distribution in this context. This research investigates the applicability of the factors of consumer power identified by Denegri-Knott (2006) to the online brand community. In addition, by acknowledging the model proposed by McAlexander, Schouten, & Koenig (2002), which emphasized that community study should focus on the role of consumers and identifying multiple relationships among the community, this research further explores how member role changes will affect power relationships as well as consumer likings of the brand. As a further extension to the literature, this study also considers cultural differences and their effect on community member roles and power structure. Based on the study of Hofstede (1980), Australia and China were chosen as two distinct samples to represent differences in two cultural dimensions, namely individualism verses collectivism and high power distance verses low power distance. This contribution to the research also helps answer the research gap identified by Muñiz Jr & O'Guinn (2001), who pointed out the lack of cross cultural studies within the online brand community context. This research adopts a case study methodology to investigate the issues identified above. Case study is an appropriate research strategy to answer “how” and “why” questions of a contemporary phenomenon in real-life context (Yin, 2003). The online brand communities of “Haloforum.net” in Australia and “NGA.cn” in China were selected as two cases. In-depth interviews were used as the primary data collection method. As a result of the geographical dispersion and the preference of a certain number of participants, online synchronic interviews via MSN messenger were utilized along with the face-to-face interviews. As a supplementary approach, online observation was carried over two months, covering a two week period prior to the interviews and a six week period following the interviews. Triangulation techniques were used to strengthen the credibility and validity of the research findings (Yin, 2003). The findings of this research study suggest a new definition of power in an online brand community. This research also redefines the consumer power types and broadens the brand community model developed by McAlexander et al. (2002) in an online context by extending the various relationships between brand and members. This presents a more complete picture of how the perceived power relationships are structured in the online brand community. A new member role is discovered in the Australian online brand community in addition to the four member roles identified by Kozinets (1999), in contrast however, all four roles do not exist in the Chinese online brand community. The research proposes a model which links the defined power types and identified member roles. Furthermore, given the results of the cross-cultural comparison between Australia and China showed certain discrepancies, the research suggests that power studies in the online brand community should be country-specific. This research contributes to the body of knowledge on online consumer power, by applying it to the context of an online brand community, as well as considering factors such as cross cultural difference. Importantly, it provides insights for marketing practitioners on how to best leverage consumer power to serve brand objective in online brand communities. This, in turn, should lead to more cost effective and successful communication strategies. Finally, the study proposes future research directions. The research should be extended to communities of different sizes, to different extents of marketer control over the community, to the connection between online and offline activities within the brand community, and (given the cross-cultural findings) to different countries. In addition, a greater amount of research in this area is recommended to determine the generalizability of this study.

Automated road pavement marking detection from high resolution aerial images based on Multi-resolution image analysis and anisotropic Gaussian filtering

Road features extraction from remote sensed imagery has been a long-term topic of great interest within the photogrammetry and remote sensing communities for over three decades. The majority of the early work only focused on linear feature detection approaches, with restrictive assumption on image resolution and road appearance. The widely available of high resolution digital aerial images makes it possible to extract sub-road features, e.g. road pavement markings. In this paper, we will focus on the automatic extraction of road lane markings, which are required by various lane-based vehicle applications, such as, autonomous vehicle navigation, and lane departure warning. The proposed approach consists of three phases: i) road centerline extraction from low resolution image, ii) road surface detection in the original image, and iii) pavement marking extraction on the generated road surface. The proposed method was tested on the aerial imagery dataset of the Bruce Highway, Queensland, and the results demonstrate the efficiency of our approach.

Robust pose estimation for a car-like vehicle

In this paper, we outline the sensing system used for the visual pose control of our experimental car-like vehicle, the autonomous tractor. The sensing system consists of a magnetic compass, an omnidirectional camera and a low-resolution odometry system. In this work, information from these sensors is fused using complementary filters. Complementary filters provide a means of fusing information from sensors with different characteristics in order to produce a more reliable estimate of the desired variable. Here, the range and bearing of landmarks observed by the vision system are fused with odometry information and a vehicle model, providing a more reliable estimate of these states. We also present a method of combining a compass sensor with odometry and a vehicle model to improve the heading estimate.

Ontology-based image annotation

With regard to the long-standing problem of the semantic gap between low-level image features and high-level human knowledge, the image retrieval community has recently shifted its emphasis from low-level features analysis to high-level image semantics extrac- tion. User studies reveal that users tend to seek information using high-level semantics. Therefore, image semantics extraction is of great importance to content-based image retrieval because it allows the users to freely express what images they want. Semantic content annotation is the basis for semantic content retrieval. The aim of image anno- tation is to automatically obtain keywords that can be used to represent the content of images. The major research challenges in image semantic annotation are: what is the basic unit of semantic representation? how can the semantic unit be linked to high-level image knowledge? how can the contextual information be stored and utilized for image annotation? In this thesis, the Semantic Web technology (i.e. ontology) is introduced to the image semantic annotation problem. Semantic Web, the next generation web, aims at mak- ing the content of whatever type of media not only understandable to humans but also to machines. Due to the large amounts of multimedia data prevalent on the Web, re- searchers and industries are beginning to pay more attention to the Multimedia Semantic Web. The Semantic Web technology provides a new opportunity for multimedia-based applications, but the research in this area is still in its infancy. Whether ontology can be used to improve image annotation and how to best use ontology in semantic repre- sentation and extraction is still a worth-while investigation. This thesis deals with the problem of image semantic annotation using ontology and machine learning techniques in four phases as below. 1) Salient object extraction. A salient object servers as the basic unit in image semantic extraction as it captures the common visual property of the objects. Image segmen- tation is often used as the �rst step for detecting salient objects, but most segmenta- tion algorithms often fail to generate meaningful regions due to over-segmentation and under-segmentation. We develop a new salient object detection algorithm by combining multiple homogeneity criteria in a region merging framework. 2) Ontology construction. Since real-world objects tend to exist in a context within their environment, contextual information has been increasingly used for improving object recognition. In the ontology construction phase, visual-contextual ontologies are built from a large set of fully segmented and annotated images. The ontologies are composed of several types of concepts (i.e. mid-level and high-level concepts), and domain contextual knowledge. The visual-contextual ontologies stand as a user-friendly interface between low-level features and high-level concepts. 3) Image objects annotation. In this phase, each object is labelled with a mid-level concept in ontologies. First, a set of candidate labels are obtained by training Support Vectors Machines with features extracted from salient objects. After that, contextual knowledge contained in ontologies is used to obtain the �nal labels by removing the ambiguity concepts. 4) Scene semantic annotation. The scene semantic extraction phase is to get the scene type by using both mid-level concepts and domain contextual knowledge in ontologies. Domain contextual knowledge is used to create scene con�guration that describes which objects co-exist with which scene type more frequently. The scene con�guration is represented in a probabilistic graph model, and probabilistic inference is employed to calculate the scene type given an annotated image. To evaluate the proposed methods, a series of experiments have been conducted in a large set of fully annotated outdoor scene images. These include a subset of the Corel database, a subset of the LabelMe dataset, the evaluation dataset of localized semantics in images, the spatial context evaluation dataset, and the segmented and annotated IAPR TC-12 benchmark.

A distributed protocol for object tracking in wireless multimedia sensor networks

We consider the problem of object tracking in a wireless multimedia sensor network (we mainly focus on the camera component in this work). The vast majority of current object tracking techniques, either centralised or distributed, assume unlimited energy, meaning these techniques don't translate well when applied within the constraints of low-power distributed systems. In this paper we develop and analyse a highly-scalable, distributed strategy to object tracking in wireless camera networks with limited resources. In the proposed system, cameras transmit descriptions of objects to a subset of neighbours, determined using a predictive forwarding strategy. The received descriptions are then matched at the next camera on the objects path using a probability maximisation process with locally generated descriptions. We show, via simulation, that our predictive forwarding and probabilistic matching strategy can significantly reduce the number of object-misses, ID-switches and ID-losses; it can also reduce the number of required transmissions over a simple broadcast scenario by up to 67%. We show that our system performs well under realistic assumptions about matching objects appearance using colour.

Towards the development of a gas sensor system for monitoring pollutant gases in the low troposphere using small unmanned aerial vehicles

The world is facing problems due to the effects of increased atmospheric pollution, climate change and global warming. Innovative technologies to identify, quantify and assess fluxes exchange of the pollutant gases between the Earth’s surface and atmosphere are required. This paper proposes the development of a gas sensor system for a small UAV to monitor pollutant gases, collect data and geo-locate where the sample was taken. The prototype has two principal systems: a light portable gas sensor and an optional electric–solar powered UAV. The prototype will be suitable to: operate in the lower troposphere (100-500m); collect samples; stamp time and geo-locate each sample. One of the limitations of a small UAV is the limited power available therefore a small and low power consumption payload is designed and built for this research. The specific gases targeted in this research are NO2, mostly produce by traffic, and NH3 from farming, with concentrations above 0.05 ppm and 35 ppm respectively which are harmful to human health. The developed prototype will be a useful tool for scientists to analyse the behaviour and tendencies of pollutant gases producing more realistic models of them.