<p>In the blooming era of smart edge devices, surveillance cameras have been deployed in many locations. Surveillance cameras are most useful when they are spaced out to maximize coverage of an area. However, deciding where to place cameras is an NP-hard problem and researchers have proposed heuristic solutions. Existing work does not consider a significant restriction of computer vision: in order to track a moving object, the object must occupy enough pixels. The number of pixels depends on many factors (How far away is the object? What is the camera resolution? What is the focal length?). In this study we propose a camera placement method that identifies effective camera placement in arbitrary spaces, and can account for different camera types as well. Our strategy represents spaces as polygons, then uses a greedy algorithm to partition the polygons and determine the cameras' locations to provide desired coverage. The solution also makes it possible to perform object tracking via overlapping camera placement. Our method is evaluated against complex shapes and real-world museum floor plans, achieving up to 85% coverage and 25% overlap.</p>

Wide-area camera networks are becoming more and more common. They have widerange of commercial and military applications from video surveillance to smart home and from traffic monitoring to anti-terrorism. The design of such a camera network is a challenging problem due to the complexity of the environment, self and mutual occlusion of moving objects, diverse sensor properties and a myriad of performance metrics for different applications. In this dissertation, we consider two such challenges: camera planing and camera fusion. Camera planning is to determine the optimal number and placement of cameras for a target cost function. Camera fusion describes the task of combining images collected by heterogenous cameras in the network to extract information pertinent to a target application. I tackle the camera planning problem by developing a new unified framework based on binary integer programming (BIP) to relate the network design parameters and the performance goals of a variety of camera network tasks. Most of the BIP formulations are NP hard problems and various approximate algorithms have been proposed in the literature. In this dissertation, I develop a comprehensive framework in comparing the entire spectrum of approximation algorithms from Greedy, Markov Chain Monte Carlo (MCMC) to various relaxation techniques. The key contribution is to provide not only a generic formulation of the camera planning problem but also novel approaches to adapt the formulation to powerful approximation schemes including Simulated Annealing (SA) and Semi-Definite Program (SDP). The accuracy, efficiency and scalability of each technique are analyzed and compared in depth. Extensive experimental results are provided to illustrate the strength and weakness of each method. The second problem of heterogeneous camera fusion is a very complex problem. Information can be fused at different levels from pixel or voxel to semantic objects, with large variation in accuracy, communication and computation costs. My focus is on the geometric transformation of shapes between objects observed at different camera planes. This so-called the geometric fusion approach usually provides the most reliable fusion approach at the expense of high computation and communication costs. To tackle the complexity, a hierarchy of camera models with different levels of complexity was proposed to balance the effectiveness and efficiency of the camera network operation. Then different calibration and registration methods are proposed for each camera model. At last, I provide two specific examples to demonstrate the effectiveness of the model: 1)a fusion system to improve the segmentation of human body in a camera network consisted of thermal and regular visible light cameras and 2) a view dependent rendering system by combining the information from depth and regular cameras to collecting the scene information and generating new views in real time.

Deployment of cameras in Wireless Multimedia Sensor Networks (WMSNs) is crucial in achieving good coverage, accuracy and fault tolerance. With the decreased costs of wireless cameras, WMSNs provide opportunities for redundant camera deployment in order to get multiple disparate views of events. Referred to as multi-perspective coverage (MPC), this thesis proposes an optimal solution for camera deployment that can achieve full MPC for a given region. The solution is based on a Bi-Level mixed integer program (MIP) which works by solving two sub-problems named master and sub-problems. The master problem identifies a solution based on an initial set of points and then calls the sub-problem to cover the uncovered points iteratively. The Bi-Level algorithm is then revised to provide MPC with the minimum cost in Heteregeneous Visual Sensor Networks (VSNs) where cameras may have different price, resolution, Field-of-View (FoV) and Depth-of-Field (DoF). For a given average resolution, area, and variety of camera sensors, we propose a deployment algorithm which minimizes the total cost while guaranteeing 100\% MPC of the area and a minimum resolution. Furthermore, revised Bi-level algorithm provides the flexibility of achieving required resolution on sub-regions for a given region. The numerical results show the superiority of our approach with respect to existing approaches.

Indiana University-Purdue University Indianapolis (IUPUI) / Image is a dominant medium among video, 3D model, and other media for visualizing environment and creating virtual access on the Internet. The location of image capture is, however, subjective and has relied on the esthetic sense of photographers up until this point. In this paper, we will not only visualize areas with images, but also propose a general framework to determine where the most distinct viewpoints should be located. Starting from elevation data, we present spatial and content information in ground-based images such that (1) a given number of images can have maximum coverage on informative scenes; (2) a set of key views can be selected with certain continuity for representing the most distinct views. According to the scene visibility, continuity, and data redundancy, we evaluate viewpoints numerically with an object-emitting illumination model. Our key view exploration may eventually reduce the visual data to transmit, facilitate image acquisition, indexing and interaction, and enhance perception of spaces. Real sample images are captured based on planned positions to form a visual network to index the area.

The objective of this thesis is to model and solve the problem of placing thermal imaging camera for monitoring piles of combustible bio-fuels. The cameras, of different models, can be mounted at discrete heights on poles at fixed positions and at discrete angles, and one seeks camera model and mounting combinations that monitor as much of the piles as possible to as low cost as possible. Since monitoring all piles may not be possible or desired, due to budget or customer constrains, the solution to the problem is a set of compromises between coverage and cost. We denote such a set of compromises a frontier. In the first part of the thesis a way of modelling the problem is presented. The model uses a discrete formulation where the area to monitor is partitioned into a grid of cells. Further, a pool of candidate camera placements is formed, containing all combinations of camera models and mounting positions. For each camera in this pool, all cells monitored are deduced using ray-casting. Finally, an optimization model is formulated, based on the pool of candidate cameras and their monitoring of the grid. The optimization model has the two objectives of minimizing the cost while maximizing the number of covered cells. In the second part, a number of heuristic optimization algorithms to solve the problem is presented: Greedy Search, Random Greedy Search, Fear Search, Unique Search, Meta-RaPS and Weighted Linear Neighbourhood Search. The performance of these heuristics is evaluated on a couple of test cases from existing real world depots and a few artificial test instances. Evaluation is made by comparing the solution frontiers using various result metrics and graphs. Whenever practically possible, frontiers containing all optimal cost and coverage combinations are calculated using a state-of-the-art solver. Our findings indicate that for the artificial test instances, the state-of-the-art solver is unmatched in solution quality and uses similar execution time as the heuristics. Among the heuristics, Fear Search and Greedy Search were the strongest performing. For the smaller real world instances, the state-of-the-art solver was still unmatched in terms of solution quality, but generating the frontiers in this way was fairly time consuming. By generating the frontiers using Greedy Search or Random Greedy Search we obtained solutions of similar quality as the state-of-the-art solver up to 70-80% coverage using one hundredth and one tenth of the time, respectively. For the larger real world problem instances, generating the frontier using the state-of-the-art solver was extremely time consuming and thus sometimes impracticable. Hence the use of heuristics is often necessary. As for the smaller instances, Greedy Search and Random Greedy Search generated the frontiers with the best quality. Often even better full coverage solutions could be found by the more time consuming Fear Search or Unique Search. / Syftet med detta examensarbete är att modellera och lösa kameraplaceringsproblemet då IR-kameror ska användas för brandövervakning av fastbränslehögar. Problemet består i att givet ett antal kamera modeller och monteringsstolpar bestämma de kombinationer av placeringar och modeller sådana att övervakningen av högarna är maximal, för alla möjliga kostnadsnivåer. I den första delen av examensarbetet presenteras en modell för detta kameraplaceringsproblem. Modellen använder sig av en diskret formulering, där området om ska övervaras är representerad av ett rutnät. De möjliga kameravalen beskrivas med en diskret mängd av möjliga kameraplaceringar. För att utröna vilka celler inom rutnätet som en kameraplacering övervakar används metoden ray-casting. Utifrån mängden av möjliga kameraplaceringar kan en optimeringsmodell med två målfunktioner formuleras. Målet i den första målfunktionen är att minimera kostnaden för övervakningen och i den andra att maximera storleken på det övervakade området. Utgående från denna modell presenteras därefter ett antal algoritmer för att lösa modellen. Dessa är: Greedy Search, Random Greedy Search, Fear Search, Unique Search, Meta-RaPS och Weighted Linear Neighbourhood Search. Algoritmerna utvärderas på två konstgjorda testproblem och ett antal problem från verkliga fastbränslelager. Utvärderingen baseras på lösningsfronter (grafer över de icke-dominerade lösningarna med de bästa kombinationerna av kostnad och täckning) samt ett antal resultatmått som tid, lägsta kostnad för lösning med full täckning, etc... Vid utvärderingen av resultaten framkom att för de konstgjorda testinstanserna presterade ingen av heuristikerna jämförbart med en standardlösare, varken i termer av kvalitén på lösningarna eller med hänsyn tagen till tidsåtgången. De heuristiker som presterade bäst på dessa problem var framförallt Fear Search och Greedy Search. Även på de mindre probleminstanserna från existerande fastbränslelager hittade standardlösaren optimala lösningsfronter och en lösning med full täckning, men tidsåtgången var här flera gånger större jämfört med vissa av heuristikerna. På en hundra- respektive en tiondel av tiden kan Greedy Search eller Random Greedy Search heuristikerna finna en lösningsfront som är jämförbar med standardlösare, upp till 70-80% täckning. För de största probleminstanserna är tidsåtgången vid användning av standardlösare så pass stor att det i många fall är praktiskt svårt att lösa problemen, både för att generera fronten och att hitta en lösning med full täckning. I dessa fall är heuristiker oftast de enda möjliga alternativen. Vi fann att Greedy Search och Random Greedy Search var de heuristiker som, liksom för de mindre probleminstanserna, genererade de bästa lösningsfronterna. Ofta kunde dock en bättre lösning för full täckning hittas med hjälp av Fear Search eller Unique Search.

Context. Automatic placement of surveillance cameras&apos; 3D models in an arbitrary floor plan containing obstacles is a challenging task. The problem becomes more complex when different types of region of interest (RoI) and minimum resolution are considered. An automatic camera placement decision support system (ACP-DSS) integrated into a 3D CAD environment could assist the surveillance system designers with the process of finding good camera settings considering multiple constraints. Objectives. In this study we designed and implemented two subsystems: a camera toolset in SketchUp (CTSS) and a decision support system using an enhanced Particle Swarm Optimization (PSO) algorithm (HPSO-DSS). The objective for the proposed algorithm was to have a good computational performance in order to quickly generate a solution for the automatic camera placement (ACP) problem. The new algorithm benefited from different aspects of other heuristics such as hill-climbing and greedy algorithms as well as a number of new enhancements. Methods. Both CTSS and ACP-DSS were designed and constructed using the information technology (IT) research framework. A state-of-the-art evolutionary optimization method, Hybrid PSO (HPSO), implemented to solve the ACP problem, was the core of our decision support system. Results. The CTSS is evaluated by some of its potential users after employing it and later answering a conducted survey. The evaluation of CTSS confirmed an outstanding satisfactory level of the respondents. Various aspects of the HPSO algorithm were compared to two other algorithms (PSO and Genetic Algorithm), all implemented to solve our ACP problem. Conclusions. The HPSO algorithm provided an efficient mechanism to solve the ACP problem in a timely manner. The integration of ACP-DSS into CTSS might aid the surveillance designers to adequately and more easily plan and validate the design of their security systems. The quality of CTSS as well as the solutions offered by ACP-DSS were confirmed by a number of field experts. / Sarmad Rohani: 004670606805 Reza Shams: 0046704030897

No description available.