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.

Three-dimensional models which contain both geometry and texture have numerous applications such as urban planning, physical simulation, and virtual environments. A major focus of computer vision (and recently graphics) research is the automatic recovery of three-dimensional models from two-dimensional images. After many years of research this goal is yet to be achieved. Most practical modeling systems require substantial human input and unlike automatic systems are not scalable. This thesis presents a novel method for automatically recovering dense surface patches using large sets (1000's) of calibrated images taken from arbitrary positions within the scene. Physical instruments, such as Global Positioning System (GPS), inertial sensors, and inclinometers, are used to estimate the position and orientation of each image. Essentially, the problem is to find corresponding points in each of the images. Once a correspondence has been established, calculating its three-dimensional position is simply a matter of geometry. Long baseline images improve the accuracy. Short baseline images and the large number of images greatly simplifies the correspondence problem. The initial stage of the algorithm is completely local and scales linearly with the number of images. Subsequent stages are global in nature, exploit geometric constraints, and scale quadratically with the complexity of the underlying scene. We describe techniques for: 1) detecting and localizing surface patches; 2) refining camera calibration estimates and rejecting false positive surfels; and 3) grouping surface patches into surfaces and growing the surface along a two-dimensional manifold. We also discuss a method for producing high quality, textured three-dimensional models from these surfaces. Some of the most important characteristics of this approach are that it: 1) uses and refines noisy calibration estimates; 2) compensates for large variations in illumination; 3) tolerates significant soft occlusion (e.g. tree branches); and 4) associates, at a fundamental level, an estimated normal (i.e. no frontal-planar assumption) and texture with each surface patch.

Object appearance models are a consequence of illumination, viewing direction, camera intrinsics, and other conditions that are specific to a particular camera. As a result, a model acquired in one view is often inappropriate for use in other viewpoints. In this work we treat this appearance model distortion between two non-overlapping cameras as one in which some unknown color transfer function warps a known appearance model from one view to another. We demonstrate how to recover this function in the case where the distortion function is approximated as general affine and object appearance is represented as a mixture of Gaussians. Appearance models are brought into correspondence by searching for a bijection function that best minimizes an entropic metric for model dissimilarity. These correspondences lead to a solution for the transfer function that brings the parameters of the models into alignment in the UV chromaticity plane. Finally, a set of these transfer functions acquired from a collection of object pairs are generalized to a single camera-pair-specific transfer function via robust fitting. We demonstrate the method in the context of a video surveillance network and show that recognition of subjects in disjoint views can be significantly improved using the new color transfer approach.

No description available.

"Patient motion, which causes artifacts in reconstructed images, can be a serious problem in Single Photon Emission Computed Tomography (SPECT) imaging. If patient motion can be detected and quantified, the reconstruction algorithm can compensate for the motion. A real-time multi-threaded Visual Tracking System (VTS) using optical cameras, which will be suitable for deployment in clinical trials, is under development. The VTS tracks patients using multiple video images and image processing techniques, calculating patient motion in three-dimensional space. This research aimed to develop and implement an algorithm for feature matching and stereo location computation using multiple cameras. Feature matching is done based on the epipolar geometry constraints for a pair of images and extended to the multiple view case with an iterative algorithm. Stereo locations of the matches are then computed using sum of squared distances from the projected 3D lines in SPECT coordinates as the error metric. This information from the VTS, when coupled with motion assessment from the emission data itself, can provide a robust compensation for patient motion as part of reconstruction."

This research concerns the development of a smart sensory system for tracking a hand-held moving device to millimeter accuracy, for slow or nearly static applications over extended periods of time. Since different operators in different applications may use the system, the proposed design should provide the accurate position, orientation, and velocity of the object without relying on the knowledge of its operation and environment, and based purely on the motion that the object experiences. This thesis proposes the design of the integration a low-cost Local Positioning System (LPS) and a low-cost StrapDown Inertial Navigation System (SDINS) with the association of the modified EKF to determine 3D position and 3D orientation of a hand-held tool within a required accuracy. A hybrid LPS/SDINS combines and complements the best features of two different navigation systems, providing a unique solution to track and localize a moving object more precisely. SDINS provides continuous estimates of all components of a motion, but SDINS loses its accuracy over time because of inertial sensors drift and inherent noise. LPS has the advantage that it can possibly get absolute position and velocity independent of operation time; however, it is not highly robust, is computationally quite expensive, and exhibits low measurement rate. This research consists of three major parts: developing a multi-camera vision system as a reliable and cost-effective LPS, developing a SDINS for a hand-held tool, and developing a Kalman filter for sensor fusion. Developing the multi-camera vision system includes mounting the cameras around the workspace, calibrating the cameras, capturing images, applying image processing algorithms and features extraction for every single frame from each camera, and estimating the 3D position from 2D images. In this research, the specific configuration for setting up the multi-camera vision system is proposed to reduce the loss of line of sight as much as possible. The number of cameras, the position of the cameras with respect to each other, and the position and the orientation of the cameras with respect to the center of the world coordinate system are the crucial characteristics in this configuration. The proposed multi-camera vision system is implemented by employing four CCD cameras which are fixed in the navigation frame and their lenses placed on semicircle. All cameras are connected to a PC through the frame grabber, which includes four parallel video channels and is able to capture images from four cameras simultaneously. As a result of this arrangement, a wide circular field of view is initiated with less loss of line-of-sight. However, the calibration is more difficult than a monocular or stereo vision system. The calibration of the multi-camera vision system includes the precise camera modeling, single camera calibration for each camera, stereo camera calibration for each two neighboring cameras, defining a unique world coordinate system, and finding the transformation from each camera frame to the world coordinate system. Aside from the calibration procedure, digital image processing is required to be applied into the images captured by all four cameras in order to localize the tool tip. In this research, the digital image processing includes image enhancement, edge detection, boundary detection, and morphologic operations. After detecting the tool tip in each image captured by each camera, triangulation procedure and optimization algorithm are applied in order to find its 3D position with respect to the known navigation frame. In the SDINS, inertial sensors are mounted rigidly and directly to the body of the tracking object and the inertial measurements are transformed computationally to the known navigation frame. Usually, three gyros and three accelerometers, or a three-axis gyro and a three-axis accelerometer are used for implementing SDINS. The inertial sensors are typically integrated in an inertial measurement unit (IMU). IMUs commonly suffer from bias drift, scale-factor error owing to non-linearity and temperature changes, and misalignment as a result of minor manufacturing defects. Since all these errors lead to SDINS drift in position and orientation, a precise calibration procedure is required to compensate for these errors. The precision of the SDINS depends not only on the accuracy of calibration parameters but also on the common motion-dependent errors. The common motion-dependent errors refer to the errors caused by vibration, coning motion, sculling, and rotational motion. Since inertial sensors provide the full range of heading changes, turn rates, and applied forces that the object is experiencing along its movement, accurate 3D kinematics equations are developed to compensate for the common motion-dependent errors. Therefore, finding the complete knowledge of the motion and orientation of the tool tip requires significant computational complexity and challenges relating to resolution of specific forces, attitude computation, gravity compensation, and corrections for common motion-dependent errors. The Kalman filter technique is a powerful method for improving the output estimation and reducing the effect of the sensor drift. In this research, the modified EKF is proposed to reduce the error of position estimation. The proposed multi-camera vision system data with cooperation of the modified EKF assists the SDINS to deal with the drift problem. This configuration guarantees the real-time position and orientation tracking of the instrument. As a result of the proposed Kalman filter, the effect of the gravitational force in the state-space model will be removed and the error which results from inaccurate gravitational force is eliminated. In addition, the resulting position is smooth and ripple-free. The experimental results of the hybrid vision/SDINS design show that the position error of the tool tip in all directions is about one millimeter RMS. If the sampling rate of the vision system decreases from 20 fps to 5 fps, the errors are still acceptable for many applications.

This research concerns the development of a smart sensory system for tracking a hand-held moving device to millimeter accuracy, for slow or nearly static applications over extended periods of time. Since different operators in different applications may use the system, the proposed design should provide the accurate position, orientation, and velocity of the object without relying on the knowledge of its operation and environment, and based purely on the motion that the object experiences. This thesis proposes the design of the integration a low-cost Local Positioning System (LPS) and a low-cost StrapDown Inertial Navigation System (SDINS) with the association of the modified EKF to determine 3D position and 3D orientation of a hand-held tool within a required accuracy. A hybrid LPS/SDINS combines and complements the best features of two different navigation systems, providing a unique solution to track and localize a moving object more precisely. SDINS provides continuous estimates of all components of a motion, but SDINS loses its accuracy over time because of inertial sensors drift and inherent noise. LPS has the advantage that it can possibly get absolute position and velocity independent of operation time; however, it is not highly robust, is computationally quite expensive, and exhibits low measurement rate. This research consists of three major parts: developing a multi-camera vision system as a reliable and cost-effective LPS, developing a SDINS for a hand-held tool, and developing a Kalman filter for sensor fusion. Developing the multi-camera vision system includes mounting the cameras around the workspace, calibrating the cameras, capturing images, applying image processing algorithms and features extraction for every single frame from each camera, and estimating the 3D position from 2D images. In this research, the specific configuration for setting up the multi-camera vision system is proposed to reduce the loss of line of sight as much as possible. The number of cameras, the position of the cameras with respect to each other, and the position and the orientation of the cameras with respect to the center of the world coordinate system are the crucial characteristics in this configuration. The proposed multi-camera vision system is implemented by employing four CCD cameras which are fixed in the navigation frame and their lenses placed on semicircle. All cameras are connected to a PC through the frame grabber, which includes four parallel video channels and is able to capture images from four cameras simultaneously. As a result of this arrangement, a wide circular field of view is initiated with less loss of line-of-sight. However, the calibration is more difficult than a monocular or stereo vision system. The calibration of the multi-camera vision system includes the precise camera modeling, single camera calibration for each camera, stereo camera calibration for each two neighboring cameras, defining a unique world coordinate system, and finding the transformation from each camera frame to the world coordinate system. Aside from the calibration procedure, digital image processing is required to be applied into the images captured by all four cameras in order to localize the tool tip. In this research, the digital image processing includes image enhancement, edge detection, boundary detection, and morphologic operations. After detecting the tool tip in each image captured by each camera, triangulation procedure and optimization algorithm are applied in order to find its 3D position with respect to the known navigation frame. In the SDINS, inertial sensors are mounted rigidly and directly to the body of the tracking object and the inertial measurements are transformed computationally to the known navigation frame. Usually, three gyros and three accelerometers, or a three-axis gyro and a three-axis accelerometer are used for implementing SDINS. The inertial sensors are typically integrated in an inertial measurement unit (IMU). IMUs commonly suffer from bias drift, scale-factor error owing to non-linearity and temperature changes, and misalignment as a result of minor manufacturing defects. Since all these errors lead to SDINS drift in position and orientation, a precise calibration procedure is required to compensate for these errors. The precision of the SDINS depends not only on the accuracy of calibration parameters but also on the common motion-dependent errors. The common motion-dependent errors refer to the errors caused by vibration, coning motion, sculling, and rotational motion. Since inertial sensors provide the full range of heading changes, turn rates, and applied forces that the object is experiencing along its movement, accurate 3D kinematics equations are developed to compensate for the common motion-dependent errors. Therefore, finding the complete knowledge of the motion and orientation of the tool tip requires significant computational complexity and challenges relating to resolution of specific forces, attitude computation, gravity compensation, and corrections for common motion-dependent errors. The Kalman filter technique is a powerful method for improving the output estimation and reducing the effect of the sensor drift. In this research, the modified EKF is proposed to reduce the error of position estimation. The proposed multi-camera vision system data with cooperation of the modified EKF assists the SDINS to deal with the drift problem. This configuration guarantees the real-time position and orientation tracking of the instrument. As a result of the proposed Kalman filter, the effect of the gravitational force in the state-space model will be removed and the error which results from inaccurate gravitational force is eliminated. In addition, the resulting position is smooth and ripple-free. The experimental results of the hybrid vision/SDINS design show that the position error of the tool tip in all directions is about one millimeter RMS. If the sampling rate of the vision system decreases from 20 fps to 5 fps, the errors are still acceptable for many applications.

Background: Video surveillance is a growing area where it can help with deterring crime, support investigation or to help gather statistics. These are just some areas where video surveillance can aid society. However, there is an improvement that could increase the efficiency of video surveillance by introducing tracking. More specifically, tracking between cameras in a network. Automating this process could reduce the need for humans to monitor and review since the tracking can track and inform the relevant people on its own. This has a wide array of usability areas, such as forensic investigation, crime alerting, or tracking down people who have disappeared. Objectives: What we want to investigate is the common setup of real-time multi-target multi-camera tracking (MTMCT) systems. Next up, we want to investigate how the components in an MTMCT system affect each other and the complete system. Lastly, we want to see how image enhancement can affect the MTMCT. Methods: To achieve our objectives, we have conducted a systematic literature review to gather information. Using the information, we implemented an MTMCT system where we evaluated the components to see how they interact in the complete system. Lastly, we implemented two image enhancement techniques to see how they affect the MTMCT. Results: As we have discovered, most often, MTMCT is constructed using a detection for discovering object, tracking to keep track of the objects in a single camera and a re-identification method to ensure that objects across cameras have the same ID. The different components have quite a considerable effect on each other where they can sabotage and improve each other. An example could be that the quality of the bounding boxes affect the data which re-identification can extract. We discovered that the image enhancement we used did not introduce any significant improvement. Conclusions: The most common structure for MTMCT are detection, tracking and re-identification. From our finding, we can see that all the component affect each other, but re-identification is the one that is mostly affected by the other components and the image enhancement. The two tested image enhancement techniques could not introduce enough improvement, but other image enhancement could be used to make the MTMCT perform better. The MTMCT system we constructed did not manage to reach real-time.

Les caméras sphériques et 360 deviennent populaires et sont utilisées notamment pour la création de vidéos immersives et la génération de contenu pour la réalité virtuelle. Elles sont souvent composées de plusieurs caméras grand-angles/fisheyes pointant dans différentes directions et rigidement liées les unes aux autres. Cependant, il n'est pas si simple de les calibrer complètement car ces caméras grand public sont rolling shutter et peuvent être mal synchronisées. Cette thèse propose des méthodes permettant de calibrer ces multi-caméras à partir de vidéos sans utiliser de mire de calibration. On initialise d'abord un modèle de multi-caméra grâce à des hypothèses appropriées à un capteur omnidirectionnel sans direction privilégiée : les caméras ont les mêmes réglages (dont la fréquence et l'angle de champs de vue) et sont approximativement équiangulaires. Deuxièmement, sachant que le module de la vitesse angulaire est le même pour deux caméras au même instant, nous proposons de synchroniser les caméras à une image près à partir des vitesses angulaires estimées par structure-from-motion monoculaire. Troisièmement, les poses inter-caméras et les paramètres intrinsèques sont estimés par structure-from-motion et ajustement de faisceaux multi-caméras avec les approximations suivantes : la multi-caméra est centrale, global shutter ; et la synchronisation précédant est imposée.Enfin, nous proposons un ajustement de faisceaux final sans ces approximations, qui raffine notamment la synchronisation (à précision sous-trame), le coefficient de rolling shutter et les autres paramètres (intrinsèques, extrinsèques, 3D). On expérimente dans un contexte que nous pensons utile pour des applications comme les vidéos 360 et la modélisation 3D de scènes : plusieurs caméras grand public ou une caméra sphérique fixée(s) sur un casque et se déplaçant le long d'une trajectoire de quelques centaines de mètres à quelques kilomètres. / 360 degree and spherical multi-cameras built by fixing together several consumer cameras become popular and are convenient for recent applications like immersive videos, 3D modeling and virtual reality. This type of cameras allows to include the whole scene in a single view.When the goal of our applications is to merge monocular videos together into one cylinder video or to obtain 3D informations from environment,there are several basic steps that should be performed beforehand.Among these tasks, we consider the synchronization between cameras; the calibration of multi-camera system including intrinsic and extrinsic parameters (i.e. the relative poses between cameras); and the rolling shutter calibration. The goal of this thesis is to develop and apply user friendly method. Our approach does not require a calibration pattern. First, the multi-camera is initialized thanks to assumptions that are suitable to an omnidirectional camera without a privileged direction:the cameras have the same setting (frequency, image resolution, field-of-view) and are roughly equiangular.Second, a frame-accurate synchronization is estimated from instantaneous angular velocities of each camera provided by monocular Structure-from-Motion.Third, both inter-camera poses and intrinsic parameters are refined using multi-camera Structure-from-Motion and bundle adjustment.Last, we introduce a bundle adjustment that estimates not only the usual parameters but also a subframe-accurate synchronization and the rolling shutter. We experiment in a context that we believe useful for applications (3D modeling and 360 videos):several consumer cameras or a spherical camera mounted on a helmet and moving along trajectories of several hundreds of meters or kilometers.

This thesis describes a conceptual design of touchless fingerprint sensor and design, implementation and testing of its firmware, which is a composition of hardware implemented in VHDL and a program implemented in C. Result of this thesis can be used as the first step of building an industrial solution.