This dissertation focuses on real-time decision-making for large-scale domain search and object classification using Multiple Autonomous Vehicles (MAV). In recent years, MAV systems have attracted considerable attention and have been widely utilized. Of particular interest is their application to search and classification under limited sensory capabilities. Since search requires sensor mobility and classification requires a sensor to stay within the vicinity of an object, search and classification are two competing tasks. Therefore, there is a need to develop real-time sensor allocation decision-making strategies to guarantee task accomplishment. These decisions are especially crucial when the domain is much larger than the field-of-view of a sensor, or when the number of objects to be found and classified is much larger than that of available sensors. In this work, the search problem is formulated as a coverage control problem, which aims at collecting enough data at every point within the domain to construct an awareness map. The object classification problem seeks to satisfactorily categorize the property of each found object of interest. The decision-making strategies include both sensor allocation decisions and vehicle motion control. The awareness-, Bayesian-, and risk-based decision-making strategies are developed in sequence. The awareness-based approach is developed under a deterministic framework, while the latter two are developed under a probabilistic framework where uncertainty in sensor measurement is taken into account. The risk-based decision-making strategy also analyzes the effect of measurement cost. It is further extended to an integrated detection and estimation problem with applications in optimal sensor management. Simulation-based studies are performed to confirm the effectiveness of the proposed algorithms.

Knowing the shape and pose of objects of interest is critical information when planning robotic grasping and manipulation maneuvers. The ability to recover this information from objects for which the system has no prior knowledge is a valuable behavior for an autonomous or semiautonomous robot. This work develops and presents an algorithm for the shape and pose recovery of unknown objects using no a priori information. Using a monocular camera in an eye-in-hand configuration, three images of the object of interest are captured from three disparate viewing directions. Machine vision techniques are employed to process these images into silhouettes. The silhouettes are used to generate an approximation of the surface of the object in the form of a three dimensional point cloud. The accuracy of this approximation is improved by fitting an eleven parameter geometric shape to the points such that the fitted shape ignores disturbances from noise and perspective projection effects. The parametrized shape represents the model of the unknown object and can be utilized for planning robot grasping maneuvers or other object classification tasks. This work is implemented and tested in simulation and hardware. A simulator is developed to test the algorithm for various three dimensional shapes and any possible imaging positions. Several shapes and viewing configurations are tested and the accuracy of the recoveries are reported and analyzed. After thorough testing of the algorithm in simulation, it is implemented on a six axis industrial manipulator and tested on a range of real world objects: both geometric and amorphous. It is shown that the accuracy of the hardware implementation performs exceedingly well and approaches the accuracy of the simulator, despite the additional sources of error and uncertainty present.

No description available.

Η παρούσα διπλωματική εργασία αφορά την ανίχνευση και παρακολούθηση ανθρώπινων μορφών σε ακολουθίες βίντεο με μεθόδους μηχανικής όρασης. Οι ακολουθίες αυτές θεωρούμε πως έχουν ληφθεί από στατική κάμερα σε εσωτερικό ή εξωτερικό χώρο. Πιο συγκεκριμένα, το εν λόγω πρόβλημα υποδιαιρείται σε τρία κυρίως μέρη τα οποία μελετώνται, αναλύονται και υλοποιούνται σε ξεχωριστά κεφάλαια. Ξεκινάμε με το κομμάτι κατάτμησης κίνησης, συνεχίζουμε με την ταξινόμηση αντικειμένων ώστε να αναγνωριστούν οι άνθρωποι ανάμεσα στις κινούμενες οντότητες και τελειώνουμε με την παρακολούθηση των ανθρώπινων σιλουετών για καταγραφή της πορείας τους όση ώρα βρίσκονται στο πλάνο. Οι αλγόριθμοι που αναπτύχθηκαν λειτούργησαν ικανοποιητικά κάτω από διάφορες συνθήκες και τα αποτελέσματά τους μπορούν να περάσουν ως είσοδοι σε μια πληθώρα εφαρμογών υψηλότερου επιπέδου με σκοπό την αναγνώριση ανθρώπινης δραστηριότητας και την κατανόηση συμπεριφοράς. / The purpose of this thesis is to deal with the problem of human tracking in video sequences. We have divided the problem in three parts: motion segmentation, human tracking and object classification. Finally we have dedicate a whole chapter to optical flow techniques and the relevant methods that can be employed to solve the same problem.

<pre>Because of the increasing population of space objects, there is an increasing necessity to monitor and predict the status of the near-Earth space environment, especially of critical regions like geosynchronous Earth orbit (GEO) and low Earth orbit (LEO) regions, for a sustainable future. Space Situational Awareness (SSA), however, is a challenging task because of the requirement for dynamically insightful fast orbit propagation models, presence of dynamical uncertainties, and limitations in sensor resources. Since initial parameters are often not known exactly and since many SSA applications require long-term orbit propagation, long-term effects of the initial uncertainties on orbital evolution are examined in this work. To get a long-term perspective in a fast and efficient manner, this work uses analytical propagation techniques. Existing analytical theories for orbital perturbations are investigated, and modifications are made to them to improve accuracy. While conservative perturbation forces are often studied, of particular interest here is the orbital perturbation due to non-conservative forces. Using the previous findings and the developments in this thesis, two SSA applications are investigated in this work. In the first SSA application, a sensor tasking algorithm is designed for the detection of new classes of GEO space objects. In the second application, the categorization of near-GEO objects is carried out by combining knowledge of orbit dynamics with machine learning techniques.</pre>

No description available.

Vision identifies objects rapidly and efficiently. In contrast, object recognition by touch is much slower. Furthermore, haptics usually serially accumulates information from different parts of objects, whereas vision typically processes object information in parallel. Is haptic object identification slower simply due to sequential information acquisition and the resulting memory load or due to more fundamental processing differences between the senses? To compare the time course of visual and haptic object recognition, we slowed visual processing using a novel, restricted viewing technique. In an electroencephalographic (EEG) experiment, participants discriminated familiar, nameable from unfamiliar, unnamable objects both visually and haptically. Analyses focused on the evoked and total fronto-central theta-band (5–7 Hz; a marker of working memory) and the occipital upper alpha-band (10–12 Hz; a marker of perceptual processing) locked to the onset of classification. Decreases in total upper alpha-band activity for haptic identification of objects indicate a likely processing role of multisensory extrastriate areas. Long-latency modulations of alpha-band activity differentiated between familiar and unfamiliar objects in haptics but not in vision. In contrast, theta-band activity showed a general increase over time for the slowed-down visual recognition task only. We conclude that haptic object recognition relies on common representations with vision but also that there are fundamental differences between the senses that do not merely arise from differences in their speed of processing.

With the introduction of Wireless Multimedia Sensor Networks, large-scale remote outdoor surveillance applications where the majority of the cameras will be battery-operated are envisioned. These are the applications where the frequency of incidents is too low to employ permanent staffing such as monitoring of land and marine border, critical infrastructures, bridges, water supplies, etc. Given the inexpensive costs of wireless resource constrained camera sensors, the size of these networks will be significantly larger than the traditional multi-camera systems. While large number of cameras may increase the coverage of the network, such a large size along with resource constraints poses new challenges, e.g., localization, classification, tracking or reactive behavior. This dissertation proposes a framework that transforms current multi-camera networks into low-cost and reactive systems which can be used in large-scale remote surveillance applications. Specifically, a remote surveillance system framework with three components is proposed: 1) Localization and tracking of objects / 2) Classification and identification of objects / and 3) Reactive behavior at the base-station. For each component, novel lightweight, storage-efficient and real-time algorithms both at the computation and communication level are designed, implemented and tested under a variety of conditions. The results have indicated the feasibility of this framework working with limited energy but having high object localization/classification accuracies. The results of this research will facilitate the design and development of very large-scale remote border surveillance systems and improve the systems effectiveness in dealing with the intrusions with reduced human involvement and labor costs.

The main objective of this dissertation is to apply Bayesian modeling to different complex and high-dimensional spatial data sets. I develop Bayesian hierarchical spatial models for both the observed location and the observation variable. Throughout this dissertation I execute the inference of the posterior distributions using Markov chain Monte Carlo by developing computational strategies that can reduce the computational cost. I start with a "high level" image analysis by modeling the pixels with a Gaussian process and the objects with a marked-point process. The proposed method is an automatic image segmentation and classification procedure which simultaneously detects the boundaries and classifies the objects in the image into one of the predetermined shape families. Next, I move my attention to the piecewise non-stationary Gaussian process models and their computational challenges for very large data sets. I simultaneously model the non-stationarity and reduce the computational cost by using the innovative technique of full-scale approximation. I successfully demonstrate the proposed reduction technique to the Total Ozone Matrix Spectrometer (TOMS) data. Furthermore, I extend the reduction method for the non-stationary Gaussian process models to a dynamic partition of the space by using a modified Treed Gaussian Model. This modification is based on the use of a non-stationary function and the full-scale approximation. The proposed model can deal with piecewise non-stationary geostatistical data with unknown partitions. Finally, I apply the method to the TOMS data to explore the non-stationary nature of the data.

The main purpose of thesis is creation and evaluation of models for change detection of arable land to grassland by Hybrid-based Change Detection method, which combined approaches based on the Vegetation Indices, Image Differencing and Principal Component Analysis. Six locations with different seasonal configuration of images with high resolution and one locality covered by image with very high resolution were used. The areas were spread across the foothill areas of the Czech Republic. The selection of predictors and the most suitable model was supported by statistical calculation. Application selected models were carried out using a multi-temporal object classification and their accuracy were verified using reference data. The benefit of this thesis is finding generally applicable model useful to investigate the land cover change and evaluation of the potentially most appropriate seasonal configuration of images. Valuable is also methodology in this thesis which focus on selection of predictors and calculation the order of the most appropriate models, which is unique in the available literature. The thesis provides useful findings fitting to insufficiently explored issue of Change Detection arable land to grassland. Powered by TCPDF (www.tcpdf.org)