No description available.

No description available.

Active docking in modular robotic systems has received a lot of interest recently as it allows small versatile robotic systems to coalesce and achieve the structural benefits of larger robotic systems. This feature enables reconfigurable modular robotic systems to bridge the gap between small agile systems and larger robotic systems. The proposed self-reconfigurable mobile robot design exhibits dual mobility using a tracked drive for longitudinal locomotion and wheeled drive for lateral locomotion. The two degrees of freedom (DOF) docking interface referred to as GHEFT (Genderless, High strength, Efficient, Fail-Safe, high misalignment Tolerant) allows for an efficient docking while tolerating misalignments in 6-DOF. In addition, motion along the vertical axis is also achieved via an additional translational DOF, allowing for toggling between tracked and wheeled locomotion modes by lowering and raising the wheeled assembly. This thesis also presents a visual-based onboard Hybrid Target Tracking algorithm to detect and follow a target robot leading to autonomous docking between the modules. As a result of this proposed approach, the tracked features are then used to bring the robots in sufficient proximity for the docking procedure using Image Based Visual Servoing (IBVS) control. Experimental results to validate the robustness of the proposed tracking method, as well as the reliability of the autonomous docking procedure, are also presented in this thesis. / Master of Science / Active docking in modular robotic systems has received a lot of interest recently as it allows small versatile robotic systems to coalesce and achieve the structural benefits of larger robotic systems. This feature enables reconfigurable modular robotic systems to bridge the gap between small agile systems and larger robotic systems. Such robots can prove useful in environments that are either too dangerous or inaccessible to humans. Therefore, in this research, several specific hardware and software development aspects related to self-reconfigurable mobile robots are proposed. In terms of hardware development, a robotic module was designed that is symmetrically invertible and exhibits dual mobility using a tracked drive for longitudinal locomotion and wheeled drive for lateral locomotion. Such interchangeable mobility is important when the robot operates in a constrained workspace. The mobile robot also has integrated two degrees of freedom (DOF) docking mechanisms referred to as GHEFT (Genderless, High strength, Efficient, Fail-Safe, high misalignment Tolerant). The docking interface allows for an efficient docking while tolerating misalignments in 6-DOF. In addition, motion along the vertical axis is also performed via an additional translational DOF, allowing for lowering and raising the wheeled assembly. The robot is equipped with sensors to provide positional feedback of the joints relative to the target robot. In terms of software development, a visual-based onboard Hybrid Target Tracking algorithm for high-speed consistent tracking iv of colored targets is also presented in this work. The proposed technique is used to detect and follow a colored target attached to the target robot leading to autonomous docking between the modules using Image Based Visual Servoing (IBVS). Experimental results to validate the robustness of the proposed tracking approach, as well as the reliability of the autonomous docking procedure, are also presented in the thesis. The thesis is concluded with discussions about future research in both structured and unstructured terrains.

Object counting is a process of determining the quantity of specific objects in images. Accurate object counting is key for various applications in image understanding. The common applications are traffic monitoring, crowd management, wildlife migration monitoring, cell counting in medical images, plant and insect counting in agriculture, etc. Occlusions, complex backgrounds, changes in scale, and variations in object appearance in real-world settings make object counting challenging. This dissertation explores a progression of techniques to achieve robust localization and counting under diverse image modalities. The exploration initiates with addressing the challenges of vehicular target localization in cluttered environments using infrared (IR) imagery. We propose a network, called TCRNet-2, that processes target and clutter information in two parallel channels and then combines them to optimize the target-to-clutter ratio (TCR) metric. Next, we explore class-agnostic object counting in RGB images using vision transformers. The primary motivation for this work is that most current methods excel at counting known object types but struggle with unseen categories. To solve these drawbacks, we propose a class-agnostic object counting method. We introduce a dual-branch architecture with interconnected cross-attention that generates feature pyramids for robust object representations, and a dedicated feature aggregator module that further improves performance. Finally, we propose a novel framework that leverages vision-language models (VLM) for zero-shot object counting. While our earlier class-agnostic counting method demonstrates high efficacy in generalized counting tasks, it relies on user-defined exemplars of target objects, presenting a limitation. Additionally, the previous zero-shot counting method was a reference-less approach, which limits the ability to control the selection of the target object of interest in multi-class scenarios. To address these shortcomings, we propose to utilize vision-language models for zero-shot counting where object categories of interest can be specified by text prompts.

L'imagerie hyperspectrale (HSI) repose sur le fait que, pour un matériau donné, la quantité de rayonnement émis varie avec la longueur d'onde. Les capteurs HSI mesurent donc le rayonnement des matériaux au sein de chaque pixel pour un très grand nombre de bandes spectrales contiguës et fournissent des images contenant des informations à la fois spatiale et spectrale. Les méthodes classiques de détection adaptative supposent généralement que le fond est gaussien à vecteur moyenne nul ou connu. Cependant, quand le vecteur moyen est inconnu, comme c'est le cas pour l'image hyperspectrale, il doit être inclus dans le processus de détection. Nous proposons dans ce travail d'étendre les méthodes classiques de détection pour lesquelles la matrice de covariance et le vecteur de moyenne sont tous deux inconnus.Cependant, la distribution statistique multivariée des pixels de l'environnement peut s'éloigner de l'hypothèse gaussienne classiquement utilisée. La classe des distributions elliptiques a été déjà popularisée pour la caractérisation de fond pour l’HSI. Bien que ces modèles non gaussiens aient déjà été exploités dans la modélisation du fond et dans la conception de détecteurs, l'estimation des paramètres (matrice de covariance, vecteur moyenne) est encore généralement effectuée en utilisant des estimateurs conventionnels gaussiens. Dans ce contexte, nous analysons de méthodes d’estimation robuste plus appropriées à ces distributions non-gaussiennes : les M-estimateurs. Ces méthodes de détection couplées à ces nouveaux estimateurs permettent d'une part, d'améliorer les performances de détection dans un environment non-gaussien mais d'autre part de garder les mêmes performances que celles des détecteurs conventionnels dans un environnement gaussien. Elles fournissent ainsi un cadre unifié pour la détection de cibles et la détection d'anomalies pour la HSI. / Hyperspectral imaging (HSI) extends from the fact that for any given material, the amount of emitted radiation varies with wavelength. HSI sensors measure the radiance of the materials within each pixel area at a very large number of contiguous spectral bands and provide image data containing both spatial and spectral information. Classical adaptive detection schemes assume that the background is zero-mean Gaussian or with known mean vector that can be exploited. However, when the mean vector is unknown, as it is the case for hyperspectral imaging, it has to be included in the detection process. We propose in this work an extension of classical detection methods when both covariance matrix and mean vector are unknown.However, the actual multivariate distribution of the background pixels may differ from the generally used Gaussian hypothesis. The class of elliptical distributions has already been popularized for background characterization in HSI. Although these non-Gaussian models have been exploited for background modeling and detection schemes, the parameters estimation (covariance matrix, mean vector) is usually performed using classical Gaussian-based estimators. We analyze here some robust estimation procedures (M-estimators of location and scale) more suitable when non-Gaussian distributions are assumed. Jointly used with M-estimators, these new detectors allow to enhance the target detection performance in non-Gaussian environment while keeping the same performance than the classical detectors in Gaussian environment. Therefore, they provide a unified framework for target detection and anomaly detection in HSI.

<p>This dissertation presents methods and associated performance bounds for spectral image processing tasks such as reconstruction and target detection, which are useful in a variety of applications such as astronomical imaging, biomedical imaging and remote sensing. The key idea behind our spectral image processing methods is the fact that important information in a spectral image can often be captured by low-dimensional manifolds embedded in high-dimensional spectral data. Based on this key idea, our work focuses on the reconstruction of spectral images from <italic>photon-limited</italic>, and distorted observations. </p><p>This dissertation presents a partition-based, maximum penalized likelihood method that recovers spectral images from noisy observations and enjoys several useful properties; namely, it (a) adapts to spatial and spectral smoothness of the underlying spectral image, (b) is computationally efficient, (c) is near-minimax optimal over an <italic>anisotropic</italic> Holder-Besov function class, and (d) can be extended to inverse problem frameworks.</p><p>There are many applications where accurate localization of desired targets in a spectral image is more crucial than a complete reconstruction. Our work draws its inspiration from classical detection theory and compressed sensing to develop computationally efficient methods to detect targets from few projection measurements of each spectrum in the spectral image. Assuming the availability of a spectral dictionary of possible targets, the methods discussed in this work detect targets that either come from the spectral dictionary or otherwise. The theoretical performance bounds offer insight on the performance of our detectors as a function of the number of measurements, signal-to-noise ratio, background contamination and properties of the spectral dictionary. </p><p>A related problem is that of level set estimation where the goal is to detect the regions in an image where the underlying intensity function exceeds a threshold. This dissertation studies the problem of accurately extracting the level set of a function from indirect projection measurements without reconstructing the underlying function. Our partition-based set estimation method extracts the level set of proxy observations constructed from such projection measurements. The theoretical analysis presented in this work illustrates how the projection matrix, proxy construction and signal strength of the underlying function affect the estimation performance.</p> / Dissertation

Ground based radars often experience difficulties in target detection and direction finding (DF) applications due to the interference between the direct and surface reflected signals when the targets fly at low altitudes. In this thesis, the phenomena governing the low angle propagation are overviewed and a multipath signal model including the effects of refraction, specular reflection, diffuse reflection, curvature of the earth and antenna polarization is presented. Then, the model is utilized to develop detection and DF algorithms for the targets at low altitudes. The target detection algorithm aims to increase signal-to-noise ratio (SNR) to overcome the effects of signal fading caused by surface reflections. The algorithm is based on diversity combining and the combining weight vector is calculated by maximizing average value of SNR. The technique is compared with Maximum Ratio Combining (MRC) algorithm which is optimal in terms of SNR. In direction finding, it is the height of the target that is explored since the target range information is obtained from the time delay. The target height is estimated by utilizing Maximum Likelihood Estimation (MLE). The performance of our algorithm is compared with that of the technique that is known in the literature as Refined Maximum Likelihood (RML).

Automatic object detection is a challenging field which has been evolving over decades. The application areas span many domains such as robotics inspection, medical imaging, military targeting, and reconnaissance. Some of the most concentrated efforts in automatic object detection have been in the military domain, where most of the problems deal with automatic target detection and scene analysis in the outdoors using a variety of sensors. One of the critical problems in Automatic Target Detection (ATD) systems is multiscenario adaptation. Most of the ATD systems developed until today perform unpredictably i.e. perform well in certain scenarios, and poorly in others. Unless ATD systems can be made adaptable, their utility in battlefield missions remains questionable. This thesis describes a methodology that adapts parameterized ATD systems with image metrics as the scenario changes so that ATD system can maintain better performance. The methodology uses experimentally obtained performance models, which are functions of image metrics and system parameters, to optimize performance measures of the ATD system. Optimization is achieved by adapting system parameters with incoming image metrics based on performance models as the system works in field. A simple ATD system is also proposed in this work to describe and test the methodology.

Continuous Wave (CW) radars are preferred for their low probability of intercept by the other receivers. Frequency modulation techniques, the linear frequency modulation (LFM) technique in particular, are commonly used in CW radars to resolve the range and the radial velocity of the detected targets. The conventional method for target detection in a linear FMCW radar makes use of a mixer followed by a low-pass filter whose output is Fourier transformed to get the range and velocity information. In this thesis, an alternative target detection technique based on the use of the Ambiguity Function (AF) will be investigated in frequency modulated CW radars. Results of the AF-based technique and the conventional Fourier-based technique will be compared for different target detection scenarios.

Submitted by Almir Azevedo (barbio1313@gmail.com) on 2015-08-24T17:42:07Z No. of bitstreams: 1 CARLOS ALEXANDRE F. JORGE D.pdf: 11356748 bytes, checksum: 59927b7a303fb41d249f403942824b9a (MD5) / Made available in DSpace on 2015-08-24T17:42:07Z (GMT). No. of bitstreams: 1 CARLOS ALEXANDRE F. JORGE D.pdf: 11356748 bytes, checksum: 59927b7a303fb41d249f403942824b9a (MD5) Previous issue date: 2015-07 / This work proposes the development of a system to evaluate received radiation dose for nuclear plants personnel. The system is conceived to operate in a complementary form to the existing approaches for radiological protection, thus o ering redundancy, what is desirable for critical plants operation. The proposed system must operate in an independent form on the actions to be performed by the operators under evaluation. Therefore, it was decided it would be based on methods used for video surveillance. The nuclear plant used as example is Argonauta Nuclear Research Reactor, belonging to Instituto de Engenharia Nuclear, Comiss~ao Nacional de Energia Nuclear (Nuclear Engineering Institute, National Nuclear Energy Commission). During this thesis research, both radiation dose rate distribution and video databases were obtained. Methods available in the literature, for targets detection and/or tracking, were evaluated for this database. From these results, a new system was proposed, with the purpose of meeting the requisites for this particular application. Given the tracked positions of each worker, the radiation dose received by each one during tasks execution is estimated, and may serve as part of a decision support system.