<p>This thesis describes and evaluates a number of algorithms for reducing fixed pattern noise in image sequences. Fixed pattern noise is the dominantnoise component for many infrared detector systems, perceived as a superimposed pattern that is approximately constant for all image frames. </p><p>Primarily, methods based on estimation of the movement between individual image frames are studied. Using scene-matching techniques, global motion between frames can be successfully registered with sub-pixel accuracy. This allows each scene pixel to be traced along a path of individual detector elements. Assuming a static scene, differences in pixel intensities are caused by fixed pattern noise that can be estimated and removed. </p><p>The algorithms have been tested by using real image data from existing infrared imaging systems with good results. The tests include both a two-dimensional focal plane array detector and a linear scanning one-dimensional detector, in different scene conditions.</p>

This thesis describes and evaluates a number of algorithms for reducing fixed pattern noise in image sequences. Fixed pattern noise is the dominantnoise component for many infrared detector systems, perceived as a superimposed pattern that is approximately constant for all image frames. Primarily, methods based on estimation of the movement between individual image frames are studied. Using scene-matching techniques, global motion between frames can be successfully registered with sub-pixel accuracy. This allows each scene pixel to be traced along a path of individual detector elements. Assuming a static scene, differences in pixel intensities are caused by fixed pattern noise that can be estimated and removed. The algorithms have been tested by using real image data from existing infrared imaging systems with good results. The tests include both a two-dimensional focal plane array detector and a linear scanning one-dimensional detector, in different scene conditions.

Hlavným cieľom práce bolo vytvorenie softvérového riešenia založeného na neurónových sieťach, pomocou ktorého bolo možné detegovať človeka a následne ho nasledovať. Tento výsledok bol dosiahnutý splnením jednotlivých bodov zadania tejto práce. V prvej časti práce je popísaný použitý hardvér, softvérové knižnice a rozhrania pre programovanie aplikácií (API), ako aj robotická platforma dodaná skupinou robotiky a umelej inteligencie ústavu automatizácie a meracej techniky Vysokého Učenia Technického v Brne, na ktorej bol výsledný robot postavený. Následne bola spracovaná rešerš viacerých typov neurónových sietí na detekciu osôb. Podrobne boli popísané štyri detektory. Niektoré z nich boli neskôr testované na klasickom počítači alebo na počítači NVIDIA Jetson Nano. V ďalšom kroku bolo vytvorené softvérové riešenie tvorené piatimi programmi, pomocou ktorého bolo dosiahnuté ciele ako rozpoznanie osoby pomocou neurónovej siete ped-100, určenie reálnej vzdialenosti vzhľadom k robotu pomocou monokulárnej kamery a riadenie roboty k úspešnému dosiahnutiu cieľa. Výstupom tejto práce je robotická platforma umožnujúca detekciu a nasledovanie osoby využiteľné v praxi.

No description available.

Enhanced vision and object detection could be useful in the aviation domain in situations of bad weather or cluttered environments. In particular, enhanced vision and object detection could improve situational awareness and aid the pilot in environment interpretation and detection of hazardous objects. The fundamental concept of object detection is to interpret what objects are present in an image with the aid of a prediction model or other feature extraction techniques. Constructing a comprehensive data set that can describe the operational environment and be robust for weather and lighting conditions is vital if the object detector is to be utilised in the avionics domain. Evaluating the accuracy and robustness of the constructed data set is crucial. Since erroneous detection, referring to the object detection algorithm failing to detect a potentially hazardous object or falsely detecting an object, is a major safety issue. Bayesian uncertainty estimations are evaluated to examine if they can be utilised to detect miss-classifications, enabling the use of a Bayesian Neural Network with the object detector to identify an erroneous detection. The object detector Faster RCNN with ResNet-50-FPN was utilised using the development framework Detectron2; the accuracy of the object detection algorithm was evaluated based on obtained MS-COCO metrics. The setup achieved a 50.327 % AP@[IoU=.5:.95] score. With an 18.1 % decrease when exposed to weather and lighting conditions. By inducing artificial artefacts and augmentations of luminance, motion, and weather to the images of the training set, the AP@[IoU=.5:.95] score increased by 15.6 %. The inducement improved the robustness necessary to maintain the accuracy when exposed to variations of environmental conditions, which resulted in just a 2.6 % decrease from the initial accuracy. To fully conclude that the augmentations provide the necessary robustness for variations in environmental conditions, the model needs to be subjected to actual image representations of the operational environment with different weather and lighting phenomena. Bayesian uncertainty estimations show great promise in providing additional information to interpret objects in the operational environment correctly. Further research is needed to conclude if uncertainty estimations can provide necessary information to detect erroneous predictions.

Knowing where ships are located is a key factor to support safe maritime transports, harbor management as well as preventing accidents and illegal activities at sea. Present international solutions for geopositioning in the maritime domain exist such as the Automatic Identification System (AIS). However, AIS requires the ships to constantly transmit their location. Real time imaginary based on geostationary satellites has recently been proposed to complement the existing AIS system making locating and tracking more robust. This thesis investigated and compared two machine learning image analysis approaches – Faster R-CNN and SSD with FPN – for detection and tracking of ships in satellite images. Faster R-CNN is a two stage model which first proposes regions of interest followed by detection based on the proposals. SSD is a one stage model which directly detects objects with the additional FPN for better detection of objects covering few pixels. The MAritime SATellite Imagery dataset (MASATI) was used for training and evaluation of the candidate models with 5600 images taken from a wide variety of locations. The TensorFlow Object Detection API was used for the implementation of the two models. The results for detection show that Faster R-CNN achieved a 30.3% mean Average Precision (mAP) while SSD with FPN achieved only 0.0005% mAP on the unseen test part of the dataset. This study concluded that Faster R-CNN is a candidate for identifying and tracking ships in satellite images. SSD with FPN seems less suitable for this task. It is also concluded that the amount of training and choice of hyper-parameters impacted the results.

No description available.

Biologically inspired logarithmic CMOS sensors offer high dynamic range imaging capabilities without the difficulties faced by linear imagers. By compressing dynamic range while encoding contrast information, they mimic the human visual system’s response to photo stimuli in fewer bits than those used in linear sensors. Despite this prospect, logarithmic sensors suffer poor image quality due to illumination dependent fixed pattern noise (FPN), making individual pixels appear up to 100 times brighter or darker. This thesis is primarily concerned with alleviating FPN in logarithmic imagers in a simple and convenient way while undertaking a system approach to its origin, distribution and effect on the quality of monochrome and colour images, after FPN correction. Using the properties of the Human visual system, I propose to characterise the errors arising from FPN in a perceptually significant manner by proposing an error measure, never used before. Logarithmic operation over a wide dynamic range is first characterised using a new model; yi j =aj +bj ln(exp sqrt(cj +djxi)−1), where yi j is the response of the sensor to a light stimulus xi and aj, bj, cj and dj are pixel dependent parameters. Using a proposed correction procedure, pixel data from a monochromatic sensor array is FPN corrected to approximately 4% error over 5 decades of illumination even after digitisation - accuracy equivalent to four times the human eyes ability to just notice an illumination difference against a uniform background. By evaluating how error affects colour, the possibility of indiscernible residual colour error after FPN correction, is analytically explored using a standard set of munsell colours. After simulating the simple FPN correction procedure, colour quality is analysed using a Delta E76 perceptual metric, to check for perceptual discrepancies in image colour. It is shown that, after quantisation, the FPN correction process yields 1−2 Delta E76 error units over approximately 5 decades of illumination; colour quality being imperceptibly uniform in this range. Finally, tone-mapping techniques, required to compress high dynamic range images onto the low range of standard screens, have a predominantly logarithmic operation during brightness compression. A new Logr'Gb' colour representation is presented in this thesis, significantly reducing computational complexity, while encoding contrast information. Using a well-known tone mapping technique, images represented in this new format are shown to maintain colour accuracy when the green colour channel is compressed to the standard display range, instead of the traditional luminance channel. The trade off between colour accuracy and computation in this tone mapping approach is also demonstrated, offering a low cost alternative for applications with low display specifications.

Diploma thesis is about image sensor security. Goal of the thesis was study data integrity gained from the image sensors. Proposed method is about source camera identification from noise characteristics in image sensors. Research was about influence of denoising algorithms applied to digital images, which was acquired from 15 different image sensors. Finally the statistical evaluation had been done from computed results.

Notre travail porte sur le développement d'algorithmes performants d'application de grammaires locales, en prenant comme référence ceux des logiciels libres existants: l'analyseur syntaxique descendant d'Unitex et l'analyseur syntaxique à la Earley d'Outilex. Les grammaires locales sont un formalisme de représentation de la syntaxe des langues naturelles basé sur les automates finis. Les grammaires locales sont un modèle de construction de descriptions précises et à grande échelle de la syntaxe des langues naturelles par le biais de l'observation systématique et l'accumulation méthodique de données. L'adéquation des grammaires locales pour cette tâche a été testée à l'occasion de nombreux travaux. À cause de la nature ambiguë des langues naturelles et des propriétés des grammaires locales, les algorithmes classiques d'analyse syntaxique tels que LR, CYK et Tomita ne peuvent pas être utilisés dans le contexte de ce travail. Les analyseurs descendant et Earley sont des alternatives possibles, cependant, ils ont des coûts asymptotiques exponentiels pour le cas des grammaires locales. Nous avons d'abord conçu un algorithme d'application de grammaires locales avec un coût polynomial dans le pire des cas. Ensuite, nous avons conçu des structures de données performantes pour la représentation d'ensembles d'éléments et de séquences. Elles ont permis d'améliorer la vitesse de notre algorithme dans le cas général. Nous avons mis en oeuvre notre algorithme et ceux des systèmes Unitex et Outilex avec les mêmes outils afin de les tester dans les mêmes conditions. En outre, nous avons mis en oeuvre différentes versions de chaque algorithme en utilisant nos structures de données et algorithmes pour la représentation d'ensembles et ceux fournis par la Standard Template Library (STL) de GNU. Nous avons comparé les performances des différents algorithmes et de leurs variantes dans le cadre d'un projet industriel proposé par l'entreprise Telefónica I+D: augmenter la capacité de compréhension d'un agent conversationnel qui fournit des services en ligne, voire l'envoi de SMS à des téléphones portables ainsi que des jeux et d'autres contenus numériques. Les conversations avec l'agent sont en espagnol et passent par Windows Live Messenger. En dépit du domaine limité et de la simplicité des grammaires appliquées, les temps d'exécution de notre algorithme, couplé avec nos structures de données et algorithmes pour la représentation d'ensembles, ont été plus courts. Grâce au coût asymptotique amélioré, on peut s'attendre à des temps d'exécution significativement inférieurs par rapport aux algorithmes utilisés dans les systèmes Unitex et Outilex, pour le cas des grammaires complexes et à large couverture.