This thesis is related to the broad subject of automatic motion detection and analysis in videosurveillance image sequence. Besides, proposing the new unique solution, some of the previousalgorithms are evaluated, where some of the approaches are noticeably complementary sometimes.In real time surveillance, detecting and tracking multiple objects and monitoring their activities inboth outdoor and indoor environment are challenging task for the video surveillance system. Inpresence of a good number of real time problems limits scope for this work since the beginning. Theproblems are namely, illumination changes, moving background and shadow detection.An improved background subtraction method has been followed by foreground segmentation, dataevaluation, shadow detection in the scene and finally the motion detection method. The algorithm isapplied on to a number of practical problems to observe whether it leads us to the expected solution.Several experiments are done under different challenging problem environment. Test result showsthat under most of the problematic environment, the proposed algorithm shows the better qualityresult.

Inthisthesiswefocusontheimpactofilluminationchangesinvideoand we discuss how we can minimize the impact of illumination variance in video processing systems. Identifyingandremovingshadowsautomaticallyisaverywellestablished and an important topic in image and video processing. Having shadowless image data would benefit many other systems such as video surveillance, tracking and object recognition algorithms. Anovelapproachtoautomaticallydetectandremoveshadowsispresented in this paper. This new method is based on the observation that, owing to the relative movement of the sun, the length and position of a shadow changes linearly over a relatively long period of time in outdoor environments,wecanconvenientlydistinguishashadowfromotherdark regions in an input video. Then we can identify the Reference Shadow as the one with the highest confidence of the mentioned linear changes. Once one shadow is detected, the rest of the shadow can also be identifiedandremoved. Wehaveprovidedmanyexperimentsandourmethod is fully capable of detecting and removing the shadows of stationary and moving objects. Additionally we have explained how reference shadows can be used to detect textures that reflect the light and shiny materials such as metal, glass and water. ...

<p>Foreground segmentation is a common first step in tracking and surveillance applications.  The purpose of foreground segmentation is to provide later stages of image processing with an indication of where interesting data can be found.  This thesis is an investigation of how foreground segmentation can be performed in two contexts: as a pre-step to trajectory tracking and as a pre-step in indoor surveillance applications.</p><p>Three methods are selected and detailed: a single Gaussian method, a Gaussian mixture model method, and a codebook method.  Experiments are then performed on typical input video using the methods.  It is concluded that the Gaussian mixture model produces the output which yields the best trajectories when used as input to the trajectory tracker.  An extension is proposed to the Gaussian mixture model which reduces shadow, improving the performance of foreground segmentation in the surveillance context.</p>

<p>A common problem when using background models to segment moving objects from video sequences is that objects cast shadow usually significantly differ from the background and therefore get detected as foreground. This causes several problems when extracting and labeling objects, such as object shape distortion and several objects merging together. The purpose of this thesis is to explore various possibilities to handle this problem.</p><p>Three methods for statistical background modeling are reviewed. All methods work on a per pixel basis, the first is based on approximating the median, the next on using Gaussian mixture models, and the last one is based on channel representation. It is concluded that all methods detect cast shadows as foreground.</p><p>A study of existing methods to handle cast shadows has been carried out in order to gain knowledge on the subject and get ideas. A common approach is to transform the RGB-color representation into a representation that separates color into intensity and chromatic components in order to determine whether or not newly sampled pixel-values are related to the background. The color spaces HSV, IHSL, CIELAB, YCbCr, and a color model proposed in the literature (Horprasert et al.) are discussed and compared for the purpose of shadow detection. It is concluded that Horprasert's color model is the most suitable for this purpose.</p><p>The thesis ends with a proposal of a method to combine background modeling using Gaussian mixture models with shadow detection using Horprasert's color model. It is concluded that, while not perfect, such a combination can be very helpful in segmenting objects and detecting their cast shadow.</p>

Nous introduisons un algorithme de décomposition intrinsèque multi-vue qui permet de ré-éclairer une scène extérieure en utilisant quelques images en entrée. Plusieurs applications comme l’architecture, jeux et films exigent de manipuler un modèle 3D d’une scène. Cependant, la modification de telles scènes est limitée par les conditions d’éclairage de capture. Notre méthode estime les images intrinsèques prises dans des conditions d’éclairage identiques avec des ombres. Nous utilisons conjointement une reconstruction 3D automatique et la direction du soleil pour obtenir la décomposition de chaque image en calques de réflectance et d’éclairage malgré l’inexactitude des données du modèle 3D. Notre approche est basée sur deux idées principales. Tout d’abord, nous raffinons l’estimation des paramètres de notre modèle de formation d’image en combinant la simulation d’éclairage 3D avec des méthodes d’optimisation basée image. Deuxièmement, nous utilisons ce modèle pour exprimer la réflectance en fonction de valeur de visibilité discrète pour l’ombre et la lumière, ce qui nous permet d’introduire un classificateur d’ombre robuste pour des paires de points dans une scène. Nos calques intrinsèques sont de qualité suffisante pour manipuler les images d’entrée. Nous déplaçons les ombres portées en créant une géométrie qui préserve les silhouettes d’ombre. Notre méthode est compatible avec les approches de rendu basé image et réduit les coûts de création de contenu 3D. Enfin, nous présentons une étude sur les limites du modèle de réflectance diffus et la difficulté d’appliquer les approches existantes dans le cadre de reconstruction 3D multi vue où les données sont imprécises. / We present a multi-view intrinsic decomposition algorithm that allows relighting of an outdoor scene using just a few photographs as input. Several applications such as architecture, games and movies require a 3D model of a scene. However, editing such scenes is limited by the lighting condition at the time of capture. Our method computes intrinsic images photos taken under the same lighting condition with existing cast shadows by the sun. We use an automatic 3D reconstruction from these photos and the sun direction as input and decompose each image into reflectance and shading layers, despite the inaccuracies and missing data of the 3D model. Our approach is based on two key ideas. First, we progressively improve the accuracy of the parameters of our image formation model by performing iterative estimation and combining 3D lighting simulation with 2D image optimization methods. Second we use the image formation model to express reflectance as a function of discrete visibility values for shadow and light, which allows us to introduce a robust shadow classifier for pairs of points in a scene. Our multi-view intrinsic decomposition is of sufficient quality for relighting of the input images. We create shadow-caster geometry which preserves shadow silhouettes and using the intrinsic layers, we can perform multi-view relighting with moving cast shadows. Our method allows image-based rendering with changing illumination conditions and reduces the cost of creating 3D content for applications. Finally, we present an initial study on the limitation of diffuse reflectance models for these computations.

Submitted by PPG Engenharia El?trica (engenharia.pg.eletrica@pucrs.br) on 2018-06-08T13:54:41Z No. of bitstreams: 1 RICARDO_VINICIUS_DOTH_DIS.pdf: 9281309 bytes, checksum: d26fbf7274d4c8eb7158a2d987437b1b (MD5) / Approved for entry into archive by Sheila Dias (sheila.dias@pucrs.br) on 2018-06-18T12:49:23Z (GMT) No. of bitstreams: 1 RICARDO_VINICIUS_DOTH_DIS.pdf: 9281309 bytes, checksum: d26fbf7274d4c8eb7158a2d987437b1b (MD5) / Made available in DSpace on 2018-06-18T12:58:59Z (GMT). No. of bitstreams: 1 RICARDO_VINICIUS_DOTH_DIS.pdf: 9281309 bytes, checksum: d26fbf7274d4c8eb7158a2d987437b1b (MD5) Previous issue date: 2018-03-27 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior - CAPES / Wide Area Motion Imagery (WAMI) systems acquire large area aerial images in real time to provide accurate situational awareness information from a region (BLASCH et al., 2014). This system is applied for urban aerial monitoring. Unfavorable environmental conditions, such as shadow regions, are factors that increase system complexity by compromising the effectiveness of tracking algorithms and human visual interpretation (PORTER; FRASER; HUSH, 2010). Several techniques of shadow removal in aerial images have been developed, however due to the characteristics of the shadow and aerial image, a specific method to evaluate and compare the removal is unknown. The main objective of this study is to develop a method to evaluate shadow removal algorithms in aerial images acquired by the WAMI system. This work proposes a radiometric approach modifying the illumination in a controlled environment, simulating an aerial scene, acquiring images with and without the presence of shadows. The image with shadows is processed by the evaluated shadow removal algorithm, with the ideal output being the shadow free image. Shadow detection is evaluated using the confusion matrix concept. Shadow removal is evaluated using the structural similarity index (SSIM). As a result the reduced scale aerial scene model is presented to generate shadow and freeshadow images and the evaluation of 3 shadow removal methods using the data sets of images obtained from the scale model applying the methodology developed. / Sistemas WAMI (Wide Area Motion Imagery) adquirem imagens a?reas de grandes ?reas em tempo real para prover informa??es precisas de uma determinada regi?o (BLASCH et al., 2014). Este sistema ? aplicado para monitoramento a?reo urbano. Condi??es ambientais desfavor?veis, como ?reas sombreadas, s?o fatores que aumentam a complexidade do sistema comprometendo a efic?cia de algoritmos de rastreamento e a interpreta??o visual humana (PORTER; FRASER; HUSH, 2010). Diversas t?cnicas de remo??o de sombra em imagens a?reas foram desenvolvidas, no entanto devido ?s caracter?sticas da sombra e da imagem a?rea ? desconhecido um m?todo espec?fico para avaliar e comparar a remo??o de sombras em imagens a?reas. O objetivo principal deste estudo ? desenvolver um m?todo para avaliar algoritmos de remo??o de sombra em imagens a?reas adquiridas pelo sistema WAMI. Este trabalho prop?e uma abordagem radiom?trica modificando a ilumina??o em um ambiente controlado, simulando uma cena a?rea, adquirindo imagens com e sem sombras. A imagem com sombra ? processada pelo algoritmo de remo??o de sombra avaliado, sendo a imagem sem sombra o resultado ideal a ser alcan?ado. A detec??o de sombra ? avaliada utilizando o conceito de matriz de confus?o (error matrix). A remo??o de sombra ? avaliada utilizando o ?ndice de similaridade estrutural entre duas imagens (SSIM). Foram desenvolvidos o modelo de cena a?rea em escala reduzida para gerar imagens com e sem sombra e a avalia??o de 3 m?todos de remo??o de sombras utilizando os data sets de imagens obtidas do modelo em escala aplicando a metodologia descrita.

Robust object detection from registered infrared and visible image streams is proposed for outdoor surveillance. In doing this, halo effect in infrared images is used as a benefit to extract object boundary by fitting active contour models (snake) to the foreground regions where these regions are detected by using the useful information from both visual and infrared domains together. Synchronization and registration are performed for each infrared and visible image couple. Various background modeling methods such as Single Gaussian, Non- Parametric and Mixture of Gaussian models are implemented. For Single Gaussian and Mixture of Gaussian background modeling, infrared, color intensity and color channels domains are modelled separately. First of all, background subtraction is applied in the infrared domain in order to find the initial foreground regions and these are used as a mask for the foreground detection in the visible domain. After removing the shadows from the foreground regions in the visible domain, pixelwise OR operation is applied between the foreground regions of the infrared and visible couple and the final foreground mask is formed. For Non-Parametric background modeling, all domains are used altogether to extract foreground regions. For all background modelling methods, the resulting mask is used to get the final foreground regions in the infrared image. Finally, snake is applied to each connected component of the foreground regions on the infrared image for the purpose of object detection. Two datasets are used to demonstrate our results for human detection where comparisons against manually segmented human regions and against other results in the literature are presented.

A method for detecting buildings from satellite/aerial images is proposed in this study. The aim is to extract rectilinear buildings by using hypothesize first verify next manner. Hypothesis generation is accomplished by using edge detection and line generation stages. Hypothesis verification is carried out by using information obtained both from the color segmentation of HSV representation of the image and the shadow detection stages&rsquo / output. Satellite/aerial image is firstly filtered to sharpen the edges. Then, edges are extracted using Canny edge detection algorithm. These edges are the input for the Hough Transform stage which will produce line segments according to these extracted edges. Then, extracted line segments are used to generate building hypotheses. Verification of these hypotheses makes use of the outputs of the HSV color segmentation and shadow detection stages. In this study, color segmentation is processed on the HSV representation of the satellite/aerial image which is less sensitive to illumination. In order to perform the shadow detection, the basic information which is shadow areas have higher value of saturation component and lower value of value component in HSV color space is used and according to this information a mask is applied to the HSV representation of the image to produce shadow pixels. The proposed method is implemented as software written in MATLAB programming software. The approach was tested in several different areas. The results are encouraging.

Rectangular-shaped building detection from high resolution aerial/satellite images is proposed for two different methods. Shadow information plays main role in both of these algorithms. One of the algorithms is based on Hough transformation, the other one is based on mean shift segmentation algorithm. Satellite/aerial images are firstly converted to YIQ color space to be used in shadow segmentation. Hue and intensity values are used in computing the ratio image which is used to segment shadowed regions. For shadow segmentation Otsu&rsquo / s method is used on the histogram of the ratio image. The segmented shadow image is used as the input for both of two building detection algorithms. In the proposed methods, shadowed regions are believed to be the building shadows. So, non-shadowed regions such as roads, cars, trees etc. are discarded before processing the image. In Hough transform based building detection algorithm, shadowed regions are firstly segmented one by one and filtered for noise removal and edge sharpening. Then, the edges in the filtered image are detected by using Canny edge detection algorithm. Then, line segments are extracted. Finally, the extracted line segments are used to construct rectangular-shaped buildings. In mean shift based building detection algorithm, image is firstly segmented by using mean shift segmentation algorithm. By using shadow image and segmented image, building rooftops are investigated in shadow boundaries. The results are compared for both of the algorithms. In the last step a shadow removal algorithm is implemented to observe the effects of shadow regions in both of two implemented building detection algorithms. Both of these algorithms are applied to shadow removed image and results are compared.

This thesis is devoted to the shadow detection and compensation in aerial images with application of the detection results to building height detection. Shadows could be defined as the parts of the scene that is not directly illuminated by a light source due to obstructing object or objects. Usually the shadows in images or video are undesirable, since they could cause degradation of the expected results during processing of the image or video for object detection, segmentation, scene surveillance or similar purposes. However shadow information could also be used for beneficial purposes like revealing information about the object&rsquo / s shape, orientation and even about the light source. In this thesis firstly shadow detection methods are overviewed. Beside the selected methods from literature, some novel approaches are also proposed and experimented. Then shadow compensation methods are overviewed and experimented. Finally an example of beneficial utilizations of shadow information is studied, where buildings&rsquo / heights are estimated from their shadow length and sun angles.