Cette thèse traite de l’utilisation de la couleur en vision par ordinateur. Deux problèmes sont étudiés : - l’estimation d’illuminants, - la mise en correspondance de descripteurs locaux pour la comparaison d’images couleur. Les surfaces achromatiques renvoient un spectre lumineux ayant la même distribution fréquentielle que le spectre de l’illuminant. Les détecter permet donc de recouvrer l'illuminant. En supposant que l’ensemble des couleurs que peut prendre un illuminant est limité (équation de Planck), il est possible de sélectionner les pixels appartenant à une surface potentiellement grise. Une méthode de vote est alors appliquée, permettant de sélectionner un ou plusieurs illuminants. L’algorithme final possède de nombreux avantages : il est efficace, intuitif, ne nécessite pas de phase d’apprentissage et requiert peu de paramètres, qui s’avèrent stables. De plus, la méthode de vote permet de s’adapter aux cas où plusieurs sources lumineuses éclairent la scène photographiée. Les descripteurs locaux sont des outils puissants pour comparer les images. Cependant, le rôle de la couleur dans l’étape d’appariement a fait l’objet de peu d’études. Le problème principal que nous considérons ici est celui de l’apport de la couleur pour l’appariement de descripteurs locaux. Un usage local de la couleur permet-il de désambiguïser les situations où la luminance seule est insuffisante ? Et si oui, dans quelles proportions ? Nous proposons quatre descripteurs permettant de décrire de manière détaillée le contexte local de points clés dans l’optique de les apparier. Les expériences proposées montrent clairement l’apport de la couleur pour la mise en correspondance locale. / This thesis addresses the use of color in image processing and computer vision. Two problems are studied: - illuminant estimation, - local descriptors matching for color images comparison. Achromatic surfaces are defined as surfaces reflecting a spectrum with the same frequency dsitribution than the illuminant. Consequently, revovering these surfaces allows to estimate the illuminant. Assuming that the range of colors taken by an illuminant is limited (Planck equation), it is possible to select the pixels belonging to a potentially gray surface. A voting procedure is then applied to select one or more illuminants. The proposed algorithm has many advantages: it is effective, intuitive, does not rely on a learning phase and requires only few parameters. In addition, the voting procedure can be adapted to handle cases where multiple light sources of different colors illuminate the scene. Local descriptors are powerful tools to compare images. However, few studies concern the influence of color in the matching step. The main problem that we consider here is the contribution of the color matching of local descriptors. Does the local use of color allow to disambiguate situations where the luminance alone is insufficient ? And if so, how much? We propose four descriptors to precisely describe the local context of key points in the matching step. The main idea developed here is that accurate information can only be obtained by describing both the color distributions and transitions between colors. The many experiences presented clearly show the positive contribution of color to the reliability of the local matching.

No description available.

<p> </p> <p>Modern remote sensing platforms such as unmanned aerial vehicles (UAVs) that can carry a variety of sensors including RGB frame cameras, hyperspectral (HS) line cameras, and LiDAR sensors are commonly used in several application domains. In order to derive accurate products such as point clouds and orthophotos, sensors’ interior and exterior orientation parameters (IOP and EOP) must be established. These parameters are derived/refined in a triangulation framework through minimizing the discrepancy between conjugate features extracted from involved datasets. Existing triangulation approaches are not general enough to deal with varying nature of data from different sensors/platforms acquired in diverse environmental conditions. This research develops a generic triangulation framework that can handle different types of primitives (e.g., point, linear, and/or planar features), and sensing modalities (e.g., RGB cameras, HS cameras, and/or LiDAR sensors) for delivering accurate products under challenging conditions with a primary focus on digital agriculture and stockpile monitoring application domains. </p>

Les changements anatomiques des patients au cours du traitement de radiothérapie peuvent engendrer des conséquences dosimétriques significatives sur les volumes cibles (VC) ou les organes à risques (OARs). Le processus de radiothérapie adaptative peut compenser ces variations, cependant son déploiement en clinique est ralentit par une charge de travail supplémentaire considérable pour les équipes médicales et aucun logiciel n'est disponible pour une utilisation en clinique. Nous avons développé un outil d'alerte dosimétrique in vivo simple permettant d'identifier rapidement les situations où une adaptation de traitement est requise pour un patient. L'évaluation dosimétrique des traitements délivrés a été réalisée sur l'imagerie embarquée 3D (CBCT) dont la précision des calculs de dose a dû être évaluée. L'outil d'alerte permet de s'affranchir d'une nouvelle délinéation de volumes d'intérêt et est basé sur des critères objectifs et quantifiables constitués par le dépassement des limites dosimétriques définies pour chacun des volumes considérés. La précision et la détectabilité de l'outil ont été validées puis il a été appliqué dans une étude rétrospective de 10 patients ORL afin de surveiller l'administration du traitement et d'identifier les patients pour lesquels une adaptation du traitement aurait pu être envisagée. Dans son implémentation clinique, le processus de radiothérapie adaptative requiert des algorithmes de recalage déformable capable de suivre les déformations locales d'un patient se produisant au cours du traitement, seulement leur utilisation n'est pas encore validée. Nous avons procédé à l'évaluation de la précision d'un algorithme de recalage déformable, de type Block Matching présentant l'avantage d'être adapté à l'imagerie multimodale CT/CBCT, en comparaison par rapport à un algorithme de recalage rigide. Une étude a été menée pour 10 patients ORL en se basant sur la comparaison de contours de volumes d'intérêt pour 76 CBCT. Les paramètres de similarité utilisés consistaient en l'Indice de Similarité Dice, la distance de Hausdorff robuste (en mm) et la différence de volume absolu (en cm3) / Changing anatomy during radiotherapy can lead to significant dosimetric consequences for organs at risk (OARs) and/or target volumes. Adaptive radiotherapy can compensate for these variations however its deployment for clinical work is hampered by the increased workload for the medical staff and there is still no commercialized software available for clinical use. We developed a simple in vivo dosimetric alert tool allowing rapid identification of patients who might benefit from an adaptive radiotherapy. Dosimetric evaluation of delivered treatment has been conducted onto 3D on board imaging (CBCT) whose dose calculation accuracy has been evaluated. The tool does not require a new volume of interest delineation. Tool alert is based on objectives and quantifiable criteria defined by the exceeding volumes of interest dose thresholds. Tool precision and detectability have been validated and applied in a retrospective study on 10 head and neck patients. The tool allows detecting patients where an adaptive treatment could have been considered. In its clinical implementation, adaptive radiotherapy process requires deformable matching algorithms to follow patient local's deformations occurring during treatment. Nevertheless, their use has not been validated. We conducted an evaluation of the Block Matching deformable algorithm, suitable for multimodality imaging (CT/CBCT), in comparison to rigid algorithm. A study has been conducted for 10 head and neck patients based on volume of interest contours comparison for 76 CBCT. Similarity parameters used consisted on Dice Similarity Index, Robust Hausdorff Distance (in mm) and the absolute volume difference (in cc)

L’appariement d’images est un sujet central de recherche en vision par ordinateur. La recherche sur cette problématique s’est longuement concentrée sur ses aspects optiques, mais ses aspects géométriques ont reçu beaucoup moins d’attention. Cette thèse promeut l’utilisation de la géométrie pour compléter les informations optique dans les tâches de mise en correspondance d’images. Tout d’abord, nous nous penchons sur les méthodes globales pour lesquelles les occlusions et arêtes vives posent des défis. Dans ces scenarios, le résultat est fortement dépendant de la contribution du terme de régularisation. À l'aide d’une caractérisation géométrique de ce comportement, nous formulons une méthode d’appariement qui dirige les lignes de la grille loin des régions problématiques. Bien que les méthodes variationnelles fournissent des résultats qui se comportent bien en général, les méthodes locales basées sur la propagation de correspondances fournissent des résultats qui s’adaptent mieux à divers structures 3D mais au détriment de la cohérence globale de la surface reconstruite. Par conséquent, nous présentons une nouvelle méthode de propagation guidée par des reconstructions locales de surface / AbstractImage matching is a central research topic in computer vision which has been mainly focused on optical aspects. The aim of the work presented herein consists in the direct use of geometry to complement optical information in the tasks of 2D matching. First, we focus on global methods based on the calculus of variations. In such methods occlusions and sharp features raise difficult challenges. In these scenarios only the contribution of the regularizer accounts for results. Based on a geometric characterization of this behaviour, we formulate a variational matching method that steers grid lines away from problematic regions. While variational methods provide well behaved results, local methods based on match propagation provide results that adapt closely to varying 3D structures although choppy in nature. Therefore, we present a novel method to propagate matches using local information about surface regularity correcting 3D positions along with corresponding 2D matchings

De nos jours les algorithmes de vision par ordinateur abondent dans les applications de vidéo-surveillance, de reconstruction 3D, de véhicules autonomes, d'imagerie médicale, etc… La détection et la mise en correspondance d'objets dans les images constitue une étape clé dans ces algorithmes.Les méthodes les plus communes pour la mise en correspondance d'objets ou d'images sont basées sur des descripteurs locaux, avec tout d'abord la détection de points d'intérêt, puis l'extraction de caractéristiques de voisinages des points d'intérêt, et enfin la construction des descripteurs d'image.Dans cette thèse, nous présentons des contributions au domaine de la mise en correspondance d'images par l'utilisation de demi filtres tournants. Nous suivons ici trois approches : la première présente un nouveau descripteur à faible débit et une stratégie de mise en correspondance intégrés à une plateforme vidéo. Deuxièmement, nous construisons un nouveau descripteur local en intégrant la réponse de demi filtres tournant dans un histogramme de gradient orienté (HOG) ; enfin nous proposons une nouvelle approche pour la construction d'un descripteur utilisant des statistiques du second ordre. Toutes ces trois approches apportent des résultats intéressants et prometteurs.Mots-clés : Demi filtres tournants, descripteur local d'image, mise en correspondance, histogramme de gradient orienté (HOG), Différence de gaussiennes. / Nowadays computer vision algorithms can be found abundantly in applications relatedto video surveillance, 3D reconstruction, autonomous vehicles, medical imaging etc. Image/object matching and detection forms an integral step in many of these algorithms.The most common methods for Image/object matching and detection are based on localimage descriptors, where interest points in the image are initially detected, followed byextracting the image features from the neighbourhood of the interest point and finally,constructing the image descriptor. In this thesis, contributions to the field of the imagefeature matching using rotating half filters are presented. Here we follow three approaches:first, by presenting a new low bit-rate descriptor and a cascade matching strategy whichare integrated on a video platform. Secondly, we construct a new local image patch descriptorby embedding the response of rotating half filters in the Histogram of Orientedgradient (HoG) framework and finally by proposing a new approach for descriptor constructionby using second order image statistics. All the three approaches provides aninteresting and promising results by outperforming the state of art descriptors.Key-words: Rotating half filters, local image descriptor, image matching, Histogram of Orientated Gradients (HoG), Difference of Gaussian (DoG).

三維城市模型之建置需求漸趨繁多，可提供都市規劃、城市導航及虛擬實境等相關應用，過去研究多以建置LOD2城市模型為主，且較著重於屋頂結構。近年來，逐漸利用垂直影像及傾斜影像作為原始資料，提供建物牆面之建置，並且，隨著無人機系統(Unmanned Aircraft System, UAS）發展，可利用其蒐集高解析度且高重疊垂直及傾斜拍攝之建物影像，並採影像密匹配技術產製高密度點雲，進而快速取得建物包含屋頂及牆面之三維資訊，而這些資訊可進一步提供後續建置LOD3建置層級之模型，而在建置前，首先須對資料進行特徵分析，萃取特徵點、線、面，進而提供建置模型所需之資訊。 因此，本研究期望利用密匹配點雲，計算其點雲特徵，並採用Mean Shift分群法（Comaniciu and Meer, 2002）萃取建物點雲資訊，並提供一最佳分群策略。首先，本研究將以UAS為載具，設計一野外率定場率定相機，並蒐集建物高重疊UAS影像密匹配產製高密度點雲，針對單棟建物高密度點雲，實驗測試點雲疏化程度後，依據疏化成果計算點雲特徵，並以此批點雲資料實驗測試Mean shift分群法（Cheng, 1995）中之參數，後設計分群流程以分離平面點群及曲面點群，探討分群成果以決定最佳分群策略。實驗結果顯示本研究提出之分群策略，可自動區分平面點群及曲面點群，並單獨將平面點群分群至各牆面。 / Unmanned Aerial System (UAS) offer several new possibilities in a wide range of applications. One example is the 3D reconstruction of buildings. In former times this was either restricted by earthbound vehicles to the reconstruction of facades or by air-borne sensors to generate only very coarse building models. UAS are able to observe the whole 3D scene and to capture images of the object of interest from completely different perspectives. Therefore, this study will use UAS to collected images of buildings and to generate point cloud from dense image matching for modeling buildings. In the proposed approach, this method computes principal orientations by PCA and identifies clusters by Mean shift clustering. Analyze the factors which can affect the clustering methods and try to decrease the use of threshold, and this result can cluster the façade of buildings automatically and offer the after building reconstruction for LOD3.

Video editing and object recognition are two significant fields in computer vi- sion: the first has remarkably assisted digital production and post-production tasks of a digital video footage; the second is considered fundamental to image classification or image based search in large databases (e.g. the web). In this thesis, we address two problems, namely we present a novel formulation that tackles video editing tasks and we develop a mechanism that allows to generate more robust descriptors for objects in an image. Concerning the first problem, this thesis proposes two variational models to perform temporally coherent video editing. These models are applied to change an object’s (rigid or non-rigid) texture throughout a given video sequence. One model is based on propagating color information from a given frame (or be- tween two given frames) along the motion trajectories of the video; while the other is based on propagating gradient domain information. The models we present in this thesis require minimal user intervention and they automatically accommodate for illumination changes in the scene. Concerning the second problem, this thesis addresses the problem of affine invariance in object recognition. We introduce a way to generate geometric affine invariant quantities that are used in the construction of feature descrip- tors. We show that when these quantities are used they do indeed achieve a more robust recognition than the state of the art descriptors. i / La edición de vídeo y el reconocimiento de objetos son dos áreas fundamentales en el campo de la visión por computador: la primera es de gran utilidad en los procesos de producción y post-producción digital de vídeo; la segunda es esencial para la clasificación o búsqueda de imágenes en grandes bases de datos (por ejemplo, en la web). En esta tesis se acometen ambos problemas, en concreto, se presenta una nueva formulación que aborda las tareas de edición de vídeo y se desarrolla un mecanismo que permite generar descriptores más robustos para los objetos de la imagen. Con respecto al primer problema, en esta tesis se proponen dos modelos variacionales para llevar a cabo la edición de vídeo de forma coherente en el tiempo. Estos modelos se aplican para cambiar la textura de un objeto (rígido o no) a lo largo de una secuencia de vídeo dada. Uno de los modelos está basado en la propagación de la información de color desde un determinado cuadro de la secuencia de vídeo (o entre dos cuadros dados) a lo largo de las trayectorias de movimiento del vídeo. El otro modelo está basado en la propagación de la información en el dominio del gradiente. Ambos modelos requieren una intervención mínima por parte del usuario y se ajustan de manera automática a los cambios de iluminación de la escena. Con respecto al segundo problema, esta tesis aborda el problema de la invariancia afín en el reconocimiento de objetos. Se introduce un nuevo método para generar cantidades geométricas afines que se utilizan en la generación de descriptores de características. También se demuestra que el uso de dichas cantidades proporciona mayor robustez al reconocimiento que los descriptores existentes actualmente en el estado del arte.

Submitted by Raquel Alves de Oliveira (raquel88@gmail.com) on 2017-12-07T10:06:49Z No. of bitstreams: 1 Oliveira_2017_TESE.pdf: 10400710 bytes, checksum: 4c4e6b235bd849c0d16074edea702847 (MD5) / Approved for entry into archive by ALESSANDRA KUBA OSHIRO null (alessandra@fct.unesp.br) on 2017-12-07T11:22:22Z (GMT) No. of bitstreams: 1 oliveira_ra_dr_prud.pdf: 10400710 bytes, checksum: 4c4e6b235bd849c0d16074edea702847 (MD5) / Made available in DSpace on 2017-12-07T11:22:23Z (GMT). No. of bitstreams: 1 oliveira_ra_dr_prud.pdf: 10400710 bytes, checksum: 4c4e6b235bd849c0d16074edea702847 (MD5) Previous issue date: 2017-06-29 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) / Recentemente, os sensores hiperespectrais miniaturizados entraram no mercado e alguns modelos adquirem bandas hiperespectrais com geometria de quadro, com a vantagem de serem também operados em veículos aéreos remotamente pilotados (VARP). As imagens deste tipo de câmara podem ser utilizadas para a geração de modelos digitais de superfície hiperespectral (MDSHs) de alta resolução, usando o VARP, sem a necessidade do registro de dados de diferentes sensores ou diferente datas de aquisição. MDSHs aumentam o conhecimento sobre os alvos, uma vez que permitem modelar a reflectância do alvo utilizando dados provenientes de diferentes direções. Neste trabalho, a câmara hiperespectral de quadro utilizada não adquire todas as bandas instantaneamente, causando um deslocamento entre as bandas devido ao movimento da plataforma. Os principais objetivos deste projeto foram estudar e desenvolver técnicas para a geração de MDSHs em áreas de florestas, investigando e avaliando as principais etapas para o processamento das imagens da câmara hiperespectral de quadro até a geração do MSDH. Considerando que a tecnologia da câmara baseia-se em filtros ajustáveis, o estudo avaliou: a auto-calibração da câmara, verificando o comportamento dos parâmetros de orientação interior em diferentes bandas espectrais; o corregistro das bandas através de transformações geométricas 2D; e a estimativa dos parâmetros de orientação exterior. Em relação à geração do MDS, uma abordagem baseada em correspondência de imagem no espaço do objeto foi desenvolvida, adaptando o método de busca em linha vertical (VLL) para a geração MDSH e foi nomeado como VLL hiperespectral (HVLL). Adicionalmente, o uso de imagens classificadas para a adaptação dos parâmetros de correspondência foi avaliado com o objetivo de melhorar o processo de correspondência para diferentes objetos (HVLLC). Posteriormente, foram utilizadas múltiplas bandas no processo de correspondência de imagens, dados como múltiplos ângulos de visada e informação espectral foram calculados simultaneamente ao processo de correspondência de imagens. A avaliação da qualidade foi realizada comparando-se os MDSs gerados com os produzidos por um software comercial e por dados Airborne Laser Scanning (ALS). Esta investigação demonstrou que a técnica proposta pode ser usada para a geração de modelos 3D integrados aos dados hiperespectrais multiangulares da câmara hiperespectral de quadro. A avaliação de todas as etapas demonstrou que esta tecnologia pode fornecer dados geométricos e espectrais precisos e os MDSHs resultantes possuem potencial para várias aplicações de sensoriamento remoto. / Recently, miniaturized hyperspectral sensors, operable from small Remotely Piloted Aerial Systems (RPAS), have entered the market and some of these sensors acquire hyperspectral bands in frame geometry. Images of the lightweight hyperspectral 2D frame camera can be used to generate high-resolution hyperspectral digital surface models (HDSMs), without the registration of data from different sensors or different dates of acquisition. HSDMs increase the knowledge about the targets since it allows modeling the target reflectance using data coming from different directions. In this study, the hyperspectral 2D frame camera used does not acquire all bands instantaneously, causing band misalignment due to the platform motion. The main aims of this project were to study and develop techniques for the generation of HDSMs in forest areas, studying and assessing the main steps to process the hyperspectral 2D frame camera images until the HDSM generation. Considering that the camera technology is based on tunable filters, the study have assessed the orientation and DSM generation steps: the self-calibrating bundle adjustment to verify the behaviour of the interior orientation parameters using different spectral bands; the co-registration of the bands using 2D geometric transformation; the exterior orientation parameter estimation. Regarding to the DSM generation, an approach based on object space image matching was developed, adapting the vertical line locus (VLL) method for HDSM generation, and was named as hyperspectral VLL (HVLL). Additionally, the use of image classification data was investigated in order to adapt the image matching parameters and improve the process of image matching for different objects (hyperspectral VLL classes - HVLLC). Further, multiple bands were used and the spectral and multiangular viewing geometry were computed simultaneously to the image matching method. Quality assessment was performed by comparing to DSMs generated to those produced by commercial software and also by Airborne Laser Scanning (ALS) data. This investigation demonstrated that the proposed technique can be used to generate integrated 3D information and multiangular hyperspectral data from hyperspectral 2D frame camera. The assessment of all steps showed that the hyperspectral 2D frame technology can provide accurate geometric and spectral data and the resulting HDSMs have potential for several remote sensing applications. / FAPESP: 2013/17787-3 / FAPESP: 2013/14444-0 / FAPESP: 2014/24844-6

Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-17T00:51:51Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-22T14:06:59Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-22T18:09:14Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-22T18:12:24Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-22T19:44:22Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-23T11:57:14Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-23T12:57:55Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-23T13:16:31Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-23T13:34:43Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-23T17:24:54Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-23T17:29:01Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-24T12:05:23Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-24T12:39:43Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Submitted by Jéssyca Maria da Silva Pestana null (jessycapestana@gmail.com) on 2017-11-24T16:47:37Z No. of bitstreams: 1 d_pestana_jms.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Approved for entry into archive by ALESSANDRA KUBA OSHIRO null (alessandra@fct.unesp.br) on 2017-11-24T17:09:16Z (GMT) No. of bitstreams: 1 pestana_jms_me_prud.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) / Made available in DSpace on 2017-11-24T17:09:16Z (GMT). No. of bitstreams: 1 pestana_jms_me_prud.pdf: 5263535 bytes, checksum: 2a7e37fc45cf0d11dab98f86b0a91969 (MD5) Previous issue date: 2017-09-18 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / A integração de plataformas aéreas e terrestres representa uma solução promissora para diversas aplicações de mapeamento, como projetos rodoviários e ferroviários. Estes sistemas possuem características complementares que permitem a visualização de um objeto na superfície a partir de diferentes perspectivas, além de, quando combinados, minimizarem limitações presentes na utilização individual dos mesmos, como o alcance da região imageada (caso terrestre) e o nível de detalhe dos dados adquiridos (caso aéreo). O problema ao integrar estes sistemas está no estabelecimento de correspondência entre as imagens. A aquisição a partir de diferentes perspectivas gera imagens com geometrias muito diferentes, dificultando o processo de correspondência, de modo que os métodos existentes não consigam solucionar o problema de maneira satisfatória. Com esta motivação, o presente trabalho propõe uma metodologia para o estabelecimento de correspondência entre imagens aéreas e terrestres, baseada na alteração prévia da geometria destas imagens, sendo necessário o conhecimento da orientação das mesmas e de um Modelo Digital do Terreno (MDT). A metodologia parte de pontos bem definidos, identificados na imagem aérea, que são projetados para o terreno e então para a imagem terrestre, definindo origens para os recortes que serão projetados e, posteriormente, submetidos à busca por correspondência. O trabalho apresenta uma revisão do estado da arte no que diz respeito a soluções para o problema de correspondência entre imagens aéreas e terrestres, bem como verifica o desempenho de métodos já existentes na solução do problema. Os experimentos foram baseados em imagens reais adquiridas sobre rodovias. Os resultados obtidos validam a metodologia proposta, mostrando que, ainda que existam limitações, é possível o estabelecimento de correspondência entre imagens aéreas e terrestres, e que este pode ser realizado tanto por métodos baseados em características como por métodos baseados em área. / The integration of aerial and terrestrial platforms represents a promising solution for several mapping applications. These systems have complementary features that allow the visualization of an object on the surface from several perspectives, and, when combined, minimize existing limitations in each individual system, such as the range of the imaged region (terrestrial case) and the level of detail of the acquired data (aerial case). When integrating these systems, the main problem that arises is related to the establishment of corresponding images. The acquisition from different perspectives generates images with very different geometries, hampering the matching process, so that the existing methods cannot solve the problem satisfactorily. With this motivation, the present work proposes a methodology for the establishment of correspondences between aerial and terrestrial images, based on the previous alteration of the geometry of these images, being necessary the knowledge of their orientation and of a Digital Terrain Model (DTM). The methodology starts with well-defined points, identified in the aerial image, that are projected to the terrain and then to the terrestrial image, defining origins for the cutouts that will be projected and later submitted to the correspondence search. The work presents a review of the state of the art regarding solutions of the correspondence between aerial and terrestrial images problem, as well as verifies the performance of existing methods in the solution of the problem. The experiments were based on actual images acquires on highways. The results obtained validate the proposed methodology, showing that, although there are limitation, it is possible to establish correspondence between aerial and terrestrial images, and that this can be done either by feature based methods or by area based methods.