Por ser não-invasiva e de baixo custo, a Ecocardiografia tem se tornado uma técnica de diagnóstico muito utilizada para a determinação dos volumes sistólicos e diastólicos do ventrículo esquerdo a fim de se calcular, indiretamente, o volume de ejeção do ventrículo esquerdo, a razão de contração muscular das cavidades cardíacas, a fração de ejeção regional e global, a espessura do miocárdio e a massa ventricular. Para isso, torna-se necessária a detecção das bordas endocárdicas do ventrículo esquerdo, o que é dificultada pelo fato da imagem de Ecocardiografia possuir ruídos que prejudicam sua definição. Apesar de haver várias técnicas de segmentação de imagem, este trabalho propõe detectar as bordas do ventrículo esquerdo de imagens ecocardiográficas utilizando uma rede neural artificial para reconhecer padrões de bordas. A fim de acelerar o processo e facilitar o processamento, uma área retangular centrada dentro da janela acústica do paciente é determinada pelo operador com o uso do \'mouse\' na qual serão realizadas todas as análises e reconhecimentos de borda pela rede neural. Após a marcação dos pontos reconhecidos pela rede neural como bordas, utilizam-se técnicas de gradientes e contorno móvel para se conectar os pontos de maior probabilidade e traçar a borda do ventrículo esquerdo. Esta técnica mostrou-se eficaz quando comparados com as bordas traçadas pelo especialista, sendo um fator importante a prática do operador ao escolher adequadamente a área a ser analisada. Após treinamento com 50 amostras de padrões de \"borda\" e 10 amostras de padrões de \"não borda\", a técnica foi testada em 108 imagens, alcançando resultados com boa precisão e rapidez quando comparamos os resultados na determinação da área do ventrículo esquerdo com outras técnicas citadas na literatura nacional e internacional. / Being non-invasive and having low cost, the echocardiography has been largely applied as diagnostic technique for left ventricle systolic and diastolic volumes determination that indirectly are used to calculate the left ventricle ejection volume, the cardiac cavities muscular contraction, the regional and global ejection fraction, the myocardial thickness, the ventricular mass, etc. For this reason, the detection of the left ventricle endocardial borders become necessary, but hampered by the noise that impairs the echocardiography images definition. In spite of having many image segmentation techniques, this work intend to detect the borders of left ventricle on echocardiography images by using a artificial neural network to recognize border patterns. To accelerate the process and facilitate the procedure, the operator uses the mouse to define a rectangular region inside the acoustic window of the pacient where all analyses and border recognitions will be accomplished. After labeling the recognized points as \'border\', gradient techniques and mobile boundary are used to connect the points of greater probability and delineate the left ventricle border. This technique has proved to be efficient when compared to the borders traced by the specialist. The ability of the operator is important in choosing of the region to be analyzed. After training with 50 samples of \"border\" pattern and 10 samples of \"no-border\" pattern, this technique was tested on 108 images, achieving good results on precision and velocitiy when we compared the calculated left ventricle area with the results of other techniques published on national and international literature.

<p>Part 1: The bandwidth of the ultrasound Doppler signal is proposed as a classification function of blood and tissue signal in transthoracial echocardiography of the left ventricle. The new echocardiographic mode, Bandwidth Imaging, utilizes the difference in motion between tissue and blood. Specifically, Bandwidth Imaging is the absolute value of the normalized autocorrelation function with lag one. Bandwidth Imaging is therefore linearly dependent on the the square of the bandwidth estimated from the Doppler spectrum. A 2-tap Finite Impulse Response high-pass filter is used prior to autocorrelation calculation to account for the high level of DC clutter noise in the apical regions. Reasonable pulse strategies are discussed and several images of Bandwidth Imaging are included. An in vivo experiment is presented, where the apparent error rate of Bandwidth Imaging is compared with apparent error rate of Second-Harmonic Imaging on 15 healthy men. The apparent error rate is calculated from signal from all myocardial wall segments defined in \cite{Cer02}. The ground truth of the position of the myocardial wall segments is determined by manual tracing of endocardium in Second-Harmonic Imaging. A hypotheses test of Bandwidth Imaging having lower apparent error rate than</p><p>Second-Harmonic Imaging is proved for a p-value of 0.94 in 3 segments of end diastole and 1 segment in end systole on non averaged data. When data is averaged by a structural element of 5 radial, 3 lateral and 4 temporal samples, the numbers of segments are increased to 9 in end diastole and to 6 in end systole. These segments are mostly located in apical and anterior wall regions. Further, a global measure GM is defined as the proportion of misclassified area in the regions close to endocardium in an image. The hypothesis test of Second-Harmonic Imaging having lower GM than Bandwidth Imaging is proved for a p-value of 0.94 in the four-chamber view in end systole in any type of averaging. On the other side, the hypothesis test of Bandwidth Imaging having lower GM than Second-Harmonic Imaging is proved for a p-value of 0.94 in long-axis view in end diastole in any type of averaging. Moreover, if images are averaged by the above structural element the test indicates that Bandwidth Imaging has a lower apparent error rate than Second-Harmonic Imaging in all views and times (end diastole or end systole), except in four-chamber view in end systole. This experiment indicates that Bandwidth Imaging can supply additional information for automatic border detection routines on endocardium.</p><p>Part 2: Knowledge Based Imaging is suggested as a method to distinguish blood from tissue signal in transthoracial echocardiography. This method utilizes the maximum likelihood function to classify blood and tissue signal. Knowledge Based Imaging uses the same pulse strategy as Bandwidth Imaging, but is significantly more difficult to implement. Therefore, Knowledge Based Imaging and Bandwidth Imaging are compared with Fundamental Imaging by a computer simulation based on a parametric model of the signal. The rate apparent error rate is calculated in any reasonable tissue to blood signal ratio, tissue to white noise ratio and clutter to white noise ratio. Fundamental Imaging classifies well when tissue to blood signal ratio is high and tissue to white noise ratio is higher than clutter to white noise ratio. Knowledge Based Imaging classifies also well in this environment. In addition, Knowledge Based Imaging classifies well whenever blood to white noise ratio is above 30 dB. This is the case, even when clutter to white noise ratio is higher than tissue to white noise ratio and tissue to blood signal ratio is zero. Bandwidth Imaging performs similar to Knowledge Based Imaging, but blood to white noise ratio has to be 20 dB higher for a reasonable classification. Also the highpass filter coefficient prior to Bandwidth Imaging calculation is discussed by the simulations. Some images of different parameter settings of Knowledge Based Imaging are visually compared with Second-Harmonic Imaging, Fundamental Imaging and Bandwidth Imaging. Changing parameters of Knowledge Based Imaging can make the image look similar to both Bandwidth Imaging and Fundamental Imaging.</p>

Part 1: The bandwidth of the ultrasound Doppler signal is proposed as a classification function of blood and tissue signal in transthoracial echocardiography of the left ventricle. The new echocardiographic mode, Bandwidth Imaging, utilizes the difference in motion between tissue and blood. Specifically, Bandwidth Imaging is the absolute value of the normalized autocorrelation function with lag one. Bandwidth Imaging is therefore linearly dependent on the the square of the bandwidth estimated from the Doppler spectrum. A 2-tap Finite Impulse Response high-pass filter is used prior to autocorrelation calculation to account for the high level of DC clutter noise in the apical regions. Reasonable pulse strategies are discussed and several images of Bandwidth Imaging are included. An in vivo experiment is presented, where the apparent error rate of Bandwidth Imaging is compared with apparent error rate of Second-Harmonic Imaging on 15 healthy men. The apparent error rate is calculated from signal from all myocardial wall segments defined in \cite{Cer02}. The ground truth of the position of the myocardial wall segments is determined by manual tracing of endocardium in Second-Harmonic Imaging. A hypotheses test of Bandwidth Imaging having lower apparent error rate than Second-Harmonic Imaging is proved for a p-value of 0.94 in 3 segments of end diastole and 1 segment in end systole on non averaged data. When data is averaged by a structural element of 5 radial, 3 lateral and 4 temporal samples, the numbers of segments are increased to 9 in end diastole and to 6 in end systole. These segments are mostly located in apical and anterior wall regions. Further, a global measure GM is defined as the proportion of misclassified area in the regions close to endocardium in an image. The hypothesis test of Second-Harmonic Imaging having lower GM than Bandwidth Imaging is proved for a p-value of 0.94 in the four-chamber view in end systole in any type of averaging. On the other side, the hypothesis test of Bandwidth Imaging having lower GM than Second-Harmonic Imaging is proved for a p-value of 0.94 in long-axis view in end diastole in any type of averaging. Moreover, if images are averaged by the above structural element the test indicates that Bandwidth Imaging has a lower apparent error rate than Second-Harmonic Imaging in all views and times (end diastole or end systole), except in four-chamber view in end systole. This experiment indicates that Bandwidth Imaging can supply additional information for automatic border detection routines on endocardium. Part 2: Knowledge Based Imaging is suggested as a method to distinguish blood from tissue signal in transthoracial echocardiography. This method utilizes the maximum likelihood function to classify blood and tissue signal. Knowledge Based Imaging uses the same pulse strategy as Bandwidth Imaging, but is significantly more difficult to implement. Therefore, Knowledge Based Imaging and Bandwidth Imaging are compared with Fundamental Imaging by a computer simulation based on a parametric model of the signal. The rate apparent error rate is calculated in any reasonable tissue to blood signal ratio, tissue to white noise ratio and clutter to white noise ratio. Fundamental Imaging classifies well when tissue to blood signal ratio is high and tissue to white noise ratio is higher than clutter to white noise ratio. Knowledge Based Imaging classifies also well in this environment. In addition, Knowledge Based Imaging classifies well whenever blood to white noise ratio is above 30 dB. This is the case, even when clutter to white noise ratio is higher than tissue to white noise ratio and tissue to blood signal ratio is zero. Bandwidth Imaging performs similar to Knowledge Based Imaging, but blood to white noise ratio has to be 20 dB higher for a reasonable classification. Also the highpass filter coefficient prior to Bandwidth Imaging calculation is discussed by the simulations. Some images of different parameter settings of Knowledge Based Imaging are visually compared with Second-Harmonic Imaging, Fundamental Imaging and Bandwidth Imaging. Changing parameters of Knowledge Based Imaging can make the image look similar to both Bandwidth Imaging and Fundamental Imaging.

Por ser não-invasiva e de baixo custo, a Ecocardiografia tem se tornado uma técnica de diagnóstico muito utilizada para a determinação dos volumes sistólicos e diastólicos do ventrículo esquerdo a fim de se calcular, indiretamente, o volume de ejeção do ventrículo esquerdo, a razão de contração muscular das cavidades cardíacas, a fração de ejeção regional e global, a espessura do miocárdio e a massa ventricular. Para isso, torna-se necessária a detecção das bordas endocárdicas do ventrículo esquerdo, o que é dificultada pelo fato da imagem de Ecocardiografia possuir ruídos que prejudicam sua definição. Apesar de haver várias técnicas de segmentação de imagem, este trabalho propõe detectar as bordas do ventrículo esquerdo de imagens ecocardiográficas utilizando uma rede neural artificial para reconhecer padrões de bordas. A fim de acelerar o processo e facilitar o processamento, uma área retangular centrada dentro da janela acústica do paciente é determinada pelo operador com o uso do \'mouse\' na qual serão realizadas todas as análises e reconhecimentos de borda pela rede neural. Após a marcação dos pontos reconhecidos pela rede neural como bordas, utilizam-se técnicas de gradientes e contorno móvel para se conectar os pontos de maior probabilidade e traçar a borda do ventrículo esquerdo. Esta técnica mostrou-se eficaz quando comparados com as bordas traçadas pelo especialista, sendo um fator importante a prática do operador ao escolher adequadamente a área a ser analisada. Após treinamento com 50 amostras de padrões de \"borda\" e 10 amostras de padrões de \"não borda\", a técnica foi testada em 108 imagens, alcançando resultados com boa precisão e rapidez quando comparamos os resultados na determinação da área do ventrículo esquerdo com outras técnicas citadas na literatura nacional e internacional. / Being non-invasive and having low cost, the echocardiography has been largely applied as diagnostic technique for left ventricle systolic and diastolic volumes determination that indirectly are used to calculate the left ventricle ejection volume, the cardiac cavities muscular contraction, the regional and global ejection fraction, the myocardial thickness, the ventricular mass, etc. For this reason, the detection of the left ventricle endocardial borders become necessary, but hampered by the noise that impairs the echocardiography images definition. In spite of having many image segmentation techniques, this work intend to detect the borders of left ventricle on echocardiography images by using a artificial neural network to recognize border patterns. To accelerate the process and facilitate the procedure, the operator uses the mouse to define a rectangular region inside the acoustic window of the pacient where all analyses and border recognitions will be accomplished. After labeling the recognized points as \'border\', gradient techniques and mobile boundary are used to connect the points of greater probability and delineate the left ventricle border. This technique has proved to be efficient when compared to the borders traced by the specialist. The ability of the operator is important in choosing of the region to be analyzed. After training with 50 samples of \"border\" pattern and 10 samples of \"no-border\" pattern, this technique was tested on 108 images, achieving good results on precision and velocitiy when we compared the calculated left ventricle area with the results of other techniques published on national and international literature.

La perception est un point clé pour le fonctionnement d'un véhicule autonome ou même pour un véhicule fournissant des fonctions d'assistance. Un véhicule observe le monde externe à l'aide de capteurs et construit un modèle interne de l'environnement extérieur. Il met à jour en continu ce modèle de l'environnement en utilisant les dernières données des capteurs. Dans ce cadre, la perception peut être divisée en deux étapes : la première partie, appelée SLAM (Simultaneous Localization And Mapping) s'intéresse à la construction d'une carte de l'environnement extérieur et à la localisation du véhicule hôte dans cette carte, et deuxième partie traite de la détection et du suivi des objets mobiles dans l'environnement (DATMO pour Detection And Tracking of Moving Objects). En utilisant des capteurs laser de grande précision, des résultats importants ont été obtenus par les chercheurs. Cependant, avec des capteurs laser de faible résolution et des données bruitées, le problème est toujours ouvert, en particulier le problème du DATMO. Dans cette thèse nous proposons d'utiliser la vision (mono ou stéréo) couplée à un capteur laser pour résoudre ce problème. La première contribution de cette thèse porte sur l'identification et le développement de trois niveaux de fusion. En fonction du niveau de traitement de l'information capteur avant le processus de fusion, nous les appelons "fusion bas niveau", "fusion au niveau de la détection" et "fusion au niveau du suivi". Pour la fusion bas niveau, nous avons utilisé les grilles d'occupations. Pour la fusion au niveau de la détection, les objets détectés par chaque capteur sont fusionnés pour avoir une liste d'objets fusionnés. La fusion au niveau du suivi requiert le suivi des objets pour chaque capteur et ensuite on réalise la fusion entre les listes d'objets suivis. La deuxième contribution de cette thèse est le développement d'une technique rapide pour trouver les bords de route à partir des données du laser et en utilisant cette information nous supprimons de nombreuses fausses alarmes. Nous avons en effet observé que beaucoup de fausses alarmes apparaissent sur le bord de la route. La troisième contribution de cette thèse est le développement d'une solution complète pour la perception avec un capteur laser et des caméras stéréo-vision et son intégration sur un démonstrateur du projet européen Intersafe-2. Ce projet s'intéresse à la sécurité aux intersections et vise à y réduire les blessures et les accidents mortels. Dans ce projet, nous avons travaillé en collaboration avec Volkswagen, l'Université Technique de Cluj-Napoca, en Roumanie et l'INRIA Paris pour fournir une solution complète de perception et d'évaluation des risques pour le démonstrateur de Volkswagen. / Perception is one of important steps for the functioning of an autonomous vehicle or even for a vehicle providing only driver assistance functions. Vehicle observes the external world using its sensors and builds an internal model of the outer environment configuration. It keeps on updating this internal model using latest sensor data. In this setting perception can be divided into two sub parts: first part, called SLAM(Simultaneous Localization And Mapping), is concerned with building an online map of the external environment and localizing the host vehicle in this map, and second part deals with finding moving objects in the environment and tracking them over time and is called DATMO(Detection And Tracking of Moving Objects). Using high resolution and accurate laser scanners successful efforts have been made by many researchers to solve these problems. However, with low resolution or noisy laser scanners solving these problems, especially DATMO, is still a challenge and there are either many false alarms, miss detections or both. In this thesis we propose that by using vision sensor (mono or stereo) along with laser sensor and by developing an effective fusion scheme on an appropriate level, these problems can be greatly reduced. The main contribution of this research is concerned with the identification of three fusion levels and development of fusion techniques for each level for SLAM and DATMO based perception architecture of autonomous vehicles. Depending on the amount of preprocessing required before fusion for each level, we call them low level, object detection level and track level fusion. For low level we propose to use grid based fusion technique and by giving appropriate weights (depending on the sensor properties) to each grid for each sensor a fused grid can be obtained giving better view of the external environment in some sense. For object detection level fusion, lists of objects detected for each sensor are fused to get a list of fused objects where fused objects have more information then their previous versions. We use a Bayesian fusion technique for this level. Track level fusion requires to track moving objects for each sensor separately and then do a fusion between tracks to get fused tracks. Fusion at this level helps remove false tracks. Second contribution of this research is the development of a fast technique of finding road borders from noisy laser data and then using these border information to remove false moving objects. Usually we have observed that many false moving objects appear near the road borders due to sensor noise. If they are not filtered out then they result into many false tracks close to vehicle making vehicle to apply breaks or to issue warning messages to the driver falsely. Third contribution is the development of a complete perception solution for lidar and stereo vision sensors and its intigration on a real vehicle demonstrator used for a European Union project (INTERSAFE-21). This project is concerned with the safety at intersections and aims at the reduction of injury and fatal accidents there. In this project we worked in collaboration with Volkswagen, Technical university of Cluj-Napoca Romania and INRIA Paris to provide a complete perception and risk assessment solution for this project.

This thesis deals with digital image stabilization. It contains a brief overview of the problem and available methods for digital image stabilization. The aim was to design and implement image stabilization system in JAVA, which is designed for RapidMiner. Two new stabilization methods have been proposed. The first is based on the motion estimation and motion compensation using Full-search and Three-step search algorithms. The basis of the second method is the detection of object boundaries. The functionality of the proposed method was tested on video sequences with contain visible shake of the scene, which has beed created for this purpose. Testing results show that with the proper set of input parameters for the object border detection method, successful stabilization of the scene is achieved. The rate of error reduction between images is approximately about 65 to 85%. The output of the method is stabilized image sequence and a set of metadata collected during stabilization, which can be further processed in an environment of RapidMiner.