Ecocardiografia fetal é uma importante ferramenta para diagnóstico. Esta tese apresenta um método que provê localização automática de cavidades cardíacas em imagens ecocardiografias fetais, onde o diagnóstico de problemas congênitos do coração pode melhorar os resultados do tratamento. As estruturas de interesse são as quatro cavidades cardíacas (átrio direito, átrio esquerdo, ventrículo direito e ventrículo esquerdo). O método é baseado na busca por cavidades cardíacas através de uma molde de busca (template) para encontrar padrões de interesse. Este molde é calculado usando uma função densidade probabilidade que recebe como parâmetro os níveis de cinza de uma região representativa da cavidade, na imagem. Além disso, em alguns testes também foram utilizadas características espaciais da imagem para cálculo do molde de busca. Nesse sentido a busca é implementada de uma forma hierárquica: (i) primeiro, é localizada a região do coração; e (ii) em seguida, baseando na região do coração a cavidade de interesse á buscada. A comparação do molde de busca e as regiões de interesse na imagem é feita utilizando o Coeficiente de Bhattacharyya, o qual é analisado ao longo dos testes para justificar sua escolha. Uma das principais características do método é a invariância a rotação apresentada pelas estruturas. / Fetal echocardiography is an important tool for diagnosing. This thesis presents a method to provide automatic localization of cardiac cavities in fetal echocardiography images, where the early diagnostics of heart congenital diseases can greatly improve results from medical treatment. The structures of interest are the four cardiac cavities (left and right atrium, left and right ventricle). The method is based in the search of cardiac structures with a mold to find the pattern of interest. This mold is calculated using a probability density function that receives as parameter the gray level of a representative image and also uses spatial features of the images to calculate the mold. A hierarchical search is performed: (i) first, the region of interest is covered to locate the heart; and (ii) based on the position of the heart, the desired structure is found in the image. The comparison of the mold and the candidate image is made using the Bhattacharyya coefficient, which our experimental tests have shown good results. One of the main characteristics of the method is its rotation invariance.

Ecocardiografia fetal é uma importante ferramenta para diagnóstico. Esta tese apresenta um método que provê localização automática de cavidades cardíacas em imagens ecocardiografias fetais, onde o diagnóstico de problemas congênitos do coração pode melhorar os resultados do tratamento. As estruturas de interesse são as quatro cavidades cardíacas (átrio direito, átrio esquerdo, ventrículo direito e ventrículo esquerdo). O método é baseado na busca por cavidades cardíacas através de uma molde de busca (template) para encontrar padrões de interesse. Este molde é calculado usando uma função densidade probabilidade que recebe como parâmetro os níveis de cinza de uma região representativa da cavidade, na imagem. Além disso, em alguns testes também foram utilizadas características espaciais da imagem para cálculo do molde de busca. Nesse sentido a busca é implementada de uma forma hierárquica: (i) primeiro, é localizada a região do coração; e (ii) em seguida, baseando na região do coração a cavidade de interesse á buscada. A comparação do molde de busca e as regiões de interesse na imagem é feita utilizando o Coeficiente de Bhattacharyya, o qual é analisado ao longo dos testes para justificar sua escolha. Uma das principais características do método é a invariância a rotação apresentada pelas estruturas. / Fetal echocardiography is an important tool for diagnosing. This thesis presents a method to provide automatic localization of cardiac cavities in fetal echocardiography images, where the early diagnostics of heart congenital diseases can greatly improve results from medical treatment. The structures of interest are the four cardiac cavities (left and right atrium, left and right ventricle). The method is based in the search of cardiac structures with a mold to find the pattern of interest. This mold is calculated using a probability density function that receives as parameter the gray level of a representative image and also uses spatial features of the images to calculate the mold. A hierarchical search is performed: (i) first, the region of interest is covered to locate the heart; and (ii) based on the position of the heart, the desired structure is found in the image. The comparison of the mold and the candidate image is made using the Bhattacharyya coefficient, which our experimental tests have shown good results. One of the main characteristics of the method is its rotation invariance.

Submitted by Patrícia Cerveira (pcerveira1@gmail.com) on 2017-06-07T18:57:51Z No. of bitstreams: 1 Fernando Otávio Gomes da Fonseca_Dissertação.pdf: 3191276 bytes, checksum: f567916527bd35630c5b6be3fb1b0c6e (MD5) / Approved for entry into archive by Biblioteca da Escola de Engenharia (bee@ndc.uff.br) on 2017-06-29T16:27:45Z (GMT) No. of bitstreams: 1 Fernando Otávio Gomes da Fonseca_Dissertação.pdf: 3191276 bytes, checksum: f567916527bd35630c5b6be3fb1b0c6e (MD5) / Made available in DSpace on 2017-06-29T16:27:45Z (GMT). No. of bitstreams: 1 Fernando Otávio Gomes da Fonseca_Dissertação.pdf: 3191276 bytes, checksum: f567916527bd35630c5b6be3fb1b0c6e (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / O presente trabalho visa estudar e comparar 2 métodos de detecção de faces em imagens, a fim de averiguar a eficiência e eficácia dos mesmos, propondo melhorias nos processos avaliados. O método de detecção de caraterísticas em imagens proposto por Viola e Jones é ainda uma referência na detecção de faces. Neste trabalho serão avaliadas propostas de melhorias nesse processo e comparados resultados quando utilizadas redes neurais mais modernas para o treinamento da base de dados. Realizamos simulações computacionais desenvolvidas em Matlab para obtenção dos resultados do comportamento dos sistemas e ao final do trabalho apresentamos as conclusões e sugestões de projetos futuros. / This work aims to study and compare two methods of face detection in images, in order to verify theirefficiency and effectiveness, proposing improvements in such processes. The feature detection method in images proposed by Viola and Jones is also a reference in detecting faces. In this work improvement proposals will be evaluated in thatprocess and compared results when used more modern neural networks for the training database. We performed computer simulations developed in Matlab to obtain theresults onsystems behavior. At the endof the work,we present the conclusions and suggestions for future projects.

Feature detection and matching is an important step in many object tracking and detection algorithms. This paper discusses methods to improve upon previous work on the SYnthetic BAsis feature descriptor (SYBA) algorithm, which describes and compares image features in an efficient and discreet manner. SYBA utilizes synthetic basis images overlaid on a feature region of interest (FRI) to generate binary numbers that uniquely describe the feature contained within the FRI. These binary numbers are then used to compare against feature values in subsequent images for matching. However, in a non-ideal environment the accuracy of the feature matching suffers due to variations in image scale, and rotation. This paper introduces a new version of SYBA which processes FRI’s such that the descriptions developed by SYBA are rotation and scale invariant. To demonstrate the improvements of this robust implementation of SYBA called rSYBA, included in this paper are applications that have to cope with high amounts of image variation. The first detects objects along an oil pipeline by transforming and comparing frame-by-frame two surveillance videos recorded at two different times. The second shows camera pose plotting for a ground based vehicle using monocular visual odometry. The third generates panoramic images through image stitching and image transforms. All applications contain large amounts of image variation between image frames and therefore require a significant amount of correct feature matches to generate acceptable results.

No description available.

A cornerstone in the industry's ongoing digital revolution, which is sometimes referred to as Industry 4.0, is the ability to trace products not only within the own production line but also throughout the remaining lifetime of the products. Traditionally, this is done by labeling products with, for instance, bar codes or radio-frequency identification (RFID) tags. In recent years, using the structure of the product itself as a unique identifier, a "fingerprint", has become a popular area of research. The purpose of this work was to develop software for an identification system using laser speckles as a unique identifier of steel components. Laser speckles, or simply speckles, are generated by illuminating a rough surface with coherent light, typically laser light. As the light is reflected, the granular pattern known as speckles can be seen by an observer. The complex nature of a speckle pattern together with its sensitivity to changes in the setup makes it robust against false-positive identifications and almost impossible to counterfeit. Because of this, speckles are suitable to be used as unique identifiers. In this work, three different identification algorithms have been tested in both simulations and experiments. The tested algorithms included one correlation-based, one method based on local feature extraction, and one method based on global feature extraction. The results showed that the correlation-based identification is most robust against speckle decorrelation, i.e changes in the speckle pattern, while being quite computationally expensive. The local feature-based method was shown to be unfit for this current application due to its sensitivity to speckle decorrelation and erroneous results. The global feature extraction method achieved high accuracy and fast computational speed when combined with a clustering method based on overlapping speckle patterns and a k-nearest neighbours (k-NN) search. In all the investigated methods, parallel calculations can be utilized to increase the computational speed.

Vision based object recognition and localization have been studied widely in recent years. Often the initial step in such tasks is detection of interest points from a grey-level image. The current state-of-the-art algorithms in this domain, like Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) suffer from low execution speeds on a GPU(graphic processing unit) based system. Generally the performance of these algorithms on a GPU is below real-time due to high computational complexity and data intensive nature and results in elevated power consumption. Since real-time performance is desirable in many vision based applications, hardware based feature detection is an emerging solution that exploits inherent parallelism in such algorithms to achieve significant speed gains. The efficient utilization of resources still remains a challenge that directly effects the cost of hardware. This work proposes a novel hardware architecture for scale-space extrema detection part of the SIFT algorithm. The implementation of proposed architecture for Xilinx Virtex-4 FPGA and its evaluation are also presented. The implementation is sufficiently generic and can be adapted to different design parameters efficiently according to the requirements of application. The achieved system performance exceeds real-time requirements (30 frames per second) on a 640 x 480 image. Synthesis results show efficient resource utilization when compared with the existing known implementations.

What people take for granted is not as easy for computers. Being able tojudge whether an image is the same even though it has a differentresolution or is taken from a different angle or light condition is easyfor humans but much more difficult for computers. Today’s mobiles aremore powerful than ever, which has opened up for more hardware-demandingalgorithms to be processed. How to effectively match handwritten notesto eliminate duplicates in an application. Are there better or worsemethods and approaches, and how do they compare to each other? Can youachieve both accuracy and speed? By analyzing images taken at differentangles, distances, and lighting conditions, different methods andapproaches have been developed and analyzed. The methods are representedin various tables where time and accuracy are represented. Eightdifferent methods were evaluated. The methods were tuned on one datasetconsisting of 150 post-it notes, each imaged under four conditions,leading to 600 images and 1800 possible pair-wise matches. The methodswere thereafter evaluated on an independent dataset consisting of 250post-it notes, each imaged under four conditions, leading to 1000 imagesand 3000 possible pair-wise matches. The best method found 99.7%, andthe worst method found 62.9% of the matching pairs. Seven of the eightevaluated matches did not make any incorrect matches. / Det människor tar för givet är inte lika lätt för datorer. Att kunna bedöma om en bild är den samma fast den har annan upplösning eller är tagen från en annan vinkel eller ljusförhållande är lätt för människor men betydligt svårare för datorer. Dagens mobiler är kraftfullare än någonsin vilket har öppnat upp för att mer hårdvaru krävande algoritmer kan processas. Hur matchar man handskrivna lappar på ett effektivt sätt för att eliminera kopior i en applikation. Finns det bättre eller sämre metoder och tillvägagångssätt, och hur står de gentemot varandra? Kan man uppnå både träffsäkerhet samt snabbhet? Genom att analysera bilder tagna får olika vinklar, avstånd samt ljusförhållanden har olika metoder och tillvägagångssätt utvecklats och analyserats. Metoderna är representerade i olika tabeller där tid, samt träffsäkerhet redovisas. Åtta olika metoder utvärderades. Metoderna ställdes in på ett dataset bestående av 150 post-it-lappar, var och en fotograferade under fyra förhållanden, vilket ledde till 600 bilder och 1800 möjliga matchningar. Metoderna utvärderades därefter på ett oberoende dataset bestående av 250 post-it-lappar, var och en fotograferade under fyra förhållanden, vilket ledde till 1000 bilder och 3000 möjliga matchningar. Den bästa metoden fann 99,7% och den sämsta metoden hittade 62,9% av de matchande paren. Sju av de åtta utvärderade metoderna gjorde inga felaktiga matchningar.

This research has been conducted in order to create a robust, lightweight feature detecting and matching algorithm that builds upon the foundation set by the TreeBASIS algorithm. The goal is to create a color-based version of the TreeBASIS algorithm that uses less hardware resources than the original, is more accurate in its matching capabilities, can successfully be deployed on a resource-limited FPGA platform, and can process in real time. This thesis first presents the newly designed hardware tri-channel FAST Feature Detector that finds features in color. Next the TreeBASIS algorithm is analyzed to discover what improvements can be made in order to reduce its resource usage sufficiently to be able to run on the Xilinx Virtex-4 FX60 while processing color features. At the same time, a software version of the Color TreeBASIS algorithm is compared to the original algorithm and is found to have a 93.3% accuracy on a test set of aerial images, surpassing the accuracy of TreeBASIS by nearly 12%. Then the hardware is meticulously reviewed to discover even more optimizations that allow the Color TreeBASIS algorithm to easily fit onto the Virtex-4 FX60. Next a new application for the matching algorithm, object detection, is introduced as well as the hardware needed to support it. Finally the algorithm is tested on the FPGA system for object detection and is able to successfully identify objects at 60 FPS. Color TreeBASIS proves itself to be more accurate than the TreeBASIS algorithm in the aerial images tests, it ends up using less memory and logic resources than its predecessor, even though it processes three times as much data, it is successfully deployed on a resource-limited FPGA system, and it shows accurate results in real-time object identification, generating an accurate homography 20 to 45% of the time while processing matches at a rate of 60 FPS.

À mesure que la population des personnes agées dans les pays industrialisés augmente au fil de années, les ressources nécessaires au maintien du niveau de vie de ces personnes augmentent aussi. Des statistiques montrent que les chutes sont l’une des principales causes d’hospitalisation chez les personnes agées, et, de plus, il a été démontré que le risque de chute d’une personne agée a une correlation avec sa capacité de maintien de l’équilibre en étant debout. Il est donc d’intérêt de développer un système automatisé pour analyser l’équilibre chez une personne, comme moyen d’évaluation objective. Dans cette étude, nous avons proposé l’implémentation d’un tel système. En se basant sur une installation simple contenant une seule caméra sur un trépied, on a développé un algorithme utilisant une implémentation de la méthode de détection d’objet de Viola-Jones, ainsi qu’un appariement de gabarit, pour suivre autant le mouvement latéral que celui antérieur-postérieur d’un sujet. On a obtenu des bons résultats avec les deux types de suivi, cependant l’algorithme est sensible aux conditions d’éclairage, ainsi qu’à toute source de bruit présent dans les images. Il y aurait de l’intérêt, comme développement futur, d’intégrer les deux types de suivi, pour ainsi obtenir un seul ensemble de données facile à interpréter. / As the senior population in developed countries increases, so will the resources dedicated to maintaining a high standard of life for the elderly. Statistics show that falls are one of the main causes of senior citizens being hospitalized. Furthermore, it has been shown that the risk of an elderly person falling is correlated to their ability to maintain their balance during standing position. It is then of interest to develop an automated system to evaluate a subject’s balance, or postural sway, as a means of objective evaluation. In this study we have proposed the implementation of such a system. Based on a simple setup of one camera on a tripod, we have developed an algorithm using the Viola-Jones implementation, as well as template matching, to track both lateral and anterior-posterior postural sway. We have obtained good results for both types of tracking, however, the tracking algorithm is sensitive to lighting conditions and any kind of noise in the images. It would be of interest, as a future development, to integrate both types of tracking, so as to obtain only one easily-interpretable dataset as a result.