The goal of this thesis is to develop a smartphone application for augmented reality view; it is an initial attempt to realize a driver assistance functionality using just a smartphone and an external lens. Initially it depicts a brief analysis about the most feasible development technologies for mobile application development, selecting a proper lens and positioning of the smartphone in the car. Later, it discusses the strategies for real-time object detection using OpenCV; the video frames are processed using the strategies to find patterns in the videos. Different techniques like Hough-line transform, watershed, contour detection, color segmentation, color thresholding and HAAR cascades are implemented and compared in terms of real time detection of the desired objects. Then a unified algorithm is implemented for the given scenario which overcomes the challenges faced during the conceptualization phase. Finally, the results are depicted with the snapshots of the real time detection done from the smartphone and then evaluated against the vision of the application and the achieved tasks. This thesis is concluded by stating the prospects of this mobile application in the future.

3D representation nowadays has attracted much more public attention than ever before. One of the most important techniques in this field is depth extraction. In this thesis, we first introduce a well-known stereo matching method using color segmentation and belief propagation, and make an implementation of this framework. The color-segmentation based stereo matching method performs well recently, since this method can keep the object boundaries accurate, which is very important to depth map. Based on the implemented framework of segmentation based stereo matching, we proposed a color segmentation based 2D-to-3D video conversion method using high quality motion information. In our proposed scheme, the original depth map is generated from motion parallax by optical flow calculation. After that we employ color segmentation and plane estimation to optimize the original depth map to get an improved depth map with sharp object boundaries. We also make some adjustments for optical flow calculation to improve its efficiency and accuracy. By using the motion vectors extracted from compressed video as initial values for optical flow calculation, the calculated motion vectors are more accurate within a shorter time compared with the same process without initial values. The experimental results shows that our proposed method indeed gives much more accurate depth maps with high quality edge information. Optical flow with initial values provides good original depth map, and color segmentation with plane estimation further improves the depth map by sharpening its boundaries.

This paper deals with traffic signs recognition. Red color area is obtained by thresholding in HSV color model. Selected radiometric deskriptors, Hough transform deskriptors and neural networs are used to classification. In conclusion has been designed complex decision algorithm.

In this thesis, a new algorithm is proposed for the recognition of triangular, circular and rectangular traffic signs and it is implemented on an FPGA platform. The system can recognize 32 different traffic signs with high recognition accuracy. In the proposed method, first the image is segmented into red and blue regions, and according to the area of the each segment, the dominant color is decided. Then, Laplacian of Gaussian (LoG) based edge detection is applied to the segmented image which is followed by Hough Transform for shape extraction. Then, recognition based on Informative Pixel Percentage (IPP) matching is executed on the extracted shapes. The Traffic Sign Recognition (TSR) system is implemented on Virtex 5 FX70T FPGA, which has an embedded PPC440 processor. Some modules of TSR algorithm are designed in the FPGA logic while remaining modules are designed in the PPC440 processor. Work division between FPGA and PPC440 is carried out considering their capabilities and shortcomings of FPGA and processor. Benefits of using an FPGA with an embedded processor are exploited to optimize the system.

This diploma thesis deals with the issue of the recognition of road signs in the video sequence. Such systems increase the traffic safety and are implemented by major car factories in the manufactured cars (Opel, BMW). First, the motivation for the utilisation of these systems is presented, followed by the survey of the current state of the art methods. Finally, a specific road-sign detection method is chosen and described in detail. The method uses advanced techniques of signal processing. Segmentation method in color space is used for sign detection and subsequent classification is accomplished by linear classification with optional use of PCA method. In addition, the method contains the prediction of road sign positions based on Kalman filtering. Implemented system yields relatively accurate results and overall analysis and discussion is enclosed.

The goal of this thesis is to develop a smartphone application for augmented reality view; it is an initial attempt to realize a driver assistance functionality using just a smartphone and an external lens. Initially it depicts a brief analysis about the most feasible development technologies for mobile application development, selecting a proper lens and positioning of the smartphone in the car. Later, it discusses the strategies for real-time object detection using OpenCV; the video frames are processed using the strategies to find patterns in the videos. Different techniques like Hough-line transform, watershed, contour detection, color segmentation, color thresholding and HAAR cascades are implemented and compared in terms of real time detection of the desired objects. Then a unified algorithm is implemented for the given scenario which overcomes the challenges faced during the conceptualization phase. Finally, the results are depicted with the snapshots of the real time detection done from the smartphone and then evaluated against the vision of the application and the achieved tasks. This thesis is concluded by stating the prospects of this mobile application in the future.

O uso da visão computacional vem ganhando espaço no contexto agrícola, especialmente com a evolução do conceito da agricultura de precisão. Aplicações como irrigação, fertilização e controle de pragas são apenas alguns dos cenários que essa tecnologia pode atender. Entretanto, a demanda por sistemas acessíveis e eficientes aliada às inconstâncias e ruídos visuais de um ambiente externo, apresentam desafios a estes processos. Foi proposto neste trabalho uma análise da literatura e uma série de investidas experimentais de técnicas de processamento de imagens, para buscar melhores relações entre custo computacional e desempenho da detecção de mudas de plantas, visando atingir operações em tempo real com o uso de hardwares comuns e de baixo custo. Para tanto o trabalho investiga a composição de estratégias de segmentação a partir de diferentes espaços de cor e métodos de constância de cor, de forma a reduzir a variação luminosa, uma das maiores fontes de instabilidade nas aplicações de visão na agricultura. Os experimentos propostos foram divididos em duas fases; na primeira o sistema de medidas foi avaliado, definindo as métricas e condições experimentais adequadas para a segunda fase, composta de uma sequência de experimentos comparativos entre estratégias de segmentação sob diferentes condições de iluminação. Os resultados mostraram que as soluções são muito dependentes das condições da cena e uma série de alternativas promissoras de segmentação foram obtidas. Sua elegibilidade, porém, depende de considerações sobre a disponibilidade computacional e contexto de aplicação. / The use of computer vision has been gaining ground in the agricultural context, especially with the evolution of the concept of precision agriculture. Applications such as irrigation, fertilization and pest control are just some of the scenarios that this technology can be used. However, the demand for accessible and efficient systems together with the variations and visual noise from an external environment presents challenges to these processes. It was proposed in this study an analysis of the literature and a series of experimental investigations of image processing techniques, to search for better relations between computational cost and performance in the detection of seedlings, aiming to achieve real time operations with the use of common and low cost hardware. For this, the work investigates the composition of segmentation strategies from different color spaces and color constancy methods, in order to combat light variation, one of the major sources of instability in agricultural vision applications. The proposed experiments were divided into two phases; in the first the measurement system was evaluated, defining the metrics and suitable conditions for the experiments at second phase, composed of a sequence of comparative experiments of segmentation strategies under different lighting conditions. The results showed that the solutions are very dependent on the conditions of the scene and a series of promising segmentation alternatives were obtained. Their eligibility, however, depends on considerations about the computational availability and context of the application.

In this thesis, detection of traffic signs is studied. Since, both color and shape properties of traffic signs are distinctive / these two properties have been employed for detection. Detection using color properties is studied in two different color domains in order to examine and compare the advantages and the disadvantages of these domains for detection purposes. In addition to their color information, shape information is also employed for detection purpose. Edge information (obtained by using the Sobel Operator) of the images/frames is considered as search domain to find triangular, rectangular, octagonal and circular traffic signs. In order to improve the performance of detection process a joint implementation of shape and color based algorithms is utilized. Two different methods have been used v in order to combine these two features. Both of the algorithms help reducing the number of pixels to check whether they belong to a sign or not. This, of course, reduces the processing time of detection process. Each utilized algorithm is tested and compared with the others by using both static images from different sources and video streams. Images having adverse properties are used in order to state algorithms response for some specific conditions such as bad illumination and shadow. After implementation, results show that joint implementation of the color and shape based detection algorithms produces more accurate results. Moreover, joint implementation reduces the processing time of the detection process when compared to application of algorithms individually since it diminishes the search domain.

Submitted by Erika Demachki (erikademachki@gmail.com) on 2015-10-23T18:23:32Z No. of bitstreams: 2 Dissertação - Rafael Divino Ferreira Feitosa - 2015.pdf: 7893703 bytes, checksum: 12af470c3ca2fb4a3d0bd3885bfde46d (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Erika Demachki (erikademachki@gmail.com) on 2015-10-23T18:25:45Z (GMT) No. of bitstreams: 2 Dissertação - Rafael Divino Ferreira Feitosa - 2015.pdf: 7893703 bytes, checksum: 12af470c3ca2fb4a3d0bd3885bfde46d (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2015-10-23T18:25:45Z (GMT). No. of bitstreams: 2 Dissertação - Rafael Divino Ferreira Feitosa - 2015.pdf: 7893703 bytes, checksum: 12af470c3ca2fb4a3d0bd3885bfde46d (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2015-04-14 / Skin detection techniques are widely applied to locate and to track parts of the human body with the objective of posterior recognition, having received great attention in recent years in the development of research in reason to the innumerable possible applications with the detection and tracking of faces, identification of naked people, identification of hand movements, among others. The present work proposed the construction of mathematical models for the detection of human skin tones such as, white, yellow, brown and black in digital color images in the RGB and HSV color spaces. Using a set of human skin tone samples, mathematical models were constructed describing how the variables of each color pixel in the RGB and HSV systems interrelate. To understand the answer of the proposed system, the mechanistic model was chosen, dividing it into components, observing the behavior of each part and the interactions that occurred between them. The proposed RGB filter reached a 98.3657% reduction index of the spectrum, classifying only 1.6343% (253,159 tones) as possible skin tones and the HSV model reduced the likely spectrum to 2.5352% (94,030 tones), discarding 97.4648% of the colors as candidates for human skin tones. When the proposed filters, were applied to the reduction of the probable range of human skin tones, well-defined bands in the geometric representation of the color spaces were selected. The experimental validation of the effectiveness of the RGB model showed that the proposed filter has conservative characteristics in the detection of skin, mistakenly classifying as skin only 6.7163% of the sample space. The proposed RGB filter has low sensitivity of 61.0831% and high specificity of 95.2769% in the detection of human skin in digital images. The HSV model had rates of (54,6333%) low sensitivity and (92,6390%) high specificity, considered low when compared to the performance of the other algorithms. / Técnicas de detecção de pele são amplamente aplicadas para localizar e rastrear partes do corpo humano com o objetivo de posterior reconhecimento, tendo recebido nos últimos anos grande atenção no desenvolvimento de pesquisas em razão das inúmeras aplicações possíveis como detecção e rastreamento de faces, identificação de pessoas nuas, identificação de movimentos das mãos, entre outras. O presente trabalho propôs construir 2 modelos matemáticos para detecção de tons de pele humana branca, amarela, parda e preta em imagens digitais coloridas nos espaços de cores RGB e HSV. Utilizandose de um conjunto de amostras de tons de pele humana foram construídos modelos matemáticos que descrevem como as variáveis de cada pixel de cor nos sistemas RGB e HSV se relacionam. Para compreender a resposta do sistema proposto, foi escolhido o modelo mecanístico, dividindo-o em componentes e observando o comportamento de cada parte e das interações que ocorreram entre elas. O filtro RGB proposto alcançou o índice de redução de 98,3657% do espectro, classificando apenas 1,6343% (253.159 tons) como possíveis tons de pele e o modelo HSV reduziu para 2,5352% (94.030 tons) o espectro provável, descartando 97,4648% das cores como candidatas a tons de pele humana. Os filtros propostos, quando aplicados à redução do espectro provável de tons de pele humana, selecionaram faixas bem definidas na representação geométrica dos espaços de cores. A validação experimental da eficácia do modelo RGB mostrou que o filtro proposto apresenta características conservadoras na detecção de pele classificando como pele, erroneamente, apenas 4,5075% do espaço amostral. O filtro RGB proposto possui baixa sensibilidade de 56,9698% e elevada especificidade de 95,4925% na detecção de pele humana em imagens digitais. O modelo HSV apresentou taxas de baixa sensibilidade (54,6333%) e alta especificidade (92,6390%), quando comparadas ao desempenho dos demais algoritmos propostos na literatura.

O uso da visão computacional vem ganhando espaço no contexto agrícola, especialmente com a evolução do conceito da agricultura de precisão. Aplicações como irrigação, fertilização e controle de pragas são apenas alguns dos cenários que essa tecnologia pode atender. Entretanto, a demanda por sistemas acessíveis e eficientes aliada às inconstâncias e ruídos visuais de um ambiente externo, apresentam desafios a estes processos. Foi proposto neste trabalho uma análise da literatura e uma série de investidas experimentais de técnicas de processamento de imagens, para buscar melhores relações entre custo computacional e desempenho da detecção de mudas de plantas, visando atingir operações em tempo real com o uso de hardwares comuns e de baixo custo. Para tanto o trabalho investiga a composição de estratégias de segmentação a partir de diferentes espaços de cor e métodos de constância de cor, de forma a reduzir a variação luminosa, uma das maiores fontes de instabilidade nas aplicações de visão na agricultura. Os experimentos propostos foram divididos em duas fases; na primeira o sistema de medidas foi avaliado, definindo as métricas e condições experimentais adequadas para a segunda fase, composta de uma sequência de experimentos comparativos entre estratégias de segmentação sob diferentes condições de iluminação. Os resultados mostraram que as soluções são muito dependentes das condições da cena e uma série de alternativas promissoras de segmentação foram obtidas. Sua elegibilidade, porém, depende de considerações sobre a disponibilidade computacional e contexto de aplicação. / The use of computer vision has been gaining ground in the agricultural context, especially with the evolution of the concept of precision agriculture. Applications such as irrigation, fertilization and pest control are just some of the scenarios that this technology can be used. However, the demand for accessible and efficient systems together with the variations and visual noise from an external environment presents challenges to these processes. It was proposed in this study an analysis of the literature and a series of experimental investigations of image processing techniques, to search for better relations between computational cost and performance in the detection of seedlings, aiming to achieve real time operations with the use of common and low cost hardware. For this, the work investigates the composition of segmentation strategies from different color spaces and color constancy methods, in order to combat light variation, one of the major sources of instability in agricultural vision applications. The proposed experiments were divided into two phases; in the first the measurement system was evaluated, defining the metrics and suitable conditions for the experiments at second phase, composed of a sequence of comparative experiments of segmentation strategies under different lighting conditions. The results showed that the solutions are very dependent on the conditions of the scene and a series of promising segmentation alternatives were obtained. Their eligibility, however, depends on considerations about the computational availability and context of the application.