Benchmark Evaluation of HOG Descriptors as Features for Classification of Traffic Signs

The purpose of this paper is to analyze the performance of the Histograms of Oriented Gradients (HOG) as descriptors for traffic signs recognition. The test dataset consists of speed limit traffic signs because of their high inter-class similarities.   HOG features of speed limit signs, which were extracted from different traffic scenes, were computed and a Gentle AdaBoost classifier was invoked to evaluate the different features. The performance of HOG was tested with a dataset consisting of 1727 Swedish speed signs images. Different numbers of HOG features per descriptor, ranging from 36 features up 396 features, were computed for each traffic sign in the benchmark testing. The results show that HOG features perform high classification rate as the Gentle AdaBoost classification rate was 99.42%, and they are suitable to real time traffic sign recognition. However, it is found that changing the number of orientation bins has insignificant effect on the classification rate. In addition to this, HOG descriptors are not robust with respect to sign orientation.

A morfodinâmica praial como subsídio ao gerenciamento costeiro : o caso da Praia de Fora - Parque Estadual de Itapuã, RS

O Parque Estadual de Itapuã é considerado a última área representativa dos ecossistemas originais da região metropolitana de Porto Alegre, sendo que nos últimos 11 anos somente foi permitida a entrada de pesquisadores em suas dependências. Após este longo período em que esteve fechado, o Parque voltará a receber turistas no início de 2002, sendo que os principais destinos serão as praias. Dentre as oito praias existentes na área, somente três serão abertas à visitação, sendo a Praia de Fora a maior delas e a única voltada para a Lagoa dos Patos. Com objetivo de fornecer subsídios para o gerenciamento da Praia de Fora, efetuou-se a análise de uma série de parâmetros morfodinâmicos consagrados na literatura mundial, aprimorando o nível de conhecimento desta praia e suas relações com a Lagoa dos Patos. Para tanto, utilizou-se os modelos de praias de Banco Único e de Bancos Múltiplos da chamada Escola Australiana com a aplicação dos seguintes parâmetros: Parâmetro Adimensional Omega (Ù), Omega Teórico (Ùterorico), Parâmetro de Banco (B), Declividade da Face de Praia (Tang ß) e Parâmetro Dimensionador de Surfe (surf scaling parameter). Outros modelos utilizados foram o Perfil de Equilíbrio de DEAN (1973), o modelo de Transporte Longitudinal dos sedimentos da zona de surfe, (SPM, 1984), o Limite Externo e Limite Interno (Profundidade de Fechamento) e o modelo de Sentido Preferencial de Transporte Perpendicular (SUNAMURA & TAKEDA, 1984). Além destes, optou-se por realizar uma análise temporal da variação da linha de praia da Praia de Fora no período entre 1978 e 2001. Os resultados obtidos indicam um ambiente com uma grande variação energética anual, sendo que a largura da face praial apresentou variações de até 16 m e a declividade de 2,8° a 11.3°. A análise dos parâmetros morfodinâmicos indicou uma praia com grande alternância de estágios morfodinâmicos, que reflete a presença de uma zona de transporte de sedimentos muito intenso por ação de ondas até a profundidade de 0,90 m, uma zona de transporte significativo entre 0,90 e 5 m e uma zona de transporte incipiente para as profundidades maiores que 6 m. O transporte no sentido longitudinal, apresenta uma bidirecionalidade com uma pequena resultante para SE e em sentido transversal apresenta uma maior incidência de transporte da zona de surfe para a antepraia, caracterizando setores erosivos na Praia de Fora. Estes setores erosivos foram detectados em 58% da extensão da Praia de Fora com uma taxa média de 3,75 m por ano. Já em 14% da extensão da praia foi observado acresção e em 28% da praia não houve variação significativa da posição da linha de praia. As taxas médias de deposição chegaram a 1,75 m por ano. A sistematização de todos os resultados permitiu a elaboração de subsídios para o gerenciamento da Praia de Fora. São eles: análise dos riscos para a segurança de banhistas na praia, manejo de dunas, restrições a explotação de areia de fundo nas adjacências da Praia de Fora e delimitação submersa do Parque de Itapuã junto à cota batimétrica dos –6m. Esta delimitação aumentaria em aproximadamente 10.920 hectares ou 196 %, a área atual de preservação do Parque de Itapuã.

Teores de licopeno e ácido ascórbico em morangos cv. Vila Nova produzidos em sistemas de cultivo orgânico e convencional

Na passagem para o século XX, a agricultura sofreu transformações no modelo de produção. Atualmente, a maior parte dos alimentos são produzidos no modelo da agricultura convencional baseada na utilização intensiva de insumos químicos e alta produtividade, em contraponto, a agricultura orgânica está alicerçada na independência de insumos externos e na qualidade dos alimentos. O morango (Fragaria x Ananassa Duch), reconhecido por suas vitaminas e compostos quimioprotetores, tais como o ácido ascórbico e licopeno, é uma cultura produzida tanto no sistema orgânico, quanto no convencional. Entretanto, não existem informações sobre os tipos de sistemas existentes dentro destas duas formas de fazer agricultura e nem dados sobre os conteúdos de ácido ascórbico e de licopeno. Os objetivos deste trabalho foram: tipificar os sistemas de cultivo praticados e identificar as características básicas da produção de morango em Porto Alegre; quantificar os indicadores nutricionais licopeno e ácido ascórbico em morangos cv. Vila Nova, oriundos de diferentes sistemas de cultivo e avaliar a possibilidade dessas substâncias servirem como descritores da qualidade biológica dos frutos produzidos nestas diferentes formas de fazer agricultura. Foram escolhidos cinco sistemas de produção de morangos no bairro Lami, Porto Alegre/RS, sendo duas propriedades orgânicas (OJ, OS) e três convencionais (CN, CP, CB) Para a tipificação foi usada à observação participativa com registro dos dados sobre a intensidade dos componentes de cultivo (manejos, adubação, controle fitossanitário, técnicas de irrigação) e sócio-econômicos. Para medir os teores de licopeno e ácido ascórbico foram cultivados morangos cv. Vila Nova, os quais foram colhidos maduros e analisados. Dentro do sistema convencional existe uma intensidade variada na utilização de insumos. No sistema orgânico um foi tipificado como agroecológico e outro como em final de transição para o orgânico. Os sistemas convencionais têm alta demanda por produtos externos, principalmente em relação à adubação (adubos minerais de alta solubilidade), irrigação (mangueiras, etc) e controle fitossanitário (produtos químicos de síntese) e os sistemas orgânicos apresentam uma baixa dependência externa em relação ao controle fitossanitários, irrigação e manejo. Eles apresentaram dependência de adubos orgânico de origem animal. Os resultados demonstraram que o conteúdo de licopeno variou de 0,033 a 0,063 mg/100g de peso fresco e que ele não foi eficiente como descritor da qualidade hortícola de morangos cultivados em sistemas orgânicos e convencionais. O conteúdo de ácido ascórbico foi de 30,05 a 69,39 mg/100g de peso fresco. Esta vitamina não discrimina diferenças entre os sistemas, e não pode ser considerada como um descritor de qualidade biológica de morangos cultivados em sistemas orgânicos e convencionais.

Plane detection from monocular image sequences

AIRES, Kelson R. T. ; ARAÚJO, Hélder J. ; MEDEIROS, Adelardo A. D. . Plane Detection from Monocular Image Sequences. In: VISUALIZATION, IMAGING AND IMAGE PROCESSING, 2008, Palma de Mallorca, Spain. Proceedings..., Palma de Mallorca: VIIP, 2008

Plane Detection Using Affine Homography

AIRES, Kelson R. T.; ARAÚJO, Hélder J.; MEDEIROS, Adelardo A. D. Plane Detection Using Affine Homography. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG: Anais... do CBA 2008.

Changes in phytoplankton composition in response to tides, wind-induced mixing conditions, and freshwater outflows in an urbanised estuarine complex

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Seleção seqüencial de descritores por análise da semântica para recuperação de imagens baseada no conteúdo

With the rapid growth of databases of various types (text, multimedia, etc..), There exist a need to propose methods for ordering, access and retrieve data in a simple and fast way. The images databases, in addition to these needs, require a representation of the images so that the semantic content characteristics are considered. Accordingly, several proposals such as the textual annotations based retrieval has been made. In the annotations approach, the recovery is based on the comparison between the textual description that a user can make of images and descriptions of the images stored in database. Among its drawbacks, it is noted that the textual description is very dependent on the observer, in addition to the computational effort required to describe all the images in database. Another approach is the content based image retrieval - CBIR, where each image is represented by low-level features such as: color, shape, texture, etc. In this sense, the results in the area of CBIR has been very promising. However, the representation of the images semantic by low-level features is an open problem. New algorithms for the extraction of features as well as new methods of indexing have been proposed in the literature. However, these algorithms become increasingly complex. So, doing an analysis, it is natural to ask whether there is a relationship between semantics and low-level features extracted in an image? and if there is a relationship, which descriptors better represent the semantic? which leads us to a new question: how to use descriptors to represent the content of the images?. The work presented in this thesis, proposes a method to analyze the relationship between low-level descriptors and semantics in an attempt to answer the questions before. Still, it was observed that there are three possibilities of indexing images: Using composed characteristic vectors, using parallel and independent index structures (for each descriptor or set of them) and using characteristic vectors sorted in sequential order. Thus, the first two forms have been widely studied and applied in literature, but there were no records of the third way has even been explored. So this thesis also proposes to index using a sequential structure of descriptors and also the order of these descriptors should be based on the relationship that exists between each descriptor and semantics of the users. Finally, the proposed index in this thesis revealed better than the traditional approachs and yet, was showed experimentally that the order in this sequence is important and there is a direct relationship between this order and the relationship of low-level descriptors with the semantics of the users

Análise de Agrupamentos Com Base na Teoria da Informação: Uma Abordagem Representativa

Currently, one of the biggest challenges for the field of data mining is to perform cluster analysis on complex data. Several techniques have been proposed but, in general, they can only achieve good results within specific areas providing no consensus of what would be the best way to group this kind of data. In general, these techniques fail due to non-realistic assumptions about the true probability distribution of the data. Based on this, this thesis proposes a new measure based on Cross Information Potential that uses representative points of the dataset and statistics extracted directly from data to measure the interaction between groups. The proposed approach allows us to use all advantages of this information-theoretic descriptor and solves the limitations imposed on it by its own nature. From this, two cost functions and three algorithms have been proposed to perform cluster analysis. As the use of Information Theory captures the relationship between different patterns, regardless of assumptions about the nature of this relationship, the proposed approach was able to achieve a better performance than the main algorithms in literature. These results apply to the context of synthetic data designed to test the algorithms in specific situations and to real data extracted from problems of different fields

Seleção de features guiada por atenção visual em imagens com fóvea

Visual attention is a very important task in autonomous robotics, but, because of its complexity, the processing time required is significant. We propose an architecture for feature selection using foveated images that is guided by visual attention tasks and that reduces the processing time required to perform these tasks. Our system can be applied in bottom-up or top-down visual attention. The foveated model determines which scales are to be used on the feature extraction algorithm. The system is able to discard features that are not extremely necessary for the tasks, thus, reducing the processing time. If the fovea is correctly placed, then it is possible to reduce the processing time without compromising the quality of the tasks outputs. The distance of the fovea from the object is also analyzed. If the visual system loses the tracking in top-down attention, basic strategies of fovea placement can be applied. Experiments have shown that it is possible to reduce up to 60% the processing time with this approach. To validate the method, we tested it with the feature algorithm known as Speeded Up Robust Features (SURF), one of the most efficient approaches for feature extraction. With the proposed architecture, we can accomplish real time requirements of robotics vision, mainly to be applied in autonomous robotics

Detecção e classificação de modos de operação do bombeio mecânico via cartas dinamométricas

The precision and the fast identification of abnormalities of bottom hole are essential to prevent damage and increase production in the oil industry. This work presents a study about a new automatic approach to the detection and the classification of operation mode in the Sucker-rod Pumping through dynamometric cards of bottom hole. The main idea is the recognition of the well production status through the image processing of the bottom s hole dynamometric card (Boundary Descriptors) and statistics and similarity mathematics tools, like Fourier Descriptor, Principal Components Analysis (PCA) and Euclidean Distance. In order to validate the proposal, the Sucker-Rod Pumping system real data are used

Segmentação Fuzzy de Texturas e Vídeos

The segmentation of an image aims to subdivide it into constituent regions or objects that have some relevant semantic content. This subdivision can also be applied to videos. However, in these cases, the objects appear in various frames that compose the videos. The task of segmenting an image becomes more complex when they are composed of objects that are defined by textural features, where the color information alone is not a good descriptor of the image. Fuzzy Segmentation is a region-growing segmentation algorithm that uses affinity functions in order to assign to each element in an image a grade of membership for each object (between 0 and 1). This work presents a modification of the Fuzzy Segmentation algorithm, for the purpose of improving the temporal and spatial complexity. The algorithm was adapted to segmenting color videos, treating them as 3D volume. In order to perform segmentation in videos, conventional color model or a hybrid model obtained by a method for choosing the best channels were used. The Fuzzy Segmentation algorithm was also applied to texture segmentation by using adaptive affinity functions defined for each object texture. Two types of affinity functions were used, one defined using the normal (or Gaussian) probability distribution and the other using the Skew Divergence. This latter, a Kullback-Leibler Divergence variation, is a measure of the difference between two probability distributions. Finally, the algorithm was tested in somes videos and also in texture mosaic images composed by images of the Brodatz album

Cancer risk assessment of ethyl carbamate in alcoholic beverages from Brazil with special consideration to the spirits cachaca and tiquira

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Shear bond strength of aesthetic materials bonded to Ni-Cr alloy

Objectives. This study was undertaken to evaluate the shear bond strength of four materials used as aesthetic material bonded to Ni-Cr alloy.Methods. Sixty-eight alloy discs were prepared and divided equally into four groups, and received four treatments for veneering: conventional feldspathic porcelain (Noritake EX-3) and three light-cured prosthodontic composite resins (Artglass, Solidex and Targis). The aesthetic materials were applied after metal structure conditioning in accordance with the manufacturers' recommendations. The specimens were stored in distilled water at 37 degreesC for 7 days. A universal testing machine was used to measure the shear bond strength of the specimens at a cross head speed of 0.5 mm/min. Fractured specimens were examined by using both optical and scanning electron microscope.Results. The analysis of variance and Tukey's test showed that the strongest mean shear bond was obtained with Noritake EX-3 (mean shear bond strength 42.90 +/- 7.82 MPa). For composites, the highest mean shear bond strength was observed for Targis (12.30 +/- 1.57 MPa); followed by Solidex (11.94 +/- 1.04 MPa) and Artglass (10.04 +/- 0.75 MPa). Optical analysis of the fractured surf aces indicated that for Targis and Noritake EX-3 all failures were a mixture of both cohesive and adhesive patterns. As for Artglass and Solidex, the fractures were mainly adhesive in nature.Conclusions. The Solidex system was equivalent to the Targis system in bond strength and exhibited greater strength than the Artglass system. The porcelain fused-to-metal showed considerably higher shear bond strength than the three metal-resin bonding techniques. (C) 2003 Elsevier B.V. Ltd. Ali rights reserved.

Influence of the environmental heterogeneity of breeding ponds on anuran assemblages from southeastern Brazil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Niche occupancy and the relative role of micro-habitat and diet in resource partitioning among pond dwelling tadpoles.

We determined microhabitat and diet niche for tadpoles from two ponds in an agricultural landscape. Additionally, we verified the intraspecific variation in resource use, and if diet and microhabitat use were correlated. Tadpoles found in the two ponds differed in microhabitat use, because in the larger pond they explored deeper places far from the margin. There were three groups with high microhabitat niche overlap. In both ponds, plant cover was the best descriptor to explain interspecific variation in microhabitat use. Tadpoles of all species ingested mainly Bacillariophyceae and Trachellomonas however the diet differed intraspecifically in the species from the two ponds. Ten items in the temporary pond and 15 items in the permanent one were ingested by all species; however, the relative abundance of each item differed. Diet similarity was not correlated to similarity in microhabitat use. In this study, diet was as important as microhabitat use to explain resource partitioning.