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.

Traffic and Road Sign Recognition

This thesis presents a system to recognise and classify road and traffic signs for the purpose of developing an inventory of them which could assist the highway engineers’ tasks of updating and maintaining them. It uses images taken by a camera from a moving vehicle. The system is based on three major stages: colour segmentation, recognition, and classification. Four colour segmentation algorithms are developed and tested. They are a shadow and highlight invariant, a dynamic threshold, a modification of de la Escalera’s algorithm and a Fuzzy colour segmentation algorithm. All algorithms are tested using hundreds of images and the shadow-highlight invariant algorithm is eventually chosen as the best performer. This is because it is immune to shadows and highlights. It is also robust as it was tested in different lighting conditions, weather conditions, and times of the day. Approximately 97% successful segmentation rate was achieved using this algorithm.Recognition of traffic signs is carried out using a fuzzy shape recogniser. Based on four shape measures - the rectangularity, triangularity, ellipticity, and octagonality, fuzzy rules were developed to determine the shape of the sign. Among these shape measures octangonality has been introduced in this research. The final decision of the recogniser is based on the combination of both the colour and shape of the sign. The recogniser was tested in a variety of testing conditions giving an overall performance of approximately 88%.Classification was undertaken using a Support Vector Machine (SVM) classifier. The classification is carried out in two stages: rim’s shape classification followed by the classification of interior of the sign. The classifier was trained and tested using binary images in addition to five different types of moments which are Geometric moments, Zernike moments, Legendre moments, Orthogonal Fourier-Mellin Moments, and Binary Haar features. The performance of the SVM was tested using different features, kernels, SVM types, SVM parameters, and moment’s orders. The average classification rate achieved is about 97%. Binary images show the best testing results followed by Legendre moments. Linear kernel gives the best testing results followed by RBF. C-SVM shows very good performance, but ?-SVM gives better results in some case.

Color detection and segmentation for road and traffic signs

This paper aims to present three new methods for color detection and segmentation of road signs. The images are taken by a digital camera mounted in a car. The RGB images are converted into IHLS color space, and new methods are applied to extract the colors of the road signs under consideration. The methods are tested on hundreds of outdoor images in different light conditions, and they show high robustness. This project is part of the research taking place in Dalarna University / Sweden in the field of the ITS.

Fuel ethanol price drivers in the Atlantic basin : Brazil & the U.S. traders perspectives

Como a oportunidade de exportação de etanol combustível é muito recente, o agronegócio carece de literatura para formação de gestores e estrategistas. Este trabalho tem como objetivo descrever o mecanismo de formação de preços de etanol tanto no Brasil como nos Estados Unidos da America. Decupei as variáveis que impactam na formação de preços, custo de produção de etanol de cana-de-açúcar, custo da logística e desidratação no Caribe, custo do etanol de milho e fiz algumas análises de cenários de formação de preços das principais variáveis e consegui organizar este conhecimento em um gráfico que contém no eixo superior preço do etanol hidratado na usina no Brasil e no eixo inferior o preço do bushel de milho em Chicago cujas interceções nas retas da taxa do dólar e do preço do gás natural, fornecem no eixo Y o preço do produto no porto de Nova York, ficando uma visualização simples das possibilidades da janela de exportação. A metodologia permite assumir diferentes cenários de oferta, demanda e preços e estabelecer diferentes estratégias de comercialização.

Análise das emissões gasosas de um veículo flex funcionando com diferentes combustíveis

Efforts in research and development of new technologies to reduce emission levels of pollutant gases in the atmosphere has intensified in the last decades. In this context, it can be highlighted the modern systems of electronic engine management, new automotive catalysts and the use of renewable fuels which contributes to reduce the environmental impact. The purpose of this study was a comparative analysis of gas emissions from a automotive vehicle, operating with different fuels: natural gas, AEHC or gasoline. To execute the experimental tests, a flex vehicle was installed on a chassis dynamometer equipped with a gas analyzer and other complementary accessories according to the standard guidelines of emission and security procedures. Tests were performed according to NBR 6601 and NBR 7024, which define the urban and road driving cycle, respectively. Besides the analysis of exhaust gases in the discharge tube, before and after the catalyst, using the suction probe of the gas analyzer to simulate the vehicle in urban and road traffic, were performed tests of fuel characterization. Final results were conclusive in indicating leaded gasoline as the fuel which most contributed with pollutant emissions in atmosphere and the usual gasoline being the fuel which less contributed with pollutant emissions in atmosphere

Soil compaction by machine traffic and least limiting water range related to soybean yield

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

Traffic soil compaction of an oxisol related to soybean development and yield

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

Briquetting of charcoal from sugar-cane bagasse fly ash (scbfa) as an alternative fuel

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

Analysis of a molten carbonate fuel cell: cogeneration to produce electricity and cold water

The fuel cell is an emerging cogeneration technology that has been applied successfully in Japan, the USA and some countries in the European Union. This system performs direct conversion of the chemical energy of the oxidation of hydrogen from fuel with atmospheric oxygen into direct current electricity and waste heat via an electrochemical process relying on the use of different electrolytes (phosphoric acid, molten carbonate and solid oxide, depending on operating temperature). This technology permits the recovery of waste heat, available from 200 degreesC up to 1000 degreesC depending on the electrolyte technology, which can be used in the production of steam, hot or cold water, or hot or cold air, depending on the associated recuperation equipment. In this paper, an energy, exergy and economic analysis of a fuel cell cogeneration system (FCCS) is presented. The FCCS is applied in a segment of the tertiary sector to show that it is a feasible alternative for rational decentralized energy production under Brazilian conditions. The technoeconomic analysis shows a global efficiency or fuel utilization efficiency of 86%. Analysis shows that the exergy losses in the fuel cell unit and the absorption refrigeration system are significant. Furthermore, the payback period estimated is about 3 and 5 years for investments in fuel cells of 1000 and 1500 US$/kW, respectively. (C) 2001 Elsevier B.V. Ltd. All rights reserved.

Fuel cell cogeneration system: a case of technoeconomic analysis

Fuel Cell is the emerging technology of cogeneration, and has been applied successfully in Japan, U.S.A. and some OECD countries. This system produces electric power by an electrolytic process, in which chemical substances (the most utilized substances are solid oxide, phosphoric acid and molten carbonate) absorb the components H-2 and O-2 of the combustion fuel. This technology allows the recovery of residual heat, available from 200 degrees C up to 1000 degrees C (depending on the electrochemical substance utilized), which can be used for the production of steam, hot or cold water, or hot or cold air, depending on the recuperation equipment used. This article presents some configurations of fuel cell cogeneration cycles and a study of the technical and economic feasibility for the installation of the cogeneration systems utilizing fuel cell, connected to an absorption refrigeration system for st building of the tertiary sector, subject to conditions in Brazil. (C) 1999 Elsevier B.V. Ltd. All rights reserved.

Thermodynamic analysis of direct steam reforming of ethanol in molten carbonate fuel cell

Fuel cell as molten carbonate fuel cell (MCFC) operates at high temperatures. Thus, cogeneration processes may be performed, generating heat for its own process or for other purposes of steam generation in the industry. The use of ethanol is one of the best options because this is a renewable and less environmentally offensive fuel, and is cheaper than oil-derived hydrocarbons, as in the case of Brazil. In that country, because of technical, environmental, and economic advantages, the use of ethanol by steam reforming process has been the most investigated process. The objective of this study is to show a thermodynamic analysis of steam reforming of ethanol, to determine the best thermodynamic conditions where the highest volumes of products are produced, making possible a higher production of energy, that is, a more efficient use of resources. To attain this objective, mass and energy balances were performed. Equilibrium constants and advance degrees were calculated to get the best thermodynamic conditions to attain higher reforming efficiency and, hence, higher electric efficiency, using the Nernst equation. The advance degree (according to Castellan 1986, Fundamentos da Fisica/Quimica, Editora LTC, Rio de Janeiro, p. 529, in Portuguese) is a coefficient that indicates the evolution of a reaction, achieving a maximum value when all the reactants' content is used of reforming increases when the operation temperature also increases and when the operation pressure decreases. However, at atmospheric pressure (1 atm), the advance degree tends to stabilize in temperatures above 700 degrees C; that is, the volume of supplemental production of reforming products is very small with respect to high use of energy resources necessary. The use of unused ethanol is also suggested for heating of reactants before reforming. The results show the behavior of MCFC. The current density, at the same tension, is higher at 700 degrees C than other studied temperatures such as 600 and 650 degrees C. This fact occurs due to smaller use of hydrogen at lower temperatures that varies between 46.8% and 58.9% in temperatures between 600 and 700 degrees C. The higher calculated current density is 280 mA/cm(2). The power density increases when the volume of ethanol to be used also increases due to higher production of hydrogen. The highest produced powers at 190 mA/cm(2) are 99.8, 109.8, and 113.7 mW/cm(2) for 873, 923, and 973 K, respectively. The thermodynamic efficiency has the objective to show the connection among operational conditions and energetic factors, which are some parameters that describe a process of internal steam reforming of ethanol.

Preconcentration and determination of metal ions in commercial ethanol used as fuel for automotive engines

The present investigation reports the synthesis, characterization, and adsorption properties of a new nanomaterial based on organomodified silsesquioxane nanocages. The adsorption isotherms for CuCl,, CoCl2, ZnCl2, NiCl2, and FeCl3 from ethanol solutions were performed by using the batchwise method. The equilibrium condition is reached very quickly (3 min), indicating that the adsorption sites are well exposed. The results obtained in the flow experiments, showed a recovery of ca. 100% of the metal ions adsorbed in a column packed with 2 g of the nanomaterial, using 5 mL of 1.0 mol L-1 HCl solution as eluent. The sorption-desorption of the metal ions made possible the development of a method for preconcentration and determination of metal ions at trace level in commercial ethanol, used as fuel for car engines. The values determined by recommended method for plants 1, 2, and 3 indicated an amount of copper of 51, 60, and 78 mu g L-1, and of iron of 2, 15, and 13 mu g L-1, respectively. These values are very close to those determined by conventional analytical methods. Thus, these similar values demonstrated the accuracy of the determination by recommended method.

Voltammetric determination of total iron in fuel ethanol using a 1,10 fenantroline/nafion carbon paste-modified electrode

This work presents a methodology for iron determination in fuel ethanol using a modified carbon paste electrode with 1.10 fenantroline/nafion. The electrochemical parameters were optimized for the proposed system and the voltammetric technique of square wave was employed for iron determination. An accumulation time of 5 minutes, such as a 100 mV of pulse magnitude (E(sw)) and frequency (f) of 25 Hz were used as optimized experimental conditions. The modified carbon paste electrode presented linear dependence of amperometric signal with iron concentration in a work range from 6.0x10(-6) until 2.0x10(-5) mol L(-1) of iron, exhibiting a linear correlation coefficient of 0.9884, a detection limit of 2.4 x10(-6) mol L(-1) (n = 3) and amperometric sensibility of 4.5x10(5) mu A/mol L(-1). Analytical curve method was used for iron determination at a commercial fuel sample. Flame atomic absorption spectroscopy was employed as comparative technique.

Application of cellulose modified with p-aminobenzoic groups in preconcentration system for determination of Cu, Fe, Ni, and Zn in fuel ethanol samples by flame atomic absorption spectrometry

Cellulose chemically modified with p-aminobenzoic groups, abbreviated as Cel-PAB, was used for preconcentration of copper, iron, nickel, and zinc from ethanol fuel, normally used in Brazil as engine fuel. The surface characteristics and the surface area of the cellulose were obtained before and after chemical modification using FT-IR, elemental analysis, and surface area analysis (B.E.T.). The retention and recovery of the analyte elements were studied by applying batch and column techniques.

Flame AAS determination of metal ions in fuel ethanol after preconcentration on acid carboxymethylcellulose (CMCH)

This paper describes the preparation of acid carboxymethylcellulose (CMCH), and the results of a study on the adsorption and preconcentration (using batch and flow-through column methods) of Cd(II), Cu(II), Cr(III), Fe(III), Ni(II) and Zn(II) in ethanol medium. The adsorption capacities for each metallic ion were (in mmol g(-1)) Cd(II) = 0.92; Cu(II) = 1.45; Cr(III) = 1.70; Fe(III) = 1.60; Ni(II) = 1.30; and Zn(II) = 1.10. By means of the flow-through method, a recovery of ca. 100% of the metallic ions adsorbed in a column packed with 2 g of CMCH was found when 5.0 mL of 1.0 mol L-1 hydrochloric acid were used as eluent. An enrichment factor of 20 (100 mt solution containing 50 mu g L-1 of the metallic ions, concentrated to 5.0 mt) was obtained by this preconcentration procedure. The sorption-desorption procedure applied allowed the development of a preconcentration and Flame AAS quantification method of metallic ions in fuel ethanol at trace levels.