In this paper, we explore a statistical relationship between green areas and traffic-related vehicle noise. A medium-sized Brazilian city was selected as the sampling area. This area was divided into 25 subareas and for each subarea a group of descriptors was developed. The parameters considered were the areas occupied by green spaces and the noise pollution index generated by vehicular traffic during day and night periods. The green areas were quantified by digital processing of satellite images. The vehicular traffic noise was measured directly at the site and analysed by the noise pollution index (Lnp), the equivalent sound level (LAeq) and the day/night sound level (Ldn). In order to establish the statistical relationship between noise descriptors and green areas, Pearson's linear correlation coefficient (r) was used. Two analysis types were developed: a generalised one, including the 25 subareas; and a specific one, classifying the subareas into clusters. The first analysis indicated a trend to a medium negative correlation between green areas and noise pollution day index (Lnpd), noise pollution night index (Lnpn) and Ldn (r= -0.577, -0.484, -0.373). In the second analysis, the subarea cluster 3 is considered, which includes areas with clinics and educational institutions. This correlation was classified as high negative (r= -0.729, -0.721, -0.541). The results show indexes with high negative correlation, statistically meaning that there is an inverse proportional relationship between green areas and noise pollution.

In this study, we propose an analysis of the vehicular traffic noise indices and comparison between field measurements and prediction data obtained from mathematical models. The study area consists of two pedestrians routes of a medium-sized South American city. University students use these routes in displacements between their universities and residences. We monitored twenty-eight points along the two routes, performing three daytime measurements for each point. The calculated values were obtained from two mathematical predicted models: the English model CRTN (Calculation of Road Traffic Noise) and the French model NMPB-Routes (Nouvelle Methode de Prevision de Bruit). The measurements considered two noise descriptors: the A-weighted equivalent sound level (LAeq) and the noise pollution index (Lnp). The results show that the pedestrians are exposed to excessive levels of vehicle traffic noise along these routes. However, the analysis showed that the two mathematical models achieved good similarity and high performance in the prediction potential. The CRTN model has a better performance than NMPB, proving to be useful as an auxiliary tool in the monitoring of vehicle traffic noise. Finally, we used the CRTN (LAeq) predictions to generate the map of noise pollution indices.

Resumo -Recentemente, um dos autores propôs um algoritmo de reconhecimento de objetos (casamento de modelos) invariante à rotação e escala chamado Forapro. Este algoritmo utiliza coeficientes de Fourier de projeções radiais e circulares para obter características locais invariantes à rotação. Neste trabalho, tornamos Forapro invariante à distorção de perspectiva utilizando a técnica de simulação de pontos de vista. Este novo algoritmo, que denominamos de Aforapro, é robusto a padrões repetidos e mudanças de brilho e contraste. Aforapro foi testada com 350 imagens e demonstrou ser bastante robusto a diferentes distorções. Palavras-Chave -Reconhecimento de objetos, casamento de modelos, invariância a perspectiva, coeficientes de Fourier, transformação afim, ASIFT, Forapro.Abstract -Recently one of the authors proposed an object recognition (template matching) algorithm invariant to rotation and scaling named Forapro. This algorithm uses the Fourier coefficients of radial and circular projections to compute rotation-invariant local features. In this paper, we make Forapro invariant to perspective distortion using the viewpoint simulation technique. This new algorithm, that we named Aforapro, is robust to repetitive patterns and changes in brightness and contrast. Aforapro was tested with 350 images and has proved to be quite robust to different distortions.

SIFT, Forapro and Ciratefi are three rotation and scale invariant template matching (or keypoint matching) algorithms. They can become viewpoint-invariant using the view simulation technique, compensating the perspective deformation by simulated affine transformations, yielding the algorithms named ASIFT (Affine-invariant SIFT), Aforapro and Aciratefi. We compare the three algorithms, evaluating their performances in different situations. We focus our attention especially to situations with illumination changes and in the presence of repetitive similar patterns. The results show that all the three algorithms have strengths and weaknesses and the user should choose the best suited algorithm according to the intended application.