Abstract: Pan-sharpening (PS) consists of combining a high spatial resolution (HR) panchromatic image (PAN) and a low spatial resolution (LR) multispectral image (MS) to generate an MS-HR image. However, some PS methods have spectral and spatial distortions that influence subsequent analyses. Thus, this study aimed to develop a PS method based on convolutional autoencoder (CAE) for Landsat 8 images and evaluate its performance in calculating spectral indices. In the PS process, we trained a CAE network and used a multiscale-guided filter. The performance of the proposed method was analyzed using the Kolmogorov-Smirnov (K-S) statistic of the empirical cumulative distribution function (eCDF) between the values of the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Normalized Difference Moisture Index (NDMI) of the PS and MS-LR images. The results show that the proposed method is effective for calculating the indices. Therefore, we conclude that it has great potential for preserving the spatial information of the PAN image and the spectral information of the MS-LR image during the PS process for calculating spectral indices. Abstract Pansharpening Pan sharpening (PS HR (HR (PAN LR (LR MS (MS MSHR However analyses Thus (CAE indices multiscaleguided multiscale guided filter KolmogorovSmirnov Kolmogorov Smirnov KS K S (K-S eCDF (eCDF NDVI, NDVI , (NDVI) NDWI, NDWI (NDWI) NDMI (NDMI MSLR Therefore (NDVI (NDWI

Abstract: Digital elevation models are responsible for providing altimetric information on a surface to be mapped. While global models of low and medium spatial resolution are available open source by several space agencies, the high-resolution ones, which are utilized in scales 1:25,000 and larger, are scarce and expensive. Here we address this limitation by the utilization of deep learning algorithms coupled with SISR techniques in digital elevation models to obtain better spatial quality versions from lower resolution inputs. The development of a GAN-based methodology enables the improvement of the initial spatial resolution of low-resolution images. A dataset with different pairs of digital elevation models was created with the objective of allowing the study to be carried out, promoting the emergence of new research groups in the area as well as enabling the comparison between the results obtained. It has been found that by increasing the number of iterations the performance of the generated model was improved and the quality of the generated image increased. Furthermore, the visual analysis of the generated image against the high- and low-resolution ones showed a great similarity between the first two.

Abstract: The present work seeks to model the simulation of the landscape of the city of Curitiba, through the use of cellular automata (CA) algorithms, together with the Geographic Information Systems (GIS) and Remote Sensing tools. Four models were elaborated, having as input data classified images from the years 2006, 2009, 2011 and 2014; and different time intervals between the initial and final landscape of the models. Geographic data of the city were also used, as well as the current legislation of the municipality, and such data contributed to the robustness of the modelling. Two validation tests were applied to verify the adequacy of the simulated models concerning the observed reality. The validation performed by the Multiple Resolutions Adjustment method indicated that the model elaborated with data from 2009 and 2011 reached the highest similarity index, being equal to 0.88. Thus, it was possible to carry out geosimulations and these indicated that, as long as the trends observed in the past are maintained, the urban expansion of the municipality will occur at the expense of vegetation.

RESUMO A vegetação nas cidades desempenha funções ecológicas, estéticas e sociais que melhoram a qualidade de vida urbana. Para que essas funções sejam eficientes é necessário a realização de estudos quantitativos e qualitativos das áreas verdes (AVs) na cidade. O objetivo do estudo foi identificar a cobertura de vegetação presente nas diferentes tipologias de AVs nas unidades administrativas de Curitiba, PR, bem como analisar sua configuração espacial ao longo da paisagem urbana. A cobertura de vegetação foi identificada por meio da classificação por árvore de decisão de imagens de satélite de alta resolução espacial – GeoEye-1. Conclui-se que Curitiba possui menos de 5% de sua área constituída por AVs, as quais, em sua maioria, apresentaram cobertura de vegetação acima de 70%. A distribuição espacial delas é desigual em quantidade e irregular quanto à sua disposição. A unidade administrativa da região Sul carece de AVs de todas as tipologias estabelecidas pela municipalidade.

ABSTRACT Vegetation in cities presents ecological, aesthetic and social functions that improve urban quality of life. However, quantitative and qualitative studies on the spatial distribution of green areas (GA) are needed to promote their efficiency. The aim of this study was to identify the vegetation cover present in different types of GAs in Curitiba, Parana state, and analyze the spatial configuration along the urban landscape. The vegetation cover was identified by means of the Decision Tree classification of high spatial resolution satellite images - GeoEye-1. The results show that Curitiba has less than 5% of its area composed of GAs, with most of them presenting vegetation coverage above 70%. The distribution of these GAs is uneven in quantity and irregular in disposal.

Resumo:Atualmente, sensores de alta resolução espacial e radiométrica adquirem imagens onde feições terrestres são representadas por pixels de resolução espacial submétrica. Aliado a isto, o ALS (Airborne LiDAR System) - tecnologia de Sensoriamento Remoto ativo de varredura a laser acoplada em aeronaves - é capaz de coletar dados de altimetria de milhares de coordenadas de pontos na superfície terrestre. A integração destas tecnologias é desejada, pois geram dados complementares. Este artigo apresenta uma metodologia para detecção de edificações em ambiente urbano, utilizando imagem GeoEye(r) e dados ALS, baseada na segmentação de objetos, e submetidos a um processo de classificação baseada em árvores de decisão. Os dados adquiridos pelo ALS permitem gerar o MDS (Modelo Digital de Superfície), o MDT (Modelo Digital de Terreno) e o MDSn (Modelo Digital de Terreno normalizado) da área de estudo. Com o MDS e a imagem GeoEye, fez-se a ortorretificação da imagem, a qual, junto com o MDSn, foi segmentada pela ação do segmentador FLSA (Full-Lambda Schedule Algorithm). Amostras representativas das classes de interesse, foram usadas para treinar o processo de classificação, com a finalidade de criar regras de decisão. Os experimentos realizados buscaram verificar os atributos mais importantes para a detecção de edificações

Abstract:Currently, the high spatial and radiometric resolution sensors are able to acquire images where features on the surface are represented by submeter pixels. Along with, the ALS ( Airborne LiDAR System, an active remote sensing technology embedded in aircrafts ( is able of collecting elevation data from thousands of coordinate points on the Earth's surface. This integration is desirable, because it can generate complementary or additional data. Therefore, this research presents a methodology to detect buildings in an urban area, using a GeoEye(r) image and ALS data, based on an object-based analysis and classification rules generated by decision trees. The ALS data enable the production of the digital models, such as the DSM (Digital Surface Model), DTM (Digital Terrain Model) and NDSM (Normalized Digital Terrain Model). The image was orthorectified by means of the DSM, and the image segmentation process relied on the NDSM using the so-called FLSA (Full Lambda Schedule Algorithm). Representative samples of the classes of interest were used to train the classification process, set parameters and create the decision rules. After training, the complete dataset was subjected to a classification process. The experiments sought to verify which attributes most contributed to building detection

O presente trabalho faz parte do programa GEOSAFRAS, estimativa e safras no Brasil, coordenado pela Companhia Nacional de Abastecimento e do Programa das Nações Unidas para o Desenvolvimento. Uma aplicação muito comum no gerenciamento de safras é o monitoramento de mudanças nos campos de cultivo usando imagens de satélite adquiridas em diferentes datas. Para isto, a compatibilidade espacial entre essas imagens é um requisito básico, mais ainda quando se trata de imagens de diferentes sensores. Nesse artigo é descrita uma metodologia para a semi-automação do processo de correção geométrica com a finalidade de facilitar o ajuste geométrico entre imagens de diferentes sensores. Inicialmente, uma imagem base é manualmente corrigida a partir de dados extraídos de uma carta topográfica digital. Após essa correção, a imagem corrigida é utilizada como elemento base de referência para corrigir as outras imagens (denominadas neste trabalho de imagens de ajuste), as quais são adquiridas em datas diferentes e/ou de diferentes sensores. Depois de corrigida a imagem base todas as imagens (base e de ajuste) são segmentadas e classificadas. Os segmentos classificados como vegetação florestal são escolhidos para compor a malha relacional. As imagens de ajuste são registradas pelo processo imagem-imagem usando os centróides dos segmentos de vegetação florestal. Os segmentos de vegetação florestal presentes na imagem base são confrontados com os segmentos correspondentes nas imagens de ajuste, para buscar correspondências (matching). O processo de matching é realizado através da aplicação de algoritmos genéticos. Ao obter um resultado satisfatório na busca de correspondência, calcula-se os centróides correspondentes aos segmentos detectados, os quais são utilizados como pontos de controle para o processo de registro das imagens. Os resultados mostram que os algoritmos genéticos encontraram a solução ótima na maior parte dos experimentos realizados. Porém, para a imagem LANDSAT 2002 reamostrada a solução encontrada foi sub-ótima, pois um segmento sofreu grandes variações em relação ao mesmo segmento na imagem base.

This work is part of the GEOSAFRAS program - estimates and harvests in Brazil - which is coordinated by the National Company of Supply and the United Nations Development Programme. A regular use in the management of harvests is the monitoring of the cultivation fields changes by using satellite images obtained at different dates. For this purpose, the spatial compatibility between these images is a necessary condition, even more when it comes to images from different sensors. This article describes a methodology for the semi-automation of the geometric rectification process aimed at facilitating the geometric adjustment between images from different sensors. First, a base image is manually rectified from data extracted from a digital topographic map. After such rectification, the correct image is used as a reference element to rectify other images (in this work, called adjustment images), which are acquired at other dates and/or from other sensors. Once the base image is rectified, all images (base and adjustment ones) are segmented and classified. The segments classified as forest vegetation are selected to compose the relational mesh. The adjustment images are registered by the image-image process by means of the forest vegetation segment centroids. The forest vegetation segments in the base image are compared to the corresponding segments in the adjustment images, to find pattern matching. The matching process involves the application of genetic algorithms. After obtaining a positive result regarding the pattern matching, the centroids corresponding to the detected segments are calculated; These centroids are used as control points for the image registry process. The results show that genetic algorithms have found the optimal solution in most experiments. However, regarding the LANDSAT 2002 resampled image, the solution found was sub-optimal because one of the segments showed large variations in relation to the same segment of the base image.

A avaliação da qualidade visual de paisagens tem-se mostrado ferramenta eficiente para a determinação de diretrizes de usos adequados do solo, levando-se em conta o potencial atrativo dos diversos tipos de cobertura da superfície terrestre. Dentre os empregos das imagens orbitais, é bastante difundida a geração de mapas de ocupação do solo que podem, por sua vez, servir de base para a avaliação da paisagem. Com o presente trabalho objetivou-se propor e testar uma metodologia para a avaliação da qualidade visual da paisagem, através do emprego de imagem orbital classificada e pós-processada e da implementação de um algoritmo específico, para avaliação dos diversos usos da superfície na área em estudo. Para tanto e com base no método indireto de avaliação da paisagem, desenvolveu-se um algoritmo computacional que se utiliza de imagens orbitais para a valoração paisagística. Os resultados obtidos foram mosaicos e mapas da qualidade visual da paisagem da área de estudo. Ao final, concluiu-se que a técnica de avaliação através do programa computacional mostrou-se adequada à finalidade proposta; no entanto, deve ainda ser tida como resultado prévio e base para estudos mais detalhados.

The evaluation of landscapes has been showing an efficient tool for purposes of determining the appropriate land uses, considering the potential attraction of the several types of terrestrial surface covering. Among the employments of the orbital images, the generation of land use maps is quite spread, which serves as base for the landscape evaluation. The present work has the objective to propose and to test a methodology for the visual quality evaluation of the landscape, through the employment of classified and post-processed orbital image and implementing a specific algorithm, for evaluation of several uses of the land surface in the study area. Thus, on the basis of indirect method of landscape evaluation, an algorithm that uses of orbital images for the landscape evaluation was developed. The obtained results were mosaics and maps of the visual quality of landscape of the studied area. At the end, it was concluded that the computational program technique evaluation was found to be appropriate for the proposed purpose, however, it should be considered as preliminary result and base for more detailed studies.