Figure 1- - uploaded by Martin Machala
Content may be subject to copyright.
Site of the first research area (green with red border) in Romania. (Source of base map-NatGeo_World_Map; ArcGIS at services.arcgisonline.com)
Source publication
Manual vectorization of multispectral images is a widely used method for making land-use or land-cover maps. Although it is usually considered relatively accurate it is very time consuming, which has prompted the use in recent years of various semiautomatic methods for classifying remotely sensed images. One of the most promising of the latter is o...
Similar publications
Citations
... Os mapas de cobertura e uso da terra foram vetorizados com base na análise e interpretação visual das imagens digitais tratadas, além da experiência do intérprete e da confirmação por reconhecimento de classes e feições em campo, que permite a redução de possíveis erros. Tal afirmação se baseia nos experimentos realizados por Machala et al. (2015) onde se obteve 93% de acurácia com a vetorização contra 84% por processos semiautomáticos. A escolha das classes de mapeamento adotadas partiu de trabalhos prévios para a área de estudo (Boori & Amaro, 2010;Rocha et al., 2011;Boori et al., 2012). ...
O objetivo deste artigo foi avaliar a distribuição espacial e quantificar as Áreas de Preservação Permanente na foz estuarina do rio Apodi-Mossoró, no Rio Grande do Norte (Nordeste do Brasil), para os anos de 1965 e 2012 de acordo com a legislação ambiental vigente. Desta forma, foi possível comparar as mudanças de zoneamento projetadas sobre a cobertura e uso da terra, além de implicações para as áreas úmidas. A metodologia envolveu a reconstrução dos cenários com base nas normas e avaliação dos mapas temáticos gerados a partir de produtos de sensores remotos. Foram aplicadas técnicas de Processamento Digital de Imagens que permitiram mapear categorias de cobertura e uso da terra e identificar os limites das áreas protegidas em cada período. A maior modificação constatada indica a perda de 1.907,09 ha de áreas inundáveis da planície flúvio-marinha, quase totalmente ocupada por salinas. No ano de 1965 foi observada a ocorrência de três categorias de APP, contabilizando 455,17 ha, mas que por limitação da norma só seriam protegidos 83,45 ha. Em relação ao ano de 2012, foram constatadas seis categorias de APP, totalizando 1.051,96 ha, decorrente da ampliação das faixas de proteção, mas as áreas consolidadas anteriormente reduzem para 787,57 ha o quantitativo de áreas protegidas no último período. O ambiente estuarino brasileiro se destaca pela carência de legislação mais específica que melhor proteja as áreas úmidas. As áreas de preservação permanente não são suficientes para tal garantia na região costeira, ainda mais na área de estudo que apresenta riscos de inundação e teve seus ecossistemas amplamente degradados.
... Os mapas de cobertura e uso da terra foram vetorizados com base na análise e interpretação visual das imagens digitais tratadas, além da expe- riência do intérprete e da confirmação por reconhe- cimento de classes e feições em campo, que permite a redução de possíveis erros. Tal afirmação se ba- seia nos experimentos realizados por Machala et al. (2015) onde se obteve 93% de acurácia com a vetori- zação contra 84% por processos semiautomáticos. A escolha das classes de mapeamento adotadas partiu de trabalhos prévios para a área de estudo (Boori & Amaro, 2010;Rocha et al., 2011;Boori et al., 2012). ...
There is a growing need for high resolution altimetry data to use in environmental research in the last years. Therefore, addition criteria must be applied for this data usage, especially due to vertical error. This paper focuses on vertical error evaluation and calibration methodology of Digital Elevation Models (DEM) obtained with Shuttle Radar Topographic Mission and with airborne Light Detection and Ranging in the Piranhas-Açu river basin; north part of Rio Grande do Norte State, Brazil. The evaluation and calibration was conducted in two sectors of the study area: regional and local. The regional sector was evaluated with SRTM data only and the local sector with DEM from SRTM and airborne LiDAR. The calibration used a network of high vertical accuracy altimetric control points data. The results show that the in the study area the SRTM DEM accuracy is satisfactory and was improved by 26-29% after calibration. In the local area, airborne LiDAR is more accurate than SRTM and was also enhanced by control points calibration (15%). This paper demonstrates the need for vertical error analysis and calibration in DEM prior to topographic use.
... Many attempts have been made to accurately create land cover maps in a timely fashion via multiple methods and using a wide variety of data types with different spatial resolutions. Remotely sensed data especially satellite images as well as aerial photographs have been considered the main raw data source for many land use/cover map creation processes [22]- [24]. Traditional techniques such as supervised, unsupervised, Principal Component Analysis (PCA), Vegetation Indices (VI), and others that rely mostly on the spectral properties of features have been used for decades and are still being extensively and successfully used in remotely sensed image classification procedures. ...
The aim of this project is to create high resolution land cover classification as well as tree canopy density maps at a regional level using high resolution spatial data. Modeling and the data manipulation and analysis of LiDAR LAS point cloud dataset as well as multispectral aerial photographs from the National Agriculture Imagery Program (NAIP) were carried out. Using geoprocessing modeling, a land cover map is created based on filtered returns from LiDAR point cloud data (LAS dataset) to extract features based on their class and return values, and traditional classification methods of high resolution multi-spectral aerial photographs of the remaining ground cover for Clarion County in Pennsylvania. The newly developed model produced 7 classes at 10 ft × 10 ft spatial resolution, namely: water bodies, structures, streets and paved surfaces, bare ground, grassland, trees, and artificial surfaces (e.g. turf). The model was tested against areas with different sizes (townships and municipalities) which revealed a classification accuracy between 94% and 96%. A visual observation of the results shows that some tree-covered areas were misclassified as built up/structures due to the nature of the available LiDAR data, an area of improvement for further studies. Furthermore, a geoprocessing service was created in order to disseminate the results of the land cover classification as well as the tree canopy density calculation to a broader audience. The service was tested and delivered in the form of a web application where users can select an area of interest and the model produces the land cover and/or the tree canopy density results (http://maps.clarion.edu/LandCoverExtractor). The produced output can be printed as a final map layout with the highlighted area of interest and its corresponding legend. The interface also allows the download of the results of an area of interest for further investigation and/or analysis.
