The constant increase in population in conjunction with unplanned and irregular urban growth, typical problems in developing countries, can promote a rapid increase in population density and related public infrastructure demand that may be hard to bear with the available economic resources. Efficient monitoring of urban development is thus a key instrument for planners and public policy makers that have to cope with this scenario. This work aims at developing a tool to aid monitoring urban growth from very-high resolution remote sensing images, focussing on the integration of available open-source software and the application of OBIA methods. Specifically, we created a method for detection of urban, land use/land cover classes based on the integration of the InterIMAGE and the Orange Canvas software packages. The image interpretation model for the particular application was constructed with the aid of dataflow building blocks (widgets) for data analysis, structured in the visual programming environment of Orange Canvas. The Classification Tree and the Classification Tree Graph widgets were used to design a decision tree that was later translated in InterIMAGE Decision Rules. The study was conducted over an image from the GeoEye-1 sensor, covering a central area of the city of Goianésia, in the Midwestern region of Brazil. Ten land use/land cover classes were the target of the supervised classification. The results obtained in the experiments confirm that the integration of the two open-source packages can provide for accurate remote sensing image analysis, while facilitating data exploration and the construction of automatic image interpretation models.
ABSTRACT:The rapid increase in the number and in the spatial resolution of aerial and orbital Earth observation systems is generating a huge amount of remote sensing data that need to be readily transformed into useful information for policy and decision makers. A possible approach to tackle the demand for image interpretation tools that can deal efficiently with very large volumes of data is to employ data analysis methods based on distributed computing. This paper presents an object-based, remote sensing image interpretation application executed over cloud-computing infrastructure. The application is implemented with InterCloud, a novel image interpretation platform designed to run on computer grids (physical clusters or cloud-computing infrastructure). The application described in this paper is a land cover/land use classification of a pansharpened GeoEye-1 image, with 19k by 23k pixels. The image covers an area of the municipality of Goianésia, in Goiás State, Brazil. The site contains sparse urban areas intermixed with rural areas and natural patches of the Brazilian Cerrado biome. Eleven classes of objects, including urban, rural and Cerrado reminiscent targets were considered. In addition to the accuracies of the classification result, in this work we evaluate the scalability capability of InterCloud by performing different runs of the application with different configurations of the cloud infrastructure, in which we vary the number of computing nodes.
Linear erosion is a natural phenomenon. However, inadequate occupation of the environment or the implementation of engineering works, without the due care, accelerates this process, which has been acknowledged as the main cause of land degradation worldwide. The use of high-resolution satellite imaging to map risk areas for this process, may contribute to devising prevention strategies. Linear erosion is a process dependent on thresholds controlled by many variables. This study has used only topographic variables (altimetry, slope, curvature profile, curvature plan, slope orientation, accumulation flow, humidity index, sediment transport capacity, potential flow and drainage network) and a vegetation index, which were selected due to their influence on linear erosion processes. The study was developed in two 6,000 x 4,500 meter areas, located in the eastern part of the Federal District-Brazil. The classification model building was done using open source software packages, namely InterIMAGE and WEKA. The aim of this study was to develop a routine for automatic mapping of areas susceptible to linear erosion. The accuracy rate achieved by the model was 87.5%, as 21 of 24 linear erosion processes were identified. The percentage of the mapped area in relation to the total study area also showed that the classification was not overestimated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.