Building extraction has been a challenging task due to complex structures and features of various land use with matching spectral and spatial attributes in a satellite data. We attempted to extract building as features using machine-learning algorithms such as Support Vector Machine (SVM), Random Forests (RF), Artificial Neural Network (ANN) and Improved Ensemble Technique as Gradient Boosting. The techniques used increases their classification accuracies using spectral properties as well as indices such as Normalized Difference Vegetation Index (NDVI) as attributes. Extracted results through various methods, performance of three different machine learning such as Ensemble method, RF and SVM are applied and results are analyzed for their behavior in different building distribution. Different algorithms showed variations in accuracies and performance in different built-up conditions. Ensemble algorithm performed very well in all conditions followed by RF and SVM performed better in coarse resolution, while ANN performed better in high resolution and overall accuracies of all algorithms increased with better spatial resolution. Ensemble algorithm showed relatively efficient performance in regions with extensive heterogeneous features. These analyses can helpful to provide quantitative data for various stocktaking analysis and city managers for better administration capabilities.
Buildings are considered prominent objects for understanding the pattern of growth in an urban setting. Remote sensing technology plays a vital role in facilitating data generation pertaining to various urban applications. Digital surface models represent the elevation of the earth
surface features, and can be obtained from stereo images, radar, laser scanning, and so on. Photogrammetric techniques applied to optical stereo satellite images are economical and fast ways to generate height information of buildings. In this work, a quantitative and qualitative analysis
of digital surface models generated from Cartosat-1 stereo images is compared with openly available data. The study finds that it is possible to acquire about 50 percent of building heights with acceptable error limits. The experimental results indicate that the quality of height information
is suitable for applications to assess urban development at a macro scale, but not for individual building-level modeling.
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.