Remote Sensing based Building Extraction

• Format: eBook
• Language: English
• Published: MDPI - Multidisciplinary Digital Publishing Institute 2020
• Subjects: History of engineering and technology; 3-D; 3D reconstruction; 3D urban expansion; 5G signal simulation; accuracy analysis; active contour model; aerial images; attention mechanism; binary decision network; boundary extraction; boundary regulated network; building; building boundary extraction; building detection; building edges detection; building extraction; building index; building reconstruction; building regularization technique; change detection; convolutional neural network; data fusion; deep convolutional neural network; deep learning; developing city; digital building height; DTM extraction; elevation map; feature extraction; feature fusion; feature-level-fusion; fully convolutional network; Gabor filter; generative adversarial network; GIS data; high resolution optical images; high spatial resolution remote sensing imagery; high spatial resolution remotely sensed imagery; high-resolution aerial imagery; high-resolution aerial images; high-resolution satellite images; image fusion; imagery; indoor modelling; Inria aerial image labeling dataset; land-use; LiDAR; LiDAR point cloud; Massachusetts buildings dataset; mathematical morphology; method comparison; mobile laser scanning; modelling; morphological attribute filter; morphological profile; multiscale Siamese convolutional networks (MSCNs); n/a; object recognition; occlusion; open data; outline extraction; point cloud; point clouds; reconstruction; regularization; remote sensing; richer convolution features; roof segmentation; semantic segmentation; simple linear iterative clustering (SLIC); straight-line segment matching; U-Net; ultra-hierarchical sampling; unmanned aerial vehicle (UAV); urban building extraction; very high resolution; very high resolution imagery; VHR remote sensing imagery; web-net
• Online Access: Open Access: DOAB: description of the publication; Open Access: DOAB, download the publication

 Building extraction from remote sensing data plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. Even though significant research has been carried out for more than two decades, the success of automatic building extraction and modeling is still largely impeded by scene complexity, incomplete cue extraction, and sensor dependency of data. Most recently, deep neural networks (DNN) have been widely applied for high classification accuracy in various areas including land-cover and land-use classification. Therefore, intelligent and innovative algorithms are needed for the success of automatic building extraction and modeling. This Special Issue focuses on newly developed methods for classification and feature extraction from remote sensing data for automatic building extraction and 3D