Remote Sensing based Building Extraction
Yang, Bisheng
Remote Sensing based Building Extraction - MDPI - Multidisciplinary Digital Publishing Institute 2020 - 1 electronic resource (442 p.)
Open Access
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
Creative Commons
English
books978-3-03928-383-5 9783039283835 9783039283828
10.3390/books978-3-03928-383-5 doi
object recognition n/a very high resolution image fusion regularization simple linear iterative clustering (SLIC) digital building height building DTM extraction 3D reconstruction imagery GIS data high-resolution satellite images building edges detection high resolution optical images point clouds building extraction land-use morphological attribute filter deep convolutional neural network boundary extraction high spatial resolution remotely sensed imagery remote sensing fully convolutional network 3-D semantic segmentation morphological profile modelling roof segmentation boundary regulated network 3D urban expansion feature fusion developing city very high resolution imagery building detection occlusion change detection building index Massachusetts buildings dataset elevation map high spatial resolution remote sensing imagery data fusion generative adversarial network unmanned aerial vehicle (UAV) high-resolution aerial images ultra-hierarchical sampling U-Net binary decision network straight-line segment matching outline extraction building boundary extraction deep learning aerial images mobile laser scanning feature extraction multiscale Siamese convolutional networks (MSCNs) urban building extraction high-resolution aerial imagery mathematical morphology indoor modelling Gabor filter active contour model attention mechanism convolutional neural network LiDAR accuracy analysis point cloud feature-level-fusion building reconstruction richer convolution features open data VHR remote sensing imagery Inria aerial image labeling dataset LiDAR point cloud method comparison 5G signal simulation reconstruction building regularization technique web-net
Remote Sensing based Building Extraction - MDPI - Multidisciplinary Digital Publishing Institute 2020 - 1 electronic resource (442 p.)
Open Access
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
Creative Commons
English
books978-3-03928-383-5 9783039283835 9783039283828
10.3390/books978-3-03928-383-5 doi
object recognition n/a very high resolution image fusion regularization simple linear iterative clustering (SLIC) digital building height building DTM extraction 3D reconstruction imagery GIS data high-resolution satellite images building edges detection high resolution optical images point clouds building extraction land-use morphological attribute filter deep convolutional neural network boundary extraction high spatial resolution remotely sensed imagery remote sensing fully convolutional network 3-D semantic segmentation morphological profile modelling roof segmentation boundary regulated network 3D urban expansion feature fusion developing city very high resolution imagery building detection occlusion change detection building index Massachusetts buildings dataset elevation map high spatial resolution remote sensing imagery data fusion generative adversarial network unmanned aerial vehicle (UAV) high-resolution aerial images ultra-hierarchical sampling U-Net binary decision network straight-line segment matching outline extraction building boundary extraction deep learning aerial images mobile laser scanning feature extraction multiscale Siamese convolutional networks (MSCNs) urban building extraction high-resolution aerial imagery mathematical morphology indoor modelling Gabor filter active contour model attention mechanism convolutional neural network LiDAR accuracy analysis point cloud feature-level-fusion building reconstruction richer convolution features open data VHR remote sensing imagery Inria aerial image labeling dataset LiDAR point cloud method comparison 5G signal simulation reconstruction building regularization technique web-net