Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGE
Fast and efficient detection and reconstruction of buildings have become essential in real-time applications such as navigation, 3D rendering, augmented reality, and 3D smart cities. In this study, a modern Deep Learning (DL)-based framework is proposed for automatic detection, localization, and hei...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2020-08-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-2-2020/321/2020/isprs-annals-V-2-2020-321-2020.pdf |
| _version_ | 1818475132724707328 |
|---|---|
| author | F. Alidoost H. Arefi M. Hahn |
| author_facet | F. Alidoost H. Arefi M. Hahn |
| author_sort | F. Alidoost |
| collection | DOAJ |
| description | Fast and efficient detection and reconstruction of buildings have become essential in real-time applications such as navigation, 3D rendering, augmented reality, and 3D smart cities. In this study, a modern Deep Learning (DL)-based framework is proposed for automatic detection, localization, and height estimation of buildings, simultaneously, from a single aerial image. The proposed framework is based on a Y-shaped Convolutional Neural Network (Y-Net) which includes one encoder and two decoders. The input of the network is a single RGB image, while the outputs are predicted height information of buildings as well as the rooflines in three classes of eave, ridge, and hip lines. The extracted knowledge by the Y-Net (i.e. buildings’ heights and rooflines) is utilized for 3D reconstruction of buildings based on the third Level of Detail (LoD2). The main steps of the proposed approach are data preparation, CNNs training, and 3D reconstruction. For the experimental investigations airborne data from Potsdam are used, which were provided by ISPRS. For the predicted heights, the results show an average Root Mean Square Error (RMSE) and a Normalized Median Absolute Deviation (NMAD) of about 3.8 m and 1.3 m, respectively. Moreover, the overall accuracy of the extracted rooflines is about 86%. |
| first_indexed | 2024-12-10T09:09:01Z |
| format | Article |
| id | doaj.art-aa3670e58a1b41cbaa8d26ed7f591599 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-12-10T09:09:01Z |
| publishDate | 2020-08-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-aa3670e58a1b41cbaa8d26ed7f5915992022-12-22T01:55:04ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502020-08-01V-2-202032132810.5194/isprs-annals-V-2-2020-321-2020Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGEF. Alidoost0H. Arefi1M. Hahn2Photogrammetry and Geoinformatics, Faculty of Geomatics, Computer Science and Mathematics, Hochschule für Technik Stuttgart, GermanySchool of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, IranPhotogrammetry and Geoinformatics, Faculty of Geomatics, Computer Science and Mathematics, Hochschule für Technik Stuttgart, GermanyFast and efficient detection and reconstruction of buildings have become essential in real-time applications such as navigation, 3D rendering, augmented reality, and 3D smart cities. In this study, a modern Deep Learning (DL)-based framework is proposed for automatic detection, localization, and height estimation of buildings, simultaneously, from a single aerial image. The proposed framework is based on a Y-shaped Convolutional Neural Network (Y-Net) which includes one encoder and two decoders. The input of the network is a single RGB image, while the outputs are predicted height information of buildings as well as the rooflines in three classes of eave, ridge, and hip lines. The extracted knowledge by the Y-Net (i.e. buildings’ heights and rooflines) is utilized for 3D reconstruction of buildings based on the third Level of Detail (LoD2). The main steps of the proposed approach are data preparation, CNNs training, and 3D reconstruction. For the experimental investigations airborne data from Potsdam are used, which were provided by ISPRS. For the predicted heights, the results show an average Root Mean Square Error (RMSE) and a Normalized Median Absolute Deviation (NMAD) of about 3.8 m and 1.3 m, respectively. Moreover, the overall accuracy of the extracted rooflines is about 86%.https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-2-2020/321/2020/isprs-annals-V-2-2020-321-2020.pdf |
| spellingShingle | F. Alidoost H. Arefi M. Hahn Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGE ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGE |
| title_full | Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGE |
| title_fullStr | Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGE |
| title_full_unstemmed | Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGE |
| title_short | Y-SHAPED CONVOLUTIONAL NEURAL NETWORK FOR 3D ROOF ELEMENTS EXTRACTION TO RECONSTRUCT BUILDING MODELS FROM A SINGLE AERIAL IMAGE |
| title_sort | y shaped convolutional neural network for 3d roof elements extraction to reconstruct building models from a single aerial image |
| url | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-2-2020/321/2020/isprs-annals-V-2-2020-321-2020.pdf |
| work_keys_str_mv | AT falidoost yshapedconvolutionalneuralnetworkfor3droofelementsextractiontoreconstructbuildingmodelsfromasingleaerialimage AT harefi yshapedconvolutionalneuralnetworkfor3droofelementsextractiontoreconstructbuildingmodelsfromasingleaerialimage AT mhahn yshapedconvolutionalneuralnetworkfor3droofelementsextractiontoreconstructbuildingmodelsfromasingleaerialimage |