KNOWLEDGE BASED 3D BUILDING MODEL RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS FROM LIDAR AND AERIAL IMAGERIES
In recent years, with the development of the high resolution data acquisition technologies, many different approaches and algorithms have been presented to extract the accurate and timely updated 3D models of buildings as a key element of city structures for numerous applications in urban mapping. I...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2016-06-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B3/833/2016/isprs-archives-XLI-B3-833-2016.pdf |
| _version_ | 1818418339392782336 |
|---|---|
| author | F. Alidoost H. Arefi |
| author_facet | F. Alidoost H. Arefi |
| author_sort | F. Alidoost |
| collection | DOAJ |
| description | In recent years, with the development of the high resolution data acquisition technologies, many different approaches and algorithms have been presented to extract the accurate and timely updated 3D models of buildings as a key element of city structures for numerous applications in urban mapping. In this paper, a novel and model-based approach is proposed for automatic recognition of buildings’ roof models such as flat, gable, hip, and pyramid hip roof models based on deep structures for hierarchical learning of features that are extracted from both LiDAR and aerial ortho-photos. The main steps of this approach include building segmentation, feature extraction and learning, and finally building roof labeling in a supervised pre-trained Convolutional Neural Network (CNN) framework to have an automatic recognition system for various types of buildings over an urban area. In this framework, the height information provides invariant geometric features for convolutional neural network to localize the boundary of each individual roofs. CNN is a kind of feed-forward neural network with the multilayer perceptron concept which consists of a number of convolutional and subsampling layers in an adaptable structure and it is widely used in pattern recognition and object detection application. Since the training dataset is a small library of labeled models for different shapes of roofs, the computation time of learning can be decreased significantly using the pre-trained models. The experimental results highlight the effectiveness of the deep learning approach to detect and extract the pattern of buildings’ roofs automatically considering the complementary nature of height and RGB information. |
| first_indexed | 2024-12-14T12:21:06Z |
| format | Article |
| id | doaj.art-c963d13da5c743d1809b8693eff22170 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-14T12:21:06Z |
| publishDate | 2016-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-c963d13da5c743d1809b8693eff221702022-12-21T23:01:29ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342016-06-01XLI-B383384010.5194/isprs-archives-XLI-B3-833-2016KNOWLEDGE BASED 3D BUILDING MODEL RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS FROM LIDAR AND AERIAL IMAGERIESF. Alidoost0H. Arefi1School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, IranSchool of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, IranIn recent years, with the development of the high resolution data acquisition technologies, many different approaches and algorithms have been presented to extract the accurate and timely updated 3D models of buildings as a key element of city structures for numerous applications in urban mapping. In this paper, a novel and model-based approach is proposed for automatic recognition of buildings’ roof models such as flat, gable, hip, and pyramid hip roof models based on deep structures for hierarchical learning of features that are extracted from both LiDAR and aerial ortho-photos. The main steps of this approach include building segmentation, feature extraction and learning, and finally building roof labeling in a supervised pre-trained Convolutional Neural Network (CNN) framework to have an automatic recognition system for various types of buildings over an urban area. In this framework, the height information provides invariant geometric features for convolutional neural network to localize the boundary of each individual roofs. CNN is a kind of feed-forward neural network with the multilayer perceptron concept which consists of a number of convolutional and subsampling layers in an adaptable structure and it is widely used in pattern recognition and object detection application. Since the training dataset is a small library of labeled models for different shapes of roofs, the computation time of learning can be decreased significantly using the pre-trained models. The experimental results highlight the effectiveness of the deep learning approach to detect and extract the pattern of buildings’ roofs automatically considering the complementary nature of height and RGB information.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B3/833/2016/isprs-archives-XLI-B3-833-2016.pdf |
| spellingShingle | F. Alidoost H. Arefi KNOWLEDGE BASED 3D BUILDING MODEL RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS FROM LIDAR AND AERIAL IMAGERIES The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | KNOWLEDGE BASED 3D BUILDING MODEL RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS FROM LIDAR AND AERIAL IMAGERIES |
| title_full | KNOWLEDGE BASED 3D BUILDING MODEL RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS FROM LIDAR AND AERIAL IMAGERIES |
| title_fullStr | KNOWLEDGE BASED 3D BUILDING MODEL RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS FROM LIDAR AND AERIAL IMAGERIES |
| title_full_unstemmed | KNOWLEDGE BASED 3D BUILDING MODEL RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS FROM LIDAR AND AERIAL IMAGERIES |
| title_short | KNOWLEDGE BASED 3D BUILDING MODEL RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS FROM LIDAR AND AERIAL IMAGERIES |
| title_sort | knowledge based 3d building model recognition using convolutional neural networks from lidar and aerial imageries |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B3/833/2016/isprs-archives-XLI-B3-833-2016.pdf |
| work_keys_str_mv | AT falidoost knowledgebased3dbuildingmodelrecognitionusingconvolutionalneuralnetworksfromlidarandaerialimageries AT harefi knowledgebased3dbuildingmodelrecognitionusingconvolutionalneuralnetworksfromlidarandaerialimageries |