Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural Network
The detection of buildings in the city is essential in several geospatial domains and for decision-making regarding intelligence for city planning, tax collection, project management, revenue generation, and smart cities, among other areas. In the past, the classical approach used for building detec...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/23/4803 |
| _version_ | 1827674725509234688 |
|---|---|
| author | Sani Success Ojogbane Shattri Mansor Bahareh Kalantar Zailani Bin Khuzaimah Helmi Zulhaidi Mohd Shafri Naonori Ueda |
| author_facet | Sani Success Ojogbane Shattri Mansor Bahareh Kalantar Zailani Bin Khuzaimah Helmi Zulhaidi Mohd Shafri Naonori Ueda |
| author_sort | Sani Success Ojogbane |
| collection | DOAJ |
| description | The detection of buildings in the city is essential in several geospatial domains and for decision-making regarding intelligence for city planning, tax collection, project management, revenue generation, and smart cities, among other areas. In the past, the classical approach used for building detection was by using the imagery and it entailed human–computer interaction, which was a daunting proposition. To tackle this task, a novel network based on an end-to-end deep learning framework is proposed to detect and classify buildings features. The proposed CNN has three parallel stream channels: the first is the high-resolution aerial imagery, while the second stream is the digital surface model (DSM). The third was fixed on extracting deep features using the fusion of channel one and channel two, respectively. Furthermore, the channel has eight group convolution blocks of 2D convolution with three max-pooling layers. The proposed model’s efficiency and dependability were tested on three different categories of complex urban building structures in the study area. Then, morphological operations were applied to the extracted building footprints to increase the uniformity of the building boundaries and produce improved building perimeters. Thus, our approach bridges a significant gap in detecting building objects in diverse environments; the overall accuracy (OA) and kappa coefficient of the proposed method are greater than 80% and 0.605, respectively. The findings support the proposed framework and methodologies’ efficacy and effectiveness at extracting buildings from complex environments. |
| first_indexed | 2024-03-10T04:46:20Z |
| format | Article |
| id | doaj.art-5124d3181f12425d8486ad5524d85a0e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T04:46:20Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5124d3181f12425d8486ad5524d85a0e2023-11-23T02:56:34ZengMDPI AGRemote Sensing2072-42922021-11-011323480310.3390/rs13234803Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural NetworkSani Success Ojogbane0Shattri Mansor1Bahareh Kalantar2Zailani Bin Khuzaimah3Helmi Zulhaidi Mohd Shafri4Naonori Ueda5Department of Civil Engineering, Geospatial Information Science Research Centre (GISRC), Faculty of Engineering, Universiti Putra Malaysia, Seri Kembangan 43400, MalaysiaDepartment of Civil Engineering, Geospatial Information Science Research Centre (GISRC), Faculty of Engineering, Universiti Putra Malaysia, Seri Kembangan 43400, MalaysiaRIKEN Center for Advanced Intelligence Project, Goal-Oriented Technology Research Group, Disaster Resilience Science Team, Tokyo 103-0027, JapanInstitute of Plantations Studies, University Putra Malaysia, Seri Kembangan 43400, MalaysiaDepartment of Civil Engineering, Geospatial Information Science Research Centre (GISRC), Faculty of Engineering, Universiti Putra Malaysia, Seri Kembangan 43400, MalaysiaRIKEN Center for Advanced Intelligence Project, Goal-Oriented Technology Research Group, Disaster Resilience Science Team, Tokyo 103-0027, JapanThe detection of buildings in the city is essential in several geospatial domains and for decision-making regarding intelligence for city planning, tax collection, project management, revenue generation, and smart cities, among other areas. In the past, the classical approach used for building detection was by using the imagery and it entailed human–computer interaction, which was a daunting proposition. To tackle this task, a novel network based on an end-to-end deep learning framework is proposed to detect and classify buildings features. The proposed CNN has three parallel stream channels: the first is the high-resolution aerial imagery, while the second stream is the digital surface model (DSM). The third was fixed on extracting deep features using the fusion of channel one and channel two, respectively. Furthermore, the channel has eight group convolution blocks of 2D convolution with three max-pooling layers. The proposed model’s efficiency and dependability were tested on three different categories of complex urban building structures in the study area. Then, morphological operations were applied to the extracted building footprints to increase the uniformity of the building boundaries and produce improved building perimeters. Thus, our approach bridges a significant gap in detecting building objects in diverse environments; the overall accuracy (OA) and kappa coefficient of the proposed method are greater than 80% and 0.605, respectively. The findings support the proposed framework and methodologies’ efficacy and effectiveness at extracting buildings from complex environments.https://www.mdpi.com/2072-4292/13/23/4803building classificationextractionconvolution neural networks (CNN)LiDARhigh-resolution aerial imagery |
| spellingShingle | Sani Success Ojogbane Shattri Mansor Bahareh Kalantar Zailani Bin Khuzaimah Helmi Zulhaidi Mohd Shafri Naonori Ueda Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural Network Remote Sensing building classification extraction convolution neural networks (CNN) LiDAR high-resolution aerial imagery |
| title | Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural Network |
| title_full | Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural Network |
| title_fullStr | Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural Network |
| title_full_unstemmed | Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural Network |
| title_short | Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural Network |
| title_sort | automated building detection from airborne lidar and very high resolution aerial imagery with deep neural network |
| topic | building classification extraction convolution neural networks (CNN) LiDAR high-resolution aerial imagery |
| url | https://www.mdpi.com/2072-4292/13/23/4803 |
| work_keys_str_mv | AT sanisuccessojogbane automatedbuildingdetectionfromairbornelidarandveryhighresolutionaerialimagerywithdeepneuralnetwork AT shattrimansor automatedbuildingdetectionfromairbornelidarandveryhighresolutionaerialimagerywithdeepneuralnetwork AT baharehkalantar automatedbuildingdetectionfromairbornelidarandveryhighresolutionaerialimagerywithdeepneuralnetwork AT zailanibinkhuzaimah automatedbuildingdetectionfromairbornelidarandveryhighresolutionaerialimagerywithdeepneuralnetwork AT helmizulhaidimohdshafri automatedbuildingdetectionfromairbornelidarandveryhighresolutionaerialimagerywithdeepneuralnetwork AT naonoriueda automatedbuildingdetectionfromairbornelidarandveryhighresolutionaerialimagerywithdeepneuralnetwork |