Attention-Gate-Based Encoder–Decoder Network for Automatical Building Extraction
Rapidly developing remote sensing technology provides massive data for urban planning, mapping, and disaster management. As a carrier of human productive activities, buildings are essential to both urban dynamic monitoring and suburban construction inspection. Fully-convolutional-network-based metho...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9351600/ |
| _version_ | 1819092722654380032 |
|---|---|
| author | Wenjing Deng Qian Shi Jun Li |
| author_facet | Wenjing Deng Qian Shi Jun Li |
| author_sort | Wenjing Deng |
| collection | DOAJ |
| description | Rapidly developing remote sensing technology provides massive data for urban planning, mapping, and disaster management. As a carrier of human productive activities, buildings are essential to both urban dynamic monitoring and suburban construction inspection. Fully-convolutional-network-based methods have provided a paradigm for automatically extracting buildings from high-resolution imagery. However, high intraclass variance and complexity are two problems in building extraction. It is hard to identify different scales of buildings by using a single receptive field. For this purpose, in this article, we use the stable encoder- decoder architecture, combined with a grid-based attention gate and atrous spatial pyramid pooling module, to capture and restore features progressively and effectively. A modified ResNet50 encoder is also applied to extract features. The proposed method could learn gated features and distinguish buildings from complex surroundings such as trees. We evaluate our model on two building datasets, WHU aerial building dataset and our DB UAV rural building dataset. Experiments show that our model outperforms other five most recent models. The results also exhibit great potential for extracting buildings with different scales and validate the effectiveness of deep learning in practical scenarios. |
| first_indexed | 2024-12-21T23:00:08Z |
| format | Article |
| id | doaj.art-469a890e6d48455e916f7f7a01c1bdaa |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-21T23:00:08Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-469a890e6d48455e916f7f7a01c1bdaa2022-12-21T18:47:18ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01142611262010.1109/JSTARS.2021.30580979351600Attention-Gate-Based Encoder–Decoder Network for Automatical Building ExtractionWenjing Deng0https://orcid.org/0000-0002-9435-7195Qian Shi1https://orcid.org/0000-0002-1276-0352Jun Li2https://orcid.org/0000-0003-1613-9448School of Geography and Planning, Guangdong Provincial Key Laboratory of Urbanization and Geosimulation, Sun Yat-sen University, Guangzhou, ChinaSchool of Geography and Planning, Guangdong Provincial Key Laboratory of Urbanization and Geosimulation, Sun Yat-sen University, Guangzhou, ChinaSchool of Geography and Planning, Guangdong Provincial Key Laboratory of Urbanization and Geosimulation, Sun Yat-sen University, Guangzhou, ChinaRapidly developing remote sensing technology provides massive data for urban planning, mapping, and disaster management. As a carrier of human productive activities, buildings are essential to both urban dynamic monitoring and suburban construction inspection. Fully-convolutional-network-based methods have provided a paradigm for automatically extracting buildings from high-resolution imagery. However, high intraclass variance and complexity are two problems in building extraction. It is hard to identify different scales of buildings by using a single receptive field. For this purpose, in this article, we use the stable encoder- decoder architecture, combined with a grid-based attention gate and atrous spatial pyramid pooling module, to capture and restore features progressively and effectively. A modified ResNet50 encoder is also applied to extract features. The proposed method could learn gated features and distinguish buildings from complex surroundings such as trees. We evaluate our model on two building datasets, WHU aerial building dataset and our DB UAV rural building dataset. Experiments show that our model outperforms other five most recent models. The results also exhibit great potential for extracting buildings with different scales and validate the effectiveness of deep learning in practical scenarios.https://ieeexplore.ieee.org/document/9351600/Attention gate (AG)building extractiondeep learningfully convolutional networks (FCNs)semantic segmentation |
| spellingShingle | Wenjing Deng Qian Shi Jun Li Attention-Gate-Based Encoder–Decoder Network for Automatical Building Extraction IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention gate (AG) building extraction deep learning fully convolutional networks (FCNs) semantic segmentation |
| title | Attention-Gate-Based Encoder–Decoder Network for Automatical Building Extraction |
| title_full | Attention-Gate-Based Encoder–Decoder Network for Automatical Building Extraction |
| title_fullStr | Attention-Gate-Based Encoder–Decoder Network for Automatical Building Extraction |
| title_full_unstemmed | Attention-Gate-Based Encoder–Decoder Network for Automatical Building Extraction |
| title_short | Attention-Gate-Based Encoder–Decoder Network for Automatical Building Extraction |
| title_sort | attention gate based encoder x2013 decoder network for automatical building extraction |
| topic | Attention gate (AG) building extraction deep learning fully convolutional networks (FCNs) semantic segmentation |
| url | https://ieeexplore.ieee.org/document/9351600/ |
| work_keys_str_mv | AT wenjingdeng attentiongatebasedencoderx2013decodernetworkforautomaticalbuildingextraction AT qianshi attentiongatebasedencoderx2013decodernetworkforautomaticalbuildingextraction AT junli attentiongatebasedencoderx2013decodernetworkforautomaticalbuildingextraction |