Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale Context
Built-up areas are the main areas for human production and life. The wide availability of high-resolution satellite images provides new opportunities for fine-scale detection and mapping of built-up areas. However, great challenges remain because built-up areas are large-scale composite geographical...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10138576/ |
| _version_ | 1797790963529154560 |
|---|---|
| author | Yixiang Chen Shuai Yao Zhongwen Hu Bo Huang Lizhi Miao Jiaming Zhang |
| author_facet | Yixiang Chen Shuai Yao Zhongwen Hu Bo Huang Lizhi Miao Jiaming Zhang |
| author_sort | Yixiang Chen |
| collection | DOAJ |
| description | Built-up areas are the main areas for human production and life. The wide availability of high-resolution satellite images provides new opportunities for fine-scale detection and mapping of built-up areas. However, great challenges remain because built-up areas are large-scale composite geographical objects, which contain diverse object classes and complex scenes, and have extremely large feature heterogeneity across space. For the automatic recognition of built-up areas in high spatial resolution satellite images, a block-level built-up area extraction framework combing densely connected dual-attention network and multiscale context is proposed. The proposed method first divides an image into multiscale blocks with a certain proportion of overlap through multisize grids and their multistep offsets. It then uses the constructed lightweight network integrating dense connection and dual attention to realize the feature representation and discrimination of image blocks. Finally, it achieves the refined detection of built-up areas by integrating the prediction results under different divisions through pixel-level multilabel voting. GaoFen-2 satellite images covering Shenzhen city, China, are used to verify the effectiveness of the proposed method. In the five selected test areas, the F1 score of the proposed method ranges from 0.8720 to 0.8983. Results visually preserve the integrity of internal morphology and have a well-defined boundary. The proposed method shows better performance than the state-of-the-art built-up area extraction methods. It can potentially be applied for fine mapping of large-scale urban built-up areas from high-resolution satellite images. |
| first_indexed | 2024-03-13T02:12:00Z |
| format | Article |
| id | doaj.art-64a9520ff1174d25995654e7a181b250 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-13T02:12:00Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-64a9520ff1174d25995654e7a181b2502023-06-30T23:01:02ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01165128514310.1109/JSTARS.2023.328136310138576Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale ContextYixiang Chen0https://orcid.org/0000-0002-3795-7530Shuai Yao1Zhongwen Hu2https://orcid.org/0000-0003-2689-3196Bo Huang3https://orcid.org/0000-0002-5063-3522Lizhi Miao4https://orcid.org/0000-0001-8768-4502Jiaming Zhang5https://orcid.org/0009-0001-5707-7290School of Geographic and Biologic Information, Nanjing University of Posts and Telecommunications, Nanjing, ChinaSchool of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, ChinaMNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, Shenzhen University, Shenzhen, ChinaDepartment of Geography and Resource Management, The Chinese University of Hong Kong, Hong KongSchool of Geographic and Biologic Information, Nanjing University of Posts and Telecommunications, Nanjing, ChinaDepartment of Biomedical Engineering, College of Engineering, Boston University, Boston, MA, USABuilt-up areas are the main areas for human production and life. The wide availability of high-resolution satellite images provides new opportunities for fine-scale detection and mapping of built-up areas. However, great challenges remain because built-up areas are large-scale composite geographical objects, which contain diverse object classes and complex scenes, and have extremely large feature heterogeneity across space. For the automatic recognition of built-up areas in high spatial resolution satellite images, a block-level built-up area extraction framework combing densely connected dual-attention network and multiscale context is proposed. The proposed method first divides an image into multiscale blocks with a certain proportion of overlap through multisize grids and their multistep offsets. It then uses the constructed lightweight network integrating dense connection and dual attention to realize the feature representation and discrimination of image blocks. Finally, it achieves the refined detection of built-up areas by integrating the prediction results under different divisions through pixel-level multilabel voting. GaoFen-2 satellite images covering Shenzhen city, China, are used to verify the effectiveness of the proposed method. In the five selected test areas, the F1 score of the proposed method ranges from 0.8720 to 0.8983. Results visually preserve the integrity of internal morphology and have a well-defined boundary. The proposed method shows better performance than the state-of-the-art built-up area extraction methods. It can potentially be applied for fine mapping of large-scale urban built-up areas from high-resolution satellite images.https://ieeexplore.ieee.org/document/10138576/Block levelbuilt-up area extractionhigh resolutionmultiscalesatellite image |
| spellingShingle | Yixiang Chen Shuai Yao Zhongwen Hu Bo Huang Lizhi Miao Jiaming Zhang Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale Context IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Block level built-up area extraction high resolution multiscale satellite image |
| title | Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale Context |
| title_full | Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale Context |
| title_fullStr | Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale Context |
| title_full_unstemmed | Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale Context |
| title_short | Built-Up Area Extraction Combing Densely Connected Dual-Attention Network and Multiscale Context |
| title_sort | built up area extraction combing densely connected dual attention network and multiscale context |
| topic | Block level built-up area extraction high resolution multiscale satellite image |
| url | https://ieeexplore.ieee.org/document/10138576/ |
| work_keys_str_mv | AT yixiangchen builtupareaextractioncombingdenselyconnecteddualattentionnetworkandmultiscalecontext AT shuaiyao builtupareaextractioncombingdenselyconnecteddualattentionnetworkandmultiscalecontext AT zhongwenhu builtupareaextractioncombingdenselyconnecteddualattentionnetworkandmultiscalecontext AT bohuang builtupareaextractioncombingdenselyconnecteddualattentionnetworkandmultiscalecontext AT lizhimiao builtupareaextractioncombingdenselyconnecteddualattentionnetworkandmultiscalecontext AT jiamingzhang builtupareaextractioncombingdenselyconnecteddualattentionnetworkandmultiscalecontext |