PCAN—Part-Based Context Attention Network for Thermal Power Plant Detection in Remote Sensing Imagery
The detection of Thermal Power Plants (TPPs) is a meaningful task for remote sensing image interpretation. It is a challenging task, because as facility objects TPPs are composed of various distinctive and irregular components. In this paper, we propose a novel end-to-end detection framework for TPP...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/7/1243 |
| _version_ | 1797540070422478848 |
|---|---|
| author | Wenxin Yin Wenhui Diao Peijin Wang Xin Gao Ya Li Xian Sun |
| author_facet | Wenxin Yin Wenhui Diao Peijin Wang Xin Gao Ya Li Xian Sun |
| author_sort | Wenxin Yin |
| collection | DOAJ |
| description | The detection of Thermal Power Plants (TPPs) is a meaningful task for remote sensing image interpretation. It is a challenging task, because as facility objects TPPs are composed of various distinctive and irregular components. In this paper, we propose a novel end-to-end detection framework for TPPs based on deep convolutional neural networks. Specifically, based on the RetinaNet one-stage detector, a context attention multi-scale feature extraction network is proposed to fuse global spatial attention to strengthen the ability in representing irregular objects. In addition, we design a part-based attention module to adapt to TPPs containing distinctive components. Experiments show that the proposed method outperforms the state-of-the-art methods and can achieve 68.15% mean average precision. |
| first_indexed | 2024-03-10T12:55:51Z |
| format | Article |
| id | doaj.art-2a182d6b30594408a4f6df5c8714ddef |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T12:55:51Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2a182d6b30594408a4f6df5c8714ddef2023-11-21T11:54:40ZengMDPI AGRemote Sensing2072-42922021-03-01137124310.3390/rs13071243PCAN—Part-Based Context Attention Network for Thermal Power Plant Detection in Remote Sensing ImageryWenxin Yin0Wenhui Diao1Peijin Wang2Xin Gao3Ya Li4Xian Sun5Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaThe detection of Thermal Power Plants (TPPs) is a meaningful task for remote sensing image interpretation. It is a challenging task, because as facility objects TPPs are composed of various distinctive and irregular components. In this paper, we propose a novel end-to-end detection framework for TPPs based on deep convolutional neural networks. Specifically, based on the RetinaNet one-stage detector, a context attention multi-scale feature extraction network is proposed to fuse global spatial attention to strengthen the ability in representing irregular objects. In addition, we design a part-based attention module to adapt to TPPs containing distinctive components. Experiments show that the proposed method outperforms the state-of-the-art methods and can achieve 68.15% mean average precision.https://www.mdpi.com/2072-4292/13/7/1243remote sensingfacility object detectionthermal power plantsconvolution neural networkspatial attentionpart-based attention |
| spellingShingle | Wenxin Yin Wenhui Diao Peijin Wang Xin Gao Ya Li Xian Sun PCAN—Part-Based Context Attention Network for Thermal Power Plant Detection in Remote Sensing Imagery Remote Sensing remote sensing facility object detection thermal power plants convolution neural network spatial attention part-based attention |
| title | PCAN—Part-Based Context Attention Network for Thermal Power Plant Detection in Remote Sensing Imagery |
| title_full | PCAN—Part-Based Context Attention Network for Thermal Power Plant Detection in Remote Sensing Imagery |
| title_fullStr | PCAN—Part-Based Context Attention Network for Thermal Power Plant Detection in Remote Sensing Imagery |
| title_full_unstemmed | PCAN—Part-Based Context Attention Network for Thermal Power Plant Detection in Remote Sensing Imagery |
| title_short | PCAN—Part-Based Context Attention Network for Thermal Power Plant Detection in Remote Sensing Imagery |
| title_sort | pcan part based context attention network for thermal power plant detection in remote sensing imagery |
| topic | remote sensing facility object detection thermal power plants convolution neural network spatial attention part-based attention |
| url | https://www.mdpi.com/2072-4292/13/7/1243 |
| work_keys_str_mv | AT wenxinyin pcanpartbasedcontextattentionnetworkforthermalpowerplantdetectioninremotesensingimagery AT wenhuidiao pcanpartbasedcontextattentionnetworkforthermalpowerplantdetectioninremotesensingimagery AT peijinwang pcanpartbasedcontextattentionnetworkforthermalpowerplantdetectioninremotesensingimagery AT xingao pcanpartbasedcontextattentionnetworkforthermalpowerplantdetectioninremotesensingimagery AT yali pcanpartbasedcontextattentionnetworkforthermalpowerplantdetectioninremotesensingimagery AT xiansun pcanpartbasedcontextattentionnetworkforthermalpowerplantdetectioninremotesensingimagery |