Shadow Detection in Remote Sensing Images Based on Multibranch Feature Aggregation and Channel-Spatial Attention
High-resolution remote sensing image shadow detection has wide applications in target recognition, land information retrieval, and other fields. However, current shadow detection technologies still face challenges, including shadow omission and difficulty in defining boundaries. To address these cha...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10806565/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554113986297856 |
|---|---|
| author | Xueli Chang Haiyang Shi Tiejun Zhang Huazhong Jin Ao Xu |
| author_facet | Xueli Chang Haiyang Shi Tiejun Zhang Huazhong Jin Ao Xu |
| author_sort | Xueli Chang |
| collection | DOAJ |
| description | High-resolution remote sensing image shadow detection has wide applications in target recognition, land information retrieval, and other fields. However, current shadow detection technologies still face challenges, including shadow omission and difficulty in defining boundaries. To address these challenges, this article proposes a shadow detection method based on a multibranch channel-spatial attention network, which combines the multibranch feature aggregation module (MFAM) and the channel-spatial parallel attention feature fusion module (C-SPAFFM). The MFAM effectively integrates shadow information at different scales, reducing missed detections caused by changes in shadow size and shape. The C-SPAFFM enhances channel information to highlight boundary features and optimizes spatial information to more accurately capture spatial variations in shadows, thereby further reducing the possibility of missed detections. The effectiveness of the proposed method was validated on the public dataset AISD and the self-constructed satellite image dataset SISD. On the AISD dataset, the F1-score, OA, IOU, and BER metrics were 93.76%, 97.36%, 88.33%, and 4.19%, respectively. On the SISD dataset, these metrics reached 91.37%, 94.91%, 84.25%, and 6.87%. Experimental results show that the proposed method performs well in shadow detection tasks for high-resolution remote sensing images. |
| format | Article |
| id | doaj-art-9967802d49084c4d9c91b439a4455270 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-9967802d49084c4d9c91b439a44552702025-01-09T00:00:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01182618263010.1109/JSTARS.2024.351974310806565Shadow Detection in Remote Sensing Images Based on Multibranch Feature Aggregation and Channel-Spatial AttentionXueli Chang0https://orcid.org/0009-0003-3539-1080Haiyang Shi1https://orcid.org/0009-0007-3772-8547Tiejun Zhang2Huazhong Jin3https://orcid.org/0000-0003-1587-4889Ao Xu4https://orcid.org/0009-0001-1763-2069School of Computer Science, Hubei University of Technology, Wuhan, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan, ChinaHigh-resolution remote sensing image shadow detection has wide applications in target recognition, land information retrieval, and other fields. However, current shadow detection technologies still face challenges, including shadow omission and difficulty in defining boundaries. To address these challenges, this article proposes a shadow detection method based on a multibranch channel-spatial attention network, which combines the multibranch feature aggregation module (MFAM) and the channel-spatial parallel attention feature fusion module (C-SPAFFM). The MFAM effectively integrates shadow information at different scales, reducing missed detections caused by changes in shadow size and shape. The C-SPAFFM enhances channel information to highlight boundary features and optimizes spatial information to more accurately capture spatial variations in shadows, thereby further reducing the possibility of missed detections. The effectiveness of the proposed method was validated on the public dataset AISD and the self-constructed satellite image dataset SISD. On the AISD dataset, the F1-score, OA, IOU, and BER metrics were 93.76%, 97.36%, 88.33%, and 4.19%, respectively. On the SISD dataset, these metrics reached 91.37%, 94.91%, 84.25%, and 6.87%. Experimental results show that the proposed method performs well in shadow detection tasks for high-resolution remote sensing images.https://ieeexplore.ieee.org/document/10806565/Attention mechanismmultibranch feature aggregationremote sensing imageshadow detection |
| spellingShingle | Xueli Chang Haiyang Shi Tiejun Zhang Huazhong Jin Ao Xu Shadow Detection in Remote Sensing Images Based on Multibranch Feature Aggregation and Channel-Spatial Attention IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention mechanism multibranch feature aggregation remote sensing image shadow detection |
| title | Shadow Detection in Remote Sensing Images Based on Multibranch Feature Aggregation and Channel-Spatial Attention |
| title_full | Shadow Detection in Remote Sensing Images Based on Multibranch Feature Aggregation and Channel-Spatial Attention |
| title_fullStr | Shadow Detection in Remote Sensing Images Based on Multibranch Feature Aggregation and Channel-Spatial Attention |
| title_full_unstemmed | Shadow Detection in Remote Sensing Images Based on Multibranch Feature Aggregation and Channel-Spatial Attention |
| title_short | Shadow Detection in Remote Sensing Images Based on Multibranch Feature Aggregation and Channel-Spatial Attention |
| title_sort | shadow detection in remote sensing images based on multibranch feature aggregation and channel spatial attention |
| topic | Attention mechanism multibranch feature aggregation remote sensing image shadow detection |
| url | https://ieeexplore.ieee.org/document/10806565/ |
| work_keys_str_mv | AT xuelichang shadowdetectioninremotesensingimagesbasedonmultibranchfeatureaggregationandchannelspatialattention AT haiyangshi shadowdetectioninremotesensingimagesbasedonmultibranchfeatureaggregationandchannelspatialattention AT tiejunzhang shadowdetectioninremotesensingimagesbasedonmultibranchfeatureaggregationandchannelspatialattention AT huazhongjin shadowdetectioninremotesensingimagesbasedonmultibranchfeatureaggregationandchannelspatialattention AT aoxu shadowdetectioninremotesensingimagesbasedonmultibranchfeatureaggregationandchannelspatialattention |