Feature Enhancement Attention for Road Extraction in High-Resolution Remote Sensing Image
Road extraction from images captured via remote sensing is a pivotal task across multiple domains, encompassing urban planning and intelligent transportation systems. In the realm of high-resolution remote sensing, traditional approaches to road extraction confront obstacles pertaining to reduced ac...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10738465/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846169468946874368 |
|---|---|
| author | Hang Yu Chenyang Li Yuru Guo Suiping Zhou |
| author_facet | Hang Yu Chenyang Li Yuru Guo Suiping Zhou |
| author_sort | Hang Yu |
| collection | DOAJ |
| description | Road extraction from images captured via remote sensing is a pivotal task across multiple domains, encompassing urban planning and intelligent transportation systems. In the realm of high-resolution remote sensing, traditional approaches to road extraction confront obstacles pertaining to reduced accuracy and resilience. This study introduces an innovative methodology for road extraction tailored to high-resolution remote sensing data. The devised algorithm integrates a feature enhancement attention module alongside parallel feature fusion. Specifically, the feature enhancement attention module is introduced to augment the network's capacity in discerning road-related information by analyzing feature maps produced at varying resolutions. Subsequently, during feature map extraction, the parallel feature fusion technique is employed to merge shallow and deep features sharing the same resolution, thus effectively leveraging the strengths of both to enhance the model's precision. Moreover, the network undertakes the computation of correlations among feature maps of differing resolutions as well as the entire feature map, thereby facilitating a holistic grasp of the global structure and semantic information embedded within the image. Experimental evaluations conducted on the CHN6-CUG and Massachusetts datasets substantiate that the proposed approach outperforms prevailing mainstream methods for road extraction in terms of both accuracy and processing speed. |
| format | Article |
| id | doaj-art-2f29f57be84a49b395a7cacfb46e2f82 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-2f29f57be84a49b395a7cacfb46e2f822024-11-13T00:00:14ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-0117198051981610.1109/JSTARS.2024.348672310738465Feature Enhancement Attention for Road Extraction in High-Resolution Remote Sensing ImageHang Yu0https://orcid.org/0000-0002-8869-6166Chenyang Li1https://orcid.org/0000-0002-5371-5574Yuru Guo2https://orcid.org/0009-0003-5252-7939Suiping Zhou3https://orcid.org/0000-0003-0914-066XSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaRoad extraction from images captured via remote sensing is a pivotal task across multiple domains, encompassing urban planning and intelligent transportation systems. In the realm of high-resolution remote sensing, traditional approaches to road extraction confront obstacles pertaining to reduced accuracy and resilience. This study introduces an innovative methodology for road extraction tailored to high-resolution remote sensing data. The devised algorithm integrates a feature enhancement attention module alongside parallel feature fusion. Specifically, the feature enhancement attention module is introduced to augment the network's capacity in discerning road-related information by analyzing feature maps produced at varying resolutions. Subsequently, during feature map extraction, the parallel feature fusion technique is employed to merge shallow and deep features sharing the same resolution, thus effectively leveraging the strengths of both to enhance the model's precision. Moreover, the network undertakes the computation of correlations among feature maps of differing resolutions as well as the entire feature map, thereby facilitating a holistic grasp of the global structure and semantic information embedded within the image. Experimental evaluations conducted on the CHN6-CUG and Massachusetts datasets substantiate that the proposed approach outperforms prevailing mainstream methods for road extraction in terms of both accuracy and processing speed.https://ieeexplore.ieee.org/document/10738465/Attention mechanismHRNetremote sensingroad extraction |
| spellingShingle | Hang Yu Chenyang Li Yuru Guo Suiping Zhou Feature Enhancement Attention for Road Extraction in High-Resolution Remote Sensing Image IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention mechanism HRNet remote sensing road extraction |
| title | Feature Enhancement Attention for Road Extraction in High-Resolution Remote Sensing Image |
| title_full | Feature Enhancement Attention for Road Extraction in High-Resolution Remote Sensing Image |
| title_fullStr | Feature Enhancement Attention for Road Extraction in High-Resolution Remote Sensing Image |
| title_full_unstemmed | Feature Enhancement Attention for Road Extraction in High-Resolution Remote Sensing Image |
| title_short | Feature Enhancement Attention for Road Extraction in High-Resolution Remote Sensing Image |
| title_sort | feature enhancement attention for road extraction in high resolution remote sensing image |
| topic | Attention mechanism HRNet remote sensing road extraction |
| url | https://ieeexplore.ieee.org/document/10738465/ |
| work_keys_str_mv | AT hangyu featureenhancementattentionforroadextractioninhighresolutionremotesensingimage AT chenyangli featureenhancementattentionforroadextractioninhighresolutionremotesensingimage AT yuruguo featureenhancementattentionforroadextractioninhighresolutionremotesensingimage AT suipingzhou featureenhancementattentionforroadextractioninhighresolutionremotesensingimage |