SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING AN ENHANCED ENCODER-DECODER ARCHITECTURE
Semantic segmentation is one of most the important computer vision tasks for the analysis of aerial imagery in many remote sensing applications, such as resource surveys, disaster detection, and urban planning. This area of research still faces unsolved challenges, especially in cluttered environmen...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-12-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-annals.copernicus.org/articles/X-1-W1-2023/1015/2023/isprs-annals-X-1-W1-2023-1015-2023.pdf |
| _version_ | 1797403581979033600 |
|---|---|
| author | N. Aburaed N. Aburaed M. Al-Saad M. Q. Alkhatib M. S. Zitouni S. Almansoori H. Al-Ahmad |
| author_facet | N. Aburaed N. Aburaed M. Al-Saad M. Q. Alkhatib M. S. Zitouni S. Almansoori H. Al-Ahmad |
| author_sort | N. Aburaed |
| collection | DOAJ |
| description | Semantic segmentation is one of most the important computer vision tasks for the analysis of aerial imagery in many remote sensing applications, such as resource surveys, disaster detection, and urban planning. This area of research still faces unsolved challenges, especially in cluttered environments and complex sceneries. This study presents a repurposed Robust UNet (RUNet) architecture for semantic segmentation, and embeds the architecture with attention mechanism in order to enhance feature extraction and construction of segmentation maps. The attention mechanism is achieved using Squeeze-and-Excitation (SE) block. The resulting network is referred to as SE-RUNet. SE is also tested with the classical UNet, termed SE-UNet, to verify the efficiency of introducing SE. The proposed approach is trained and tested using “Semantic Segmentation of Aerial Imagery” dataset. The results are evaluated using Accuracy, Precision, Recall, F-score and mean Intersection over Union (mIoU) metrics. Comparative evaluation and experimental results show that using SE to embed attention mechanism into UNet and RUNet significantly improves the overall performance. |
| first_indexed | 2024-03-09T02:40:34Z |
| format | Article |
| id | doaj.art-963fc4370bf942c9b929e7924146a389 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-03-09T02:40:34Z |
| publishDate | 2023-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-963fc4370bf942c9b929e7924146a3892023-12-06T04:55:22ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502023-12-01X-1-W1-20231015102010.5194/isprs-annals-X-1-W1-2023-1015-2023SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING AN ENHANCED ENCODER-DECODER ARCHITECTUREN. Aburaed0N. Aburaed1M. Al-Saad2M. Q. Alkhatib3M. S. Zitouni4S. Almansoori5H. Al-Ahmad6College of Engineering and IT, University of Dubai, Dubai, UAEDepartment of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, UKCollege of Engineering and IT, University of Dubai, Dubai, UAECollege of Engineering and IT, University of Dubai, Dubai, UAECollege of Engineering and IT, University of Dubai, Dubai, UAEMohammed Bin Rashid Space Centre, Dubai, UAECollege of Engineering and IT, University of Dubai, Dubai, UAESemantic segmentation is one of most the important computer vision tasks for the analysis of aerial imagery in many remote sensing applications, such as resource surveys, disaster detection, and urban planning. This area of research still faces unsolved challenges, especially in cluttered environments and complex sceneries. This study presents a repurposed Robust UNet (RUNet) architecture for semantic segmentation, and embeds the architecture with attention mechanism in order to enhance feature extraction and construction of segmentation maps. The attention mechanism is achieved using Squeeze-and-Excitation (SE) block. The resulting network is referred to as SE-RUNet. SE is also tested with the classical UNet, termed SE-UNet, to verify the efficiency of introducing SE. The proposed approach is trained and tested using “Semantic Segmentation of Aerial Imagery” dataset. The results are evaluated using Accuracy, Precision, Recall, F-score and mean Intersection over Union (mIoU) metrics. Comparative evaluation and experimental results show that using SE to embed attention mechanism into UNet and RUNet significantly improves the overall performance.https://isprs-annals.copernicus.org/articles/X-1-W1-2023/1015/2023/isprs-annals-X-1-W1-2023-1015-2023.pdf |
| spellingShingle | N. Aburaed N. Aburaed M. Al-Saad M. Q. Alkhatib M. S. Zitouni S. Almansoori H. Al-Ahmad SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING AN ENHANCED ENCODER-DECODER ARCHITECTURE ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING AN ENHANCED ENCODER-DECODER ARCHITECTURE |
| title_full | SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING AN ENHANCED ENCODER-DECODER ARCHITECTURE |
| title_fullStr | SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING AN ENHANCED ENCODER-DECODER ARCHITECTURE |
| title_full_unstemmed | SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING AN ENHANCED ENCODER-DECODER ARCHITECTURE |
| title_short | SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGERY USING AN ENHANCED ENCODER-DECODER ARCHITECTURE |
| title_sort | semantic segmentation of remote sensing imagery using an enhanced encoder decoder architecture |
| url | https://isprs-annals.copernicus.org/articles/X-1-W1-2023/1015/2023/isprs-annals-X-1-W1-2023-1015-2023.pdf |
| work_keys_str_mv | AT naburaed semanticsegmentationofremotesensingimageryusinganenhancedencoderdecoderarchitecture AT naburaed semanticsegmentationofremotesensingimageryusinganenhancedencoderdecoderarchitecture AT malsaad semanticsegmentationofremotesensingimageryusinganenhancedencoderdecoderarchitecture AT mqalkhatib semanticsegmentationofremotesensingimageryusinganenhancedencoderdecoderarchitecture AT mszitouni semanticsegmentationofremotesensingimageryusinganenhancedencoderdecoderarchitecture AT salmansoori semanticsegmentationofremotesensingimageryusinganenhancedencoderdecoderarchitecture AT halahmad semanticsegmentationofremotesensingimageryusinganenhancedencoderdecoderarchitecture |