Multiscale feature tuned trans-DeepLabV3+ based semantic segmentation of aerial images using improved red piranha optimization algorithm
Abstract The use of higher-resolution spatial aerial images for semantic segmentation in everyday tasks has increased due to recent advancements in remote sensing and several other applications. Nonetheless, supervised learning necessitates a substantial quantity of images with pixel-level labeling....
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-12940-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849226393363152896 |
|---|---|
| author | P. Anilkumar K. Lokesh A. Naveen Kumar D. John Pradeep Y. V. Pavan Kumar Rammohan Mallipeddi |
| author_facet | P. Anilkumar K. Lokesh A. Naveen Kumar D. John Pradeep Y. V. Pavan Kumar Rammohan Mallipeddi |
| author_sort | P. Anilkumar |
| collection | DOAJ |
| description | Abstract The use of higher-resolution spatial aerial images for semantic segmentation in everyday tasks has increased due to recent advancements in remote sensing and several other applications. Nonetheless, supervised learning necessitates a substantial quantity of images with pixel-level labeling. Currently, available techniques, which are mostly Deep Semantic Segmentation Networks (DSSN), might not be appropriate for application domains with a dearth of labels containing targeted masks of outputs. For “semantic segmentation of higher-quality aerial images", multi-scale semantic details have to be extracted. Many techniques have been executed in recent years to increase the networks’ capacity to capture multi-scale details in a variety of ways. However, these techniques consistently exhibit poor efficiency regarding speed and accuracy when dealing with aerial images. In this work, an effective image semantic segmentation method utilizing deep learning techniques is designed using a heuristic technique. Standard information sources are used to collect the aerial photos. The Multi-Scale RetiNex (MSRN) technique is employed to enhance the obtained images’ color quality. The Multiscale Feature Tuned-Trans-Deeplabv3+ (MSTDeepLabV3+) system is then used to receive the improved image as its input for the feature extraction task. The Improved Red Piranha Optimization (IRPO) approach is deployed to fine-tune the MSTDeepLabV3+ parameters. The MSTDeepLabV3+ helps to provide the final semantically segmented aerial images. To assess how well the implemented model performs, an experimental setup is carried out. The excellent performance offered by the executed model is proved using the simulation outcome. |
| format | Article |
| id | doaj-art-f73a43e3e1c84b2080deea4c60d22f98 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-f73a43e3e1c84b2080deea4c60d22f982025-08-24T11:22:23ZengNature PortfolioScientific Reports2045-23222025-08-0115112910.1038/s41598-025-12940-5Multiscale feature tuned trans-DeepLabV3+ based semantic segmentation of aerial images using improved red piranha optimization algorithmP. Anilkumar0K. Lokesh1A. Naveen Kumar2D. John Pradeep3Y. V. Pavan Kumar4Rammohan Mallipeddi5Department of Electronics and Communication Engineering, Mother Theresa Institute of Engineering and TechnologyDepartment of Artificial Intelligence and Data Science, Mother Theresa Institute of Engineering and TechnologyDepartment of Science and Humanities, Mother Theresa Institute of Engineering and TechnologySchool of Electronics Engineering, VIT-AP UniversitySchool of Electronics Engineering, VIT-AP UniversityDepartment of Artificial Intelligence, School of Electronics Engineering, Kyungpook National UniversityAbstract The use of higher-resolution spatial aerial images for semantic segmentation in everyday tasks has increased due to recent advancements in remote sensing and several other applications. Nonetheless, supervised learning necessitates a substantial quantity of images with pixel-level labeling. Currently, available techniques, which are mostly Deep Semantic Segmentation Networks (DSSN), might not be appropriate for application domains with a dearth of labels containing targeted masks of outputs. For “semantic segmentation of higher-quality aerial images", multi-scale semantic details have to be extracted. Many techniques have been executed in recent years to increase the networks’ capacity to capture multi-scale details in a variety of ways. However, these techniques consistently exhibit poor efficiency regarding speed and accuracy when dealing with aerial images. In this work, an effective image semantic segmentation method utilizing deep learning techniques is designed using a heuristic technique. Standard information sources are used to collect the aerial photos. The Multi-Scale RetiNex (MSRN) technique is employed to enhance the obtained images’ color quality. The Multiscale Feature Tuned-Trans-Deeplabv3+ (MSTDeepLabV3+) system is then used to receive the improved image as its input for the feature extraction task. The Improved Red Piranha Optimization (IRPO) approach is deployed to fine-tune the MSTDeepLabV3+ parameters. The MSTDeepLabV3+ helps to provide the final semantically segmented aerial images. To assess how well the implemented model performs, an experimental setup is carried out. The excellent performance offered by the executed model is proved using the simulation outcome.https://doi.org/10.1038/s41598-025-12940-5High-resolution aerial imagesRemote sensingSemantic segmentationImage enhancementMulti-Scale RetiNexMultiscale feature tuned-trans-Deeplabv3+ |
| spellingShingle | P. Anilkumar K. Lokesh A. Naveen Kumar D. John Pradeep Y. V. Pavan Kumar Rammohan Mallipeddi Multiscale feature tuned trans-DeepLabV3+ based semantic segmentation of aerial images using improved red piranha optimization algorithm Scientific Reports High-resolution aerial images Remote sensing Semantic segmentation Image enhancement Multi-Scale RetiNex Multiscale feature tuned-trans-Deeplabv3+ |
| title | Multiscale feature tuned trans-DeepLabV3+ based semantic segmentation of aerial images using improved red piranha optimization algorithm |
| title_full | Multiscale feature tuned trans-DeepLabV3+ based semantic segmentation of aerial images using improved red piranha optimization algorithm |
| title_fullStr | Multiscale feature tuned trans-DeepLabV3+ based semantic segmentation of aerial images using improved red piranha optimization algorithm |
| title_full_unstemmed | Multiscale feature tuned trans-DeepLabV3+ based semantic segmentation of aerial images using improved red piranha optimization algorithm |
| title_short | Multiscale feature tuned trans-DeepLabV3+ based semantic segmentation of aerial images using improved red piranha optimization algorithm |
| title_sort | multiscale feature tuned trans deeplabv3 based semantic segmentation of aerial images using improved red piranha optimization algorithm |
| topic | High-resolution aerial images Remote sensing Semantic segmentation Image enhancement Multi-Scale RetiNex Multiscale feature tuned-trans-Deeplabv3+ |
| url | https://doi.org/10.1038/s41598-025-12940-5 |
| work_keys_str_mv | AT panilkumar multiscalefeaturetunedtransdeeplabv3basedsemanticsegmentationofaerialimagesusingimprovedredpiranhaoptimizationalgorithm AT klokesh multiscalefeaturetunedtransdeeplabv3basedsemanticsegmentationofaerialimagesusingimprovedredpiranhaoptimizationalgorithm AT anaveenkumar multiscalefeaturetunedtransdeeplabv3basedsemanticsegmentationofaerialimagesusingimprovedredpiranhaoptimizationalgorithm AT djohnpradeep multiscalefeaturetunedtransdeeplabv3basedsemanticsegmentationofaerialimagesusingimprovedredpiranhaoptimizationalgorithm AT yvpavankumar multiscalefeaturetunedtransdeeplabv3basedsemanticsegmentationofaerialimagesusingimprovedredpiranhaoptimizationalgorithm AT rammohanmallipeddi multiscalefeaturetunedtransdeeplabv3basedsemanticsegmentationofaerialimagesusingimprovedredpiranhaoptimizationalgorithm |