UniU-Net: A Unified U-Net Deep Learning Approach for High-Precision Areca Palm Segmentation in Remote Sensing Imagery
This study introduces a novel deep learning-based model, UniU-Net, designed to achieve the high-precision segmentation of areca palms in remote sensing imagery. UniU-Net incorporates an auxiliary encoder and a unified attention fusion module (UAFM), enhancing the model’s anti-overfitting capabilitie...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/9/4813 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850137743168897024 |
|---|---|
| author | Shaohua Wang Yan Wang Jianwei Yue Haojian Liang Zihan Zhang Bojun Li |
| author_facet | Shaohua Wang Yan Wang Jianwei Yue Haojian Liang Zihan Zhang Bojun Li |
| author_sort | Shaohua Wang |
| collection | DOAJ |
| description | This study introduces a novel deep learning-based model, UniU-Net, designed to achieve the high-precision segmentation of areca palms in remote sensing imagery. UniU-Net incorporates an auxiliary encoder and a unified attention fusion module (UAFM), enhancing the model’s anti-overfitting capabilities to improve its overall segmentation performance. Specifically, the primary and auxiliary encoders, through isomorphic parallel processing, leverage the principles of structural reparameterization to enhance the model’s effective learning of areca palm features while reducing the risk of overfitting. The UAFM utilizes a spatial attention mechanism to facilitate the effective fusion of multi-scale features. This architecture enables the model to capture intricate morphological details and accurately delineate the boundaries of areca palms, even under complex and heterogeneous environmental conditions such as mixed vegetation and varying illumination. To validate the effectiveness of UniU-Net, comprehensive experiments were conducted on a specialized areca palm dataset, demonstrating superior performance compared to several state-of-the-art semantic segmentation models. The proposed method achieves significant improvements in key evaluation metrics, such as the F1-score and intersection over union (IoU), highlighting its robustness and precision in automated areca palm extraction tasks. The integration of advanced attention mechanisms not only enhances the model’s ability to focus on relevant regions but also improves the segmentation accuracy in challenging scenarios. Beyond the specific application of areca palm segmentation, the methodologies introduced in this study hold substantial practical significance for broader agricultural applications, such as precision farming and crop monitoring. |
| format | Article |
| id | doaj-art-e485e46c7c3f45bb89147cba1a14f4e7 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-e485e46c7c3f45bb89147cba1a14f4e72025-08-20T02:30:45ZengMDPI AGApplied Sciences2076-34172025-04-01159481310.3390/app15094813UniU-Net: A Unified U-Net Deep Learning Approach for High-Precision Areca Palm Segmentation in Remote Sensing ImageryShaohua Wang0Yan Wang1Jianwei Yue2Haojian Liang3Zihan Zhang4Bojun Li5State Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaFaculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaFaculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaFaculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaCollege of Resource Environment and Tourism, Capital Normal University, Beijing 100048, ChinaThis study introduces a novel deep learning-based model, UniU-Net, designed to achieve the high-precision segmentation of areca palms in remote sensing imagery. UniU-Net incorporates an auxiliary encoder and a unified attention fusion module (UAFM), enhancing the model’s anti-overfitting capabilities to improve its overall segmentation performance. Specifically, the primary and auxiliary encoders, through isomorphic parallel processing, leverage the principles of structural reparameterization to enhance the model’s effective learning of areca palm features while reducing the risk of overfitting. The UAFM utilizes a spatial attention mechanism to facilitate the effective fusion of multi-scale features. This architecture enables the model to capture intricate morphological details and accurately delineate the boundaries of areca palms, even under complex and heterogeneous environmental conditions such as mixed vegetation and varying illumination. To validate the effectiveness of UniU-Net, comprehensive experiments were conducted on a specialized areca palm dataset, demonstrating superior performance compared to several state-of-the-art semantic segmentation models. The proposed method achieves significant improvements in key evaluation metrics, such as the F1-score and intersection over union (IoU), highlighting its robustness and precision in automated areca palm extraction tasks. The integration of advanced attention mechanisms not only enhances the model’s ability to focus on relevant regions but also improves the segmentation accuracy in challenging scenarios. Beyond the specific application of areca palm segmentation, the methodologies introduced in this study hold substantial practical significance for broader agricultural applications, such as precision farming and crop monitoring.https://www.mdpi.com/2076-3417/15/9/4813areca palm extractionremote sensingdeep learningattention mechanismUniU-Net |
| spellingShingle | Shaohua Wang Yan Wang Jianwei Yue Haojian Liang Zihan Zhang Bojun Li UniU-Net: A Unified U-Net Deep Learning Approach for High-Precision Areca Palm Segmentation in Remote Sensing Imagery Applied Sciences areca palm extraction remote sensing deep learning attention mechanism UniU-Net |
| title | UniU-Net: A Unified U-Net Deep Learning Approach for High-Precision Areca Palm Segmentation in Remote Sensing Imagery |
| title_full | UniU-Net: A Unified U-Net Deep Learning Approach for High-Precision Areca Palm Segmentation in Remote Sensing Imagery |
| title_fullStr | UniU-Net: A Unified U-Net Deep Learning Approach for High-Precision Areca Palm Segmentation in Remote Sensing Imagery |
| title_full_unstemmed | UniU-Net: A Unified U-Net Deep Learning Approach for High-Precision Areca Palm Segmentation in Remote Sensing Imagery |
| title_short | UniU-Net: A Unified U-Net Deep Learning Approach for High-Precision Areca Palm Segmentation in Remote Sensing Imagery |
| title_sort | uniu net a unified u net deep learning approach for high precision areca palm segmentation in remote sensing imagery |
| topic | areca palm extraction remote sensing deep learning attention mechanism UniU-Net |
| url | https://www.mdpi.com/2076-3417/15/9/4813 |
| work_keys_str_mv | AT shaohuawang uniunetaunifiedunetdeeplearningapproachforhighprecisionarecapalmsegmentationinremotesensingimagery AT yanwang uniunetaunifiedunetdeeplearningapproachforhighprecisionarecapalmsegmentationinremotesensingimagery AT jianweiyue uniunetaunifiedunetdeeplearningapproachforhighprecisionarecapalmsegmentationinremotesensingimagery AT haojianliang uniunetaunifiedunetdeeplearningapproachforhighprecisionarecapalmsegmentationinremotesensingimagery AT zihanzhang uniunetaunifiedunetdeeplearningapproachforhighprecisionarecapalmsegmentationinremotesensingimagery AT bojunli uniunetaunifiedunetdeeplearningapproachforhighprecisionarecapalmsegmentationinremotesensingimagery |