Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification Framework
Wheat lodging has a significant impact on yields and quality, necessitating the accurate acquisition of lodging information for effective disaster assessment and damage evaluation. This study presents a novel approach for wheat lodging detection in large and heterogeneous fields using UAV remote sen...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/18/4572 |
| _version_ | 1797577172398899200 |
|---|---|
| author | Kai Zhang Rundong Zhang Ziqian Yang Jie Deng Ahsan Abdullah Congying Zhou Xuan Lv Rui Wang Zhanhong Ma |
| author_facet | Kai Zhang Rundong Zhang Ziqian Yang Jie Deng Ahsan Abdullah Congying Zhou Xuan Lv Rui Wang Zhanhong Ma |
| author_sort | Kai Zhang |
| collection | DOAJ |
| description | Wheat lodging has a significant impact on yields and quality, necessitating the accurate acquisition of lodging information for effective disaster assessment and damage evaluation. This study presents a novel approach for wheat lodging detection in large and heterogeneous fields using UAV remote sensing images. A comprehensive dataset spanning an area of 2.3117 km<sup>2</sup> was meticulously collected and labeled, constituting a valuable resource for this study. Through a comprehensive comparison of algorithmic models, remote sensing data types, and model frameworks, this study demonstrates that the Deeplabv3+ model outperforms various other models, including U-net, Bisenetv2, FastSCN, RTFormer, Bisenetv2, and HRNet, achieving a noteworthy F1 score of 90.22% for detecting wheat lodging. Intriguingly, by leveraging RGB image data alone, the current model achieves high-accuracy rates in wheat lodging detection compared to models trained with multispectral datasets at the same resolution. Moreover, we introduce an innovative multi-branch binary classification framework that surpasses the traditional single-branch multi-classification framework. The proposed framework yielded an outstanding F1 score of 90.30% for detecting wheat lodging and an accuracy of 86.94% for area extraction of wheat lodging, surpassing the single-branch multi-classification framework by an improvement of 7.22%. Significantly, the present comprehensive experimental results showcase the capacity of UAVs and deep learning to detect wheat lodging in expansive areas, demonstrating high efficiency and cost-effectiveness under heterogeneous field conditions. This study offers valuable insights for leveraging UAV remote sensing technology to identify post-disaster damage areas and assess the extent of the damage. |
| first_indexed | 2024-03-10T22:05:21Z |
| format | Article |
| id | doaj.art-57638dd42407453db411f0825cd63fe3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T22:05:21Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-57638dd42407453db411f0825cd63fe32023-11-19T12:49:37ZengMDPI AGRemote Sensing2072-42922023-09-011518457210.3390/rs15184572Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification FrameworkKai Zhang0Rundong Zhang1Ziqian Yang2Jie Deng3Ahsan Abdullah4Congying Zhou5Xuan Lv6Rui Wang7Zhanhong Ma8Jiangjin Meteorological Bureau, China Meteorological Administration Key Open Laboratory of Transforming Climate Resources to Economy, Chongqing 402260, ChinaDepartment of Plant Pathology, College of Plant Protection, China Agricultural University, Beijing 100193, ChinaDepartment of Plant Pathology, College of Plant Protection, China Agricultural University, Beijing 100193, ChinaJiangjin Meteorological Bureau, China Meteorological Administration Key Open Laboratory of Transforming Climate Resources to Economy, Chongqing 402260, ChinaDepartment of Plant Pathology, College of Plant Protection, China Agricultural University, Beijing 100193, ChinaDepartment of Plant Pathology, College of Plant Protection, China Agricultural University, Beijing 100193, ChinaDepartment of Plant Pathology, College of Plant Protection, China Agricultural University, Beijing 100193, ChinaKaifeng Experimental Station, China Agricultural University, Kaifeng 475000, ChinaDepartment of Plant Pathology, College of Plant Protection, China Agricultural University, Beijing 100193, ChinaWheat lodging has a significant impact on yields and quality, necessitating the accurate acquisition of lodging information for effective disaster assessment and damage evaluation. This study presents a novel approach for wheat lodging detection in large and heterogeneous fields using UAV remote sensing images. A comprehensive dataset spanning an area of 2.3117 km<sup>2</sup> was meticulously collected and labeled, constituting a valuable resource for this study. Through a comprehensive comparison of algorithmic models, remote sensing data types, and model frameworks, this study demonstrates that the Deeplabv3+ model outperforms various other models, including U-net, Bisenetv2, FastSCN, RTFormer, Bisenetv2, and HRNet, achieving a noteworthy F1 score of 90.22% for detecting wheat lodging. Intriguingly, by leveraging RGB image data alone, the current model achieves high-accuracy rates in wheat lodging detection compared to models trained with multispectral datasets at the same resolution. Moreover, we introduce an innovative multi-branch binary classification framework that surpasses the traditional single-branch multi-classification framework. The proposed framework yielded an outstanding F1 score of 90.30% for detecting wheat lodging and an accuracy of 86.94% for area extraction of wheat lodging, surpassing the single-branch multi-classification framework by an improvement of 7.22%. Significantly, the present comprehensive experimental results showcase the capacity of UAVs and deep learning to detect wheat lodging in expansive areas, demonstrating high efficiency and cost-effectiveness under heterogeneous field conditions. This study offers valuable insights for leveraging UAV remote sensing technology to identify post-disaster damage areas and assess the extent of the damage.https://www.mdpi.com/2072-4292/15/18/4572wheat lodging detectionUAVdeep learningmultispectral imageryRGB imageryDeeplabv3+ |
| spellingShingle | Kai Zhang Rundong Zhang Ziqian Yang Jie Deng Ahsan Abdullah Congying Zhou Xuan Lv Rui Wang Zhanhong Ma Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification Framework Remote Sensing wheat lodging detection UAV deep learning multispectral imagery RGB imagery Deeplabv3+ |
| title | Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification Framework |
| title_full | Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification Framework |
| title_fullStr | Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification Framework |
| title_full_unstemmed | Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification Framework |
| title_short | Efficient Wheat Lodging Detection Using UAV Remote Sensing Images and an Innovative Multi-Branch Classification Framework |
| title_sort | efficient wheat lodging detection using uav remote sensing images and an innovative multi branch classification framework |
| topic | wheat lodging detection UAV deep learning multispectral imagery RGB imagery Deeplabv3+ |
| url | https://www.mdpi.com/2072-4292/15/18/4572 |
| work_keys_str_mv | AT kaizhang efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework AT rundongzhang efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework AT ziqianyang efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework AT jiedeng efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework AT ahsanabdullah efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework AT congyingzhou efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework AT xuanlv efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework AT ruiwang efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework AT zhanhongma efficientwheatlodgingdetectionusinguavremotesensingimagesandaninnovativemultibranchclassificationframework |