Ensemble Learning-Based Weed Detection from a Duck’s Perspective Using an Aquatic Drone in Rice Paddies
Source abstract
Abstract
Semantic segmentation using neural networks (NNs) has significant potential for weed detection in agricultural fields. However, conventional datasets captured from aerial perspectives often fail to detect weeds that are either hidden beneath crops or submerged in water. This study proposes a method for accurately detecting weed pixels through ensemble learning-based semantic segmentation, using forward-facing images captured by a camera mounted on an aquatic drone navigating between rice plants. We also present a paddy field weed image dataset constructed to train the NN models. Multiple semantic segmentation models were trained, compared, and evaluated, achieving a weed intersection over union (IoU) of 0.441, mean IoU (mIoU) of 0.706, and pixel accuracy of 0.971.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Spectroscopy and Chemometric Analyses · Advanced Chemical Sensor Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering and Computer Science, Graduate School of Engineering, Tokyo University of Agriculture and Technology, Tokyo 184-8588, Japan
New Green, Inc., Tokyo 184-0012, Japan
Division of Advanced Information Technology Computer Science, Institute of Engineering, Tokyo University of Agriculture and Technology, Tokyo 184-8588, Japan
Division of Science of Biological Production, Institute of Agriculture, Tokyo University of Agriculture and Technology, Tokyo 183-8538, Japan
Funding
JSPS Grant-in-Aid for Scientific Research
References (33)
Show source-provided references
1. (2025, April 10). Ministry of Agriculture, Forestry and Fisheries (MAFF): Measures for Achievement of Decarbonization and Resilience with Innovation (MeaDRI), Available online: https://www.maff.go.jp/j/kanbo/kankyo/seisaku/midori/attach/pdf/index-10.pdf.
2. (2025, April 10). Ministry of Agriculture, Forestry and Fisheries (MAFF): Survey of Organic Farmers on Their Awareness and Intentions Regarding Organic Farming and Other Initiatives, Available online: https://www.maff.go.jp/j/finding/mind/attach/pdf/index-75.pdf.
3. (2025, April 10). Ministry of Agriculture, Forestry and Fisheries (MAFF): Current Status of Smart Agriculture, Available online: https://www.maff.go.jp/j/kanbo/smart/attach/pdf/index-165.pdf.
4. Iseki Co., Ltd. (2025, April 10). NEWGREEN Inc: Aigamo Robot. Available online: https://aigamo.iseki.co.jp/.
5. Routrek Networks Co., Ltd. (2025, April 11). ZeRo.agri. Available online: https://www.routrek.co.jp/service/.
6. Kubota Corporation (2025, April 11). DRH1200A-A. Available online: https://agriculture.kubota.co.jp/product/combineDRH-1200A-A/index.html.
7. Nileworks Inc. (2025, April 11). Nile-JZ. Available online: https://www.nileworks.co.jp/product/nile-jz/.
8. Song, W., He, H., Dai, J., and Jia, G. (2025). Spatially adaptive interaction network for semantic segmentation of high-resolution remote sensing images. Sci. Rep., 15.10.1038/s41598-025-99428-4 ↗
9. Research on Image Classification and Semantic Segmentation Model Based on Convolutional Neural Network
10. Stanford Vision Lab, Stanford University, and Princeton University (2025, April 10). IMAGE NET. Available online: https://image-net.org/index.php.
11. Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2025, April 10). Automatic Differentiation in PyTorch. Available online: https://openreview.net/forum?id=BJJsrmfCZ.
12. Ensemble learning: A survey10.1002/widm.1249 ↗
13. Rosle, R., Che’Ya, N.N., Ang, Y., Rahmat, F., Wayayok, A., Berahim, Z., Fazlil Ilahi, W.F., Ismail, M.R., and Omar, M.H. (2021). Weed Detection in Rice Fields Using Remote Sensing Technique: A Review. Appl. Sci., 11.10.3390/app112210701 ↗
14. Hasan, A.S.M.M., Sohel, F., Diepeveen, D., Laga, H., and Jones, M.G.K. (2021). Weed Recognition using Deep Learning Techniques on Class-imbalanced Imagery. arXiv.
15. A modified U-Net with a specific data argumentation method for semantic segmentation of weed images in the field10.1016/j.compag.2021.106242 ↗
16. Ma, X., Deng, X., Qi, L., Jiang, Y., Li, H., Wang, Y., and Xing, X. (2019). Fully convolutional network for rice seedling and weed image segmentation at the seedling stage in paddy fields. PLoS ONE, 14.10.1371/journal.pone.0215676 ↗
17. Yang, Q., Ye, Y., Gu, L., and Wu, Y. (2023). MSFCA-Net: A Multi-Scale Feature Convolutional Attention Network for Segmenting Crops and Weeds in the Field. Agriculture, 13.10.3390/agriculture13061176 ↗
18. Asuka, S., Machida, K., Nakamura, T., Shimizu, I., Ookawa, T., and Nakajo, H. (November, January 29). Weed Detection from the Duck’s Perspective Using Aqua-Drone in Rice Paddies. Proceedings of the 2024 IEEE 13th Global Conference on Consumer Electronics (GCCE), Kitakyushu, Japan.10.1109/GCCE62371.2024.10760248 ↗
19. Methods and datasets on semantic segmentation: A review10.1016/j.neucom.2018.03.037 ↗
20. Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., and Liang, J. (2018). UNet++: A Nested U-Net Architecture for Medical Image Segmentation. arXiv.10.1007/978-3-030-00889-5_1 ↗
21. Chen, L.-C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv.
22. A survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
23. Ruder, S. (2017). An overview of gradient descent optimization algorithms. arXiv.
24. Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.
25. Li, M., Soltanolkotabi, M., and Oymak, S. (2019). Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks. arXiv.
26. Ensemble deep learning: A review10.1016/j.engappai.2022.105151 ↗
27. Dwyer, B., Nelson, J., and Solawetz, J. (2025, April 10). Roboflow (Version 1.0). Available online: https://roboflow.com/.
28. Morales, J., Saldivia, C., Lobo, R., Pino, M.D., Muñoz, M., Caniggia, G., Catalán, J., Hayde, R., and Poblete, V. (2025). Visual analysis of deep learning semantic segmentation applied to petrographic thin sections. Sci. Rep., 15.10.1038/s41598-025-99767-2 ↗
29. Hertel, R., and Benlamri, R. (2002). A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis. Biomed. Eng. Adv., 3.10.1016/j.bea.2022.100041 ↗
30. Kaushal, A., Gupta, A.K., and Sehgal, V.K. (2024). A semantic segmentation framework with UNet-pyramid for landslide prediction using remote sensing data. Sci. Rep., 14.10.1038/s41598-024-79266-6 ↗
31. Iakubovskii, P. (2025, April 10). Segmentation Models Pytorch. Available online: https://github.com/qubvel/segmentation_models.pytorch.
32. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.10.1109/CVPR.2016.90 ↗
33. Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A.A. (2020). Albumentations: Fast and Flexible Image Augmentations. Information, 11.10.3390/info11020125 ↗