Annotation-efficient weed mapping in sorghum fields using two-stage U-Net crop segmentation and HSV greenness analysis

Mohamed El Amine Bouhadjer; Sarah Mazari; Miloud Chikr El Mezouar

doi:10.18011/bioeng.2026.v20.1389

Authors

Mohamed El Amine Bouhadjer Department of Electronics, Djillali Liabes University, Sidi Bel Abbes, Algeria https://orcid.org/0009-0008-7828-9648
Sarah Mazari Department of Electronics, Djillali Liabes University, Sidi Bel Abbes, Algeria https://orcid.org/0000-0002-7925-2547
Miloud Chikr El Mezouar Department of Electronics, Djillali Liabes University, Sidi Bel Abbes, Algeria https://orcid.org/0000-0003-3491-0355

DOI:

https://doi.org/10.18011/bioeng.2026.v20.1389

Keywords:

Weed detection, Precision agriculture, Vegetation indices, Greenness analysis, Annotation-efficient learning

Abstract

Accurate weed mapping is essential for site-specific weed management in sorghum, but pixel-level weed annotation is labor-intensive and limits practical deployment. This work proposes an annotation-efficient two-stage approach using Unmanned Aerial Vehicle (UAV) RGB imagery that first segments crop pixels with U-Net and then detects weeds in non-crop regions using greenness-based analysis. Convolutional Neural Network (CNN)- and transformer-based encoders were evaluated for crop segmentation, and hue, saturation, value (HSV) filtering was compared with the Excess Green index (ExG) and the Color Index of Vegetation Extraction (CIVE) for weed detection. Among the evaluated configurations, the best-performing combination used U-Net with an EfficientNet-B5 encoder for crop segmentation and HSV-based filtering for weed detection. The approach was evaluated across sorghum growth stages (BBCH 15, 17, and 19) and produced practical weed-mapping outputs while substantially reducing annotation requirements, because only crop masks were needed and manual weed labeling was avoided. In total, 4,470 weed instances did not require manual annotation. When compared with a fully supervised end-to-end multi-class model, the proposed two-stage framework showed lower but practically useful segmentation performance while substantially reducing annotation requirements. The method also generated field-scale weed distribution maps and weed-cover estimates that can support targeted scouting and site-specific herbicide application. These results support the proposed approach as a practical and scalable alternative for precision weed management under real field conditions.

Downloads

Download data is not yet available.

References

Ahmad, J., Muhammad, K., Ahmad, I., Ahmad, W., Smith, M. L., Smith, L. N., Smith, L. N., Jain, D. K., Wang, H., & Mehmood, I. (2018). Visual features based boosted classification of weeds for real-time selective herbicide sprayer systems. Computers in Industry, 98, 23–33. https://doi.org/10.1016/j.compind.2018.02.005 DOI: https://doi.org/10.1016/j.compind.2018.02.005

Aktar, M. W., Sengupta, D., & Chowdhury, A. (2009). Impact of pesticides use in agriculture: Their benefits and hazards. Interdisciplinary Toxicology, 2, 1–12. https://doi.org/10.2478/v10102-009-0001-7 DOI: https://doi.org/10.2478/v10102-009-0001-7

Asad, M. H., & Bais, A. (2020). Weed detection in canola fields using maximum likelihood classification and deep convolutional neural network. Information Processing in Agriculture, 7, 535–545. https://doi.org/10.1016/j.inpa.2019.12.002 DOI: https://doi.org/10.1016/j.inpa.2019.12.002

Chen, C., Yuan, X., Gan, S., Luo, W., Bi, R., Li, R., & Gao, S. (2024). A new vegetation index based on UAV for extracting plateau vegetation information. International Journal of Applied Earth Observation and Geoinformation, 128, 103668. https://doi.org/10.1016/j.jag.2024.103668 DOI: https://doi.org/10.1016/j.jag.2024.103668

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations. https://openreview.net/forum?id=YicbFdNTTy

Garibaldi-Márquez, F., Martínez-Barba, D. A., Montañez-Franco, L. E., Flores, G., & Valentín-Coronado, L. M. (2025). Enhancing site-specific weed detection using deep learning transformer architectures. Crop Protection, 190, 107075. https://doi.org/10.1016/j.cropro.2024.107075 DOI: https://doi.org/10.1016/j.cropro.2024.107075

Genze, N., Ajekwe, R., Güreli, Z., Haselbeck, F., Grieb, M., & Grimm, D. G. (2022). Deep learning-based early weed segmentation using motion blurred UAV images of sorghum fields. Computers and Electronics in Agriculture, 202, 107388. https://doi.org/10.1016/j.compag.2022.107388 DOI: https://doi.org/10.1016/j.compag.2022.107388

Genze, N., Wirth, M., Schreiner, C., Ajekwe, R., Grieb, M., & Grimm, D. G. (2023). Improved weed segmentation in UAV imagery of sorghum fields with a combined deblurring segmentation model. Plant Methods, 19(1), 87. https://doi.org/10.1186/s13007-023-01060-8 DOI: https://doi.org/10.1186/s13007-023-01060-8

Hasan, A. S. M. M., Sohel, F., Diepeveen, D., Laga, H., & Jones, M. G. K. (2021). A survey of deep learning techniques for weed detection from images. Computers and Electronics in Agriculture, 184, 106067. https://doi.org/10.1016/j.compag.2021.106067 DOI: https://doi.org/10.1016/j.compag.2021.106067

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778). https://doi.org/10.1109/CVPR.2016.90 DOI: https://doi.org/10.1109/CVPR.2016.90

Hess, M., Barralis, G., Bleiholder, H., Buhr, L., Eggers, T. H., Hack, H., & Stauss, R. (1997). Use of the extended BBCH scale – General for the descriptions of the growth stages of mono- and dicotyledonous weed species. Weed Research, 37(6), 433–441. https://doi.org/10.1046/j.1365-3180.1997.d01-70.x DOI: https://doi.org/10.1046/j.1365-3180.1997.d01-70.x

Huang, G., Liu, Z., Van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2261–2269). https://doi.org/10.1109/CVPR.2017.243 DOI: https://doi.org/10.1109/CVPR.2017.243

Huang, T., Yang, G., & Tang, G. (1979). A fast two-dimensional median filtering algorithm. IEEE Transactions on Acoustics, Speech, and Signal Processing, 27(1), 13–18. https://doi.org/10.1109/TASSP.1979.1163188 DOI: https://doi.org/10.1109/TASSP.1979.1163188

Jin, X., Che, J., & Chen, Y. (2021). Weed identification using deep learning and image processing in vegetable plantation. IEEE Access, 9, 1666–1678. https://doi.org/10.1109/ACCESS.2021.3050296 DOI: https://doi.org/10.1109/ACCESS.2021.3050296

Kataoka, T., Kaneko, T., Okamoto, H., & Hata, S. (2003). Crop growth estimation system using machine vision. In Proceedings of the 2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM 2003) (Vol. 2, pp. 1079–1083). https://doi.org/10.1109/AIM.2003.1225492 DOI: https://doi.org/10.1109/AIM.2003.1225492

Kawamura, K., Asai, H., Yasuda, T., Soisouvanh, P., & Phongchanmixay, S. (2021). Discriminating crops/weeds in an upland rice field from UAV images with the SLIC-RF algorithm. Plant Production Science, 24(2), 198–215. https://doi.org/10.1080/1343943X.2020.1829490 DOI: https://doi.org/10.1080/1343943X.2020.1829490

Li X, Xu F, Liu F, Lyu X, Tong Y, Xu Z (2023). A synergistical attention model for semantic segmentation of remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–16. https://doi.org/10.1109/TGRS.2023.3243954 DOI: https://doi.org/10.1109/TGRS.2023.3243954

Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 10012–10022). https://doi.org/10.1109/ICCV48922.2021.00986 DOI: https://doi.org/10.1109/ICCV48922.2021.00986

Macedo, F. L., Nóbrega, H., de Freitas, J. G. R., & Pinheiro de Carvalho, M. A. A. (2025). Assessment of vegetation indices derived from UAV imagery for weed detection in vineyards. Remote Sensing, 17(11), 1899. https://doi.org/10.3390/rs17111899 DOI: https://doi.org/10.3390/rs17111899

Olsen A, Konovalov DA, Philippa B, Ridd P, Wood JC, Johns J, Banks W, Girgenti B, Kenny O, Whinney J, Calvert B, Rahimi Azghadi M, White RD. (2019). DeepWeeds: A multiclass weed species image dataset for deep learning. Scientific Reports, 9, 3928. https://doi.org/10.1038/s41598-018-38343-3 DOI: https://doi.org/10.1038/s41598-018-38343-3

Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62–66. https://doi.org/10.1109/TSMC.1979.4310076 DOI: https://doi.org/10.1109/TSMC.1979.4310076

Patel, D. D., & Kumbhar, B. A. (2016). Weed and its management: A major threat to crop economy. Journal of Pharmaceutical Sciences and Bioscientific Research, 6, 453–758.

Rai, N., Zhang, Y., Ram, B. G., Schumacher, L., Yellavajjala, R. K., Bajwa, S., & Sun, X. (2023). Applications of deep learning in precision weed management: A review. Computers and Electronics in Agriculture, 206, 107698. https://doi.org/10.1016/j.compag.2023.107698 DOI: https://doi.org/10.1016/j.compag.2023.107698

Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of MICCAI (pp. 234–241). https://doi.org/10.1007/978-3-319-24574-4_28 DOI: https://doi.org/10.1007/978-3-319-24574-4_28

Štroner, M., Urban, R., & Suk, T. (2023). Filtering green vegetation out from colored point clouds of rocky terrains based on various vegetation indices: Comparison of simple statistical methods, support vector machine, and neural network. Remote Sensing, 15(13), 3254. https://doi.org/10.3390/rs15133254 DOI: https://doi.org/10.3390/rs15133254

Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (ICML) (pp. 6105–6114). https://proceedings.mlr.press/v97/tan19a.html

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. https://doi.org/10.48550/arXiv.1706.03762

Wang, A., Zhang, W., & Wei, X. (2019). A review on weed detection using ground-based machine vision and image processing techniques. Computers and Electronics in Agriculture, 158, 226–240. https://doi.org/10.1016/j.compag.2019.02.005 DOI: https://doi.org/10.1016/j.compag.2019.02.005

Woebbecke, D., Meyer, G., Von Bargen, K., & Mortensen, D. (1995). Shape features for identifying young weeds using image analysis. Transactions of the ASAE, 38, 271–281. https://doi.org/10.13031/2013.27839 DOI: https://doi.org/10.13031/2013.27839

World Health Organization. (1990). Public health impact of pesticides used in agriculture. Geneva, Switzerland: World Health Organization.

Wu, Z., Lin, M., Guo, L., & Wang, Y. (2021). Review of weed detection methods based on computer vision. Sensors, 21(11), 3647. https://doi.org/10.3390/s21113647 DOI: https://doi.org/10.3390/s21113647

Yang, W., Wang, S., Zhao, X., Zhang, J., & Feng, J. (2015). Greenness identification based on HSV decision tree. Information Processing in Agriculture, 2(3–4), 149–160. https://doi.org/10.1016/j.inpa.2015.07.003 DOI: https://doi.org/10.1016/j.inpa.2015.07.003

Zou, K., Chen, X., Zhang, F., Zhou, H., & Zhang, C. (2021). A field weed density evaluation method based on UAV imaging and modified U-Net. Remote Sensing, 13(2), 310. https://doi.org/10.3390/rs13020310 DOI: https://doi.org/10.3390/rs13020310