Abstract
Accurate localization of plant growth points is essential for precision agriculture applications, including electro-weeding and laser weeding. While crop and weed detection has been extensively studied, existing methods focus primarily on object-level recognition and often neglect fine-grained growth point localization. To address this limitation, we propose a novel training strategy, epoch-based prior annealing (EPA), which incorporates the excess green minus excess red (ExG-ExR) index as prior knowledge and introduces schedule factor and gain factor to effectively steer keypoint regression. The experimental results show that incorporating EPA improves keypoint localization performance, with mAP50 increasing by 0.024 and mAP50:95 by 0.011, while maintaining bounding box detection performance. The parameter sensitivity experiments confirmed that both excessively strong and weak guidance can hinder training. Furthermore, analysis of parameters and computational cost shows that the additional overhead introduced by the EPA strategy accounts for less than 0.5% of the total, and be considered negligible. In summary, the proposed EPA strategy significantly improves the accuracy, robustness, and generalizability of plant and growth point detection models, offering a practical and scalable solution for precision agricultural applications.
Similar content being viewed by others
Data availability
You can access the dataset used in this study at the following links: https://github.com/cropandweed/cropandweed-dataset.
References
Wiles, L. J. Beyond patch spraying: site-specific weed management with several herbicides. Precis Agric. 10, 277–290 (2009).
Machleb, J., Peteinatos, G. G., Kollenda, B. L., Andújar, D. & Gerhards, R. Sensor-based mechanical weed control: present state and prospects. Comput. Electron. Agric. 176, 105638 (2020).
Andreasen, C., Scholle, K. & Saberi, M. Laser weeding with small autonomous vehicles: friends or foes? Front. Agron. 4, 841086 (2022).
Slaven, M. J., Koch, M. & Borger, C. P. D. Exploring the potential of electric weed control: a review. Weed Sci. 71, 403–421 (2023).
Fatima, H. S. et al. Formation of a lightweight, deep learning-based weed detection system for a commercial autonomous laser weeding robot. Appl. Sci. 13, 3997 (2023).
Ma, C., Chi, G., Ju, X., Zhang, J. & Yan, C. YOLO-CWD: A novel model for crop and weed detection based on improved YOLOv8. Crop Prot. 192, 107169 (2025).
Wang, Q. et al. A deep learning approach incorporating YOLO v5 and attention mechanisms for field real-time detection of the invasive weed solanum rostratum Dunal seedlings. Comput. Electron. Agric. 199, 107194 (2022).
Zhou, Y. A YOLO-NL object detector for real-time detection. Expert Syst. Appl. 238, 122256 (2024).
Ascard, J. Effects of flame weeding on weed species at different developmental stages. Weed Res. 35, 397–411 (1995).
Norouzi, R. et al. A dual-feature two-sided attention network for anticancer natural products detection. Comput. Biol. Med. 194, 110442 (2025).
Abbasi, K. et al. Computational drug design in the artificial intelligence era: A systematic review of molecular representations, generative architectures, and performance assessment. Pharmacol. Rev. 78, 100095 (2026).
Xue, C. et al. Similarity-guided layer-adaptive vision transformer for UAV tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 6730–6740 (2025).
lv, X. et al. Dynamic whole-life cycle measurement of individual plant height in oilseed rape through the fusion of point cloud and crop root zone localization. Comput. Electron. Agric. 236, 110505 (2025).
Li, Q., Du, Q., Tian, L., Shao, Y. & Lu, G. Enhancing point cloud feature representation via historical node state increments in graph neural networks. Pattern Recognit. 172, 112603 (2026).
Li, P., Wen, M., Zeng, Z. & Tian, Y. Cherry tomato bunch and picking point detection for robotic harvesting using an RGB-D sensor and a StarBL-YOLO network. Horticulturae 11, 949 (2025).
Shuai, L. et al. An improved YOLOv5-based method for multi-species tea shoot detection and picking point location in complex backgrounds. Biosyst Eng. 231, 117–132 (2023).
Wu, X., Tian, Y., Zeng, Z. & LEFF-YOLO: A lightweight Cherry tomato detection YOLOv8 network with enhanced feature fusion. In Advanced Intell. Comput. Technol. Applications 474–488 (2025).
Cai, Y. et al. Cherry tomato detection for harvesting using multimodal perception and an improved YOLOv7-Tiny neural network. Agronomy 14, 2320 (2024).
Güldenring, R., Andersen, R. E. & Nalpantidis, L. Zoom in on the plant: fine-grained analysis of leaf, stem, and vein instances. IEEE Robot Autom. Lett. 9, 1588–1595 (2024).
Lac, L., Costa, D., Donias, J. P., Keresztes, M., Bardet, A. & B. & Crop stem detection and tracking for precision hoeing using deep learning. Comput. Electron. Agric. 192, 106606 (2022).
Xiang, W., Wu, D. & Wang, J. Enhancing stem localization in precision agriculture: A Two-Stage approach combining YOLOv5 with effistemnet. Comput. Electron. Agric. 231, 109914 (2025).
Li, J., Güldenring, R. & Nalpantidis, L. Real-time joint-stem prediction for agricultural robots in grasslands using multi-task learning. Agronomy 13, 2365 (2023).
Xue, Y. et al. FMTrack: Frequency-aware interaction and Multi-Expert fusion for RGB-T tracking. IEEE Trans. Circuits Syst. Video Technol. 1–1 (2025).
Chai, S., Wen, M., Li, P., Zeng, Z. & Tian, Y. DCFA-YOLO: A dual-channel cross-feature-fusion attention YOLO network for Cherry tomato bunch detection. Agriculture 15, 271 (2025).
Chen, X., Lin, F., Ma, F. & Du, C. Effects of long-term input of controlled-release Urea on maize growth monitored by UAV-RGB imaging. Agronomy 15, 716 (2025).
Le, V. N. T., Ahderom, S. & Alameh, K. Performances of the LBP based algorithm over CNN models for detecting crops and weeds with similar morphologies. Sensors 20, 2193 (2020).
Meyer, G. E. & Neto, J. C. Verification of color vegetation indices for automated crop imaging applications. Comput. Electron. Agric. 63, 282–293 (2008).
Zou, K., Chen, X., Zhang, F., Zhou, H. & Zhang, C. A field weed density evaluation method based on UAV imaging and modified U-Net. Remote Sens. 13, 310 (2021).
Bengio, Y., Louradour, J., Collobert, R. & Weston, J. Curriculum learning. In Proceedings of the 26th Annual International Conference on Machine Learning 41–48 (2009).
Loshchilov, I. & Hutter, F. SGDR: stochastic gradient descent with warm restarts. https://arxiv.org/abs/1608.03983 (2016).
Steininger, D., Trondl, A., Croonen, G., Simon, J. & Widhalm, V. The cropandweed dataset: a multi-modal learning approach for efficient crop and weed manipulation. 2023 IEEE/CVF Winter Conf. Appl. Comput. Vis. (WACV). 3718–3727 (2023).
Liu, D. et al. Towards efficient and intelligent laser weeding: method and dataset for weed stem detection. Proc. AAAI Conf. Artif. Intell. 39, 28204–28212 (2025).
Zheng, T., Jiang, M., Li, Y. & Feng, M. Research on tomato detection in natural environment based on RC-YOLOv4. Comput. Electron. Agric. 198, 107029 (2022).
Wang, Y., Yang, Z., Kootstra, G. & Khan, H. A. The impact of variable illumination on vegetation indices and evaluation of illumination correction methods on chlorophyll content Estimation using UAV imagery. Plant. Methods. 19, 51 (2023).
Tian, Y., Wen, M., Lu, D., Zhong, X. & Wu, Z. Biological basis and computer vision applications of image phase congruency: a comprehensive survey. Biomimetics 9, 422 (2024).
Han, X. et al. A rapid segmentation method for weed based on CDM and exg index. Crop Prot. 172, 106321 (2023).
Yang, B., Zhu, Y. & Zhou, S. Accurate wheat lodging extraction from multi-channel UAV images using a lightweight network model. Sensors 21, 6826 (2021).
Lottes, P., Behley, J., Chebrolu, N., Milioto, A. & Stachniss, C. Joint stem detection and crop-weed classification for plant-specific treatment in precision farming. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 8233–8238 (2018).
Funding
This research was funded by the National Natural Science Foundation of China (NSFC), grant number 62505316.
Author information
Authors and Affiliations
Contributions
C.M. writing—original draft preparation. Z.Z. and F.T. writing—review and editing. Y.H. funding acquisition. C.Y. supervision. All authors reviewed and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Ma, C., Zhang, Z., Tian, F. et al. Plant growth point localization via epoch-based prior annealing. Sci Rep (2026). https://doi.org/10.1038/s41598-026-35009-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-35009-3
