HURA-Net: A New Model for Agricultural Field Boundary Detection

Alizadeh, Mehdi; Ahmadi, Parvin; Azimzadeh, Masoumeh

doi:10.22044/jadm.2026.16909.2823

Document Type : Original/Review Paper

Authors

Dept. Information Technology, ICT Research Institute, Tehran, Iran

https://doi.org/10.22044/jadm.2026.16909.2823

Abstract

Field boundary detection is a critical task in modern agriculture, enabling precision farming, optimized resource management, and efficient crop monitoring. Despite its importance, existing deep learning models often fail to achieve high accuracy in delineating field boundaries due to challenges such as complex landscapes, varying resolutions, and noise in remote sensing images. To overcome these limitations, we propose HURA-Net, an advanced deep learning framework that intelligently integrates UNet++, ResUNet, and an attention mechanism into a unified architecture. By hybridizing these models, HURA-Net effectively combines their strengths—such as multi-scale feature extraction (UNet++), residual learning (ResUNet), and focus on salient regions (attention mechanism)—while minimizing their individual weaknesses. To further enhance performance, we introduce a refined loss function that not only improves segmentation precision but also addresses the class imbalance problem, which is common in boundary detection tasks. Extensive experiments on a diverse dataset of high-resolution satellite images from different regions of Iran demonstrate that HURA-Net significantly outperforms existing state-of-the-art models. Specifically, it achieves a recall of 45.85% (a 15.59% improvement over ResUNet) and an F1-score of 42.62% (7.27% higher than ResUNet), setting a new benchmark for accuracy. Moreover, our study highlights the critical role of strategic data augmentation in boosting model generalization, particularly in handling variations in lighting, crop types, and field shapes. The success of HURA-Net underscores the importance of innovative architecture design, optimized loss functions, and robust training strategies in advancing remote sensing image segmentation.

Keywords

Main Subjects

H.6.5.10. Remote sensing

References

[1] H. Pourghasem, "Comparing the semantic segmentation of high-resolution images using deep convolutional networks: Segnet, hrnet, cse-hrnet and rca-fcn," J. Inf. Syst. Telecommun., vol. 4, no. 44, pp. 359–368, Dec. 2023.

[2] M. J. CM, "Convolutional neural networks for medical image segmentation and classification: A review," J. Inf. Syst. Telecommun., vol. 4, no. 44, pp. 347–358, Dec. 2023.

[3] E. Yadolahi and S. Abolmaali, "Improving the Efficiency of Semantic Segmentation Implemented in Spiking Neural Networks," Journal of AI and Data Mining, vol. 13, no. 1, pp.25–39, 2025.

[4] F. Waldner and F. I. Diakogiannis, "Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network," Remote Sens. Environ., vol. 245, p. 111741, 2020.

[5] A. Taravat, M. P. Wagner, R. Bonifacio, and D. Petit, "Advanced fully convolutional networks for agricultural field boundary detection," Remote Sens., vol. 13, no. 4, p. 722, 2021.

[6] O. Oktay et al., "Attention u-net: Learning where to look for the pancreas," arXiv preprint arXiv:1804.03999, 2018.

[7] S. S. M. Salehi, D. Erdogmus, and A. Gholipour, "Tversky loss function for image segmentation using 3D fully convolutional deep networks," in Int. Workshop Mach. Learn. Med. Imag., 2017, pp. 379–387.

[8] P. Tripathy, K. Baylis, K. Wu, J. Watson, and R. Jiang, "Investigating the Segment Anything Foundation Model for mapping smallholder agriculture field boundaries without training labels," arXiv preprint arXiv:2407.01846, 2024.

[9] H. Kerner, S. Sundar, and M. Satish, "Multi-region transfer learning for segmentation of crop field boundaries in satellite images with limited labels," arXiv preprint arXiv:2404.00179, 2024.

[10] O. Ronneberger, P. Fischer, and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," in Med. Image Comput. Comput.-Assist. Interv., 2015, pp. 234–241.

[11] Z. Zhou, M. M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, "Unet++: A nested u-net architecture for medical image segmentation," in Deep Learn. Med. Image Anal. Multimodal Learn. Clin. Decis. Support, 2018, pp. 3–11.

[12] Z. Zhang, Q. Liu, and Y. Wang, "Road extraction by deep residual u-net," IEEE Geosci. Remote Sens. Lett., vol. 15, no. 5, pp. 749–753, 2018.

[13] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 770–778.

[14] R. Yang, Z. U. Ahmed, U. C. Schulthess, M. Kamal, and R. Rai, "Detecting functional field units from satellite images in smallholder farming systems using a deep learning based computer vision approach: A case study from Bangladesh," Remote Sens. Appl.: Soc. Environ., vol. 20, p. 100413, 2020.

[15] M. Wang, J. Wang, Y. Cui, J. Liu, and L. Chen, "Agricultural field boundary delineation with satellite image segmentation for high-resolution crop mapping: A case study of rice paddy," Agronomy, vol. 12, no. 10, p. 2342, 2022.

[16] F. I. Diakogiannis, F. Waldner, P. Caccetta, and C. Wu, "ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data," ISPRS J. Photogramm. Remote Sens., vol. 162, pp. 94–114, 2020.

[17] M. Jong, K. Guan, S. Wang, Y. Huang, and B. Peng, "Improving field boundary delineation in ResUNets via adversarial deep learning," Int. J. Appl. Earth Observ. Geoinf., vol. 112, p. 102877, 2022.

[18] G. M. Musyoka, "Automatic delineation of small holder agricultural field boundaries using fully convolutional networks," M.S. thesis, Univ. Twente, 2018.

[19] Z. Du, J. Yang, C. Ou, and T. Zhang, "Smallholder crop area mapped with a semantic segmentation deep learning method," Remote Sens., vol. 11, no. 7, p. 888, 2019.

[20] M. Torre, B. Remeseiro, P. Radeva, and F. Martinez, "DeepNEM: Deep network energy-minimization for agricultural field segmentation," IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 13, pp. 726–737, 2020.

[21] R. d'Andrimont et al., "AI4Boundaries: An open AI-ready dataset to map field boundaries with Sentinel-2 and aerial photography," Earth Syst. Sci. Data, vol. 15, no. 1, pp. 317–329, 2023.

HURA-Net: A New Model for Agricultural Field Boundary Detection

References

References

Volume 14, Issue 3July 2026Pages 395-406

Volume 14, Issue 3
July 2026
Pages 395-406