Enhanced obstacle detection for intelligent agricultural machinery via transfer learning and improved YOLO11
Keywords:
agricultural machinery, obstacle detection, transfer learning, YOLO11, embedded deploymentAbstract
Reliable obstacle detection is critical for the safe operation of intelligent agricultural machinery in unstructured farmland environments. However, achieving robust detection in agricultural settings remains challenging due to limited annotated data and significant domain shifts between generic visual datasets and agricultural scenes, which constrain the effectiveness of existing object detection models. To address these challenges, this study proposes an enhanced YOLO11 framework with task-aligned transfer learning for detecting obstacles in farmland. The proposed approach consists of three core components: 1) architectural refinements, including the integration of CBAM attention modules and an improved SPPF structure to enhance multi-scale feature representation; 2) task-aligned pretraining on a curated COCO subset comprising 70 552 images containing task-relevant object categories; and 3) a staged fine-tuning strategy that combines backbone freezing with subsequent end-to-end optimization on a farmland obstacle dataset. Experimental results demonstrate that the proposed method achieves a mAP@0.5 of 0.934 on the test set, improving mAP@0.5 by 6.4 percentage points over YOLO11-s. Furthermore, after TensorRT optimization, the model reaches 82.6 FPS on the Jetson AGX Orin platform while maintaining a mAP@0.5 of 0.927, confirming its suitability for real-time deployment. These findings indicate that task-aligned transfer learning, combined with targeted architectural enhancements, effectively mitigates data scarcity and domain shift in agricultural obstacle detection.
Key words: agricultural machinery; obstacle detection; transfer learning; YOLO11; embedded deployment
DOI: 10.25165/j.ijabe.20261904.10644
Citation: Wan H, Guan X L, Ou Y Z, Jiang R, Zhou Z Y. Enhanced obstacle detection for intelligent agricultural machinery
via transfer learning and improved YOLO11. Int J Agric & Biol Eng, 2026; 19(4): 256–267.
References
[1] Campos Y, Sossa H, Pajares G. Spatio-temporal analysis for obstacle detection in agricultural videos. Applied Soft Computing, 2016; 45(C): 86–97.
[2] Yu Y, Liu Y F, Wang J C, Noguchi N, He Y. Obstacle avoidance method based on double DQN for agricultural robots. Computers and Electronics in Agriculture, 2023; 204: 107546.
[3] Christiansen P, Nielsen L N, Steen K A, Jørgensen R N, Karstoft H. DeepAnomaly: Combining background subtraction and deep learning for detecting obstacles and anomalies in an agricultural field. Sensors, 2016; 16(11): 1904.
[4] Skoczeń M, Ochman M, Spyra K, Nikodem M, Krata D, Panek M, et al. Obstacle detection system for agricultural mobile robot application using RGB-D cameras. Sensors, 2021; 21(16): 5292.
[5] Ghazal S, Munir A, Qureshi W S. Computer vision in smart agriculture and precision farming: Techniques and applications. Artificial Intelligence in Agriculture, 2024; 13: 64–83.
[6] Wang T H, Chen B, Wang N, Ji Y H, Li H, Zhang M. Zero-shot obstacle detection using panoramic vision in farmland. Journal of Field Robotics, 2024; 41(7): 2169–2183.
[7] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 2005; pp.886–893. doi: 10.1109/CVPR.2005.177.
[8] Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004; 60(2): 91–110.
[9] Wang T H, Chen B, Zhang Z Q, Li H, Zhang M. Applications of machine vision in agricultural robot navigation: A review. Computers and Electronics in Agriculture, 2022; 198: 107085.
[10] Sharma A, Kumar V, Longchamps L. Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species. Smart Agricultural Technology, 2024; 9: 100648.
[11] Li Y, Li M, Qi J T, Zhou D Y, Zou Z F, Liu K. Detection of typical obstacles in orchards based on deep convolutional neural network. Computers and Electronics in Agriculture, 2021; 181: 105932.
[12] Zhang J C, Tian M M, Yang Z R, Li J H, Zhao L L. An improved target detection method based on YOLOv5 in natural orchard environments. Computers and Electronics in Agriculture, 2024; 219: 108780.
[13] Zhou X, Chen W, Wei X. Improved field obstacle detection algorithm based on YOLOv8. Agriculture, 2024; 14(12): 2263.
[14] Wang A, Chen H, Liu L H, Chen K, Lin Z J, Han J G, et al. YOLOv10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems, 2024; pp.107984–108011.
[15] Kamilaris A, Prenafeta-Boldú F X. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 2018; 147: 70–90.
[16] Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, et al. Microsoft COCO: Common objects in context. Computer Vision – ECCV, Springer, 2014; pp.740–755. doi: 10.1007/978-3-319-10602-1_48.
[17] Geiger A, Lenz P, Stiller C, Urtasun R. Vision meets robotics: The KITTI dataset. The International Journal of Robotics Research, 2013; 32(11): 1231–1237.
[18] Wang M, Deng W H. Deep visual domain adaptation: A survey. Neurocomputing, 2018; 312: 135–153.
[19] Zhuang F Z, Qi Z Y, Duan K Y, Xi D B, Zhu Y C, Zhu H S, et al. A comprehensive survey on transfer learning. Proceedings of the IEEE, 2021; 109(1): 43–76.
[20] Karki S, Basak J K, Tamrakar N, Deb N C, Paudel B, Kook J H, et al. Strawberry disease detection using transfer learning of deep convolutional neural networks. Scientia Horticulturae, 2024; 332: 113241.
[21] Cao B, Zhang B., Zheng W, Zhou J, Lin Y, Chen Y. Real-time, highly accurate robotic grasp detection utilizing transfer learning for robots manipulating fragile fruits with widely variable sizes and shapes. Computers and Electronics in Agriculture, 2022; 200: 107254.
[22] Ruchay A, Kolpakov V, Guo H, Pezzuolo A. On-barn cattle facial recognition using deep transfer learning and data augmentation. Computers and Electronics in Agriculture, 2024; 225: 109306.
[23] Hirahara K, Nakane C, Ebisawa H, Kuroda T, Iwaki Y, Utsumi T, et al. D4: Text-guided diffusion model-based domain adaptive data augmentation for vineyard shoot detection. Computers and Electronics in Agriculture, 2025; 230: 109849.
[24] Magistri F, Weyler J, Gogoll D, Lottes P, Behley J, Petrinic N, et al. From one field to another—Unsupervised domain adaptation for semantic segmentation in agricultural robotics. Computers and Electronics in Agriculture, 2023; 212: 108114.
[25] Bertoglio R, Mazzucchelli A, Catalano N, Matteucci M. A comparative study of Fourier transform and CycleGAN as domain adaptation techniques for weed segmentation. Smart Agricultural Technology, 2023; 4: 100188.
[26] Ma Y C, Zhang Z, Yang H L, Yang Z W. An adaptive adversarial domain adaptation approach for corn yield prediction. Computers and Electronics in Agriculture, 2021; 187: 106314.
[27] Chen L, Zou J X, Yuan Y, He H Y. Improved domain adaptive rice disease image recognition based on a novel attention mechanism. Computers and Electronics in Agriculture, 2023; 208: 107806.
[28] Wang C-Y, Mark Liao H-Y, Wu Y-H, Chen P-Y, Hsieh J-W, Yeh I-H. CSPNet: A new backbone that can enhance learning capability of CNN. Seattle: IEEE, 2020; pp.1571–1580. doi: 10.1109/CVPRW50498.2020.00203.
[29] Woo S, Park J, Lee J-Y, Kweon I S. CBAM: Convolutional block attention module. Computer Vision – ECCV 2018, Springer, 2018; pp.3–19.
[30] Zheng Z H, Wang P, Ren D W, Liu W, Ye R G, Hu Q H. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Transactions on Cybernetics, 2022; 52(8): 8574–8586.
[31] Ma S, Xu Y. MPDIoU: A loss for efficient and accurate bounding box regression. arXiv: 2307.07662.
[32] Jocher G, Qiu J, Chaurasia A. Ultralytics YOLO. 2023. https://github.com/ultralytics
[33] Chattopadhay A, Sarkar A, Howlader P, Balasubramanian V N. Grad-CAM++: Generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe: IEEE, 2018; pp.839–847. doi: 10.1109/WACV.2018.00097.
[34] Baker S, Matthews I. Lucas-Kanade 20 years on: A unifying framework. International Journal of Computer Vision, 2004; 56: 221–255.
[35] Xu H Z, Li S C, Ji Y H, Cao R Y, Zhang M. Dynamic obstacle detection based on panoramic vision in the moving state of agricultural machineries. Computers and Electronics in Agriculture, 2021; 184: 106104.
[36] Cheng K Y, Zhu X S, Zhan Y Z, Pei Y S. Video deblurring and flow-guided feature aggregation for obstacle detection in agricultural videos. International Journal of Multimedia Information Retrieval, 2022; 11(4): 577–588.
[37] Rivera G, Porras R, Florencia R, Sánchez-Solís J P. LiDAR applications in precision agriculture for cultivating crops: A review of recent advances. Computers and Electronics in Agriculture, 2023; 207: 107737.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
