Enhanced obstacle detection for intelligent agricultural machinery via transfer learning and improved YOLO11OA
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 70552 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.
Huan Wan;Xianlu Guan;Yuanzhen Ou;Rui Jiang;Zhiyan Zhou
College of Engineering,South China Agricultural University and Guangdong Laboratory for Lingnan Modern Agriculture,Guangzhou 510642,China Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence(GDKL-AAI),Guangzhou 510642,ChinaCollege of Engineering,South China Agricultural University and Guangdong Laboratory for Lingnan Modern Agriculture,Guangzhou 510642,China Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence(GDKL-AAI),Guangzhou 510642,ChinaCollege of Engineering,South China Agricultural University and Guangdong Laboratory for Lingnan Modern Agriculture,Guangzhou 510642,China Guangdong Engineering Research Center for Agricultural Aviation Application(ERCAAA),Guangzhou 510642,ChinaCollege of Engineering,South China Agricultural University and Guangdong Laboratory for Lingnan Modern Agriculture,Guangzhou 510642,China Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence(GDKL-AAI),Guangzhou 510642,China Guangdong Engineering Research Center for Agricultural Aviation Application(ERCAAA),Guangzhou 510642,China Key Laboratory of Key Technology on Agricultural Machine and Equipment(South China Agricultural University),Ministry of Education,Guangzhou 510642,China State Key Laboratory of Agricultural Equipment Technology,Guangzhou 510642,China Key Technology Innovation Research Center of Rice Smart Farming of South China Agricultural University-Dongyuan County,Heyuan 517554,Guangdong,China Heyuan Branch,Guangdong Laboratory for Lingnan Modern Agriculture,Heyuan 517000,Guangdong,ChinaCollege of Engineering,South China Agricultural University and Guangdong Laboratory for Lingnan Modern Agriculture,Guangzhou 510642,China Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence(GDKL-AAI),Guangzhou 510642,China Guangdong Engineering Research Center for Agricultural Aviation Application(ERCAAA),Guangzhou 510642,China Key Laboratory of Key Technology on Agricultural Machine and Equipment(South China Agricultural University),Ministry of Education,Guangzhou 510642,China State Key Laboratory of Agricultural Equipment Technology,Guangzhou 510642,China Key Technology Innovation Research Center of Rice Smart Farming of South China Agricultural University-Dongyuan County,Heyuan 517554,Guangdong,China Heyuan Branch,Guangdong Laboratory for Lingnan Modern Agriculture,Heyuan 517000,Guangdong,China The Centre for Pesticide Application and Safety(CPAS),School of Agriculture and Food Sciences,the University of Queensland,Gatton,QLD 4343,Australia
农业科技
agricultural machineryobstacle detectiontransfer learningYOLO11embedded deployment
《International Journal of Agricultural and Biological Engineering》 2026 (4)
P.256-267,12
supported by the National Key R&D Program of China(2022YFD2001501)in part by Laboratory of Lingnan Modern Agriculture Project(NT2025006)Science and Technology Plan of Guangdong Province of China(2023B10564002)the National Natural Science Foundation of China(32301707)the Natural Science Foundation of Guangdong Province(2024A1515012608)Guangzhou Key Research and Development Program(2024B03J1356).
评论