A LIGHTWEIGHT DETECTION ALGORITHM FOR MULTIPLE WHEAT DISEASES BASED ON IMPROVED YOLOV11
Keywords:
Wheat disease detection, YOLOv11, Lightweight network, Deep learning, Edge computing, Precision agricultureAbstract
Wheat planting areas face complex field environments, while embedded edge devices are restricted by limited computing power. Conventional detection models fail to balance recognition accuracy and real-time inference speed for multiple wheat diseases. This paper proposes a lightweight multi-disease detection algorithm based on improved YOLOv11. Taking YOLOv11s as the baseline, lightweight optimizations are conducted on the backbone, neck and detection head. A self-built wheat disease image dataset is constructed for model evaluation. The improved model achieves drastically reduced parameters and computational overhead, outperforming original lightweight YOLOv11 variants in detection accuracy. Ablation experiments verify the independent performance gain of each optimized module. After ONNX export and TensorRT FP16 quantization, the model is deployed on Raspberry Pi 5 and attains an ultra-high inference frame rate. The proposed lightweight algorithm addresses the challenge of real-time wheat disease detection on field edge terminals, delivering a practical high-precision, low-latency solution for intelligent crop disease diagnosis in farmlands.References
[1] Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 2015, 28.
[2] Nie C. Detection Method of Common Wheat Diseases Based on Improved YOLOv8. Proceedings of the 2025 6th International Conference on Computer Information and Big Data Applications. 2025: 19-24.
[3] Yao X, Yang F, Yao J. YOLO-Wheat: A wheat disease detection algorithm improved by YOLOv8s. IEEE Access, 2024, 12: 133877-133888.
[4] Zhang X, Wei L, Yang R. TriPerceptNet: a lightweight multi-scale enhanced YOLOv11 model for accurate rice disease detection in complex field environments. Frontiers in Plant Science, 2025, 16: 1614929.
[5] Kumar D, Kukreja V. Impact of image segmentation and feature sets in automated plant disease classification: a comprehensive review based on wheat plant images. Progress in Artificial Intelligence, 2025, 14(4): 451-504.
[6] Bouskour S, Zaggaf M H, Bahatti L. Deep learning recognition of wheat leaf disease using MobileNetV2 model. 2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET). IEEE, 2024: 1-6.
[7] Zhang P, Li R, Liu Y, et al. I-GhostNetV3: A Lightweight Deep Learning Framework for Vision-Sensor-Based Rice Leaf Disease Detection in Smart Agriculture. Sensors, 2026, 26(3): 1025.
[8] Wang X, Li C, Zhao C, et al. GrainNet: efficient detection and counting of wheat grains based on an improved YOLOv7 modeling. Plant Methods, 2025, 21(1): 44.
[9] Liu W, Xu L, Chang X, et al. Focal-HAIN: a lightweight model with adaptive modulation and hierarchical interaction for real-time crop pest and disease monitoring. Frontiers in Plant Science, 2026, 17: 1778883.
[10] Hmache F, Bellout A, Zarboubi M, et al. Pruning, Knowledge Distillation and Quantization of YOLOv8n for Edge-Based Precision Agriculture. International Conference on Advanced Communications with Modern Circuits and Systems Technologies. Cham: Springer Nature Switzerland, 2025: 248-254.
[11] Masykur F, Adi K, Nurhayati O D. Measuring Agricultural Area Using YOLO Object Detection and ArUco Markers. Ingenierie des Systemes d'Information, 2024, 29(1).
[12] Liu H, Zhang Y, Liu S, et al. UAV wheat rust detection based on FasterNet-YOLOv8. 2023 IEEE international conference on robotics and biomimetics (ROBIO). IEEE, 2023: 1-6.
[13] Rodrigo M, Cuevas C, García N. Comprehensive comparison between vision transformers and convolutional neural networks for face recognition tasks. Scientific reports, 2024, 14(1): 21392.
[14] Karthikeyan R, Karthik S, Harshavardhan A. Real-time plant disease detection on Raspberry Pi using lightweight deep learning models. Sustainable Computing: Informatics and Systems, 2025, 37: 100892.