Li Ruiheng, Liu Jiarui, Shi Binqin, Zhao Hanyi, Li Yan, Zheng Xinran, Peng Chao, Lv Chunli
China Agricultural University, Beijing 100083, China.
Plants (Basel). 2024 Sep 28;13(19):2720. doi: 10.3390/plants13192720.
This paper introduces a novel deep learning model for grape disease detection that integrates multimodal data and parallel heterogeneous activation functions, significantly enhancing detection accuracy and robustness. Through experiments, the model demonstrated excellent performance in grape disease detection, achieving an accuracy of 91%, a precision of 93%, a recall of 90%, a mean average precision (mAP) of 91%, and 56 frames per second (FPS), outperforming traditional deep learning models such as YOLOv3, YOLOv5, DEtection TRansformer (DETR), TinySegformer, and Tranvolution-GAN. To meet the demands of rapid on-site detection, this study also developed a lightweight model for mobile devices, successfully deployed on the iPhone 15. Techniques such as structural pruning, quantization, and depthwise separable convolution were used to significantly reduce the model's computational complexity and resource consumption, ensuring efficient operation and real-time performance. These achievements not only advance the development of smart agricultural technologies but also provide new technical solutions and practical tools for disease detection.
本文介绍了一种用于葡萄病害检测的新型深度学习模型，该模型集成了多模态数据和并行异构激活函数，显著提高了检测精度和鲁棒性。通过实验，该模型在葡萄病害检测中表现出色，准确率达到91%，精确率为93%，召回率为90%，平均精度均值（mAP）为91%，每秒处理56帧（FPS），优于YOLOv3、YOLOv5、检测变压器（DETR）、TinySegformer和Tranvolution-GAN等传统深度学习模型。为满足快速现场检测的需求，本研究还为移动设备开发了一个轻量级模型，并成功部署在iPhone 15上。采用了结构剪枝、量化和深度可分离卷积等技术，显著降低了模型的计算复杂度和资源消耗，确保了高效运行和实时性能。这些成果不仅推动了智能农业技术的发展，也为病害检测提供了新的技术解决方案和实用工具。
