Yan Changqing, Liang Zeyun, Yin Ling, Wei Shumei, Tian Qi, Li Ying, Cheng Han, Liu Jindong, Yu Qiang, Zhao Gang, Qu Junjie
College of Intelligent Equipment, Shandong University of Science and Technology, Taian 271019, China.
Guangxi Crop Genetic Improvement and Biotechnology Key Lab, Guangxi Academy of Agricultural Sciences, Nanning 530007, China.
Plant Phenomics. 2024 Sep 11;6:0246. doi: 10.34133/plantphenomics.0246. eCollection 2024.
Monitoring spores is crucial for predicting and preventing fungal- or oomycete-induced diseases like grapevine downy mildew. However, manual spore or sporangium detection using microscopes is time-consuming and labor-intensive, often resulting in low accuracy and slow processing speed. Emerging deep learning models like YOLOv8 aim to rapidly detect objects accurately but struggle with efficiency and accuracy when identifying various sporangia formations amidst complex backgrounds. To address these challenges, we developed an enhanced YOLOv8s, namely, AFM-YOLOv8s, by introducing an Adaptive Cross Fusion module, a lightweight feature extraction module FasterCSP (Faster Cross-Stage Partial Module), and a novel loss function MPDIoU (Minimum Point Distance Intersection over Union). AFM-YOLOv8s replaces the C2f module with FasterCSP, a more efficient feature extraction module, to reduce model parameter size and overall depth. In addition, we developed and integrated an Adaptive Cross Fusion Feature Pyramid Network to enhance the fusion of multiscale features within the YOLOv8 architecture. Last, we utilized the MPDIoU loss function to improve AFM-YOLOv8s' ability to locate bounding boxes and learn object spatial localization. Experimental results demonstrated AFM-YOLOv8s' effectiveness, achieving 91.3% accuracy (mean average precision at 50% IoU) on our custom grapevine downy mildew sporangium dataset-a notable improvement of 2.7% over the original YOLOv8 algorithm. FasterCSP reduced model complexity and size, enhanced deployment versatility, and improved real-time detection, chosen over C2f for easier integration despite minor accuracy trade-off. Currently, the AFM-YOLOv8s model is running as a backend algorithm in an open web application, providing valuable technical support for downy mildew prevention and control efforts and fungicide resistance studies.
监测孢子对于预测和预防由真菌或卵菌引起的疾病（如葡萄霜霉病）至关重要。然而，使用显微镜手动检测孢子或孢子囊既耗时又费力，往往导致准确率低和处理速度慢。像YOLOv8这样的新兴深度学习模型旨在快速准确地检测物体，但在复杂背景中识别各种孢子囊形态时，在效率和准确性方面存在困难。为应对这些挑战，我们通过引入自适应交叉融合模块、轻量级特征提取模块FasterCSP（更快的跨阶段部分模块）和新颖的损失函数MPDIoU（最小点距离交并比），开发了一种增强的YOLOv8s，即AFM - YOLOv8s。AFM - YOLOv8s用更高效的特征提取模块FasterCSP取代C2f模块，以减少模型参数大小和整体深度。此外，我们开发并集成了自适应交叉融合特征金字塔网络，以增强YOLOv8架构内多尺度特征的融合。最后，我们利用MPDIoU损失函数来提高AFM - YOLOv8s定位边界框和学习物体空间定位的能力。实验结果证明了AFM - YOLOv8s的有效性，在我们自定义的葡萄霜霉病孢子囊数据集上达到了91.3%的准确率（50%交并比下的平均精度均值），比原始的YOLOv8算法显著提高了2.7%。FasterCSP降低了模型复杂度和大小，增强了部署通用性，并改善了实时检测，尽管在精度上有轻微折衷，但因其更易于集成而被选用于替代C2f。目前，AFM - YOLOv8s模型正在一个开放的网络应用程序中作为后端算法运行，为霜霉病防控工作和杀菌剂抗性研究提供了有价值的技术支持。
