College of Food Science and Technology, Yunnan Agricultural University, Kunming 650201, China.
The Key Laboratory for Crop Production and Smart Agriculture of Yunnan Province, Kunming 650201, China.
Sensors (Basel). 2024 May 1;24(9):2896. doi: 10.3390/s24092896.
In order to efficiently identify early tea diseases, an improved YOLOv8 lesion detection method is proposed to address the challenges posed by the complex background of tea diseases, difficulty in detecting small lesions, and low recognition rate of similar phenotypic symptoms. This method focuses on detecting tea leaf blight, tea white spot, tea sooty leaf disease, and tea ring spot as the research objects. This paper presents an enhancement to the YOLOv8 network framework by introducing the Receptive Field Concentration-Based Attention Module (RFCBAM) into the backbone network to replace C2f, thereby improving feature extraction capabilities. Additionally, a mixed pooling module (Mixed Pooling SPPF, MixSPPF) is proposed to enhance information blending between features at different levels. In the neck network, the RepGFPN module replaces the C2f module to further enhance feature extraction. The Dynamic Head module is embedded in the detection head part, applying multiple attention mechanisms to improve multi-scale spatial location and multi-task perception capabilities. The inner-IoU loss function is used to replace the original CIoU, improving learning ability for small lesion samples. Furthermore, the AKConv block replaces the traditional convolution Conv block to allow for the arbitrary sampling of targets of various sizes, reducing model parameters and enhancing disease detection. the experimental results using a self-built dataset demonstrate that the enhanced YOLOv8-RMDA exhibits superior detection capabilities in detecting small target disease areas, achieving an average accuracy of 93.04% in identifying early tea lesions. When compared to Faster R-CNN, MobileNetV2, and SSD, the average precision rates of YOLOv5, YOLOv7, and YOLOv8 have shown improvements of 20.41%, 17.92%, 12.18%, 12.18%, 10.85%, 7.32%, and 5.97%, respectively. Additionally, the recall rate (R) has increased by 15.25% compared to the lowest-performing Faster R-CNN model and by 8.15% compared to the top-performing YOLOv8 model. With an FPS of 132, YOLOv8-RMDA meets the requirements for real-time detection, enabling the swift and accurate identification of early tea diseases. This advancement presents a valuable approach for enhancing the ecological tea industry in Yunnan, ensuring its healthy development.
为了高效识别早期茶树病害，针对茶树病害背景复杂、小病灶检测困难、相似表型症状识别率低等问题，提出了一种改进的 YOLOv8 病灶检测方法。该方法以茶树炭疽病、茶白星病、茶煤污病、茶轮斑病为研究对象。本文在 YOLOv8 网络框架中引入了基于感受野集中注意力模块（RFCBAM）代替 C2f，以提高特征提取能力；在骨干网络中提出了混合池化模块（MixSPPF），增强不同层次特征之间的信息融合；在 neck 网络中，用 RepGFPN 替换 C2f 进一步增强特征提取；在检测头部分嵌入了动态头模块，应用多种注意力机制提高多尺度空间位置和多任务感知能力；使用内交并损失函数（Inner-IoU Loss）代替原有的 CIoU 损失函数，提高对小病灶样本的学习能力；此外，使用 AKConv 模块替换传统卷积 Conv 模块，实现对各种大小目标的任意采样，减少模型参数，提高病害检测能力。在自建数据集上的实验结果表明，改进后的 YOLOv8-RMDA 在检测小目标病灶区域时具有更优的检测性能，对早期茶树病变的识别准确率达到 93.04%。与 Faster R-CNN、MobileNetV2 和 SSD 相比，YOLOv5、YOLOv7 和 YOLOv8 的平均精度分别提高了 20.41%、17.92%、12.18%、12.18%、10.85%、7.32%和 5.97%，召回率（R）比表现最低的 Faster R-CNN 模型提高了 15.25%，比表现最高的 YOLOv8 模型提高了 8.15%。YOLOv8-RMDA 的帧率（FPS）达到 132，满足实时检测要求，能够快速准确地识别早期茶树病害。这一改进为提升云南生态茶产业提供了有益的方法，确保其健康发展。
