Ai Junchen, Li Yadong, Gao Shengxiang, Hu Rongsheng, Che Wengang
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China.
School of Data Science and Engineering, Kunming City College, Kunming 650101, China.
Sensors (Basel). 2025 Jul 2;25(13):4129. doi: 10.3390/s25134129.
Tea disease detection is of great significance to the tea industry. In order to solve the problems such as mutual occlusion of leaves, light disturbance, and small lesion area under complex background, YOLO-SSM, a tea disease detection model, was proposed in this paper. The model introduces the SSPDConv convolution module in the backbone of YOLOv8 to enhance the global information perception of the model under complex backgrounds; a new ESPPFCSPC module is proposed to replace the original spatial pyramid pool SPPF module, which optimizes the multi-scale feature expression; and the MPDIoU loss function is introduced to optimize the problem that the original CIoU is insensitive to the change of target size, and the positioning ability of small targets is improved. Finally, the map values of 89.7% and 68.5% were obtained on a self-made tea data set and a public tea disease data set, which were improved by 3.9% and 4.3%, respectively, compared with the original benchmark model, and the reasoning speed of the model was 164.3 fps. Experimental results show that the proposed YOLO-SSM algorithm has obvious advantages in accuracy and model complexity and can provide reliable theoretical support for efficient and accurate detection and identification of tea leaf diseases in natural scenes.
茶叶病害检测对茶叶产业具有重要意义。为了解决复杂背景下叶片相互遮挡、光照干扰以及病斑面积小等问题，本文提出了一种茶叶病害检测模型YOLO-SSM。该模型在YOLOv8的主干中引入了SSPDConv卷积模块，以增强模型在复杂背景下的全局信息感知能力；提出了一种新的ESPPFCSPC模块来取代原来的空间金字塔池化SPPF模块，优化了多尺度特征表达；引入了MPDIoU损失函数，优化了原CIoU对目标尺寸变化不敏感的问题，提高了小目标的定位能力。最后，在自制茶叶数据集和公开茶叶病害数据集上分别获得了89.7%和68.5%的mAP值，与原基准模型相比分别提高了3.9%和4.3%，且模型推理速度为164.3fps。实验结果表明，所提出的YOLO-SSM算法在准确性和模型复杂度方面具有明显优势，可为自然场景下茶叶病害的高效准确检测与识别提供可靠的理论支持。
