基于改进YOLOv8s的轻量级果园李子检测方法  

Detecting plum fruits in orchard using lightweight improved YOLOv8s

作　　者：张冬妍[1] 陈诺 张淇[1] 吴晨旭 张榄翔 ZHANG Dongyan;CHEN Nuo;ZHANG Qi;WU Chenxu;ZHANG Lanxiang(College of Computer and Control Engineering,The University of Northeast Forestry,Harbin 150040,China)

机构地区：[1]东北林业大学计算机与控制工程学院,哈尔滨150040

出　　处：《农业工程学报》2025年第1期154-160,共7页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金项目(32202147)。

摘　　要：为了解决果园李子受枝叶和果实遮蔽、环境变化等因素影响,难以准确检测的问题,该研究提出了一种基于改进YOLOv8s的轻量级果园李子检测模型。首先,采用自设计主干网络Faster-EMA缩减模型复杂度、提高检测精度。其次,引入焦点调制网络(focal modulation)替换原模型中的SPPF模块增强特征融合能力,丰富特征提取的语义信息;最后,引入参数共享策略并实现轻量级检测头LDetect,满足了低功耗嵌入式设备部署需求。试验结果表明,优化后模型的平均检测精度达到97.2%,与原模型相比,检测精度提高了7.4个百分点;模型计算量降低了44.8%;模型参数数量减小了25.8%;部署在边缘计算设备Jetson Nano 4GB上,检测帧率达到了48.3帧/s。该研究所提出的方法能有效的解决复杂背景下果园李子的智能化检测,有助于促进李子智能化采摘技术的发展。Plum fruit is often requiring timely harvesting during specific seasons,due to the significant nutritional and culinary value.However,it is still challenging to accurately detect the plums in real-world orchard environments,such as the shading from foliage,and the overlapping of fruits.These influencing factors have also posed the higher demands on intelligent harvesting,in terms of speed,accuracy and real-time performance.In this study,an efficient and reliable fruit detection model was proposed to fully meet the specific needs of the plums in the complex orchard environments using an enhanced and lightweight version of YOLOv8s.Firstly,the backbone network(named Faster-EMA)was developed to reduce the overall complexity of the model with the high detection accuracy.The architecture of the backbone network was optimized to more effectively extract the critical features from the input images,even when the plums were occluded by branches or surrounded by other fruits.The optimal network structure was then achieved for the accurate detection with the few computational resources.Secondly,Focal Modulation was introduced to replace the spatial pyramid pooling(SPPF)module in original YOLOv8s.The multi-scale features were integrated to detect the plums at different sizes under varying environmental conditions.The semantic information was also captured during feature extraction.The key aspects of the plums were then focused(such as the shape and color),rather than the less relevant background elements.The feature fusion mechanism was significantly enhanced the overall performance of the model.Thirdly,the parameter-sharing strategy(LDetect)was introduced to implement the lightweight detection head.The parameters were shared across different branches of the detection head,in order to maintain the high detection performance while significantly reducing the number of parameters and computational complexity.This lightweight detection head was designed specifically to meet the deployment requirements of low-power embedded device

关 键 词：目标检测 YOLOv8 轻量化 李子 LDetect 

分 类 号：S24[农业科学—农业电气化与自动化]