基于改进YOLOv8和无人机遥感影像的大田烟株数量检测  

Detection of tobacco plant numbers in large fields based on improved YOLOv8 and UAV remote sensing imagery

作　　者：肖恒树 李军营[2] 梁虹[1] 马二登[2] 张宏 Xiao Hengshu;Li Junying;Liang Hong;Ma Erdeng;Zhang Hong(School of Information Science and Technology,Yunnan University,Kunming 650504,China;Yunnan Academy of Tobacco Agriculture Science,Kunming 650021,China)

机构地区：[1]云南大学信息学院,昆明650504 [2]云南省烟草农业科学研究院,昆明650021

出　　处：《电子测量技术》2024年第9期163-171,共9页Electronic Measurement Technology

基　　金：中国烟草总公司云南省公司科技计划项目(2021530000241025);云南大学研究生科研创新基金(KC-23235266)项目资助。

摘　　要：植株精确计数在精准化农业中至关重要,是监测作物生长和预测产量的重要基础。针对成熟期烟草植株存在的密植、重叠和高空小目标等难题,研究提出了一种轻量级GEW-YOLOv8烟株检测算法。该算法采用GhostC2f模块减少了模型的参数和计算量,并应用高效的多尺度注意力机制来区分被遮挡的烟草植株。此外,还引入了WIoU损失函数,以加速模型收敛并提高准确性。实验结果表明,与原始模型相比,模型的效率和准确性有了显著提高,浮点运算次数减少了24.7%,模型大小减少了26.7%。改进后的模型烟草植株检测平均精度AP 0.5和AP 0.5~0.95分别为99.1%和86.2%,相较于原YOLOv8n模型分别提高了0.8%和3.6%。改进后的模型能够更快、更精确地识别田间烟草植物,为智慧烟草农业提供技术支持。Accurate plant counting is crucial in precision agriculture,forming a critical foundation for monitoring crop growth and predicting yield.To address challenges such as densely packed,overlapping,and aerial small targets of tobacco plants during the maturity stage,a lightweight GEW-YOLOv8 tobacco plant counting algorithm was proposed.The algorithm utilizes the GhostC2f module to reduce the parameters and computational workload of the model and employs an efficient multi-scale attention mechanism to discern occluded tobacco plants.Additionally,the WIoU loss function is introduced to accelerate model convergence and improve accuracy.Experimental results show a significant improvement in efficiency and accuracy compared to the original model,with a 24.7%reduction in FLOPs and a 26.7%decrease in model size.The improved model tobacco plant detection accuracy AP 0.5 and AP 0.5~0.95 reached 99.1%and 86.2%respectively,which were increased by 0.8%and 3.6%respectively compared with the original YOLOv8n model.The improved model can more swiftly and accurately identify field tobacco plants,providing technical support for intelligent tobacco agriculture.

关 键 词：YOLO 无人机 遥感影像 目标检测 烟草植株计数 轻量化 

分 类 号：TN911.73[电子电信—通信与信息系统]