MI-YOLO多光谱无人机图像中 松材线虫病轻度变色木检测

打开文本图片集

中图分类号：S763.7;TP391.4 文献标志码：A 文章编号：1000-2006（2026）02-0019-10

MI-YOLO model for detecting mildly discolored pine trees infected with pinewilt disease with multispectral UAV images

SHAO Xinxin1，LIU Wenping1*，WANG Han1，ZONG Shixiang²，YUANBo1 （1.School of Information Science and Technology，Beijing Forestry University，Beijing 1Ooo83，China; 2.College ofForestry，BeijingForestryUniversity，Beijing1OOo83，China）

Abstract：【Objective】This researchaims toaccuratelyand eficientlydetect mildlydiscolored pine trees infected with pine wilt disease inreal time using multispectralunmannedaerial vehicle（UAV）remote sensing images，a Multispectral Images YOLO（MI-YOLO）model isproposed based onYOLOv8n.【Method】First，multispectral images arerapidlyalignedusing thecrosspowerspectruminthefrequencydomain.Second，atinymulti-branchauxiliaryfeature pyramidnetwork isintroducedas theneck network toenhance featureutilization whilemaintaining model lightweight. Finally，theoriginal C2ffeature fusionmoduleinYOLOv8nisreplacedwithalightweight C2f-Faster moduletoreduce redundant computation.【Result】The proposed MI-YOLO model achieves an average precision of 84.5% at an IoU threshold of 0.5（ AP50 ），with 2.1 MB parameters and 7.25 GB floating point operations（FLOPs）. Compared with YOLOv8n， AP50 is improved by10.5 percentage points，while the number of parameters and FLOPs are reduced by 30% （204号 and 13% ，respectively.【Conclusion】The MI-YOLO object detection model exhibits high accuracyanda lightweight structure，enablingreal-timedetectionofmildlydiscoloredpinetrees infectedwithpinewiltdiseaseinmultispectral images.

Keywords：multispectral images；unmanned aerial vehicle（UAV）；pine wilt disease；object detection松材线虫病（pinewiltdisease，PWD）又称作 松树萎蔫病，是由松材线虫（Bursaphelenchus xylophilus）引起的一种松树毁灭性病害。（剩余19090字）