基于特征融合FRCNet的草地高光谱识别分类研究  

Hyperspectral Image Classification of Grassland Based on Feature Fusion FRCNet Model

作　　者：刘雨珂 刘一磊 罗小玲[1] 郜晓晶[1] 潘新[1] LIU Yuke;LIU Yilei;LUO Xiaoling;GAO Xiaojing;PAN Xin(College of Computer and Information Engineering,Inner Mongolia Agricultural University,Hohhot 010010,China)

机构地区：[1]内蒙古农业大学计算机与信息工程学院,内蒙古呼和浩特010010

出　　处：《内蒙古师范大学学报(自然科学版)》2025年第2期159-169,共11页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：内蒙古自治区自然科学基金资助项目“多模态牧草图像特征提取与识别”(2023LHMS06014)。

摘　　要：为解决高光谱草地识别分类任务中存在的精度低、计算成本高的问题,提出了FRCNet(faster R-CNN,FRC)网络模型。通过无人机搭载高光谱成像仪进行草地平扫拍摄,建立四种类别的草地高光谱数据集。采用高斯滤波器与主成分分析法(principal component analysis,PCA)对高光谱图像降噪与降维处理,建立主要由FRC模块与FAC模块组成的FRCNet网络模型进行分类任务。实验采用平均精度(average accuracy,AA)、总体精度(overall accuracy,OA)、F1分数与运行时间作为性能指标,并且使用八种方法与FRCNet进行对比实验。结果表明,FRCNet网络表现最好,AA为93.36%,OA为93.49%,F1分数为96.64,较其他方法准确度提高了10%~20%。同时使用三个公开数据集进行对比试验,FRCNet表现最好,准确度提升了2%~20%。研究结果证明,FRCNet网络模型在高光谱草地分类任务中的有效性,可以作为当前高光谱精度低、计算成本高问题的一种高效解决方案。To address the issues of low accuracy and high computational cost in hyperspectral image classification tasks of grassland,this study proposed the FRCNet network model.Hyperspectral images of grasslands were captured using an unmanned aerial vehicle equipped with a hyperspectral imager,and a hyperspectral dataset for four grassland categories was established.Gaussian filtering and principal component analysis(PCA)were applied to noise reduction and dimensionality reduction of the hyperspectral images.The FRCNet network model,primarily consisting of the FRC module and the FAC module,was established for classification tasks.Average accuracy(AA),overall accuracy(OA),F1 score,and runtime were taken as performance indicators,and comparative experiments were conducted between FRCNet and eight methods.The results showed that the FRCNet network performed best with AA of 93.36%,OA of 93.49%,and F1 score of 96.64,improving accuracy by 10%-20%compared to the other methods.In addition,the comparative experiments on three public datasets demonstrated that FRCNet performed best,with accuracy improvements ranging from 2%-20%.The research results proved the effectiveness of the FRCNet network model in hyperspectral image classification tasks of grassland.It can serve as an efficient solution to the current issues of low hyperspectral accuracy and high computational cost.

关 键 词：高光谱影像分类 识别分类 特征融合 重参数化重聚焦卷积 注意力机制 

分 类 号：S2[农业科学—农业工程] TP3[自动化与计算机技术—计算机科学与技术]