摘要
为实现高粱品种的快速检测,建立了光谱重建技术结合机器学习分类模型的高粱品种检测方法。将软阈值(ST)函数与压缩激励(SE)模块结合嵌入到多级光谱智能自注意网络(MST++)深层结构中,构建通道自适应阈值模块(CW)-MST++,以MST++、分层回归网络(HRNet)、基于卷积的RGB图像高光谱恢复网络(HSCNN+)为对照,以平均相对绝对值误差(MRAE)、均方根误差(RMSE)比较重建模型性能。采用4种重建网络的高光谱数据建立支持向量机(SVM)模型,以平均精度(ACC)、平均召回率(Recall)和F1分数评价检测模型性能。结果表明,与MST++、HRNet及HSCNN+网络相比,CW-MST++重建的高光谱图像误差最小(验证集MRAE=0.0175、RMSE=0.0076),网络参数量及网络浮点运算数较低(Params为1.77 M、Flops为20.80 G);其重建的高光谱数据建立的SVM模型预测效果最佳(测试集ACC=94.52%、Recall=94.24%、F1分数=94.14%)。与原始高光谱数据相比,CW-MST++重建高光谱数据ACC、Recall、F1分数分别仅相差2.06%、2.54%、2.52%,实现了酿酒高粱的快速准确检测。
In order to realize the rapid detection of sorghum varieties,a sorghum variety detection method based on spectral reconstruction technology combined with machine learning classification model was established.Firstly,the soft threshold(ST)function and squeeze-and-excitation(SE)module were embedded in the deep structure of the multi-stage spectral-wise transformer(MST++),and the channel-wise(CW)-MST++was constructed.Using MST++,hierarchical regression network(HRNet)and CNN-based hyperspectral recovery from RGB images(HSCNN+)as controls,the performance of rebuild model was compared usingmean relative absolute error(MRAE)and root mean square error(RMSE).Secondly,the Support Vector Machine(SVM)model was established by hyperspectral data of four reconstructed networks,and the performance of the detection model was evaluated by average accuracy(ACC),average recall rate(Recall)and F1 scores.The results showed that compared with MST++,HRNet and HSCNN+networks,the hyperspectral image reconstructed by CW-MST++had the smallest error(MRAE=0.0175,RMSE=0.0076 in validation set),low number of network parameters and floating point operations(Params was 1.77M,Flops was 20.80 G),and the SVM model established by the reconstructed hyperspectral data had the optimal prediction effect(ACC=94.52%,Recall=94.24%,F1 scores=94.14 in the testing set).Compared with the original hyperspectral data,the differences in ACC,Recall and F1 scores of hyperspectral data reconstructed by CW-MST++were only 2.06%,2.54%and 2.52%,respectively,which realized the rapid and accurate detection of sorghum.
作者
何林
胡新军
王俊
田建平
谢亮亮
杨海栗
陈满娇
HE Lin;HU Xinjun;WANG Jun;TIAN Jianping;XIE Liangliang;YANG Haili;CHEN Manjiao(School of Mechanical Engineering,Sichuan University of Science and Engineering,Yibin 644000,China;Sichuan Provincial Key Laboratory of Brewing Biotechnology and Application,Yibin 644000,China)
出处
《中国酿造》
CAS
北大核心
2024年第10期258-264,共7页
China Brewing
基金
四川省科技厅项目(2023YFS0451)
酿酒生物技术及应用四川省重点实验室开放课题(NJ2022-04)
过程装备与控制工程四川省高校重点实验室(GK202306)
四川轻化工大学研究生创新基金资助项目(Y2023097)。
关键词
高粱
重建光谱
深度学习
高光谱图像
品种检测
sorghum
reconstructing spectra
deep learning
hyperspectral images
variety detection
