基于多光谱图像角度融合测定库尔勒香梨理化指标

doi:10.3964/j.issn.1000-0593(2024)03-0649-07

摘要
参考文献
相关文章 (15)

全文: PDF (4474 KB)
输出: BibTeX | EndNote (RIS)

摘要：基于多光谱图像角度融合，提出了一种库尔勒香梨快速无损检测的方法。以库尔勒香梨为研究对象，应用多光谱成像采集系统，以10°为间隔，获取了相对方位角为10°~90°内的多光谱图像。使用ENVI5.1软件进行多光谱图像角度融合并提取感兴趣区域（ROI），获得多光谱数据。对光谱反射率、波段和相对方位角进行了皮尔逊相关性分析，发现波段和相对方位角都对光谱反射率呈极显著相关性，且相对方位角相关系数为0.1大于波段相关系数0.053，有必要在建模过程中加入相对方位角因素。采用标准正态变量变换（SNV）、均值中心化变换（MC）、卷积平滑处理（S_G）和归一化处理（Nor）等预处理方法，选用偏最小二乘回归（PLSR）建立全波段检测模型，通过校正集相关系数（R_c）、预测集相关系数（R_p）、校正集均方根误差（RMSEC）和预测集均方根误差（RMSEP）对模型的效果进行评价，对比探究特征角度下和角度融合下库尔勒香梨关键指标的模型检测效果。结果表明：采用角度融合处理后，所建立的PLSR和SVM模型预测效果都有显著提升。预测库尔勒香梨含水率最优模型为采用角度融合的偏最小二乘回归模型（AF-PLSR），其R_c为0.936，RMSEC为0.298，R_p为0.901，RMSEP为0.285；预测库尔勒香梨硬度和糖度的最优模型为以角度融合的支持向量机模型（AF-SVM），R_c分别为0.894、0.905，RMSEC为0.527、0.376；R_p为0.830、0.901，RMSEP为0.532、0.379。角度融合将不同角度下的光谱数据结合在一起，获得了比单一角度更加丰富的信息，得到了更加完善的光谱。所建立的检测模型精度更高。结果证明：基于多光谱图像角度融合技术预测库尔勒香梨的含水率、硬度和糖度是可行的。为提高多光谱无损检测精度和高光谱无损检测精度提供了一种新的思路。

关键词：多光谱成像；融合光谱；库尔勒香梨；偏最小二乘回归

Abstract：Based on a multispectral image angle fusion. Multispectral images were obtained from 10° to 90 °at 10° intervals. Multispectral image angle fusion and the region of interest (ROI) were extracted using ENVI5.1 software to obtain the multispectral data. The Pearson correlation analysis of the spectral reflectance, band, and relative azimuth found that both the band and relative azimuth were extremely significantly correlated with the spectral reflectance, and the relative azimuth correlation coefficient of 0.1 is greater than the band correlation coefficient of 0.053. Therefore, it is necessary to add the relative azimuth factors in the modeling process. Using standard normal variable transformation (SNV), mean centralization transformation (MC), convolution smoothing treatment (S_G), normalization treatment (Nor), partial least squares regression (PLSR) to evaluate the full band set correlation coefficient (R_c), prediction set correlation coefficient (R_p), correction set root mean square error (RMSEC) and prediction set root mean square error (RMSEP) to explore the effect of the model. The results show that the prediction effect of the established PLSR and SVM models is significantly improved after adopting the angle fusion treatment. The optimal model is a partial least squares regression model (AF-PLSR) with R_c of 0.936, RMSEC of 0.298, R_p of 0.901, RMSEP of 0.285; the optimal prediction model is the support vector machine model (AF-SVM), R_c is 0.894, 0.527, 0.376; R_p is 0.830, 0.901, and RMSEP is 0.532, 0.379 respectively. Angle fusion combines the spectral data from different angles together to obtain more abundant information than a single angle and a more perfect spectral information. The established detection model has a higher accuracy. The results proved that it is feasible to predict the water content, hardness, and sugar content of Korla's fragrant pear based on the multispectral image angle fusion technology. The results provide a new idea for improving MMS and HMS NDE accuracy.

Key words：Multi-spectral imaging; Fusion spectrum; Korla fragrant pear; Partial least squares regression

收稿日期: 2022-08-22 修订日期: 2022-10-31

中图分类号:

O433.4

基金资助: 国家自然科学基金项目（11964030），塔里木大学现代农业工程重点实验室项目（TDNG2020202）资助

通讯作者: 孔德国 E-mail: 461080623@qq.com

作者简介: 刘鸿阳，1999年生，塔里木大学机械电气化工程学院硕士研究生 e-mail: liuhongyang739@163.com

引用本文:

刘鸿阳，孔德国，罗华平，高峰，王聪颖. 基于多光谱图像角度融合测定库尔勒香梨理化指标[J]. 光谱学与光谱分析, 2024, 44(03): 649-655.
LIU Hong-yang, KONG De-guo, LUO Hua-ping, GAO Feng, WANG Cong-ying. Physical and Chemical Indexes Were Determined Based on Multispectral Image Angle Fusion. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(03): 649-655.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2024)03-0649-07 或 https://www.gpxygpfx.com/CN/Y2024/V44/I03/649

[1] JING Chun-zhi(井春芝). Xinjiang Forestry(新疆林业), 2018，(3): 25.
[2] GAO Sheng, WANG Qiao-hua, FU Dan-dan, et al(高升, 王巧华, 付丹丹，等). Acta Optica Sinica(光学学报), 2019, 39(10): 1030004.
[3] WANG Dan, ZHAO Peng, SUN Jia-bo, et al(王丹，赵朋，孙家波，等). Shandong Agricultural Sciences(山东农业科学), 2021, 53(6): 121.
[4] SUN Hong, ZHAO Yi, ZHANG Meng, et al(孙红，赵毅，张猛，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2015, 31(S2): 186.
[5] DONG Jian-wei, LIU Yuan-yuan, CHEN Fei, et al(董建伟，刘媛媛，陈斐，等). Journal of Agricultural Mechanization Research(农机化研究), 2021, 43(9): 35.
[6] YANG Sheng-hui, ZHENG Yong-jun, LIU Xing-xing, et al(杨圣慧, 郑永军, 刘星星，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(10): 3220.
[7] DAI Jia-wei, WANG Hai-peng, CHEN Pu, et al(戴嘉伟，王海朋，陈瀑，等). Chinese Journal of Analytical Chemistry(分析化学), 2022, 50(6): 839.
[8] ZHANG Zuo-jing, FU Xin-yang, CHEN Ke-ming, et al(张佐经, 付新阳, 陈柯铭，等). Food and Fermentation Industries(食品与发酵工业), 2022, 48(15): 281.
[9] ZHANG Hui, ZHANG Wen-wei, ZHANG Yong-yi, et al(张慧, 张文伟, 张永毅，等). Acta Tabacaria Sinica (中国烟草学报), 2022, 28(3): 72.
[10] ZHANG Fan, SHU Ying, ZHANG Zhi-sheng, et al(张凡, 淑英, 张志胜，等). Journal of Chinese Institute of Food Science and Technology(中国食品学报), 2021, 21(11): 191.
[11] JIN Rui, LI Xiao-yu, YAN Yi-yun(金瑞, 李小昱, 颜伊芸). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2015, 31(16): 258.
[12] Li Q, Huang Y, Zhang J, et al. Spectrochim. Acta, Part A, 2021, 247: 119119.
[13] Ge W Z, Zhang L, Li X L, et al. Biosyst. Eng., 2021, 210: 299.
[14] Rios-Reina R, Callejon R M, Savorani F, et al. Talanta, 2019, 198: 560.
[15] YAN Guang-jian, JIANG Hai-lan, YAN Kai(阎广建, 姜海兰, 闫凯). National Remote Sensing Bulletin(遥感学报), 2021, 25(1): 83.