| 313 | 6 | 11 |
| 下载次数 | 被引频次 | 阅读次数 |
为解决鲜烟叶成熟度、烘烤质量评价及青烟等级判定过程中存在人为因素对判定结果影响较大等问题，基于高光谱成像技术，通过分析鲜烟叶黄化过程和烤烟正常区域与泛青区域光谱特征差异，采用光谱吸收指数（spectral absorption index,SAI）对烟叶泛青特征进行量化表征。结果表明：(1)在400～780 nm波段，烟叶泛青区域光谱呈现“两谷一峰”特征，随着泛青程度的减弱，吸收谷深度逐渐减小，烘烤后烤烟正常区域在680 nm左右处的波谷基本消失；(2)烟叶泛青程度越高，其SAI值越大；(3)烤烟SAI阈值范围设置为1.19～1.28时，可准确区分正组、微带青组、青黄1级、青黄2级烤烟组别；(4)设定不同的SAI阈值，结合颜色映射，可实现烟叶不同泛青程度相应的泛青区域位置分布。该方法可为鲜烟叶成熟度评价、烘烤变黄期进程的衡量及烤烟等级的判定提供技术支持。
Abstract：In order to minimize potential human bias on the evaluation of the maturity and flue-curing quality of fresh tobacco leaves and the grading of greenish tobacco leaves, the yellowing process of fresh tobacco leaves and the difference of spectral characteristics between the normal area and the greenish area of flue-cured tobacco were analyzed based on the hyperspectral imaging technology, and the greenish characteristics of tobacco leaves were quantitatively characterized by using the spectral absorption index(SAI) method. The results showed that: 1) Within the band of400-780 nm, the spectrum of the greenish area in tobacco leaves had the characteristics of“two valleys and one peak”. With the weakening of the greenish level, the depth of the absorption valley gradually decreased, and the valley of the normal area in flue-cured tobacco basically disappeared at about 680 nm after curing. 2) The higher the greenish level, the higher the SAI value. 3) When the SAI threshold range was set to 1.19-1.28, the normal group, slightly green group, greenish-yellow grade 1, and greenish-yellow grade 2 of flue-cured tobacco leaves could be accurately distinguished.4) By setting different SAI thresholds and combining with color mapping, the location distribution of greenish areas corresponding to different greenish levels in tobacco leaves could be realized. This method provides technical support for the maturity assessment of fresh tobacco leaves, the determination of the yellowing stage progression, and the evaluation of the flue-cured tobacco grade.
[1]林宝辉，邹勇，何振峰.不同成熟度烟叶质量特点及对分级成熟度的判定[J].安徽农业科学，2015,43(24):230-231,234.LIN Baohui, ZOU Yong, HE Zhenfeng. Different maturity tobacco quality features and correct judgment during flue-cured tobacco grading[J]. Journal of Anhui Agricultural Sciences,2015,43(24):230-231,234.
[2]张广普，李峥，黄广华，等.基于BP神经网络的烘烤变黄期烟叶含水量预测[J].天津农业科学，2021,27(10):62-67,73.ZHANG Guangpu,LI Zheng,HUANG Guanghua,et al. Prediction of moisture content of tobacco leaves in yellowing stage based on back propagation artificial neural network[J]. Tianjin Agricultural Sciences,2021,27(10):62-67,73.
[3]鲁梦瑶，周强，姜舒文，等.基于深度学习与多尺度特征融合的烤烟烟叶分级方法[J].中国农机化学报，2022,43(1):158-166.LU Mengyao,ZHOU Qiang,JIANG Shuwen,et al.Flue-cured tobacco leaf grading method based on deep learning and multi-scale feature fusion[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(1):158-166.
[4]段宏，李金宝，孔广才，等.烤烟专业化分级散叶收购模式对比及收购质量改进建议[J].现代农业科技，2019(3):265.DUAN Hong, LI Jinbao, KONG Guangcai, et al.Comparison of acquisition modes of specialized graded loose leaves of flue-cured tobacco and suggestions for improvement of acquisition quality[J]. Modern Agricultural Science and Technology,2019(3):265.
[5]雒慧心.基于深度学习的烤烟分选算法研究[D].北京：北京交通大学，2019.LUO Huixin. Research on flue-cured tobacco classification algorithm based on deep learning[D].Beijing:Beijing Jiaotong University,2019.
[6]李同泉，典瑞丽，倪克平.谈微带青烟叶分级技术[J].现代农业科技，2009(9):221-222.LI Tongquan,DIAN Ruili, NI Keping. Classification technology of greenish tobacco leaves[J]. Modern Agricultural Science and Technology, 2009(9):221-222.
[7]贾中林，尹启生，戴华鑫，等.烤烟上部烟叶成熟生理特性研究进展[J].烟草科技，2022,55(7):99-112.JIA Zhonglin,YIN Qisheng,DAI Huaxin,et al.Research progress on physiological characteristics of mature upper leaves of flue-cured tobacco[J]. Tobacco Science&Technology,2022,55(7):99-112.
[8]韦克苏，涂永高，王丰，等.基于近红外光谱的烟叶烘烤过程质体色素实时监测[J].江苏农业科学，2021,49(16):184-188.WEI Kesu,TU Yonggao,WANG Feng,et al. Real-time quantitative analysis of chlorophyll and carotene in tobacco during bulk curing process by near-infrared spectroscopy[J]. Jiangsu Agricultural Sciences,2021,49(16):184-188.
[9]黄涛，雷强，俞世康，等.烟叶烘烤过程中烤房内挥发性成分的变化规律[J].河南农业科学，2022,51(2):169-180.HUANG Tao,LEI Qiang,YU Shikang,et al. Changes of volatile components in tobacco curing room during flue-curing[J]. Journal of Henan Agricultural Sciences,2022,51(2):169-180.
[10]兰玉鲜.浅谈烤烟含青对烟叶质量影响[J].轻工科技，2015,31(6):116-117.LAN Yuxian. Effect of greenish parts in flue-cured tobacco leaves on their quality[J]. Light Industry Science and Technology,2015,31(6):116-117.
[11]史龙飞，宋朝鹏，贺帆，等.基于机器视觉技术的烤烟鲜烟叶成熟度检测[J].湖南农业大学学报（自然科学版），2012,38(4):446-450.SHI Longfei, SONG Chaopeng, HE Fan, et al.Determination of the maturity grades of fresh leaves for flue-cured tobacco[J]. Journal of Hunan Agricultural University(Natural Sciences),2012,38(4):446-450.
[12]段史江.图像处理技术在烤烟烘烤过程中的应用研究[D].郑州：河南农业大学，2012.DUAN Shijiang. Research on application of image processing technology during curing process of flue-cured tobacco[D]. Zhengzhou:Henan Agricultural University,2012.
[13]张富贵，叶磊，李德伦，等.基于RF-PSO-SVM的烟叶等级分类模型[J].计算机与数字工程，2022,50(8):1833-1838.ZHANG Fugui,YE Lei,LI Delun,et al. Tobacco leaf grading model based on RF-PSO-SVM[J]. Computer&Digital Engineering,2022,50(8):1833-1838.
[14] Zhang J J,Cheng T,Guo W,et al. Leaf area index estimation model for UAV image hyperspectral data based on wavelength variable selection and machine learning methods[J]. Plant Methods,2021,17(1):49.
[15] Zhao C H,Li C,Feng S. A spectral-spatial method based on fractional Fourier transform and collaborative representation for hyperspectral anomaly detection[J].IEEE Geoscience and Remote Sensing Letters,2021,18(7):1259-1263.
[16] Jia S,Jiang S,Lin Z,et al. A survey:deep learning for hyperspectral image classification with few labeled samples[J]. Neurocomputing,2021,448:179-204.
[17] Yan L B,Zhao M,Wang X H,et al. Object detection in hyperspectral images[J]. IEEE Signal Processing Letters,2021,28:508-512.
[18]李懂懂，唐晓燕.基于高光谱成像技术的水果损伤检测[J].工程技术研究，2020,5(3):261-262.LI Dongdong,TANG Xiaoyan. Fruit damage detection based on hyperspectral imaging technology[J].Engineering and Technological Research,2020,5(3):261-262.
[19]李智慧，梅吉帆，李辉，等.高光谱成像的非烟物质分类识别研究[J].中国烟草学报，2022,28(3):81-88.LI Zhihui,MEI Jifan,LI Hui,et al. Research on classification and recognition of non-tobacco related material(NTRM)based on hyperspectral imaging technology[J]. Acta Tabacaria Sinica,2022,28(3):81-88.
[20]成功，李嘉璇，王朝鹏，等.离子型稀土矿含量高光谱定量反演研究[J].光谱学与光谱分析，2019,39(5):1571-1578.CHENG Gong,LI Jiaxuan,WANG Chaopeng,et al.Study on hyperspectral quantitative inversion of ionic rare earth ores[J]. Spectroscopy and Spectral Analysis,2019,39(5):1571-1578.
[21] GB 2635—1992烤烟[S].GB 2635—1992 Flue-cured tobacco[S].
[22]李应果，杨洁.基于阈值分割的单板穿孔缺陷识别算法研究[J].西北林学院学报，2022,37(3):199-204.LI Yingguo,YANG Jie. Recognition algorithm of single plate perforation defect based on threshold segmentation[J]. Journal of Northwest Forestry University,2022,37(3):199-204.
[23]宁鸿章，谭鑫，李宇航，等.空-谱维联合SavitzkyGolay高光谱滤波算法及其应用[J].光谱学与光谱分析，2020,40(12):3699-3704.NING Hongzhang,TAN Xin,LI Yuhang,et al. Joint space-spectrum SG filtering algorithms for hyperspectral images and its application[J]. Spectroscopy and Spectral Analysis,2020,40(12):3699-3704.
[24]童庆禧，张兵，郑兰芬.高光谱遥感——原理、技术与应用[M].北京：高等教育出版社，2006.TONG Qingxi, ZHANG Bing, ZHENG Lanfen.Hyperspectral remote sensing—Principle,technology and application[M]. Beijing:Higher Education Press,2006.
[25]梁莉，李尧，叶成名，等.一种基于综合吸收能力的高光谱遥感植被指数计算方法[J].地球物理学进展，2017,32(4):1454-1457.LIANG Li,LI Yao,YE Chengming,et al. Method of vegetation index assessed by the absorption ability to electromagnetic energy based on hyperspectral remote sensing[J]. Progress in Geophysics,2017,32(4):1454-1457.
[26]孙林，程丽娟.植被叶片生化组分的光谱响应特征分析[J].光谱学与光谱分析，2010,30(11):3031-3035.SUN Lin, CHENG Lijuan. Analysis of spectral response of vegetation leaf biochemical components[J].Spectroscopy and Spectral Analysis, 2010, 30(11):3031-3035.
[27]闫克玉，赵铭钦.烟草原料学[M].北京：科学出版社，2008.YAN Keyu,ZHAO Mingqin. Tobacco material science[M]. Beijing:Science Press,2008.
基本信息:
DOI：10.16135/j.issn1002-0861.2022.0815
中图分类号:TS41;O657.3
引用信息:
[1]郭文孟,薛宇毅,罗靖等.基于高光谱成像的烟叶泛青特征分析与表征[J].烟草科技,2023,56(07):84-91.DOI:10.16135/j.issn1002-0861.2022.0815.
基金信息:
郑州烟草研究院青年人才托举工程计划项目“基于光谱成像的非烟物质识别技术与应用研究”（222021CR0050）; 福建中烟工业有限责任公司科技项目“基于光谱成像技术的在线杂物智能识别与剔除系统的研发及应用”（FJZYHZJH2021020）