高级检索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于可见光-近红外图像的幼龄檀香全磷含量诊断

陈珠琳 王雪峰 孙汉中

陈珠琳, 王雪峰, 孙汉中. 基于可见光-近红外图像的幼龄檀香全磷含量诊断[J]. 北京林业大学学报, 2019, 41(2): 88-96. doi: 10.13332/j.1000-1522.20180214
引用本文: 陈珠琳, 王雪峰, 孙汉中. 基于可见光-近红外图像的幼龄檀香全磷含量诊断[J]. 北京林业大学学报, 2019, 41(2): 88-96. doi: 10.13332/j.1000-1522.20180214
Chen Zhulin, Wang Xuefeng, Sun Hanzhong. Diagnosis of total phosphorus content in young sandalwood based on visible light and near infrared images[J]. Journal of Beijing Forestry University, 2019, 41(2): 88-96. doi: 10.13332/j.1000-1522.20180214
Citation: Chen Zhulin, Wang Xuefeng, Sun Hanzhong. Diagnosis of total phosphorus content in young sandalwood based on visible light and near infrared images[J]. Journal of Beijing Forestry University, 2019, 41(2): 88-96. doi: 10.13332/j.1000-1522.20180214

基于可见光-近红外图像的幼龄檀香全磷含量诊断

doi: 10.13332/j.1000-1522.20180214
基金项目: 

林业科学技术推广项目 [2016]11号

中央级科研院所基本科研业务费专项项目 CAFYBB2014MA006

详细信息
    作者简介:

    陈珠琳。主要研究方向:森林资源监测与计算机视觉。Email:825511059@qq.com 地址:北京市海淀区东小府1号中国林业科学研究院资源信息研究所

    责任作者:

    王雪峰,博士,研究员。主要研究方向:森林资源监测与计算机视觉。Email:xuefeng@ifrit.ac.cn 地址:同上

  • 中图分类号: S794.9; TP79

Diagnosis of total phosphorus content in young sandalwood based on visible light and near infrared images

  • 摘要: 目的檀香是一种典型珍贵树种,在幼龄期时,不合理的田间施肥会影响其正常生长,降低存活率。因此,本文提出了一种基于可见光-近红外图像的幼龄檀香全磷营养诊断方法,为实时监测珍贵树种生长状态及养分需求提供参考。方法通过将野外获取的檀香图像转换到HSI颜色空间,提取S和Ⅰ通道,利用二者在使用Otsu分割后产生的优势互补,并结合形态学运算,从复杂背景中提取出檀香。计算出形状、纹理和光谱及植被指数特征后,分别使用显著性分析(ST)和平均影响值(MIV)方法进行变量筛选,并使用遗传算法(GA)初始化BP神经网络的权值和阈值,最终得到预测结果。结果(1) 复杂背景下的檀香分割中,S通道和Ⅰ通道相结合可以将大部分背景(天空、土壤、其他绿色植物)与目标檀香分割开,同时结合7×7中值滤波、形态学运算和超G因子,将其他毛刺去除。与常用的支持向量机相比,本文提出的分割算法结果更接近于目视解译,像素数和颜色误差更小。(2)对不同施磷水平下各特征进行分析发现,适当增加施磷量有利于促进叶绿素的形成,使得纹理更均匀清晰,加快叶片生长;当过量时则会破坏叶绿体,造成叶片组织出现变化,导致叶片黄化,叶片出现网状脉纹,增加了纹理复杂程度。(3)ST与MIV筛选出的变量差异较大,通过GA-BPNN训练结果可知,MIV方法筛选出的变量对全磷含量的影响更大,预测集得到的决定系数达到0.801,平均残差为0.032 g/kg,均方根误差为0.666 g/kg。结论通过处理可见光-近红外图像,实现了幼龄檀香的全磷含量诊断,有效提高了磷肥利用率,同时也可以减小过量施肥引起的地下水污染等生态问题。

     

  • 图  1  不同通道图像Otsu分割结果

    Figure  1.  Images segmentation using Otsu method of different channels

    图  2  复杂背景下檀香图像分割过程及结果

    a. S通道分割后7×7中值滤波掩膜图像Mask image after 7×7 median filtering and channel S segmentation; b. Ⅰ通道Otsu法分割结果Segmentation result of Otsu method in channel Ⅰ; c. 7×7中值滤波结果Result after 7×7 median filtering; d.形态学处理后掩膜图像Mask image after Morphological process; e.超G因子处理后最终图像Final result using excess green feature

    Figure  2.  Segmentation process and result of sandalwood image in complex background

    图  3  不同磷含量下光谱反射率变化趋势

    Figure  3.  Variation trend of spectral reflectance under different phosphorus content

    图  4  预测集的预测值与实测值散点图

    Figure  4.  Scatter plots between measured and predicted values with different selection method in prediction set

    表  1  植被指数计算公式

    Table  1.   Calculation equations of vegetation indices

    植被指数
    Vegetation index
    计算公式
    Formula
    参考文献
    Reference
    比值植被指数1 Ratio vegetation index 1(RVI1) NIR/B [13]
    比值植被指数2 Ratio vegetation index 2(RVI2) NIR/G [14]
    比值植被指数3 Ratio vegetation index 3(RVI3) NIR/R [13]
    差值植被指数1 Difference vegetation index 1(DVI1) NIR-B [13]
    差值植被指数2 Difference vegetation index 2(DVI2) NIR-G [13]
    差值植被指数3 Difference vegetation index 3(DVI3) NIR-R [13]
    归一化差值植被指数1 Normalized difference vegetation index 1(NDVI1) (NIR-R)/(NIR+R) [14]
    归一化差值植被指数2 Normalized difference vegetation index 2(NDVI2) (NIR-G)/(NIR+G) [15]
    归一化差值植被指数3 Normalized difference vegetation index 3(NDVI3) (NIR-B)/(NIR+B) [14]
    重整化差值植被指数1 Renormalized difference vegetation index 1(RDVI1) (NIR-B)/(NIR+B)1/2 [16]
    重整化差值植被指数2 Renormalized difference vegetation index 2(RDVI2) (NIR-G)/(NIR+G)1/2 [16]
    重整化差值植被指数3 Renormalized difference vegetation index 3(RDVI3) (NIR-R)/(NIR+R)1/2 [16]
    叶绿素指数Chlorophyll index(CI) NIR/G-1 [17]
    宽动态范围植被指数1 Wide dynamic range vegetation index 1(WDRVI1) (0.12NIR-R)/(0.12NIR+R) [18]
    宽动态范围植被指数2 Wide dynamic range vegetation index 2(WDRVI2) (0.12NIR-G)/(0.12NIR+G) [18]
    宽动态范围植被指数3 Wide dynamic range vegetation index 3(WDRVI3) (0.12NIR-B)/(0.12NIR+B) [18]
    调整简单比值Modified simple ratio(MSR) (NIR/R-1)/(NIR/R+1)1/2 [19]
    植被指数简单比值Simple ratio vegetation index(SR) R/G×NIR [20]
    调整归一化差值植被指数1 Modified normalized difference vegetation index 1(MNDVI1) (NIR-R+2G)/(NIR+R-2G) [21]
    调整归一化差值植被指数2 Modified normalized difference vegetation index 2(MNDVI2) (NIR-R+2B)/(NIR+R-2B) [21]
    红边归一化植被指数Red edge normalized difference vegetation index(NDVIRE) (RE-R)/(RE+R) [22]
    改进红边比值植被指数Modified red edge simple ratio index(MSRIRE) (RE-B)/(RE+B) [22]
    改进红边归一化植被指数Modified red edge normalized difference vegetation index(MNDVIRE) (RE-R)/(RE+R-2B) [22]
    注:BGR、RE、NIR分别代表蓝、绿、红、红边、近红外波段校正后的光谱反射率。Note: B, G, R, RE, NIR represent the corrected spectral reflectance of blue band, green band, red band, red edge band and near infrared band.
    下载: 导出CSV

    表  2  分割方法评价

    Table  2.   Segmentation method evaluation proposed in this paper

    编号
    No.
    处理方法
    Treating method
    像素数误差
    Pixel number error/%
    红波段(R)均值
    Mean value of red band (R)
    ER/% 绿波段(G)均值
    Mean value of green band (G)
    EG/% 蓝波段(B)均值
    Mean value of blue band (B)
    EB/%
    2.76 140.9 1.294 158.9 1.732 84.82 3.007
    图像1 Image 1 3.94 143.1 2.876 156.4 3.278 89.09 1.875
    0.00 139.1 0.000 161.7 0.000 87.45 0.000
    3.37 118.4 1.743 154.8 0.781 89.99 3.036
    图像2 Image 2 4.45 121.5 0.830 149.1 2.930 94.05 2.710
    0.00 120.5 0.000 153.6 0.000 92.24 0.000
    2.05 124.8 0.319 173.5 0.459 86.75 2.250
    图像3 Image 3 2.46 122.3 2.316 178.1 2.180 82.31 2.486
    0.00 125.2 0.000 174.3 0.000 84.46 0.000
    注:①代表本文提出算法;②代表支持向量机算法;③代表Photoshop CS5处理;ER、EG、EB分布代表R、G、B波段的均值误差。Notes: ① stands for the algorithm presented in this paper; ② stands for support vector machine algorithm; ③ stands for image processing used photoshop CS5; and ER, EG and EB stand for mean value error of band R, G and B, respectively.
    下载: 导出CSV

    表  3  ST及MIV筛选结果

    Table  3.   Selection results of ST and MIV

    方法
    Method
    形状特征
    Shape feature
    纹理特征
    Texture feature
    光谱及植被指数
    Spectrum and vegetation index
    ST 面积凹凸比、偏心率
    Area concavo-convex ratio, eccentricity ratio
    B能量、R相关性、G相关性、近红外对比度、近红外相关性
    Energy(B), correlation(R), correlation(G), contrast(NIR), correlation(NIR)
    MNDVI1、MSRIRE、B、DVI2、RNDVI2
    MIV 面积凹凸比、形状复杂度
    Area concavo-convex ratio, shape complexity
    B能量、B相关性、近红外相关性、G能量、R相关性
    Energy(B), correlation(B), correlation(NIR), energy(G), correlation(R)
    MNDVI1、MSRIRE、B、DVI2、NDVI3
    注:表中各变量出现的顺序代表其在不同类别特征中的重要性。Note: the order of variables in this table represents its importance in different categories.
    下载: 导出CSV

    表  4  不同输入变量筛选方法下GA-BPNN神经网络模型拟合结果

    Table  4.   Fitting results of GA-BPNN neural network models with different input variables

    筛选方法
    Selection method
    样本集(n=55)
    Sample set (n=55)
    R2 ME/(g·kg-1) RMSE/(g·kg-1)
    ST 0.790 0.103 0.482
    MIV 0.815 -0.021 0.433
    未处理Undisposed 0.726 -0.110 0.592
    下载: 导出CSV
  • [1] 刘小金, 徐大平, 杨曾奖, 等.海南尖峰岭檀香心材比例、精油含量和成分的分布特征[J].华南农业大学学报, 2016, 37(5):66-71. http://d.old.wanfangdata.com.cn/Periodical/hnnydxxb201605012

    Liu X J, Xu D P, Yang Z J, et al. Heartwood proportion and distribution of essential oil content and composition of Santalum album in Jianfeng Mountain Hainan[J]. Journal of South China Agricultural University, 2016, 37(5):66-71. http://d.old.wanfangdata.com.cn/Periodical/hnnydxxb201605012
    [2] 林芬芳, 丁晓东, 付志鹏, 等.基于互信息理论的水稻磷素营养高光谱诊断[J].光谱学与光谱分析, 2009, 29(19): 2467-2470. http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx200909039

    Lin F F, Ding X D, Fu Z P, et al. Application of mutual information to variable selection in diagnosis of phosphorus nutrition in rice[J]. Spectroscopy and Spectral Analysis, 2009, 29(19): 2467-2470. http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx200909039
    [3] 王艳丽, 王京, 刘国顺, 等.磷施用量对烤烟根系生理及叶片光合特性的影响[J].植物营养与肥料学报, 2016, 22(2):410-417. http://d.old.wanfangdata.com.cn/Periodical/zwyyyflxb201602015

    Wang Y L, Wang J, Liu G S, et al. Effects of different phosphorus levels on root physiological and leaf photosynthetic characteristics of flue-cured tobacco[J]. Journal of Plant Nutrition and Fertilizer, 2016, 22(2):410-417. http://d.old.wanfangdata.com.cn/Periodical/zwyyyflxb201602015
    [4] 连慧达, 裴红宾, 张永清, 等.施磷量对不同品种红小豆形态和生理特性的影响[J].植物营养与肥料学报, 2015, 21(3):792-799. http://d.old.wanfangdata.com.cn/Periodical/zwyyyflxb201503027

    Lian H D, Pei H B, Zhang Y Q, et al. Effect of phosphorus fertilization on morphological and physiological characteristics of adzuki beans[J]. Journal of Plant Nutrition and Fertilizer, 2015, 21(3):792-799. http://d.old.wanfangdata.com.cn/Periodical/zwyyyflxb201503027
    [5] 郑亚萍, 信彩云, 王才斌, 等.磷肥对花生根系形态、生理特性及产量的影响[J].植物生态学报, 2013, 37(8):777-785. http://d.old.wanfangdata.com.cn/Periodical/zwstxb201308009

    Zheng Y P, Xin C Y, Wang C B, et al. Effects of phosphorus fertilizer on root morphology, physiological characteristics and yield in peanut (Arachis hypogaea)[J]. Chinese Journal of Plant Ecology, 2013, 37(8):777-785. http://d.old.wanfangdata.com.cn/Periodical/zwstxb201308009
    [6] 赵霞, 徐大平, 杨曾奖, 等.养分胁迫对降香黄檀幼苗生长及叶片养分状况的影响[J].生态学杂志, 2017, 36(6): 1503-1508. http://d.old.wanfangdata.com.cn/Periodical/stxzz201706006

    Zhao X, Xu D P, Yang Z J, et al. Effects of nutrient stress on seedling growth and foliar nutrient status of Dalbergia odorifera[J]. Chinese Journal of Ecology, 2017, 36(6): 1503-1508. http://d.old.wanfangdata.com.cn/Periodical/stxzz201706006
    [7] 李美清, 李晋阳, 毛罕平.基于光谱特征和生理特征的番茄磷营养诊断方法[J].农业机械学报, 2016, 47(3):286-291. http://d.old.wanfangdata.com.cn/Periodical/nyjxxb201603040

    Li M Q, Li J Y, Mao H P. Tomatoes phosphorus nutrition diagnosis based on spectral and physiological characteristics[J]. Transactions of The Chinese Society of Agricultural Machinery, 2016, 47(3):286-291. http://d.old.wanfangdata.com.cn/Periodical/nyjxxb201603040
    [8] 何彩莲, 郑顺林, 万年鑫, 等.马铃薯光谱及数字图像特征参数对氮素水平的响应及其应用[J].光谱学与光谱分析, 2016, 36(9):2930-2936. http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx201609039

    He C L, Zheng S L, Wan N X, et al. Potato spectrum and the digital image feature parameters on the response of the nitrogen level and its application[J]. Spectroscopy and Spectral Analysis, 2016, 36(9): 2930-2936. http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx201609039
    [9] 陈敏, 郑曙峰, 刘小玲, 等.基于数码图像识别的棉花氮营养诊断研究[J].农学学报, 2017, 7(7):77-83. http://d.old.wanfangdata.com.cn/Periodical/zgncxkkj201707013

    Chen M, Zheng S F, Liu X L, et al. Cotton nitrogen nutrition diagnosis based on digital image[J]. Journal of Agriculture, 2017, 7(7):77-83. http://d.old.wanfangdata.com.cn/Periodical/zgncxkkj201707013
    [10] Osborne S L, Schepers J S, Francis D D, et al. Detection of phosphorus and nitrogen deficiencies in corn using spectral radiance measurements[J]. Agronomy Journal, 2002, 94(6): 1215-1221. doi: 10.2134/agronj2002.1215
    [11] 黄双萍, 岳学军, 洪添胜.基于高光谱的柑橘叶片磷含量估算模型实验[J].农业工程学报, 2013, 44(4):202-207. http://d.old.wanfangdata.com.cn/Periodical/nyjxxb201304035

    Huang S P, Yue X J, Hong T S. Hyperspectral estimation model of total phosphorus content for citrus leaves[J]. The Chinese Society of Agricultural Machinery, 2013, 44(4):202-207. http://d.old.wanfangdata.com.cn/Periodical/nyjxxb201304035
    [12] 高洪燕, 毛罕平, 张晓东.生菜叶中磷含量的光谱定量分析[J].农业机械学报, 2014, 45(增刊):276-280. http://d.old.wanfangdata.com.cn/Conference/8619613

    Gao H Y, Mao H P, Zhang X D. Quantitative determination of phosphorus in lettuce leaf using spectroscopy[J]. The Chinese Society of Agricultural Machinery, 2014, 45(Suppl.):276-280. http://d.old.wanfangdata.com.cn/Conference/8619613
    [13] Tucker C J. Red and photographic infrared linear combinations for monitoring vegetation[J]. Remote Sensing of Environment, 1979, 8:127-150. doi: 10.1016/0034-4257(79)90013-0
    [14] Buschmann C, Nagel E. In vivo spectroscopy and internal optics of leaves as basis for remote sensing of vegetation[J]. International Journal of Remote Sensing, 1993, 14:711-722. doi: 10.1080/01431169308904370
    [15] Gitelson A A, Kaufman Y J, Merzlyak M N. Use of green channel in remote sensing of global vegetation from EOS-MODIS[J]. Remote Sensing of Environment, 1996, 58:289-298. doi: 10.1016/S0034-4257(96)00072-7
    [16] Roujean J L, Breon F M. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements[J]. Remote Sensing of Environment, 1995, 51:375-384. doi: 10.1016/0034-4257(94)00114-3
    [17] Gitelson A A, Gritz Y, Merzlyak M N. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves[J]. Journal of Plant Physiology, 2003, 160:271-282. doi: 10.1078/0176-1617-00887
    [18] Gitelson A A. Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation[J]. Journal of Plant Physiology, 2004, 161:165-173. doi: 10.1078/0176-1617-01176
    [19] Chen J M. Evaluation of vegetation indices and a modified simple ratio for boreal applications[J]. Canadian Journal of Remote Sensing, 1996, 22:229-242. doi: 10.1080/07038992.1996.10855178
    [20] Datt B. Visible/near infrared reflectance and chlorophyll content in eucalyptus leaves[J]. International Journal of Remote Sensing, 1999, 20:2741-2759. doi: 10.1080/014311699211778
    [21] Wang W, Yao X, Yao X F, et al. Estimating leaf nitrogen concentration with three-band vegetation indices in rice and wheat[J]. Field Crops Res, 2012, 129:90-98. doi: 10.1016/j.fcr.2012.01.014
    [22] Mutanga O, Adam E, Adjorlolo C, et al. Evaluating the robustness of models developed from field spectral data in predicting African grass foliar nitrogen concentration using WorldView-2 image as an independent test dataset[J]. International Journal of Applied Earth Observation and Geoinformation, 2015, 34:178-187. doi: 10.1016/j.jag.2014.08.008
    [23] 张恒德, 张庭玉, 李涛, 等.基于BP神经网络的污染物浓度多模式集成预报[J].中国环境科学, 2018, 38(4): 1243-1256. http://d.old.wanfangdata.com.cn/Periodical/zghjkx201804004

    Zhang H D, Zhang T Y, Li T, et al. Forecast of air quality pollutants' concentrations based on BP neural network multi-model ensemble method[J]. China Environmental Science, 2018, 38(4):1243-1256. http://d.old.wanfangdata.com.cn/Periodical/zghjkx201804004
    [24] 李哲, 张飞, 陈丽华, 等.光谱指数的植物叶片叶绿素含量估算模型[J].光谱学与光谱分析, 2018, 38(5):1533-1539. http://d.old.wanfangdata.com.cn/Periodical/stxb201420007

    Li Z, Zhang F, Chen L H, et al. Research on spectrum variance of vegetation leaves and estimation model for leaf chlorophyll content based on the spectral index[J]. Spectroscopy and Spectral Analysis, 2018, 38(5):1533-1539. http://d.old.wanfangdata.com.cn/Periodical/stxb201420007
    [25] 刘丽颖, 官冬杰, 杨清伟, 等.基于MIV-BP型的喀斯特地区水资源安全影响因素分析[J].水土保持通报, 2017, 37(5):128-134. http://d.old.wanfangdata.com.cn/Periodical/stbctb201705022

    Liu L Y, Guan D J, Yang Q W, et al. Influence factors of water resource security in karst area based on MIV-BP model[J]. Bulletin of Soil and Water Conservation, 2017, 37(5):128-134. http://d.old.wanfangdata.com.cn/Periodical/stbctb201705022
    [26] 张婉婉, 杨可明, 汪国平, 等.基于EMD-SD光谱的玉米叶片叶绿素含量GA-BP模型反演[J].浙江农业学报, 2016, 28(8):1297-1303. doi: 10.3969/j.issn.1004-1524.2016.08.04

    Zhang W W, Yang K M, Wang G P, et al. Study on GA-BP inversing modeling method of corn leaf chlorophyll content based on EMD and spectral derivative method[J]. Acta Agriculture Zhejiangnsis, 2016, 28(8):1297-1303. doi: 10.3969/j.issn.1004-1524.2016.08.04
    [27] 杨梅花, 赵小敏.基于可见-近红外光谱变量选择的土壤全氮含量估测研究[J].中国农业科学, 2014, 47(12):2374-2383. doi: 10.3864/j.issn.0578-1752.2014.12.010

    Yang M H, Zhao X M. Study on soil total N estimation by Vis-NIR spectra with variable selection[J]. Scientia Agriculture Sinica, 2014, 47(12):2374-2383. doi: 10.3864/j.issn.0578-1752.2014.12.010
    [28] 迟德霞, 张伟, 王洋.基于EXG因子的水稻秧苗图像分割[J].安徽农业科学, 2012(36):17902-17903. doi: 10.3969/j.issn.0517-6611.2012.36.164

    Chi D X, Zhang W, Wang Y. Segmentation of rice seedling image based on EXG factor[J]. Journal of Anhui Agricultural Science, 2012(36):17902-17903. doi: 10.3969/j.issn.0517-6611.2012.36.164
    [29] 苏义鑫, 夏慧雯.用于风电功率预测的RPCL优化神经网络模型[J].北京工业大学学报, 2016, 42(5):674-678. http://d.old.wanfangdata.com.cn/Periodical/bjgydxxb201605005

    Su Y X, Xia H W. Rival penalized competitve learning-based neural network model for wind power forecasting[J]. Journal of Beijing University of Technology, 2016, 42(5):674-678. http://d.old.wanfangdata.com.cn/Periodical/bjgydxxb201605005
  • 加载中
图(4) / 表(4)
计量
  • 文章访问数:  719
  • HTML全文浏览量:  194
  • PDF下载量:  21
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-07-02
  • 修回日期:  2018-08-09
  • 刊出日期:  2019-02-01

目录

    /

    返回文章
    返回