基于无人机多光谱影像的棉叶螨识别方法

doi:10.6048/j.issn.1001-4330.2018.08.011

摘要/Abstract

摘要： 【目的】利用无人机遥感在空间分辨率和光谱分辨率上的优势,研究大面积棉田棉叶螨监测方法,为类似的农作物虫害遥感监测研究提供参考。【方法】选20种光谱指数作为螨害监测的特征因子,使用赤池信息准则作为模型优选依据,获取最佳建模特征,建立棉田螨害监测识别的logistic回归模型。【结果】在所分析的全部光谱指数中,TVI、DVI和RDVI为螨害监测的最佳特征因子,基于该3个因子构建的logistic回归模型的分类准确率为95%,F1值为95.1%,能够较好地实现棉田螨害识别。【结论】监测模型可以实现区域范围的棉叶螨快速识别。

关键词: 棉叶螨; 无人机; 遥感; logistic回归模型; 特征选择

Abstract: 【Objective】 It aims to explore the monitoring method of cotton leaf mites identification in large area of cotton field using the advantage of unmanned aerial vehicle (UAV) remote sensing in spatial resolution and spectral resolution.【Method】 Twenty kinds of spectral indexes were taken as the primary characteristic factors for mite damage monitoring, and the Akaike's Information Criterion was used as the model selection basis. The best modeling features were obtained, and the logistic regression model for monitoring and identification of cotton mite damage in fields was established.【Result】 Among all the spectral indexes, TVI, DVI and RDVI were the best feature factors for mite damage monitoring. The classification accuracy of the logistic regression model based on these three factors was 95%, and the F1 value was 95.1%, which can better realize the identification of cotton mite damage.【Conclusion】 The monitoring model proposed in this paper can realize the rapid identification of cotton spider mites in the region. The research methods and results have provided reference for similar remote sensing monitoring of crop pests.

Key words: cotton spider mites; UAV; remote sensing; logistic regression model; feature selection

中图分类号:

S252
S49

崔美娜,戴建国,王守会,张国顺,薛金利. 基于无人机多光谱影像的棉叶螨识别方法[J]. 新疆农业科学, 2018, 55(8): 1457-1466.

CUI Mei-na, DAI Jian-guo, WANG Shou-hui, ZHANG Guo-shun, XUE Jin-li. Research on Identification Method of Mite Infection Cotton Based on of UAV Multi-Spectral Image[J]. Xinjiang Agricultural Sciences, 2018, 55(8): 1457-1466.

参考文献

[1] 张竞成,袁琳,王纪华等.作物病虫害遥感监测研究进展[J].农业工程学报,2012,28(20):1-11.
ZHANG Jing-cheng, YUAN Lin, WANG Ji-hua, et al. (2012). Research progress of crop diseases and pests monitoring based on remote sensing [J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE) , 28(20): 1-11. (in Chinese)
[2]Zhang, J., Huang, W., Li, J., Yang, G., Luo, J., & Gu, X., et al. (2011). Development, evaluation and application of a spectral knowledge base to detect yellow rust in winter wheat. Precision Agriculture, 12(5): 716-731.
[3]陈兵,王克如,李少昆等.棉花黄萎病冠层高光谱遥感监测技术研究[J].新疆农业科学,2007,44(6):740-745.
CHEN Bing, WANG Ke-ru, LI Shao-kun, et al. (2007). Studies on monitoring canopy spectrum of cotton verticillium wilt by remote sensing technique [J]. Xinjiang Agricultural Sciences, 44(6):740-745. (in Chinese)
[4]李卫国,蒋楠.农作物病虫害遥感监测研究进展与发展对策[J].江苏农业科学,2012,40(8):1-3.
LI Wei-guo, JIANG Nan. (2012). Research advances and developmental countermeasures of crop disease and pest remote sensing monitoring [J]. Jiangsu Agricultural Sciences, 40(8):1-3. (in Chinese)
[5]杨德松,姬华,王星等.影响新疆棉叶螨发生因素的研究[J].中国棉花,2004,(6):10-11.
YANG De-song, JI Hua, WANG Xing, et al. (2004). Study on the affecting factors of cotton leaf mites [J]. China Cotton, (6):10-11. (in Chinese)
[6]赵亮,陈兵,肖春华等.棉花棉叶螨叶片遥感监测技术研究[J].甘肃农业大学学报,2015,5(50):94-99.
ZHAO Liang, CHEN Bin, XIAO Chun-hua, et al. (2015). Remote sensing monitoring technique on cotton leaves infected by spider mites [J]. Journal of Gansu Agricultural University, 5(50):94-99. (in Chinese)
[7]王利民,刘佳,杨玲波等.基于无人机影像的农情遥感监测应用[J].农业工程学报,2013,29(18):136-145.
WANG Li-min, LIU Jia, YANG Ling-bo, et al. (2013). Applications of unmanned aerial vehicle images on agricultural remote sensing monitoring [J]. Transactions of the CSAE, 29(18):136-145. (in Chinese)
[8]竞霞,黄文江,琚存勇等.基于PLS算法的棉花黄萎病高空间分辨率遥感监测[J].农业工程学报,2010,26(8):229-235.
JING Xia, HUANG Wen-jiang, JU Cun-yong, et al. (2010). Remote sensing monitoring severity level of cotton verticillium wilt based on partial least squares regressive analysis [J]. Transactions of the CSAE, 26(8):229-235. (in Chinese)
[9]Franke, J., & Menz, G. (2007). Multi-temporal wheat disease detection by multi-spectral remote sensing. Precision Agriculture, 8(3): 161-172.
[10]Zhang, J., Pu, R., Yuan, L., Wang, J., Huang, W., & Yang, G. (2014). Monitoring powdery mildew of winter wheat by using moderate resolution multi-temporal satellite imagery. Plos One, 9(4):e93107.
[11]陈雯,武威,孙成明等.无人机遥感在作物监测中的应用与展望[J].上海农业学报,2016,32(2):138-143.
CHEN Wen, WU Wei, SUN Cheng-ming, et al. (2016). Application and prospect of UAV remote sensing in crop monitoring [J]. Acta Agriculturae Shanghai, 32(2):138-143. (in Chinese)
[12]刘良云,黄木易,黄文江等.利用多时相的高光谱航空图像监测冬小麦条锈病[J].遥感学报,2004,(3):275-281.
LIU Liang-yun, HUANG Mu-yi, HUANG Wen-jiang, et al. (2004). Monitoring Stripe Rust Disease of Winter Wheat Using Multi-temporal Hyperspectral Airborne Data [J]. Journal of Remote Sensing, (3):275-281. (in Chinese)
[13]乔红波,师越,司海平等.基于无人机数字图像与高光谱数据融合的小麦全蚀病等级的快速分类技术[J].植物保护,2015,41(6):157-162.
QIAO Hong-bo, SHI Yue, SI Hai-ping, et al. (2015). Fast multi-classification of wheat take-all levels based on the fusion of unmanned aerial vehicle digital images and spectral data [J]. Plant Protection, 41(6):157-162. (in Chinese)
[14]陈鹏程.地面高光谱遥感在棉叶螨监测中的应用研究[D]. 石河子: 石河子大学硕士论文,2006.
CHEN Peng-cheng. (2006). Application of ground-based hyperspectral remote sensing to detect spider mite[D]. Master Dissertation. Shihezi University, Shihezi. (in Chinese)
[15]赵庆展,刘伟,尹小君等.基于无人机多光谱影像特征的最佳波段组合研究[J].农业机械学报,2016,47(3):242-248, 291.
ZHAO Qing-zhan, LIU Wei, YIN Xiao-jun, et al. (2016). Selection of optimum bands combination based on multispectral images of UAV [J]. Transactions of the Chinese Society for Agricultural Machinery, 47(3):242-248, 291. (in Chinese)
[16]韩峰,刘昭,刘伟等.重叠度对无人机图像拼接效率的影响[J].江苏农业科学,2017,45(12):182-187.
HAN Feng, LIU Zhao, LIU Wei, et al. (2017). Influence of overlap on the efficiency of UAV image splicing [J]. Jiangsu Agricultural Sciences, 45(12):182-187. (in Chinese)
[17]GB/T 15802-2011. 棉花叶螨测报技术规范[S].
GB/T 15802-2011. [S]. Rules for monitoring and forecast of the cotton spider mites (tetranychus spp. ) Standard Press of China. (in Chinese)
[18]谭宏卫,曾捷.Logistic回归模型的影响分析[J].数理统计与管理,2013,32(3):476-485.
TAN Hong-wei, ZENG Jie. (2013).Influence analysis for logistic regression model [J]. Journal of Applied Statistics and Management, 32(3):476-485. (in Chinese)
[19]Rouse, J. W. (1974). Monitoring vegetation systems in the great plains with erts. Nasa Special Publication, (351): 309-317.
[20]Pearson, R. L., & Miller, L. D. (1972). Remote Mapping of Standing Crop Biomass for Estimation of the Productivity of the Shortgrass Prairie. Remote Sensing of Environment, VIII (Vol.45, pp.7-12). Remote Sensing of Environment, VIII.
[21]Merton, R., & Huntington, J. (1999). Early simulation results of the aries-1 satellite sensor for multi-temporal vegetation research derived from AVIRIS[C]. Summaries of the Eight JPL Airborne Earth Science Workshop. Pasadena CA: JPL Publication: 299-307.
[22]Roujean, J. L., & Breon, F. M. (1995). Estimating par absorbed by vegetation from bidirectional reflectance measurements. Remote Sensing of Environment, 51(3): 375-384.
[23]Gitelson, A. A., Kaufman, Y. J., & Merzlyak, M. N. (1996). Use of a green channel in remote sensing of global vegetation from eos-modis. Remote Sensing of Environment, 58(3): 289-298.
[24]Gregory A. Carter. (1994). Ratios of leaf reflectance in narrow wavebands as indicators of plant stress. International Journal of Remote Sensing, 15(3): 697-703.
[25]RONDEAUX G, STEVEN M, BARET F, et al. (1996). Optiuni zation of soil-adjusted vegetation indices. Remote sensing Enuranment, 55(2):95-107.
[26]Daughtry, C. S. T., Walthall, C. L., Kim, M. S., Colstoun, E. B. D., & Mcmurtrey, J. E. I. (2000). Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sensing of Environment, 74(2): 229-239.
[27]Chen, J. M. (1996). Evaluation of vegetation indices and a modified simple ratio for boreal applications. Canadian Journal of Remote Sensing, 22(3): 229-242.
[28]Broge, N. H., & Leblanc, E. (2001). Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote Sensing of Environment, 76(2): 156-172.
[29]Haboudane, D., Miller, J. R., Tremblay, N., Zarco-Tejada, P. J., & Dextraze, L. (2002). Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Remote Sensing of Environment, 81(2): 416-426.
[30]Vogelmann, J. E., Rock, B. N., & Moss, D. M. (1993). Red edge spectral measurements from sugar maple leaves. International Journal of Remote Sensing, 14(8): 1,563-1,575.
[31]Gamon, J. A., Penuelas, J., & Field, C. B. (1992). A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sensing of Environment, 41(1):35-44.
[32]Henderson, D., Williams, C. J., & Miller, J. S. (2007). Forecasting late blight in potato crops of southern idaho using logistic regression analysis. Plant Disease, 91(8): 951-956.
[33]杨福芹,冯海宽,李振海等.基于赤池信息量准则的冬小麦叶面积指数高光谱估测[J].农业工程学报,2016,32(3):163-168.
YANG Fu-qin, FENG Hai-kuan, LI Zhen-hai, et al. (2016). Hyperspectral estimation of leaf area index for winter wheat based on Akaike's information criterion [J]. Transactions of the CSAE, 32(3):163-168. (in Chinese)
[34]宋喜芳,李建平,胡希远.模型选择信息量准则AIC及其在方差分析中的应用[J].西北农林科技大学学报(自然科学版),2009,37(2):88-92.
SONG Xi-fang, LI Jian-ping, HU Xi-yuan, et al. (2009). Model selection criterion AIC and its application in ANOVA [J]. Journal of Northwest A and F University (Natural Science Edition) , 37(2):88-92. (in Chinese)
[35]王成,刘亚峰,王新成,等.分类器的分类性能评价指标[J].电子设计工程,2011,19(8):13-15, 21.
WANG Cheng, LIU Ya-feng, WANG Xin-cheng, et al. (2011). Appraisal identification of classifier's performance [J]. Electronic Design Engineering, 19(8):13-15, 21. (in Chinese)