Light stress diagnosis of rapeseed seedling stage based on hyperspectral imaging technology

doi:10.3785/j.issn.1008-9209.2021.03.081

Journal of Zhejiang University (Agriculture and Life Sciences)

2022, Vol. 48

Issue (1): 106-116 DOI: 10.3785/j.issn.1008-9209.2021.03.081

Agricultural engineering

Light stress diagnosis of rapeseed seedling stage based on hyperspectral imaging technology

Yitian WANG^1,²(

),Xiaomin ZHANG^1,²(

),Haiyi JIANG³,Yanning ZHANG^1,²,Yangyang LIN^1,²,Xiuqin RAO^1,²(

)

^1.College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
^2.Key Laboratory of On-Site Processing Equipment for Agricultural Products, Ministry of Agriculture and Rural Affairs, Hangzhou 310058, China
^3.School of Mathematical Sciences, Zhejiang University, Hangzhou 310058, China

Download:

HTML

HTML ( )

PDF(3103KB)
Export: BibTeX | EndNote (RIS)

Abstract

Light stress can restrict the normal growth and development of rapeseed seedlings. In order to realize the early diagnosis of light stress in rapeseed seedlings, a 21 d experiment was conducted on rapeseed seedlings of two leaves and one heart stage using hyperspectral imaging technology. After preprocessing the collected canopy leaf spectra, the light-stress-sensitive bands were extracted through spectral reflectance and continuous wavelet transform. Then successive projection algorithm was used to extract characteristic wavelengths, and the continuous wavelet transform-stepwise discriminant analysis method was used to extract wavelet features. To further improve the accuracy of the stress detection model, a total of four features including the area under curvein the 939-978 nm band, the tangent value of the characteristic angle (tan θ), the reflectances at 984 and 1 408 nm were selected by analyzing the characteristics of the spectral band and the evolution of the spectral characteristics at the seedling stage of rapeseed to establish a multi-feature fusion Fisher discriminant model. The results showed that the average classification accuracy of the model was 86.88%, which achieved the best classification effect in the d₂₀ family, with an accuracy of 95.00%. The research provides a powerful reference for the rapid diagnosis of light stress in rapeseed based on hyperspectral imaging technology.

Key words： rapeseed light stress hyperspectral imaging feature fusion

Received: 08 March 2021 Published: 04 March 2022

CLC:

S 24

Corresponding Authors: Xiuqin RAO E-mail: 21713018@zju.edu.cn;xqrao@zju.edu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yitian WANG
	Xiaomin ZHANG
	Haiyi JIANG
	Yanning ZHANG
	Yangyang LIN
	Xiuqin RAO

Cite this article:

Yitian WANG,Xiaomin ZHANG,Haiyi JIANG,Yanning ZHANG,Yangyang LIN,Xiuqin RAO. Light stress diagnosis of rapeseed seedling stage based on hyperspectral imaging technology. Journal of Zhejiang University (Agriculture and Life Sciences), 2022, 48(1): 106-116.

URL:

https://www.zjujournals.com/agr/10.3785/j.issn.1008-9209.2021.03.081 OR https://www.zjujournals.com/agr/Y2022/V48/I1/106

基于高光谱成像技术的油菜苗期光照胁迫诊断

为实现油菜苗早期光照胁迫诊断，利用高光谱成像技术对进入两叶一心阶段的油菜苗进行为期21 d的光照胁迫实验，对采集到的冠层叶片光谱进行预处理后，通过光谱反射率和连续小波变换提取光照胁迫敏感波段，然后分别采用连续投影算法和连续小波变换-逐步判别分析法提取特征波长和小波特征。为进一步提升光照胁迫检测模型的准确率，通过分析油菜苗期光谱波段特征及其随时间的演化规律，筛选出939～978 nm波段曲线面积、特征角正切值tan θ以及984和1 408 nm处反射率共4个特征，建立多特征融合的光照胁迫Fisher判别模型。结果表明，该模型的平均分类准确率为86.88%，在d₂₀族达到最佳分类效果，准确率为95.00%。本研究为后续基于高光谱成像技术的油菜光照胁迫快速诊断方法提供了有力的参考。

关键词： 油菜, 光照胁迫, 高光谱成像, 特征融合

Fig. 1 Hyperspectral image acquisition of rapeseed leavesA. Q285 hyperspectral imaging system; B. SOC710 SWIR hyper-spectral imaging system.

Fig. 2 Mean spectral curves of leaf and background areas at 450-998 nm (A) and 917-1 717 nm (B)

Fig. 3 Segmentation results of 546 and 1 121 nm imagesA. 546 nm grayscale image; B. 546 nm binary image; C. 1 121 nm grayscale image; D. 1 121 nm binary image.

Fig. 4 Mahalanobis distance distribution of group OD₁ on day 1 (A) and group OD₃ on day 10 (B)

Fig. 5 Distribution of light-stress-sensitive wavelength within single growth period based on the significance analysis of spectral reflectance

Fig. 6 Gray-level matrix map of P value in the family d₁ at 498-950 nm (A) and 939-1 681 nm (B)

Fig. 7 Light-stress-sensitive wavelet coefficient map in the family d₁ at 498-950 nm (A) and 939-1 681 nm (B)

Fig. 8 Distribution of light-stress-sensitive wavelengths in whole growth period based on CWT

Fig. 9 Distribution of light-stress-sensitive wavelengths within single growth period based on CWT at 498-950 nm (A) and 939- 1 681 nm (B)

Table 1 Canopy spectral sample set division

Table 2 Characteristic wavelengths of C₁-C₄

Table 3 Wavelet coefficients of C₁-C₄

Table 4 Discrimination results of light stress of characteristic wavelengths optimized by SPA under Fisher discriminant model

Table 5 Discrimination results of light stress of wavelet coefficients optimized by CWT-SDA under Fisher discriminant model

Fig. 10 Fitting curve by third-order polynomial method (A) and changes of tangent slope (B) at 939-978 nm

Fig. 11 Schematic diagram of band characteristic tan θ at 939-978 nmtan θ =Tangent value of ∠M′OA′.

Fig. 12 Variation trends ofareas under curve (A) and tan θ (B) with observation period at 939-978 nm

Fig. 13 Variation trends of reflectance with observation period at 984 nm (A) and 1 408 nm (B)

Fig. 14 Variation trends of total classification accuracy (A) and OD₁ group classification accuracy (B) by Fisher discriminant model based on multi feature fusion


[1]	陈莎莎 .长江流域油菜生产规模效益研究[D].武汉:华中农业大学,2017. CHEN S S . The research of rapeseed production scale profit in Yangtze River Basin[D]. Wuhan: Huazhong Agricultural University, 2017. (in Chinese with English abstract)

[2]	农业部种植业管理司 .全国大宗油料作物生产发展规划(2016—2020年)[J].中国农业信息,2017(1):6-15. DOI:10.1002/wea.2944 Ministry of Agriculture . Planting Industry Management Department. Development plan for national bulk oil crop production (2016—2020)[J]. China Agricultural Information, 2017(1): 6-15. (in Chinese) doi: 10.1002/wea.2944

[3]	LEE S H , TEWARI R K , HAHN E J , et al . Photon flux density and light quality induce changes in growth, stomatal development, photosynthesis and transpiration of Withania somnifera (L.) Dunal. plantlets[J]. Plant Cell, Tissue and Organ Culture, 2007, 90(2): 141-151. DOI:10.1007/s11240-006-9191-2 doi: 10.1007/s11240-006-9191-2

[4]	ASKARI-KHORASGANI O , HATTERMAN-VALENTI H , FLORES F B , et al . Managing plant-environment-symbiont interactions to promote plant performance under low temperature stress[J]. Journal of Plant Nutrition, 2019, 42(16): 2010-2027. DOI:10.1080/01904167.2019.1648682 doi: 10.1080/01904167.2019.1648682

[5]	要旭阳 .光温调控对植物工厂油菜幼苗生长的影响[D].南京:南京农业大学,2016. YAO X Y . Research on the growth of Brassica napus L. seedlings in plant factory based on light and temperature regulation[D]. Nanjing: Nanjing Agricultural University, 2016. (in Chinese with English abstract)

[6]	YAO X Y , LIU X Y , XU Z G , et al . Effects of light intensity on leaf microstructure and growth of rape seedlings cultivated under a combination of red and blue LEDs[J]. Journal of Integrative Agriculture, 2017, 16(1): 97-105. DOI:10.1016/s2095-3119(16)61393-x doi: 10.1016/s2095-3119(16)61393-x

[7]	POTTER T I , ROOD S B , ZANEWICH K P . Light intensity, gibberellin content and the resolution of shoot growth in Brassica [J]. Planta, 1999, 207(4): 505-511. DOI:10.1007/s004250050510 doi: 10.1007/s004250050510

[8]	LEE Y H , KIM K S , JANG Y S , et al . Global gene expression responses to waterlogging in leaves of rape seedlings[J]. Plant Cell Reports, 2014, 33(2): 289-299. DOI:10.1007/s00299-013-1529-8 doi: 10.1007/s00299-013-1529-8

[9]	王访,廖桂平,王晓乔,等 .基于多重分形理论的油菜缺素叶片特征提取[J].农业工程学报,2013,29(24):181-189. DOI:10.3969/j.issn.1002-6819.2013.24.02 WANG F , LIAO G P , WANG X Q , et al . Feature description for nutrient deficiency rape leaves based on multifractal theory[J]. Transactions of the CSAE, 2013, 29(24): 181-189. (in Chinese with English abstract) doi: 10.3969/j.issn.1002-6819.2013.24.02

[10]	徐胜勇,林卫国,伍文兵,等 .基于颜色特征的油菜缺素症图像诊断[J].中国油料作物学报,2015,37(4):576-582. DOI:10.7505/j.issn.1007-9084.2015.04.022 XU S Y , LIN W G , WU W B , et al . Nutrient deficiency image diagnose of rapeseed based on color feature[J]. Chinese Journal of Oil Crop Sciences, 2015, 37(4): 576-582. (in Chinese with English abstract) doi: 10.7505/j.issn.1007-9084.2015.04.022

[11]	张凯兵,章爱群,李春生 .基于HSV空间颜色直方图的油菜叶片缺素诊断[J].农业工程学报,2016,32(19):179-187. DOI:10.11975/j.issn.1002-6819.2016.19.025 ZHANG K B , ZHANG A Q , LI C S . Nutrient deficiency diagnosis method for rape leaves using color histogram on HSV space[J]. Transactions of the CSAE, 2016, 32(19): 179-187. (in Chinese with English abstract) doi: 10.11975/j.issn.1002-6819.2016.19.025

[12]	SUN Y Y , TONG C , HE S , et al . Identification of nitrogen, phosphorus, and potassium deficiencies based on temporal dynamics of leaf morphology and color[J]. Sustainability, 2018, 10(3): 762. DOI:10.3390/su10030762 doi: 10.3390/su10030762

[13]	THOMAS S , KUSKA M T , BOHNENKAMP D , et al . Benefits of hyperspectral imaging for plant disease detection and plant protection: a technical perspective[J]. Journal of Plant Diseases and Protection, 2018, 125(1): 5-20. DOI:10.1007/s41348-017-0124-6 doi: 10.1007/s41348-017-0124-6

[14]	LIU Z Y , QI J G , WANG N N , et al . Hyperspectral discrimination of foliar biotic damages in rice using principal component analysis and probabilistic neural network[J]. Precision Agriculture, 2018, 19(6): 973-991. DOI:10.1007/s11119-018-9567-4 doi: 10.1007/s11119-018-9567-4

[15]	薛惠云,张永江,刘连涛,等 .干旱胁迫与复水对棉花叶片光谱、光合和荧光参数的影响[J].中国农业科学,2013,46(11):2386-2393. DOI:10.3864/j.issn.0578-1752.2013.11.024 XUE H Y , ZHANG Y J , LIU L T , et al . Responses of spectral reflectance, photosynthesis and chlorophyll fluorescence in cotton during drought stress and rewatering[J]. Scientia Agricultura Sinica, 2013, 46(11): 2386-2393. (in Chinese with English abstract) doi: 10.3864/j.issn.0578-1752.2013.11.024

[16]	KUSKA M T , BRUGGER A , THOMAS S , et al . Spectral patterns reveal early resistance reactions of barley against Blumeria graminis f. sp. hordei [J]. Phytopathology, 2017, 107(11): 1388-1398. DOI:10.1094/phyto-04-17-0128-r doi: 10.1094/phyto-04-17-0128-r

[17]	RUMPF T , MAHLEIN A K , STEINER U , et al . Early detection and classification of plant diseases with support vector machines based on hyperspectral reflectance[J]. Computers and Electronics in Agriculture, 2010, 74(1): 91-99. DOI:10.1016/j.compag.2010.06.009 doi: 10.1016/j.compag.2010.06.009

[18]	IORI A , SCALA V , CESARE D , et al . Hyperspectral and molecular analysis of Stagonospora nodorum blotch disease in durum wheat[J]. European Journal of Plant Pathology, 2015, 141(4): 689-702. DOI:10.1007/s10658-014-0571-x doi: 10.1007/s10658-014-0571-x

[19]	XIE C Q , SHAO Y N , LI X L , et al . Detection of early blight and late blight diseases on tomato leaves using hyperspectral imaging[J]. Scientific Reports, 2015, 5(1): 1-11. DOI:10.1038/srep16564 doi: 10.1038/srep16564

[20]	刘燕德,肖怀春,孙旭东,等 .柑橘叶片黄龙病光谱特征选择及检测模型[J].农业工程学报,2018,34(3):180-187. DOI:10.11975/j.issn.1002-6819.2018.03.024 LIU Y D , XIAO H C , SUN X D , et al . Spectral feature selection and discriminant model building for citrus leaf Huanglongbing[J]. Transactions of the CSAE, 2018, 34(3): 180-187. (in Chinese with English abstract) doi: 10.11975/j.issn.1002-6819.2018.03.024

[21]	MA B D , PU R L , ZHANG S , et al . Spectral identification of stress types for maize seedlings under single and combined stresses[J]. IEEE Access, 2018, 6: 13773-13782. DOI:10.1109/access.2018.2810084 doi: 10.1109/access.2018.2810084

[22]	GERHARDS M , ROCK G , SCHLERF M , et al . Water stress detection in potato plants using leaf temperature, emissivity, and reflectance[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 53: 27-39. DOI:10 .1016/j.jag.2016.08.004 doi: 10

[23]	冷锁虎,夏建飞,胡志中,等 .油菜苗期叶片光合特性研究[J].中国油料作物学报,2002,24(4):10-13. DOI:10.3321/j.issn:1007-9084.2002.04.003 LENG S H , XIA J F , HU Z Z , et al . Studies on photosynthetic characteristics of rapeseed leaves[J]. Chinese Journal of Oil Crop Sciences, 2002, 24(4): 10-13. (in Chinese with English abstract) doi: 10.3321/j.issn:1007-9084.2002.04.003

[24]	LIU Y N , XU Q Z , LI W C , et al . Long-term high light stress induces leaf senescence in wheat (Triticum aestivum L.)[J]. Photosynthetica, 2019, 57(3): 830-840. DOI:10.32615/ps.2019.086 doi: 10.32615/ps.2019.086

[25]	TIAN Y L , SACHARZ J , WARE M A , et al . Effects of periodic photoinhibitory light exposure on physiology and productivity of Arabidopsis plants grown under low light[J]. Journal of Experimental Botany, 2017, 68(15): 4249-4262. DOI:10.1093/jxb/erx213 doi: 10.1093/jxb/erx213

[1]	Meng ZHANG,Guanghui LI. Detection method of slight bruises of apples based on hyperspectral imaging and RELIEF-extreme learning machine[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2019, 45(1): 126-134.

[2]	WEN Xuewei, CHEN Yangyang, WU Bin, HU Dongwei, LIANG Wusheng. *Screening of acetolactate synthase inhibitors against Sclerotinia sclerotiorum* for the purpose of controlling rapeseed Sclerotinia disease**[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2017, 43(5): 589-598.

[3]	WANG Li1,2, DENG Fei1,2, ZHENG Jun1, ZHAO Liu1, REN Wan-jun1,2, YANG Wen-yu1,2. Response of root system growth to low-light stress in indica* rice**[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2012, 38(6): 700-708.

[4]	WU Yifei1, YAO Xiaohong1, SUN Hong2, WANG Xin1, TANG Jiangwu1. Optimization of solidstate fermentation conditions of rapeseed meal using response surface analysis combined with principal component analysis[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2012, 38(4): 490-496.

[5]	FENG Lei，ZHANG Derong， CHEN Shuangshuang，FENG Bin, XIE Chuanqi，CHEN Youyuan，HE Yong. Early detection of gray mold on eggplant leaves using hyperspectral imaging technique.[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2012, 38(3): 311-317.

[6]	ZOU Wei,FANG Hui,ZHOU Kang-yun,BAO Yi-dan,HE Yong. Identification of rapeseed varieties based on hyperspectral imagery[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2011, 37(2): 175-180.

Viewed

Full text

Abstract

Cited

Shared

Discussed