Nondestructive Testing of Lettuce Nitrogen Stress Based on Multidimensional Image
DOI:
https://doi.org/10.24297/jaa.v12i.9063Keywords:
Information fusion, 3D laser scanning, Hyperspectral images, Nitrogen, LettuceAbstract
Visible light near infrared (VS-NIR) hyperspectral combined with three-dimensional laser scanning was applied to extract the VS-NIR features of lettuce nitrogen between 400-1700 nm and 3D morphological features of the plants. Such combination realizes the rapid quantitative detection of lettuce nitrogen. This study is based on the hyperspectral image data cube achieved from lettuce leaves with different nitrogen levels. Stepwise regression sensitive area was used and adaptive band selection method was combined to extract the characteristic spectrum and feature image of lettuce nitrogen and characterize the average image intensity. Also; the error caused by moisture variation content in lettuce nitrogen image features was compensated. Then a model of lettuce nitrogen hyperspectral image diagnosis was built. The reverse engineering software Geomagic Qualify was used to repair and smooth interference noise and discontinuous range which are based on the 3D laser scanning data of lettuce. Accordingly, the stem diameter, plant height, leaf area, and biomass features of different nitrogen levels of lettuce are obtained and the model of nitrogen detection about lettuce growth features was built based on reverse engineering and integral method. Multi-scale fusion lettuce nitrogen detection model is built by using the acquired hyperspectral images with growing features of lettuce nitrogen and adopting genetic algorithm combined with partial least squares regression. Results show the correlation coefficient R of the built model is 0.95; the model precision is much better than single feature of hyperspectral images and 3D laser scanning model. The feature extraction algorithm and the eigenvectors provide the reference for development of facilities for online monitoring system of crop growth information.
Downloads
References
Bei MR，Luo XH，Yang HZ. Simultaneous determination of nitrogen，phosphorus and potassium in rubber leaf samples by AA3 continuous flow analyzer (CFA) [J]. Chinese Journal of Tropical Crops, 2011, 32(7):1258-1264.( in Chinese). DOI:10.3969/j.issn.1000-2561.2011.07.015
Gu Q, Deng JS, Lu C, Shi YY, Wang K, Shen ZQ. Diagnosis of Rice Nitrogen Nutrition Based on Spectral and Shape Characteristics of Scanning Leaves[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 43(8):170- 174. (In Chinese). DOI:10. 6041/j. issn. 1000-1298. 2012. 08. 031
Giacomo D, Stefania D. A multivariate regression model for detection of fumonisins content in maize from near infrared spectra[J].Food Chemistry,2013, 141(4):4289-4294.DOI:10.1016/j.foodchem.2013.07.021
Hoyos-Villegas V, Fritschi FB, 2013. Relationships among vegetation indices derives from aerial photographs and soybean growth and yield[J]. Crop Science, 53(6): 2631-2642. DOI: 10.2135/cropsci2013.02.0126
Hao Y. Chen B. Quantitative determination of low amino acid contents in tea by using near-infrared spectroscopy [J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(6): 216- 220. DOI: 10.6041 /j.issn.1000-1298.2014.06.033
Kamruzzaman M, Sun DW, EIMasry G. Fast detection and visualization of minced lamb meat adulteration using NIR hyperspectral imaging and multivariate image analysis[J]. Talanta, 2014, 21(103): 130-136.
Knox NM, Skidmore AK. Remote sensing of forage nutrients: combining ecological and spectral absorption feature data［J］.ISPRS Journal of Photogrammetry and Remote Sensing, 2012 72: 27- 35.
Lorente D, Aleixos N, GmezSanchis J. Recent advances and applications of hyperspectral imaging for fruit and vegetable quality assessment[J]. Food Bioprocess Technol, 2015, 5(4): 1121-1142. DOI: 10.1007/s11947-011-0725-1
Li F. The principle of regression analysis method and the actual operation of SPSS [M]. Beijing: China Financial Publishing House, 2014(3).
Li XW, Lu X, Zhang Z, Chen J, Shi HG ,Tian M. Diagnosis of Nutriton and Recommended Model of Topdressing For Cotton［J］.Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(12) :209- 214. DOI: 10.6041 /j.issn.1000-1298.2014.12.031
Nativ R, Zeev S, Y Cohen, Victor A, Ran E, Timea I, Clara Shendereya, Arnon D, Uri Y. Estimating olive leaf nitrogen concentration using visible and near-infrared spectral reflectance [J]. Bio systems Engineering, 2012, 114(2013):426-434. DOI: 10.1016/j.biosystemseng.2012.09.005
[Ouyang AG, Xie XQ, Liu YD. Selection of NIR variables for online detecting soluble solids content of apple［J. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(4): 220-225. DOI: 10.6041 /j.issn.1000-1298.2014.04.035
Pu RL, Gong P. Hyperspectral Remote Sensing and Its Application[M]. Beijing: Higher Education Press, 2000(8).
Qin JW, Thomas FB, Mark AR. Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence[J]. Journal of Food Engineering, 2009, 93(2):183-191.DOI: 10.1016/j.jfoodeng.2009.01.014
Ramoelo A, Skidmore AK, Schlerf M. Savanna grass nitrogen to phosphorous ratio estimation using field spectroscopy and the potential for estimation with imaging spectroscopy[J]. Journal of Applied Earth Observation and Geoinformation, 2013, 23:334 -343. DOI: 10.1016/j.jag.2012.10.009
Shetty N, Gislum R. Quantification of frusta concentration in grasses using NIR spectroscopy and PLSR[J]. Field Crops Research, 2011, 120(1): 31-37. DOI: 10.1016/j.fcr.2010.08.008
Su JM, Fu RH, Zhou JB. Practical Guide to Statistical Software SPSS for Windows [M]. Beijing: Publishing House of Electronics Industry, 2000(6).
Tong QX. Analysis of typical spectral features and their characteristics in China[M]. Beijing: Science Press, 1990(8).
Wang ZG. Nutrition and Quality of Vegetables [M]. Beijing: Science Press, 2009: 36-37.
WANG YY, HE P, WEI T, LI SS. A Research of an Infrared Image Segmentation Algorithm Based on the Two-dimensional Entropy[J]. Journal of Air Force Engineering University (Natural Science Edition), 2015, 16(1):77-80. DOI:10.3969/j.issn.1009-2015.01.017
Yang Wei, Li MZ, Sun H, Zheng LH. De-noising Algorithm of Multispectral Images and Nonlinear Estimation of Nitrogen Content of Cucumber Leaves in Greenhouse[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(7) :216- 220. DOI: 10.6041 /j.issn.1000-1298.2013.07.038
Zhang ZA, Luo B. New approach for image retrieval based on color and spatial features [J]. Journal of xidian university, 2008, 35(2): 577-581.
Zhang XL, Liu F, He Y. Detecting macronutrients content and distribution in oilseed rape leaves based on hyperspectral imaging[J]. Biosystems Engineering, 2013, 15(1): 56-65.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2021 Bao Guo Shen, Jin Yue Dai, Xiao Dong Zhang, Zhao Hui Duan
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in Journal of Advances in Linguistics are licensed under a Creative Commons Attribution 4.0 International License.
