Гиперспектр буюу хэт олон сувагт “LCTF” камер ашиглан ургамлыг төрөл зүйлээр ангилан ялгах шинэ алгоритм
DOI:
https://doi.org/10.22353/physics.v35i594.5602Keywords:
Vegetation Classification, hyperspectral camera, spectral reflectanceAbstract
Энэ судалгааны хүрээнд хэт олон сувагт LCTF (Liquid Crystal Tunable Filter) буюу шингэн кристалл шүүлтүүртэй камерын тусламжтай ургамлын зүйлийг түүний спектр шинж чанарт тулгуурлан ялгаж, навчны талбайн индекс LAI (Leaf Area Index) тооцож гаргах шинэ алгоритмыг туршин үзэв. 2022 оны 7-р сарын эхний долоо хоногт Хар Ямаат байгалийн нөөц газарт хэд хэдэн бодит талбарт LCTF камераар хээрийн ургамлуудын зургийг авч, цуглуулсан зурган мэдээллээс ургаж буй олон зүйлийн ургамлуудын гэрлийн ойлтын спектрийг дүрс боловсруулах аргаар ялгаж, түүгээр спектр сан үүсгэв. Үүсгэсэн сангийн мэдээллээс бид улаан хилийн зурваст тулгуурлан өвслөг ургамлын зүйлийн бүрдлийг тодорхойлох алгоритм туршиж үзсэн. Тухайн алгоритмаар навчны талбайн индексийг мөн тооцож гаргахад эрүүл ургамлыг хагдарсан өвс болон ургамал бус зүйлээс 95% дээш нийлэмжтэй ялгаж байна. Энэ ажлын үр дүнд ургамлын төрөл зүйлийг машинаар олон сувагт камерын тусламжтай өндөр нарийвчлалтай ялгах боломжтойг харуулж байна. Цаашид орчин үеийн хиймэл дагуул, дроноор авсан зургаас уг бидний хөгжүүлсэн алгоритмыг ашиглан хаана ямар төрөл зүйлийн ургамал хэр хэмжээгээр ургаж буйг ялгах боломж бүрдэх юм.
[ENGLISH]
Within the framework of this research, a new algorithm was designed to determine the plant’s red edge slope and the Leaf Area Index (LAI) based on their spectral characteristics using a hyperspectral LCTF (Liquid Crystal Tunable Filter) camera. In the first week of July 2022, we took pictures of field vegetation in several fields in the Khar Yamaat Nature Reserve with the LCTF camera. From the collected data, the light reflectance spectrum of many species of growing plants was distinguished with the help of image processing, and with that, we created a spectrum dataset of 21 different species. From the generated dataset, we designed an algorithm to determine plant species or dry grass based on the red edge slope, which works with approximately 95% accuracy. The algorithm also calculates the leaf area index, and healthy plants are distinguished from damaged grass and non-plant species. The results of this work demonstrate that vegetation can be classified by vegetation’s red edge slope using hyperspectral cameras. In the future, it will be possible to determine the location and number of growing plants using the algorithm we developed on the images taken by modern satellites and drones.
Downloads
References
Lowe S, Ball DL, Reeves MK, Amidon F, Miller SE. Hawai’i: Mesic forests. Encyclopedia of the World’s Biomes 2020;3–5:346–72.
Talaviya T, Shah D, Patel N, Yagnik H, Shah M. Implementation of artificial intelligence in agriculture for optimisation of irrigation and application of pesticides and herbicides. Artificial Intelligence in Agriculture2020;4:58–73.
Yao L, Liu T, Qin J, Lu N, Zhou C. Tree counting with high spatial-resolution satellite imagery based on deep neural networks. Ecol Indic 2021;125.
Ishida T, Kurihara J, Viray FA, Namuco SB, Paringit EC, Perez GJ, et al. A novel approach for vegetation classification using UAV-based hyperspectral imaging. Comput Electron Agric [Internet] 2018 [cited 2018 Aug 13];144:80–5. Available from: https://www.sciencedirect.com/science/article/pii/S0168169917310499
Grube A, Donaldson D, Kiely T, Wu L. Pesticide Industry Sales and Usage Report: 2006 and 2007 Market Estimates. 2006.
Caiati C, Pollice P, Favale S, Lepera ME. The Herbicide Glyphosate and Its Apparently Controversial Effect on Human Health: An Updated Clinical Perspective. Endocr Metab Immune Disord Drug Targets 2019;20:489–505.
Lindenmayer DB, Likens GE, Andersen A, Bowman D, Bull CM, Burns E, et al. Value of long-term ecological studies. Austral Ecol [Internet] 2012 [cited 2023 Apr 13];37:745–57. Available from: https://onlinelibrary.wiley.com/doi/full/10.1111/j.1442-9993.2011.02351.x
Ditria EM, Buelow CA, Gonzalez-Rivero M, Connolly RM. Artificial intelligence and automated monitoring for assisting conservation of marine ecosystems: A perspective. Front Mar Sci 2022;9:1313.
Painter TH, Dozier J. Measurements of the hemispherical-directional reflectance of snow at fine spectral and angular resolution. J Geophys Res [Internet] 2004 [cited 2019 Jan 8];109:D18115. Available from: http://doi.wiley.com/10.1029/2003JD004458
Nicodemus F, Richmond J, Hsia J, Ginsberg I, Limperis T. Geometrical Considerations and Nomenclature for Reflectance. 1977 [cited 2018 Feb 22];Available from: https://graphics.stanford.edu/courses/cs448-05-winter/papers/nicodemus-brdf-nist.pdf
Walter-Shea EA, Norman JM, Blad BL. Leaf bidirectional reflectance and transmittance in corn and soybean. Remote Sens Environ 1989;29:161–74.
Schaepman-Strub G, Schaepman ME, Painter TH, Dangel S, Martonchik J V. Reflectance quantities in optical remote sensing-definitions and case studies. Remote Sens Environ 2006;103:27–42.
Grum F, Luckey GW. Optical Sphere Paint and a Working Standard of Reflectance. Applied Optics, Vol. 7, Issue 11, pp. 2289-2294 [Internet] 1968 [cited 2023 Apr 13];7:2289–94. Available from: https://opg.optica.org/viewmedia.cfm?uri=ao-7-11-2289&seq=0&html=true
Walter-Shea EA, Norman JM, Blad BL. Leaf bidirectional reflectance and transmittance in corn and soybean. Remote Sens Environ 1989;29:161–74.
BEGZSUREN TUMENDEMBEREL トゥメンテンプレル ベグズスレン 北 海 道 大 学 Supervisor by, Takahashi Y. STUDY OF SPECTRO-POLARIMETRIC BIDIRECTIONAL REFLECTANCE PROPERTIES OF LEAVES. 2019;
SAKAMOTO Y, SUGIMURA N, FUKUDA K, KUWAHARA T, YOSHIDA K, KURIHARA J, et al. Development and Flight Results of Microsatellite Bus System for RISING-2. TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES, AEROSPACE TECHNOLOGY JAPAN [Internet] 2016 [cited 2018 Feb 22];14:Pf_89-Pf_96. Available from: https://www.jstage.jst.go.jp/article/tastj/14/ists30/14_Pf_89/_article
Remote Sensing Based Vegetation Classification Using Machine Learning Algorithms | IEEE Conference Publication | IEEE Xplore [Internet]. [cited 2023 Apr 16];Available from: https://ieeexplore.ieee.org/document/9194217
Fu B, Zuo P, Liu M, Lan G, He H, Lao Z, et al. Classifying vegetation communities karst wetland synergistic use of image fusion and object-based machine learning algorithm with Jilin-1 and UAV multispectral images. Ecol Indic 2022;140:108989.
Ahmad AM, Minallah N, Ahmed N, Ahmad AM, Fazal N. Remote sensing based vegetation classification using machine learning Algorithms. 2019 International Conference on Advances in the Emerging Computing Technologies, AECT 2019 2020;
Grant L. Diffuse and specular characteristics of leaf reflectance. Remote Sens Environ 1987;22:309–22.
Vanderbilt VC, Grant L. Plant Canopy Specular Reflectance Model. IEEE Transactions on Geoscience and Remote Sensing 1985;GE-23:722–30.
Grant L, Daughtry CST, Vanderbilt VC. Polarized and specular reflectance variation with leaf surface features. Physiol Plant [Internet] 1993 [cited 2019 Jan 11];88:1–9. Available from: http://doi.wiley.com/10.1111/j.1399-3054.1993.tb01753.x
Grant L, Daughtry CST, Vanderbilt VC. Polarized and specular reflectance variation with leaf surface features. Physiol Plant [Internet] 1993 [cited 2019 Jan 7];88:1–9. Available from: http://doi.wiley.com/10.1111/j.1399-3054.1993.tb01753.x
Liu W, Wu EY. Comparison of non-linear mixture models: sub-pixel classification. Remote Sens Environ 2005;94:145–54.
Nemani R, Running SW. Implementation of a hierarchical global vegetation classification in ecosystem function models. Journal of Vegetation Science [Internet] 1996 [cited 2019 Jan 11];7:337–46. Available from: http://doi.wiley.com/10.2307/3236277
Downloads
Published
How to Cite
License
Copyright (c) 2024 Physics
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.