초분광 영상을 이용한 Potherb Mustard (Mizuna)의 주요성분 추정
Estimation of the Main Properties in Potherb Mustard (Mizuna) using Hyperspectral Imagery
1
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
미즈나의 주요성분인 건물중, 전탄소, 전질소, Fe 및 Ca 함유량을 초분광 영상을 이용하여 추정하였다. 샘플은 인공재배기에서 실내온도 20℃, 일조시간 13 h의 조건에서 6 주간 재배한 샘플과 온실에서동일기간 재배된 샘플을 이용하였다. 재배조건, 영상취득시의 광 환경에 따라 인공재배기, 하우스, 전처리의 유무 및 모든 데이터를 이용한 그룹으로 나누어 각각 모델을 작성하였다. 실내 재배에서는 건물중, 전탄소, 전질소의 경우 전처리에 따라 평균상대오차(MRE)가 5% 이상 향상되었으나 하우스의 경우전처리의 효과가 없었다. Ca 이온의 경우 조건에 관계없이 모델을 구축할 수 있었으나 Fe 이온의 경우하우스 재배에서는 모델을 구축할 수 없었다. 모든 데이터를 이용해 미즈나의 건물중, 전질소, 전탄소,Fe 및 Ca 함유량을 추정할 경우 반사율을 이용해 62% 이상 설명이 가능하였고 검증결과도 57% 이상으로 나타났다. 전처리를 거칠 경우 반사율을 이용해 71% 이상 설명이 가능하였고 검증결과도 62% 이상으로 나타났다. 전처리를 했을 경우 각각 추정오차는 건물중이 0.54 g/m2, 전질소가 39.8 mg/m2, 전탄소가 185 mg/m2, Fe 이온이 0.35 mg/m2, Ca 이온이 14.1 mg/m2였다.
Abstract
In this study, the amount of main properties, such as dry mass, total carbon (TC), total nitrogen(TN), Iron (from Latin: ferrum, Fe), and Calcium (Ca), in Potherb Mustard (Mizuna) was estimatedby hyperspectral imagery. The samples were cultivated in the greenhouse and in the controlledchamber with 20℃ and 13 h day light conditions during 6 weeks. Each model was establisheddepending on the conditions of cultivation and reflectance in the image, such as the groups ofgrowth chamber, green house, preprocessing, and all data. In the case of the group of growthchamber, MRE(Mean of Relative Error) was improved more than 5% when the reflectance waspreprocessed, but it was not in the case of the group of green house. It was possible to make amodel for the ion of Ca in spite of any conditions but it was not for the ion of Fe. When themodel was established by all data, the precision of calibration was more than 62% and it of validation was more than 57%. When the reflectance was preprocessed, it was possible to explain the precision of calibration for all data more than 71% and it of validation was more than 62%. The RMSE of validation about the preprocessed model was 0.54 g/m2 for DM, 39.8 mg/m2 forTN, 185 mg/m2 for TN, 0.35 mg/m2 for Fe ion and 14.1 mg/m2 for Ca ion.
참고문헌 (17)
- 안치국, "초분광 반사광 영상을 이용한 배추 종자(Brassica campestris L) 비파괴 품질 측정기술 개발", 산업식품공학, 16(3), pp.257~262 (2012), 한국산업식품공학회
- Ananingsih, V. K., "Green tea catechins during food processing and storage : A review on stability and detection", Food Research International, 50(2), pp.469~479 (2011)
- Dobermann, A., "Indirect leaf area index measurement as a tool for characterizing rice growth at the field scale", Communications on Soil Science and Plant Analysis, 26, pp.1507~1523 (1995)
- "Food composition" (2010)[URL]
- Gab-Sue Jang, "Relating Hyperspectral Image Bands and Vegetation Indices to Corn and Soybean Yield", 대한원격탐사학회지, 22(3), pp.183~197 (2006), 대한원격탐사학회
- Kondo, K., "Effects of fertilizer application rate on the growth and nitrate concentration in mizuna and komatsuna", Journal of SHITA, 20(4), pp.242~246 (2008)
- 권태협, "Forest Canopy Density Estimation Using Airborne Hyperspectral Data", 대한원격탐사학회지, 28(3), pp.297~305 (2012), 대한원격탐사학회[DOI]
- Miyashita, W., "A basic study on controlling cultivation of potherb mustard (Mizuna) by using LED irradiation", Bulletin of the Faculty of Agriculture, 63(2), pp.115~118 (2011), Niigata University
- 노현권, "하이퍼 스펙트랄 반사광 및 형광 산란을 이용한 사과 품질 측정", 바이오시스템공학, 34(1), pp.37~43 (2009), 한국농업기계학회
- Onoyama, H., "Estimation of rice protein content using ground-based hyperspectral remote sensing", Journal of Engineering in Agriculture, Environment and Food, 4(3), pp.71~76 (2011)
- Rinnan, A., "Review of the most common pre-processing techniques for near-infrared spectra", Trends in Analytical Chemistry, 28(10), pp.1201~1222 (2009)
- Ryu, C. S., "Estimation of the quantity and quality of green tea using hyperspectral sensing", Japanese Society of Agricultural Machinery, 72(1), pp.46~53 (2010)
- Ryu, C. S., "Estimating catechin concentration of new shoots in the green tea field using ground-based hyperspectral image", SPIE conference in Remote Sensing 2013 (2013)
- Ryu, C. S., "Making nitrogen contents model using hyperspectral remote sensing and estimation nitrogens content by nitrogen contnet model", Japanese Society of Agricultural Machinery, 67(6), pp.47~54 (2005)
- Sharma, R. K., "Heavy metal contamination of soil and vegetables in suburban areas of varanasi, India", Ecotoxicology and environmental safety, 66(2), pp.258~266 (2007)
- Tanaka, A., "Current state and future effort of Kyoto vegetables", Agriculture Today, 45(8), pp.17~21 (2001)
- Yi, Q. X., "Monitoring rice nitrogen status using hyperspectral reflectance and artificial neural network", Environment Science Technology, 41, pp.6770~6775 (2007)