• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.88-88
• /
• 2022

Detection of stress responses in crops is important to diagnose crop growth and evaluate yield. Also, the multi-spectral sensor is effectively known to evaluate stress caused by nutrient and moisture in crops or biological agents such as weeds or diseases. Therefore, in this experiment, multispectral images were taken by an unmanned aerial vehicle(UAV) under field condition. The experiment was conducted in the long-term fertilizer field in the National Institute of Crop Science, and experiment area was divided into different status of NPK(Control, N-deficiency, P-deficiency, K-deficiency, Non-fertilizer). Total 11 vegetation indices were created with RGB and NIR reflectance values using python. Variations in nutrient content in plants affect the amount of light reflected or absorbed for each wavelength band. Therefore, the objective of this experiment was to evaluate vegetation indices derived from multispectral reflectance data as input into machine learning algorithm for the classification of nutritional deficiency in rice. RandomForest model was used as a representative ensemble model, and parameters were adjusted through hyperparameter tuning such as RandomSearchCV. As a result, training accuracy was 0.95 and test accuracy was 0.80, and IPCA, NDRE, and EVI were included in the top three indices for feature importance. Also, precision, recall, and f1-score, which are indicators for evaluating the performance of the classification model, showed a distribution of 0.7-0.9 for each class.

• Journal of Electrical Engineering and Technology
• /
• 제12권4호
• /
• pp.1641-1648
• /
• 2017

Many researchers had examined the validity of using the high-to-low ratio between two fixed frequency band amplitudes (H/L-FFB) from the surface electromyography of a face and body as the first spectral index to assess muscle fatigue. Despite these studies, the disadvantage of this index is the lack of a criterion for choosing the optimal border frequency. We tested the potential of using the high-to-low ratio between two signal spectral moments (H/L-SSM), without fixed border frequencies, to evaluate muscle fatigue and predict endurance time ($T_{end}$), which was determined when the subject was exhausted and could no longer follow the fixed contraction cycle. Ten healthy participants performed five sets of voluntary isotonic contractions until they could only produce 10% and 20% of their maximum voluntary contraction (MVC). The $T_{end}$ values for all participants were $138{\pm}35s$ at 10% MVC and $69{\pm}20s$ at 20% MVC. Changes in conventional spectral indices, such as the mean power frequency (MPF), Dimitrov spectral index (DSI), H/L-FFB, and H/L-SSM, were extracted from surface EMG signals and were monitored using the initial slope computed every 10% of $T_{end}$ as a statistical indicator and compared as a predictor of $T_{end}$. Significant correlations were found between $T_{end}$ and the initial H/L-SSM slope as computed over 30% of $T_{end}$. In conclusion, initial H/L-SSM slope can be used to describe changes in the spectral content of surface EMG signals and can be employed as a good predictor of $T_{end}$ compared to that of conventional spectral indices.

• 한국지리정보학회지
• /
• 제16권4호
• /
• pp.16-28
• /
• 2013

최근 초분광영상의 활용 연구사례와 다양한 분광지수들의 개발과 평가가 지속적으로 증가하고 있다. 특히 식생원격탐사 분야에서는 식생의 스트레스와 활력에 대한 지표로 식생지수가 사용되며 일반적으로 NIR과 red 파장대의 두 개 혹은 이상의 분광밴드를 선택적으로 사용하고 있다. 항공 초분광영상은 좁고 연속적인 수많은 밴드를 가지기 때문에 식생지수를 위한 밴드선택에 혼돈을 야기할 수 있다. 만약 식생지수를 개발하는 과정에서 사용된 밴드와 항공기를 이용해 취득한 센서의 밴드정보와 동일하지 않다면, 탐지 대상의 광학특성에 대한 설명력이 높은 적절한 밴드를 선택하는 것이 필요하다. 따라서 본 연구에서는 NIR과 red 파장영역에 속하는 4개의 후보밴드를 선택하고 이들의 조합으로 계산된 NDVI(normalized difference vegetation index)와 MSRI(modified simple ratio index)를 산출하였다. 산출된 식생지수들에 대해서 각 지수들의 변이를 살펴보기 위해 변화탐지 기법의 차연산(image differencing)을 이용하였다. 또한 보다 직접적인 분석을 위해서 분광미분(spectral derivative)을 통하여 임상도로 구분되는 식생의 종류별 분광특성을 가장 잘 설명할 수 있는 밴드를 확인하였다. 연구 결과로 후보밴드들 중에서 red #3(680.2nm)와 NIR #2(801.7nm)가 수림에 영향을 적게 받고 밴드의 변동이 적은 적절한 밴드로 선택할 수 있었다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.696-701
• /
• 2002

This paper describes some results of change detection in Tokyo metropolitan area, Japan , using the Landsat TM data, and methods to quantify the ground cover classes. The changes are analyzed using the measures of not only conventional spectral classes but also a set of landscape indices to describe spatial properties of ground cove types using fractal dimension of objects, entropy in the specific windows defining the neighbors of focusing locations. In order eliminate the seasonal radiometric effects on TM data, an automated class labeling method is also attempted. Urban areas are also delineated automatically by defining the boundaries of the urban area. These procedures for urban change detection were implemented by the unified image computing methods proposed by the author, they can be automated in coherent and systematic ways, and it is anticipated to automate the whole procedures. The results of this analysis suggest that Tokyo metropolitan area was extended to the suburban areas along the new transportation networks and the high density area of Tokyo were also very much extended during the period between 1985 and 1995.

• 천문학논총
• /
• 제8권1호
• /
• pp.17-31
• /
• 1993

In order to check whether the 4-degree objective prism spectra can be used for deep spectroscopic studies of galactic structure, we measured the Rose(1984)'s seven indices between 3500 A and 4400 A for 19 Hyades stars on the Kiso Schmidt prism plate, K3496. By comparing the $4^{\circ}$-indices with those of Rose(1984), we have found that $H{\delta}/FeI$, $H{\gamma}/4325$, and P(3912)/P(CN) measured on the 4-degree prism spectra, are still useful for the derivation physical parameters.

• Bulletin of the Korean Chemical Society
• /
• 제25권12호
• /
• pp.1840-1844
• /
• 2004

The mass spectra of benzophenones, 2-benzoylthiophenes, 2-benzoylpyrroles, and 2-benzoylfurans which have substituents at the m- and p-positions of the benzoyl ring were analyzed to find correlations against the Hammett substituent parameter ${\sigma}\;and\;{\sigma}^+$. The slopes of the plots of the intensities of the fragments from the heterocycles against those of the benzene gave sets of meaningful values for the indices of aromaticity of the heterocycles: benzene 1.00; thiophene 0.94, pyrrole 0.82, and furan 0.74.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.405-407
• /
• 2003

An attempt has been in this study to delineate the characteristics of spectral signatures of the vegetation in terms of various VIs, particularly made the Normalized Difference Vegetation Index(NDVI), Modified Soil Adjusted Vegetation Index2(MSAVI2) and Enhanced Vegetation Index(EVI). Multitemporal SPOT-4 VEGETATION data from 1998 to 2002 have been used for the analysis. They have been compared with each other for their similarities and differences. The correlations between the vegetation indices observed at various degree of vegetation coverage during their different stages of growth were examined. All of the VIs have shown qualitative relationships to variations in vegetation. Apparently, the NDVI and MSAVI2 are highly correlated for all of the temporal changes, representing the different stages of phenology.

• 항공우주기술
• /
• 제8권2호
• /
• pp.26-32
• /
• 2009

위성영상의 융합에 있어, 가장 중요한 점은 전정영상의 공간적 세밀함과 다중분광영상의 분광정보 모두를 보존하는 것이다. 다양한 영상융합 기법 중에서, IHS 변환을 이용한 융합기법은 폭넓게 사용되고 있으며, 계산과정이 매우 단순하다는 장점을 갖고 있다. 본 연구에서는, fast IHS 변환과 trade-off 파라미터 $\alpha^i$를 이용한 융합기법을 제안한다. 제안한 융합 기법은 분광 ERGAS와 공간 ERGAS의 평가를 통하여, 융합영상에서 분광정보와 공간적 세밀함 사이의 trade-off 최적화를 가능하게 한다. IKONOS 영상의 실험결과, 제안한 기법은 기존의 fast IHS 변환을 이용한 융합기법에 비해 공간적 세밀함과 분광정보의 보존측면에서 더 효과적임을 확인할 수 있었다.

• 대한원격탐사학회지
• /
• 제35권4호
• /
• pp.561-571
• /
• 2019

In this paper, we analyze the effect of the representative spectral indices, normalized difference vegetation index (NDVI), normalized difference water index (NDWI) and normalized difference built-up index (NDBI) on classification accuracies of Landsat-8 OLI image.After creating these spectral index images, we propose five methods to select the spectral index images as classification features together with Landsat-8 OLI bands from 1 to 7. From the experiments we observed that when the spectral index image of NDVI or NDWI is used as one of the classification features together with the Landsat-8 OLI bands from 1 to 7, we can obtain higher overall accuracy and kappa coefficient than the method using only Landsat-8 OLI 7 bands. In contrast, the classification method, which selected only NDBI as classification feature together with Landsat-8 OLI 7 bands did not show the improvement in classification accuracies.

• Journal of the Optical Society of Korea
• /
• 제7권4호
• /
• pp.234-239
• /
• 2003

Objective methods to assess quantitatively port wine stain (PWS) blanching in response to laser therapy are needed to improve laser therapeutic outcome. Previous studies have attempted to assess objectively PWS color based on point measurement devices. To date, these approaches have typically been limited by a number of factors such as small test area and need for contact. To address these issues, a polarization spectral imaging system and an image analysis method have been developed to evaluate quantitatively erythema and melanin content distribution in skin. The developed polarization spectral imaging system minimizes artifacts such as glaring, shadowing, and non-uniform illumination that interfere with image fidelity. Furthermore, the image analysis method has been employed to get images of skin melanin and erythema indices from the acquired color images for quantitative analysis. Finally, using PWS patient color image, the effectiveness in laser treatment of PWS was evaluated by calculating relative erythema index image that is the relative erythema index of PWS region to the normal region. The developed device and analysis method appears to be a simple and effective method for quantitative analysis of PWS blanching.