• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.6 no.3
• /
• pp.9-16
• /
• 2003

In support of remote sensing applications for monitoring processes of the Earth system, research was conducted to analyze the basic spectral response related to background soil and vegetation cover characteristics in the visible and reflective infrared wavelengths. Surface samples of seven stations were examined. Five soils were from land-field and two soils from tideland areas. The vegetation cover experiment was conducted on seven soil samples with known natural moisture content (%) by weight. To study the effect of vegetation cover, spectral measurements were taken on five or six vegetation cover treatments of the seven soils with 3 replications in air dry conditions. For collecting RS base data, used spectro-radiometer that measures reflection characteristics between 300~1,100nm was used and measured the reflection of vegetation from bean leaves. The relationships were evaluated for both a general soil line and for the individual lines of five soils, under air-dried condition as well as different vegetation cover ratio, through the determination of the line parameters. As vegetation cover ratio in bean leaves increases, features of soil reflectance decrease and those of plant reflectance become more and more apparent. In proportion to vegetation cover rate, near-infrared reflectance increased and visible reflectance decreased. Analysis results are compared to commonly used vegetation indices(RVI and NDVI ).

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.423-423
• /
• 2004

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.23 no.6
• /
• pp.15-28
• /
• 2020

Urbanization and industrialization have caused increasing damage to national lands, and ecological restoration has proceeded without any specific assessment of this damage. The purpose of this study is to select indices to assess damaged areas through literature review and panel discussions, and to derive the importance of damaged area assessment indices by analyzing them through the Analytic Hierarchy Process (AHP). This study has derived, via literature review, six types of damage and a total of 18 related assessment indices. A total of 51 responses were collected from surveys and given to experts, and an AHP analysis conducted. As a result of the analysis, "Landform change (0.268)" was of the highest importance, with associated damage types as follows: "Soil contamination (0.193)", "Vegetation damaged (0.149)", "Surface soil loss (0.143)", "Change in soil physiochemical property (0.125)", and "Vegetation decline (0.122)". The analysis determined that the item of the highest importance in the overall assessment of damage was "Slope occurred area (0.100)", and that "Conductivity (0.022)" was of the lowest importance. This study can be presented as a criterion in determining the type and degree of damage in setting priorities for future ecological restoration projects.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• 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 the Korean Society of Environmental Restoration Technology
• /
• v.24 no.1
• /
• pp.97-110
• /
• 2021

Vegetation index information is an important figure that is used in many fields such as landscape architecture, urban planning, and environment. Vegetation may vary slightly in vegetation vitality depending on photosynthesis and chlorophyll content. In this study, a range of vegetation worth preserving in the Taehwa River water system was determined, and hyperspectral images of drones were acquired (August, October), and the results were presented through DVI(Normalized Defference Vegetation Index), EVI(Enhanced Vegetation Index), PRI(Photochemical Reflectance Index), ARI (Anthocyanin Reflectance Index) index analysis. In addition, field spectral data and VRS-GPS(Virtual Reference System-GPS) surveys were performed to ensure the quality and location accuracy of the spectral band. As a result of the analysis, NDVI and EVI showed low vegetation vitality in October, -0.165 and -0.085, respectively, and PRI and ARI increased to 0.011 and 7.588 in October, respectively. For general vegetation vitality, it was suggested that NDVI and EVI analysis were effectively performed, and PRI and ARI were thought to be effective in analyzing detailed characteristics of plants by spectral band. It is expected that it can be widely used for park design and landscape information modeling by using drone image information construction and vegetation information.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.26 no.1
• /
• pp.96-112
• /
• 1998

This study aims to evaluate the potential of pro-environmental application(PEP) in streams conceptualized ecological conservation and recreational use to be in harmony with. The main content of research are to clarify the PEP, to establish the evaluation model, and to evaluate 3 streams(Dongchon, Seokhyunchon, Okchon) in Sunchon city. Researchers introduced 12 evaluation items(water quality, water quantity, vegetation-water area, vegetation conservation, streamscape, neighborhood landscape, stream width, optimum area, nearby landuse, facility in stream, distance from user, obstacle to acces) by 5 scales to evaluate the characteristics of natural and artificial factors in stream area and nearby area. Also to decide the weight of items, researchers surveyed the opinion of 22 landscape architects experienced stream-plan through delphi method. Lastly the pro-environmental potential on streams were calculated by the ecological potential and recreational potential indices to be standardized and indicidual sections in streams were divided 5 grades on the basis of PEP. The result of this study are as follows; 1) The evaluation model of PEP was constructed by 4 steps, such as the decision of weight, the measurement of scale, the calculation of potential indices, the gradation of individual sections in streams. 2) The ecological potential were highly influenced by natural factor such as water quality, vegetation conservation, vegetation-water area, but on the other hand the recreational potential were influenced by optimum area, distance from user, water quantity, obstacle to access. 3) The factors such as vegetation conservation, optimum area, nearby landuse, distance from user were function as discernment factors to evaluate relatively ecological and recreational potential. and water quality, water quantity, vegetation -water area, neighborhood landscape were acted as important items to decide PEP.

• Korean Journal of Remote Sensing
• /
• v.32 no.5
• /
• pp.483-497
• /
• 2016

Unmanned Aerial Vehicle (UAV) imagery are being assessed for analyzing within field spatial variability for agricultural precision management, because UAV imagery may be acquired quickly during critical periods of rapid crop growth. This study refers to the derivation of barley and wheat growth prediction equation by using UAV derived vegetation index. UAV imagery was taken on the test plots six times from late February to late June during the barley and wheat growing season. The field spectral reflectance during growing period for the 5 variety (Keunal-bori, Huinchalssal-bori, Saechalssal-bori, Keumkang and Jopum) were measured using ground spectroradiometer and three growth parameters, including plant height, shoot dry weight and number of tiller were investigated for each ground survey. Among the 6 Vegetation Indices (VI), the RVI, NDVI, NGRDI and GLI between measured and image derived showed high relationship with the coefficient of determination respectively. Using the field investigation data, the vegetation indices regression curves were derived, and the growth parameters were tried to compare with the VIs value.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.147-150
• /
• 2008

This study refers to develop a semi-automatic extraction of agricultural land use and vegetation information using high resolution satellite images. Data of IKONOS satellite image (May 25 of 2001) and QuickBird satellite image (May 1 of 2006) which resembles with the spatial resolution and spectral characteristics of KOMPSAT3. The precise agricultural land use classification was tried using ISODATA unsupervised classification technique and the result was compared with on-screen digitizing land use accompanying with field investigation. For the extraction of vegetation information, three crops of paddy, com and red pepper were selected and the spectral characteristics were collected during each growing period using ground spectroradiometer. The vegetation indices viz. RVI, NDVI, ARVI, and SAVI for the crops were evaluated. The evaluation process is under development using the ERDAS IMAGINE Spatial Modeler Tool.

• Korean Journal of Remote Sensing
• /
• v.20 no.1
• /
• pp.13-21
• /
• 2004

The usefulness of the multi-temporal satellite image to monitoring the vegetation recovery process after forest fire was tested. Using multi-temporal Landsat TM and ETM＋data, NDVI and NBR changes over times were analyzed. Both NDVI and NBR values were rapidly decreased after the fire and gradually increased for all forest type and damage class. However, NBR curve showed much clearer tendency of vegetation recovery than NDVI. Both indices yielded the lowest values in severely damaged red pine forest. The results show the vegetation recovery process after forest fire can detect and monitor using multi-temporal Landsat image. NBR was proved to be useful to examine the recovering and development process of the vegetation after fire. In the not damaged forest, however the NDVI shows more potential capability to discriminate the forest types than NBR..

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.