• Korean Journal of Remote Sensing
• /
• v.36 no.5_1
• /
• pp.823-833
• /
• 2020

In order to stably produce crops, there is an increasing demand for effective crop monitoring techniques in domestic agricultural areas. In this manuscript, a cultivation area extraction method by using deep learning model is developed, and then, applied to satellite imagery. Training dataset for crop cultivation areas were generated using RapidEye satellite images that include blue, green, red, red-edge, and NIR bands useful for vegetation and environmental analysis, and using this, we tried to estimate the crop cultivation area of onion and garlic by deep learning model. In order to training the model, atmospheric-corrected RapidEye satellite images were used, and then, a deep learning model using FC-DenseNet, which is one of the representative deep learning models for semantic segmentation, was created. The final crop cultivation area was determined as object-based data through combination with cadastral maps. As a result of the experiment, it was confirmed that the FC-DenseNet model learned using atmospheric-corrected training data can effectively detect crop cultivation areas.

• Korean Journal of Remote Sensing
• /
• v.35 no.3
• /
• pp.375-387
• /
• 2019

The use of drone-based hyperspectral image offers considerable advantages in high resolution remote sensing applications. The primary objective of this study was to select the optimal bands based on hyperspectral image for the estimation yield of the chinese cabbage. The hyperspectral narrow bands were acquired over 403.36 to 995.19 nm using a 3.97 nm wide, 150 bands, drone-based hyperspectral imaging sensor. Fresh weight data were obtained from 2,031 sample for each field survey. Normalized difference vegetation indices were computed using red, red-edge and near-infrared bands and their relationship with quantitative each fresh weights were established and compared. As a result, predominant proportion of fresh weights are best estimated using data from three narrow bands, in order of importance, centered around 697.29 nm (red band), 717.15 nm (red-edge band) and 808.51 nm (near-infrared band). The study determined three spectral bands that provide optimal chinese cabbage productivity in the visible and near-infrared portion of the spectrum.

• Journal of the Korean Wood Science and Technology
• /
• v.29 no.3
• /
• pp.14-20
• /
• 2001

On the bending process, metal-strap plays an important role in dispersing the stress generated in wood. Therefore, the metal-strap has more influence on the property of bentwood materials. The effect of the metal-strap thickness for bentwood was examined. The effect of metal-strap on the bending properties of Korean red pine(Pinus densiflora Sieb. et Zucc.)was investigated in this research. The metal-strap thickness is divided into 4 kinds such as 1.0, 0.8, 0.6, 0.4 mm. The specimens were selected by grain such as annual ring angles, flat grain and half-edge grain specimens. As a result of this study, the bending ability of 1.0, 0.8 mm, thickness of half-edge grain specimens was better than flat grain specimens but the result of 0.6, 0.4 mm were reversed. The bending ability of half-edge grain was better than flat grain and the grade was higher. When the processed specimens were dried, the radius of curvature(ROC) was decreased became drying-stress was not perfectly dispersed. An optimum drying-condition would deminish this phenomenon.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.33 no.4 s.111
• /
• pp.119-128
• /
• 2005

This study was carried out to obtain fundamental information of growth response of interior landscape plants under a fluorescent lighting, a sunlight at indoor. Ficus elastica Roxb. vu. decora Hort, Spathiphyllum 'Clevelandii', Codiaeum variegatum Blume var. pictum Mvell. Arg. 'Exalant' and Cordyline terminalis Kunth var. red edge Hort were examined under 100lux, 500lux, 1,000lux and 2,000lux light intensity consisted of fluorescent lighting and sunlight at indoor condition. Result of experiments are as follows; 1. A Ficus elastica Roxb. var. decora Hort plant growth status was better showed under fluorescent lighting than sunlight. A plant growth status showed the best result under 2,000lux light intensity of fluorescent lighting in cases of all conditions. 2. A Spathiphyllum 'Clevelandii' showed the best effective adaptations under law intensity among experimental plants. A Spathiphyllum 'Clevelandii', plant growth status was better showed under fluorescent lighting than sunlight. A plant growth status showed the best result under 1,000lux light intensity of fluorescent lighting in cases of all conditions. 3. It need the best high establishment of fluorescent lighting among experimental plants for good plant growth. A Codiaeum variegatum Blume var. pictum Mvell. Arg. 'Exalant' plant growth status was better showed under fluorescent lighting than sunlight. A plant growth status was better showed under high light intensity in case of same light source. A plant growth status showed the best result under 2,000lux light intensity of fluorescent lighting. 4. A Cordyline terminalis Kunth var. red edge Hort plant growth status was better showed under fluorescent lighting than sunlight. but, A plant growth status was better showed under $500lux\sim1,000lux$ than 2,000lux in cases of all intensity of fluorescent lighting. while, A plant growth status was better showed under $1,000lux\sim2,000lux$ in cases of all intensity of sunlight.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.5
• /
• pp.471-476
• /
• 2010

In this paper, we propose an effective method that recognizes the vehicle license plate using RGB color information and back-propagation neural network algorithm. First, the image of the vehicle license plate is adjusted by the Mean of Blue values in the vehicle plate and two candidate areas of Red and Green region are classified by calculating the differences of pixel values and the final Green area is searched by back-propagation algorithm. Second, our method detects the area of the vehicle plate using the frequence of the horizontal and the vertical histogram. Finally, each of codes are detected by an edge detection algorithm and are recognized by error back-propagation algorithm. In order to evaluate the performance of our proposed extraction and recognition method, we have run experiments on a new car plates. Experimental results showed that the proposed license plate extraction is better than that of existing HSI information model and the overall recognition was effective.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.12
• /
• pp.63-73
• /
• 2009

This paper presents a vehicle detection method that uses convolution matching method based on a simple color information. An input image is expressed as 8 oriented color expression(Red, Green, Blue, White, Black, Cyan, Yellow, Magenta) considering an orientation of a pixel color vector. It makes the image very reliable and strong against changes of illumination condition or environment. This paper divides the vehicle detection into a hypothesis generation step and a hypothesis verification step. In the hypothesis generation step, the vehicle candidate region is found by vertical edge and shadow. In the hypothesis verification step, the convolution matching and the complexity of image edge are used to detect real vehicles. It is proved that the proposed method has the fast and high detection rate on various experiments where the illumination source and environment are changed.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.45-56
• /
• 2024

Faced with aging populations, declining resources, and limited agricultural productivity, rural areas in South Korea require innovative solutions. This study investigated the potential of drone-based vegetation indices (VIs) to analyze soybean growth patterns in open-field smart agriculture in Goesan-gun, Chungbuk Province, South Korea. We monitored multi-seasonal normalized difference vegetation index (NDVI) and the normalized difference red edge (NDRE) data for three soybean lots with different irrigation methods (subsurface drainage, conventional, subsurface drip irrigation) using drone remote sensing. Combining NDVI (photosynthetically active biomass, PAB) and NDRE (chlorophyll) offered a comprehensive analysis of soybean growth, capturing both overall health and stress responses. Our analysis revealed distinct growth patterns for each lot. LotA(subsurface drainage) displayed early vigor and efficient resource utilization (peaking at NDVI 0.971 and NDRE 0.686), likely due to the drainage system. Lot B (conventional cultivation) showed slower growth and potential limitations (peaking at NDVI 0.963 and NDRE 0.681), suggesting resource constraints or stress. Lot C (subsurface drip irrigation) exhibited rapid initial growth but faced later resource limitations(peaking at NDVI 0.970 and NDRE 0.695). By monitoring NDVI and NDRE variations, farmers can gain valuable insights to optimize resource allocation (reducing costs and environmental impact), improve crop yield and quality (maximizing yield potential), and address rural challenges in South Korea. This study demonstrates the promise of drone-based VIs for revitalizing open-field agriculture, boosting farm income, and attracting young talent, ultimately contributing to a more sustainable and prosperous future for rural communities. Further research integrating additional data and investigating physiological mechanisms can lead to even more effective management strategies and a deeper understanding of VI variations for optimized crop performance.

• Journal of Biosystems Engineering
• /
• v.28 no.1
• /
• pp.45-52
• /
• 2003

Red ginsengs are inspected manually by examining those in the dark room with back light illumination. Manual inspection is often influenced by physical condition of inspectors. Sometimes. the best grade, heaven. has some inner holes though it was inspected by a specialist. In order to resolve this problem, this study was performed to develop image processing algorithm to detect the inner holes in the x-ray image of ginseng. Because of little gray value difference between background and ginseng in the image. simple thresholding method was not appropriate. Modified watershed algorithm was used to differentiate the inner holes from background and normal ginseng body. Inner hole edge region detected by watershed algorithm consists of many number of blobs including normal portions. With line profile analysis with scanning one line at a time beginning the starting point. it shelved two peaks both ends representing extracting each blobs. in which setting threshold value as of lower peak value enabled us to obtain inner hole image. Once this procedure has to be done till the finishing point it is completing inner hole detection for one blob. Thus. conducting ail blobs by this procedure is completing inner detection of one whole ginseng. Detection results of the inner holes fer various size of red ginsengs were good even though there was small detection variation. 6.2%. according to position of x-rat tube.

• Horticultural Science & Technology
• /
• v.33 no.1
• /
• pp.143-148
• /
• 2015

A new Dianthus cultivar 'URI 2010-6' was selected among F1 progenies from a cross between interspecific hybrid 'Evergreen Emerald' as the seed parent and D. chinensis ' Ruby' as the pollen parent. In 2007, the cross w as made, and the seedlings of $F_1$ progenies were obtained and investigated. After three rounds of characteristic evaluation from 2008 to 2010, a clone was selected and registered as 'URI 2010-6' at the Korea Seed and Variety Service (plant variety protection number: 4431) in 2011. The flower of 'URI 2010-6' is caryophyllaceous, single type, and mainly bright red (Red, N79C) with secondary white (White, N155C) on the edge or as spots on the petal. The flower has diameter of 2.7 cm and length of 0.8 cm. This cultivar blooms continuously about 150 d on average and may be used as evergreen plant during winter months.

• Bulletin of the Korean Chemical Society
• /
• v.25 no.2
• /
• pp.298-300
• /
• 2004

An alternative molecular porphyrin-phthalocyanine aggregate was prepared and characterized with UV-visible and X-ray absorption spectroscopies. UV-visible experiments evidence 1-dimensional porphyrin-phthalo-cyanine array formed by mixing $SnTPPCl_2 ({\lambda}_{max}=429,\;{\varepsilon}=2.4{\times10^ 5 /M{\cdot}cm)\;and\;NiPc(OBu)_8({\lambda}_{max}=744 nm,\;{\varepsilon}= 2.0{\times}10^ 5 /M{\cdot}cm)$ in solution. In the UV-visible spectrum of the porphyrin-phthalocyanine array, $(SnPNiPc)_n$, a new Q-band appeared at 844 nm with decrease of the Q-band peak of $NiPc(OBu)_8$ at 744 nm. The red-shift of Q-band evidences an alternative porphyrin-phthalocyanine array formed in solution through metal-halide interaction rather than ${\pi}-{\pi}$ facial interaction, in which nickel of $NiPc(OBu)_8$ coordinates with chloride of $SnTPPCl_2$ through self assembly. Ni K-edge XANES (X-ray absorption near edge structure) spectra also support the axial ligation of nickel to chloride. The square planar structure of $NiPc(OBu)_8$ turns to an octahedral structure in (SnPNiPcSnP) by axial ligation. A higher energy-shift (0.2 eV) of the preedge peak of (SnPNiPcSnP) indicaties partial oxidation of nickel by charge transfer from NiPc$(OBu)_8$ to SnTPPCl$_2$.