• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.959-974
• /
• 2021

Forel-Ule Index (FUI) is an index which classifies the colors of inland and seawater exist in nature into 21 gradesranging from indigo blue to cola brown. FUI has been analyzed in connection with the eutrophication, water quality, and light characteristics of water systems in many studies, and the possibility as a new water quality index which simultaneously contains optical information of water quality parameters has been suggested. In thisstudy, Ocean Colour-Climate Change Initiative (OC-CCI) based 4 km FUI was spatially downscaled to the resolution of 500 m using the Geostationary Ocean Color Imager (GOCI) data and Random Forest (RF) machine learning. Then, the RF-derived FUI was examined in terms of its correlation with various water quality parameters measured in coastal areas and its spatial distribution and seasonal characteristics. The results showed that the RF-derived FUI resulted in higher accuracy (Coefficient of Determination (R²)=0.81, Root Mean Square Error (RMSE)=0.7784) than GOCI-derived FUI estimated by Pitarch's OC-CCI FUI algorithm (R²=0.72, RMSE=0.9708). RF-derived FUI showed a high correlation with five water quality parameters including Total Nitrogen, Total Phosphorus, Chlorophyll-a, Total Suspended Solids, Transparency with the correlation coefficients of 0.87, 0.88, 0.97, 0.65, and -0.98, respectively. The temporal pattern of the RF-derived FUI well reflected the physical relationship with various water quality parameters with a strong seasonality. The research findingssuggested the potential of the high resolution FUI in coastal water quality management in the Korean Peninsula.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1281-1293
• /
• 2021

The recent launch of the GOCI-II enables South Korea to have the world's first capability in deriving the ocean color data at geostationary satellite orbit for about 20 years. It is necessary to develop a consistent long-term ocean color time-series spanning GOCI to GOCI-II mission and improve the accuracy through validation using in situ data. To assess the GOCI-II's early mission performance, the objective of this study is to compare the GOCI-II Chlorophyll-a concentration (Chl-a), Colored Dissolved Organic Matter (CDOM), and remote sensing reflectances (R_rs) through comparison with the GOCI data. Overall, the distribution of GOCI-II Chl-a corresponds with that of the GOCI over the Yellow Sea, Korea Strait, and the Ulleung Basin. In particular, a smaller RMSE value (0.07) between GOCI and GOCI-II over the summer Ulleung Basin confirms the GOCI-II data's reliability. However, despite the excellent correlation, the GOCI-II tends to overestimate Chl-a than the GOCI over the Yellow Sea and Korea Strait. The similar over-estimation bias of the GOCI-II is also notable in CDOM. Whereas no significant bias or error is found for R_rs at 490 nm and 550 nm (RMSE~0), the underestimation of R_rs at 443 nm contributes to the overestimation of GOCI-II Chl-a and CDOM over the Yellow Sea and the Korea Strait. Also, we show over-estimation of GOCI-II R_rs at 660 nm relative to GOCI to cause a possible bias in Total suspended sediment. In conclusion, this study confirms the initial reliability of the GOCI-II ocean color products, and upcoming update of GOCI-II radiometric calibration will lessen the inconsistency between GOCI and GOCI-II ocean color products.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.453-462
• /
• 2021

A lot of license plate data is required for car number recognition. License plate data needs to be balanced from past license plates to the latest license plates. However, it is difficult to obtain data from the actual past license plate to the latest ones. In order to solve this problem, a license plate recognition study through deep learning is being conducted by creating a synthetic license plates. Since the synthetic data have differences from real data, and various data augmentation techniques are used to solve these problems. Existing data augmentation simply used methods such as brightness, rotation, affine transformation, blur, and noise. In this paper, we apply a style transformation method that transforms synthetic data into real-world data styles with data augmentation methods. In addition, real license plate data are noisy when it is captured from a distance and under the dark environment. If we simply recognize characters with input data, chances of misrecognition are high. To improve character recognition, in this paper, we applied the DeblurGANv2 method as a quality improvement method for character recognition, increasing the accuracy of license plate recognition. The method of deep learning for license plate detection and license plate number recognition used YOLO-V5. To determine the performance of the synthetic license plate data, we construct a test set by collecting our own secured license plates. License plate detection without style conversion recorded 0.614 mAP. As a result of applying the style transformation, we confirm that the license plate detection performance was improved by recording 0.679mAP. In addition, the successul detection rate without image enhancement was 0.872, and the detection rate was 0.915 after image enhancement, confirming that the performance improved.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1657-1667
• /
• 2021

Anthropogenic activities and natural processes have been causes of land subsidence which is sudden sinking or gradual settlement of the earth's solid surface. Mexico City, the capital of Mexico, is one of the most severe land subsidence areas which are resulted from excessive groundwater extraction. Because groundwater is the primary water resource occupies almost 70% of total water usage in the city. Traditional terrestrial observations like the Global Navigation Satellite System (GNSS) or leveling survey have been preferred to measure land subsidence accurately. Although the GNSS observations have highly accurate information of the surfaces' displacement with a very high temporal resolution, it has often been limited due to its sparse spatial resolution and highly time-consuming and high cost. However, space-based synthetic aperture radar (SAR) interferometry has been widely used as a powerful tool to monitor surfaces' displacement with high spatial resolution and high accuracy from mm to cm-scale, regardless of day-or-night and weather conditions. In this paper, advanced interferometric approaches have been applied to get a time-series of land subsidence of Mexico City using four-year-long twenty ALOS PALSAR L-band observations acquired from Feb-11, 2007 to Feb-22, 2011. We utilized persistent scatterer interferometry (PSI) and small baseline subset (SBAS) techniques to suppress atmospheric artifacts and topography errors. The results show that the maximum subsidence rates of the PSI and SBAS method were -29.5 cm/year and -27.0 cm/year, respectively. In addition, we discuss the different subsidence rates where the study area is discriminated into three districts according to distinctive geotechnical characteristics. The significant subsidence rate occurred in the lacustrine sediments with higher compressibility than harder bedrock.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1631-1645
• /
• 2021

This research aims to provide the characteristics of the world's first active lidar sensor Atmospheric Laser Doppler Instrument (ALADIN) wind data and Geostationary Korea Multi Purpose Satellite 2A (GK2A) Atmospheric Motion Vector (AMV) data by comparing two wind data. As a result of comparing the data from September 2019 to August 1, 2020, The total number of collocated data for the AMV (using IR channel) and Mie channel ALADIN data is 177,681 which gives the Root Mean Square Error (RMSE) of 3.73 m/s and the correlation coefficient is 0.98. For a more detailed analysis, Comparison result considering altitude and latitude, the Normalized Root Mean Squared Error (NRMSE) is 0.2-0.3 at most latitude bands. However, the upper and middle layers in the lower latitudes and the lower layer in the southern hemispheric are larger than 0.4 at specific latitudes. These results are the same for the water vapor channel and the visible channel regardless of the season, and the channel-specific and seasonal characteristics do not appear prominently. Furthermore, as a result of analyzing the distribution of clouds in the latitude band with a large difference between the two wind data, Cirrus or cumulus clouds, which can lower the accuracy of height assignment of AMV, are distributed more than at other latitude bands. Accordingly, it is suggested that ALADIN wind data in the southern hemisphere and low latitude band, where the error of the AMV is large, can have a positive effect on the numerical forecast model.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_2
• /
• pp.1829-1836
• /
• 2021

Cloud detection means determining the presence or absence of clouds in a pixel in a satellite image, and acts as an important factor affecting the utility and accuracy of the satellite image. In this study, among the satellites of various advanced organizations that provide cloud detection data, we intend to perform quantitative and qualitative comparative analysis on the difference between the cloud detection data of GK-2A/AMI, Terra/MODIS, and Suomi-NPP/VIIRS. As a result of quantitative comparison, the Proportion Correct (PC) index values in January were 74.16% for GK-2A & MODIS, 75.39% for GK-2A & VIIRS, and 87.35% for GK-2A & MODIS in April, and GK-2A & VIIRS showed that 87.71% of clouds were detected in April compared to January without much difference by satellite. As for the qualitative comparison results, when compared with RGB images, it was confirmed that the results corresponding to April rather than January detected clouds better than the previous quantitative results. However, if thin clouds or snow cover exist, each satellite were some differences in the cloud detection results.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1773-1784
• /
• 2021

In order to minimize damage to oil spill accidents in the ocean, it is essential to collect a spilled area as soon as possible. Thus satellite-based remote sensing is a powerful source to detect oil spills in the ocean. With the recent rapid increase in the number of available satellites, it has become possible to generate a status report of marine oil spills soon after the accident. In this study, the oil spill area was calculated using various satellite images for the Symphony oil spill accident that occurred off the coast of Qingdao Port, China, on April 27, 2021. In particular, improving the accuracy of oil spill area determination was applied using high-resolution commercial satellite images with a spatial resolution of 2m. Sentinel-1, Sentinel-2, LANDSAT-8, GEO-KOMPSAT-2B (GOCI-II) and Skysat satellite images were collected from April 27 to May 13, but five images were available considering the weather conditions. The spilled oil had spread northeastward, bound for coastal region of China. This trend was confirmed in the Skysat image and also similar to the movement prediction of oil particles from the accident location. From this result, the look-alike patch observed in the north area from the Sentinel-1A (2021.05.01) image was discriminated as a false alarm. Through the survey period, the spilled oil area tends to increase linearly after the accident. This study showed that high-resolution optical satellites can be used to calculate more accurately the distribution area of spilled oil and contribute to establishing efficient response strategies for oil spill accidents.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.321-335
• /
• 2021

Particulate matter (PM10 and PM2.5 with a diameter less than 10 and 2.5 ㎛, respectively) can be absorbed by the human body and adversely affect human health. Although most of the PM monitoring are based on ground-based observations, they are limited to point-based measurement sites, which leads to uncertainty in PM estimation for regions without observation sites. It is possible to overcome their spatial limitation by using satellite data. In this study, we developed machine learning-based retrieval algorithm for ground-level PM10 and PM2.5 concentrations using aerosol parameters from Geostationary Ocean Color Imager (GOCI) satellite and various meteorological parameters from a numerical weather prediction model during January to December of 2019. Gradient Boosted Regression Trees (GBRT) and Light Gradient Boosting Machine (LightGBM) were used to estimate PM concentrations. The model performances were examined for two types of feature sets-all input parameters (Feature set 1) and a subset of input parameters without meteorological and land-cover parameters (Feature set 2). Both models showed higher accuracy (about 10 % higher in R2) by using the Feature set 1 than the Feature set 2. The GBRT model using Feature set 1 was chosen as the final model for further analysis(PM10: R2 = 0.82, nRMSE = 34.9 %, PM2.5: R2 = 0.75, nRMSE = 35.6 %). The spatial distribution of the seasonal and annual-averaged PM concentrations was similar with in-situ observations, except for the northeastern part of China with bright surface reflectance. Their spatial distribution and seasonal changes were well matched with in-situ measurements.

• Korean Journal of Environmental Agriculture
• /
• v.37 no.4
• /
• pp.283-290
• /
• 2018

BACKGROUND: Pesticide residue analysis is an essential activity in order to establish the food safety of agricultural products. Analytical approaches to the food safety are required to meet internationally the guideline of Codex (Codex Alimentarius Commission, CAC/GL 40). In this study, we developed a liquid chromatograph-tandem mass spectrometer (LC-MS/MS) method to determine the herbicide clopyralid in food matrixes. METHODS AND RESULTS: Clopyralid was extracted with aqueous acetonitrile containing formic acid and the extracts were mixed in a citrate buffer consisted of magnesium sulfate anhydrous, NaCl, sodium citrate dihydrate and disodium hydrogencitrate sesquihydrate followed by centrifugation. The supernatants were filtered through a nylon membrane filter and used for the analysis of clopyralid. The method was validated by accuracy and precision experiments on the samples fortified at 3 different levels of clopyralid. LC-MS/MS in positive mode was employed to quantitatively determine clopyralid in the food samples. Matrix-matched calibration curves were inearranged from 0.001 to 0.25 mg/kg with r2 > 0.994. The limits of detection and quantification were determined to be 0.001 and 0.01 mg/kg, respectively. There covery values of clopyralid for tified at 0.01 mg/kg in the control samples ranged from approximately 82 to 106% with relative standard deviations below 2 0%. CONCLUSION: The method developed in this study meets successfully the Codex guideline for pesticide residue analysis in food samples. This, the method could be applicable to determine pesticides in foods produced domestically and internationally.