• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.341-348
• /
• 2020

The ability to extract useful information from an image, such as the human eye, is an interface technology essential for AI computer implementation. The building recognition technology has a lower recognition rate than other image recognition technologies due to the various building shapes, the ambient noise images according to the season, and the distortion by angle and distance. The computer vision based building recognition algorithms presented so far has limitations in discernment and expandability due to manual definition of building characteristics. This paper introduces the deep learning CNN (Convolutional Neural Network) model, and proposes new method to improve the recognition rate even by changes of building images caused by season, illumination, angle and perspective. This paper introduces the partial images that characterize the building, such as windows or wall images, and executes the training with whole building images. Experimental results show that the building recognition rate is improved by about 14% compared to the general CNN model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1434-1442
• /
• 2019

In this paper, the channel change was continuously measured for 24 hours from July 5, 2017 on the coast near Deokjeok-do, Incheon. The underwater channel has various channel environment characteristics as the change in the time axis and the change in the frequency axis occurs in real time, and the underwater communication performance decreases due to the multipath fading and the Doppler effect. Therefore, in this study, we performed the OFDM system performance analysis in the underwater channel environment by applying the repetitive transmission diversity scheme in the time and frequency domain to improve the communication performance in the real-world underwater communication environment. Using the collected data, we compared the channel environment in the time and frequency domain and analyzed the BER performance according to the pilot spacing and the number of repetitive transmissions in the time and frequency axis.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.57 no.4
• /
• pp.351-364
• /
• 2021

In this study, the vertical distribution of giant jellyfish analyzed echo counting method and such survey methods as sighting and trawl were used to compare its density estimates. In May and July 2021, surveys were conducted in the East China Sea and the coastal waters of Korea. As a result, Nemopilema nomurai were evenly distributed in all water layers in East China Sea in May and July. When considered the correlation by each survey methods, it is possible to identify jellyfish in the surface area by sighting method and using sampling net; however, it has a low correlation with acoustic estimates due to marine environmental factor such as weather condition, wind and atmospheric pressure. Therefore, the result can be utilized by basic data when estimating jellyfish's distribution patterns and density estimates from each survey methods hereafter.

• Journal of the Korean earth science society
• /
• v.39 no.6
• /
• pp.555-567
• /
• 2018

In order to identify the characteristics of sea surface temperature (SST) differences between microwave SST from GCOM-W1/AMSR2 and in-situ measurements in the western coast of Korea, a total of 6,457 collocated matchup data were produced using the in-situ temperature measurements from marine buoy stations (Deokjeokdo, Chilbaldo, and Oeyeondo) from July 2012 to December 2017. The accuracy of satellite microwave SSTs was presented by comparing the ocean buoy data of Deokjeokdo, Chilbaldo, and Oeyeondo stations with the AMSR2 SST data more than five years. The SST differences between the microwave SST and the in-situ temperature measurements showed some dependence on environmental factors, such as wind speed and water temperature. The AMSR2 SSTs were tended to be higher than the in-situ temperature measurements during the daytime when the wind speed was low ($<6ms^{-1}$). On the other hand, they showed positive deviation increasingly as the wind speed increased for nighttime. In addition, increasing tendency of SST differences was related to decreasing sensitivity of microwave sensors at low temperatures and data contamination by land. A monthly analysis of the SST difference showed that unlike the previous trend, which was known to be the largest in winter when strong winds were blowing, the SST difference was largest in summer in Deokjeokdo and Chilbaldo buoy stations. This seemed to be induced by differential tidal mixing at the collocated matchup points. This study presented problems and limitations of the use of microwave SSTs with high contribution to the SST composites in the western coastal region off the Korean peninsula.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.429-434
• /
• 2002

The Synthetic Aperture Radar (SAR) data are considered to contain the greatest amount of information among various microwave techniques developed for measuring ocean variables from aircraft or satellites. They have the potential of measuring wavelength, wave direction and wave height of the ocean waves. But, it is difficult to retrieve significant ocean wave heights and surface current from conventional SAR data, since the imaging mechanism of ocean waves by a SAR is determined by the three basic modulation processes arise through the tilt modulation, hydrodynamic modulation and velocity bunching which are poorly known functions. Along-Track Interferometric (ATI) SAR systems can directly detect the Doppler shift associated with each pixel of a SAR image and have been used to estimate wave fields and surface currents. However, the Doppler shift is not simply proportional to the component of the mean surface current. It includes also contributions associated with the phase velocity of the Brags waves and orbital motions of all ocean waves that are longer than Brags waves. In this paper, we have developed a new method for extracting the surface current vector using multiple-frequency (L- & C-band) ATI SAR data, and have generated surface wave height information.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.740-743
• /
• 2006

We identify two distinct finer-scale frontal bands: 'Mainland China Coastal Front' (MCCF) and 'Kuroshio Front' (KF). The MCCF is along the 50-m isobath with large temperature gradient. The front is a boundary between the Mainland China Coastal Current and the offshore shelf waters. On the other hand, the KF is extending from the northeastern coast of Taiwan toward the northeast and into the shelf of south ECS. It forms a broad semicircle-shape and curving along 100-m isobath, it also deviates from eastward at around 26.5N-122E and leaves the shelf of ECS. This front should be the boundary between the Kuroshio water and the other shelf waters.

• Journal of Korean Society for Atmospheric Environment
• /
• v.15 no.E
• /
• pp.39-43
• /
• 1999

To help idntify the potential sources of volatile organic sulfur compounds within the continental environment, we have conducted preliminary measurements of dimethylsulfide(DMS) during field campains held from three reference sites. These sampling sites were located within a waste reclamation facility in Won Ju City, Kang Won Province. The results of our measurements showed that DMS levels spanned over 1 to 55 pptv with a mean and 1 standard deviation(1SD) of 12 and 18 pptv(N=13). In a comparison of the data derived from the strongest sources, i.e., oceanic environment, the DMS levels in thre reclamation facility were jpronouncingly low with high day-to-night concentration ratios. It was noted that a significant difference in DMS levels between daytime and nighttime periods was mainly driven by a few exceptional data measured during daytime. Despite limitations of our measurement data in deriving meaningful interpretations of spatiotemporal distributions of DMS in inland facilities, the existence of extraordinary trends, i.e., especially "lower-than-expectedL" DMS values, can be explained in terms of mixed effects of several factors. Most importantly, we can infer that the rates of DMS production and of its destruction in the study site are at or near steady-state condition. Another possibility is that DMS is not adequate enough to explain the generally malordorous environment of reclamation sites, of particular in Won Ju area.n Ju area.

• Journal of environmental and Sanitary engineering
• /
• v.21 no.4 s.62
• /
• pp.61-76
• /
• 2006

A Line Density algorithm was developed to quantify the sea surface temperature distribution using NOAA Sea Surface Temperature(SST) data and Geographic Information Systems(GIS), In addition, a GIS based automation model was designed to extract the Line Density Indices were determined by applying K-means Cluster. SST data in terms of March to May obtained on the coastal area of the Uljin from 2001 to 2004 in spring were used to make two data sets of average sea water temperature map in terms of year as well as month. From the result it was formed that water temperature gradient in April was the strongest among the other months, In particular very strog formation of oceanic front as well as temperature gradients were observed in front of the coastal area around Wonduk and Jukbyeon countries. Because those coastal area is a confront zone of two cold and a warm. It is expected that the development of a Line Density Algorithm would contribute to quantify of the SST for the research of Sea Surface Front(SSF) related to marine life management and the sea environmental conservation.

• Ocean and Polar Research
• /
• v.31 no.4
• /
• pp.401-414
• /
• 2009

Yellow Sea Buoy (YSB) was moored in the center of the Yellow Sea at 35$^{\circ}$51'36"N, 124$^{\circ}$34'42"E, on 12 September 2007. YSB is a large buoy of 10 m diameter, and as such is more durable against collision by ships and less likely to be lost or removed by fishing nets compared to small ordinary buoys of 2.3 m diameter. YSB is equipped with 12 kinds of oceanic and meteorologic instruments, and transfers its realtime observation data to KORDI through ORBCOMM system every 1 hour. Data on ocean winds, air temperature, air pressure, and sea temperature appear to be accurate, while water property sensors (AAQ1183), which are sensitive to fouling, are producing errors. YSB (2007), Ieodo ocean research station (2003), and Gageocho ocean research station, which was completed in October 2009, will establish the 2 degrees interval by latitude in the Yellow Sea, and they will contribute though the 'Operational Oceanography System' as the important realtime observation network.

• Journal of Korea Water Resources Association
• /
• v.31 no.5
• /
• pp.613-620
• /
• 1998

Field and laboratory studies of the near field behavior of the San Francisco ocean outfall were reported. The data sets cover broad ranges of discharge conditions and oceanic conditions, and are associated with a typical type of outfall discharges with multiport diffusers. The laboratory data sets were obtained in density-stratified towing tanks to replicate the field tests. Model studies of wastefield behavior using these data sets were predicted by the mathematical models UM, UDKHDEN, RSB, and CORMIX2 for minimum dilution, the height to top of wastefield, and wastefield thickness. In this paper, the results are discussed and compared measurements with mathematical model predictions. The hydraulic model studies reproduced the major features observed in the field. It also afforded considerable insight into the mechanics of mixing of multiport risers which could have been obtained neither from the field test nor the mathematical models.