• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.515-518
• /
• 2019

Semantic segmentation has remained as a challenging problem in the field of computer vision. Given the immense power of Convolution Neural Network (CNN) models, many complex problems have been solved in computer vision. Semantic segmentation is the challenge of classifying several pixels of an image into one category. With the help of convolution neural networks, we have witnessed prolific results over the time. We propose a convolutional neural network model which uses Fully CNN with deconvolutional pixel layers. The goal is to create a hierarchy of features while the fully convolutional model does the primary learning and later deconvolutional model visually segments the target image. The proposed approach creates a direct link among the several adjacent pixels in the resulting feature maps. It also preserves the spatial features such as corners and edges in images and hence adding more accuracy to the resulting outputs. We test our algorithm on Karlsruhe Institute of Technology and Toyota Technologies Institute (KITTI) street view data set. Our method achieves an mIoU accuracy of 92.04 %.

• Korean Journal of Remote Sensing
• /
• v.26 no.3
• /
• pp.335-346
• /
• 2010

Recently, ESA (European Space Agency) has launched CryoSAT-2 for polar ice observations. CryoSAT-2 is equipped with a SIRAL (SAR/interferometric radar altimeter), which is a high spatial resolution radar altimeter. Conventional altimeters cannot measure a precise three-dimensional ground position because of the large footprint diameter, while SIRAL altimeter system accomplishes a precise three-dimensional ground positioning by means of interferometric synthetic aperture radar technique. In this study, we developed an efficient SIRAL SARIn mode processing technique to measure a precise three-dimensional ground position. We first simulated SIRAL SARIn RAW data for the ideal target by assuming the flat Earth and linear flight track, and second accessed the precision of three-dimensional geopositioning achieved by the proposed algorithm. The proposed algorithm consists of 1) azimuth processing that determines the squint angle from Doppler centroid, and 2) range processing that estimates the look angle from interferometric phase. In the ideal case, the precisions of look and squint angles achieved by the proposed algorithm were about -2.0 ${\mu}deg$ and 98.0 ${\mu}deg$, respectively, and the three-dimensional geopositioning accuracy was about 1.23 m, -0.02 m, and -0.30 m in X, Y and Z directions, respectively. This means that the SIRAL SARIn mode processing technique enables to measure the three-dimensional ground position with the precision of several meters.

• Korean Journal of Remote Sensing
• /
• v.24 no.1
• /
• pp.79-89
• /
• 2008

Irregular temporal sampling is a common feature of geophysical and biological time series in remote sensing. This study proposes an on-line system for reconstructing observation image series contaminated by noises resulted from mechanical problems or sensing environmental condition. There is also a high likelihood that during the data acquisition periods the target site corresponding to any given pixel may be covered by fog or cloud, thereby resulting in bad or missing observation. The surface parameters associated with the land are usually dependent on the climate, and many physical processes that are displayed in the image sensed from the land then exhibit temporal variation with seasonal periodicity. A feedback system proposed in this study reconstructs a sequence of images remotely sensed from the land surface having the physical processes with seasonal periodicity. The harmonic model is used to track seasonal variation through time, and a Gibbs random field (GRF) is used to represent the spatial dependency of digital image processes. The experimental results of this simulation study show the potentiality of the proposed system to reconstruct the image series observed by imperfect sensing technology from the environment which are frequently influenced by bad weather. This study provides fundamental information on the elements of the proposed system for right usage in application.

• Korean Journal of Remote Sensing
• /
• v.25 no.6
• /
• pp.465-474
• /
• 2009

Convective/stratiform radar echo classification schemes by Steiner et al. (1995) and Biggerstaff and Listemaa (2000) are examined on a monsoonal front during the summer monsoon-Changma period, which is organized as a cloud cluster with mesoscale convective complex. Target radar is S-band with wavelength of 10cm, spatial resolution of 1km, elevation angle interval of 0.5-1.0 degree, and minimum elevation angle of 0.19 degree at Jindo over the Korean Peninsula. For verification of rainfall amount retrieved from the echo classification, ground-based rain gauge observations (Automatic Weather Stations) are examined, converting the radar echo grid data to the station values using the inverse distance weighted method. Improvement from the echo classification is evaluated based on the correlation coefficient and the scattered diagram. Additionally, an optimal use method was designed to produce combined rainfalls from the radar echo and Tropical Rainfall Measuring Mission Precipitation Radar (TRMM/PR) data. Optimal values for the radar rain and TRMM/PR rain are inversely weighted according to the error variance statistics for each single station. It is noted how the rainfall distribution during the summer monsoon frontal system is improved from the classification of convective/stratiform echo and the use of the optimal use technique.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.4
• /
• pp.55-64
• /
• 2021

In this study, the operation method and accuracy of Terrestrial Laser Scanner(TLS) are reviewed and discussed by experimental measurements, and guidelines of TLS surveying operation are proposed. Ground control points and TLS station points were measured by TS and/or GPS, in TLS observation experiments, and wood targets were used which designed by this study team. RMSE accuracy of TLS scan shows that TLS surveying operation can be used in the topographic mapping of 1/250 scale and level of 1/100 BIM, the drone data also used in TLS data completeness. Additionally, as the results of the field experiment, the guidelines for TLS surveying operartions were proposed.

• Journal of Environmental Science International
• /
• v.28 no.2
• /
• pp.191-201
• /
• 2019

This study suggested a vegetation restoration plan for a coastal area where the ecosystem conservation fund return project, targeting the whole area of Dalmaji-gil, located in Haeundae, Busan. After distinguishing if it would be a proper site for the operation of the ecosystem conservation fund return project by analyzing the ecological environment, human environment, and the current status of land owners, the target species for vegetation restoration was determined, and the facilities and programs were selected in accordance with the spatial division of the biosphere reserve. The basic direction is as follows. First, is the expansion of green space and the securement of life habitats downtown. Second, is the conservation of core areas by separating the conserved area from the space for use. Third, is the establishment of ecological resting space and the reinforcement of an ecological educational programs. The significance of this study is to suggest a vegetation restoration plan of a coastal area, fully utilizing the existing vegetation of the subject area, by suggesting the land use and flow planning, environmental improvement (vegetation restoration) plan, life habitats establishment plan, planting plan, and hydrologic plan, facilities, maintenance, and monitoring plan based on the basic direction. This study would provide useful basic data for ecosystem conservation and restoration in the Korean Peninsula, surrounded by the ocean on three sides.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.186-189
• /
• 2019

Image inpainting is an image processing technique that restores an image by naturally filling the empty or damaged regions in an image. In this paper, we present a new image inpainting technique that can suppress the generation of texture garbage which is one of the artifacts of existing exemplar-based image inpainting. Unlike the existing technique, only the stationary source patch is sampled as the exemplar patch based on the assumption of spatial stationarity of the texture. This prevents the texture garbage, which is an inconsistent piece of texture from being copied to the target region. Experimental results show that the texture synthesis using the proposed method produces more natural inpainting results than the existing method.

• Journal of Korean Society of Water Science and Technology
• /
• v.26 no.6
• /
• pp.43-51
• /
• 2018

In order to systematically and scientifically manage the organic and heavy metals against sediment at Daecheon Port, this study conducted particle composition, organic materials and heavy metals irradiation studies of sediments. Analysis of the grain size composition of sediments in the target study area showed the distribution characteristics of the mix of sand, silt and clay. That is, Station C (Stn. C) showed superior by fine-grained sediment, Station A and B (Stn. A and B) showed superior by coarse-grained sediment. The organic matter(COD, TOC, and IL) of Stn. C was appeared to be heavily polluted more than Stn. A and B. These data for the spatial properties in sediment showed that organic matter was related positively to the sediment silt-clay content. Also, in the case of heavy metals contamination in surface sediments, Stn. C was higher than Stn. A and B. Particularly, at the Stn. C, high organic matter concentration and C/N ratio value( >10) indicated that the sediment was composed highly of land-derived organic matter. From these results, it considered that the correlation analysis among to silt-clay, organic matter and heavy metal was found to have a good interrelationship.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.35 no.5
• /
• pp.132-138
• /
• 2021

Artificial intelligence technology sheds light on new ways of innovating acupuncture research. As acupoint selection is specific to target diseases, each acupoint is generally believed to have a specific indication. However, the specificity of acupoint selection may be not always same with the specificity of acupoint indication. In this review, we propose that the specificity of acupoint indication can be inferred from clinical data using reverse inference. Using forward inference, the prescribed acupoints for each disease can be quantified for the specificity of acupoint selection. Using reverse inference, targeted diseases for each acupoint can be quantified for the specificity of acupoint indication. It is noteworthy that the selection of an acupoint for a particular disease does not imply the acupoint has specific indications for that disease. Electronic medical record includes various symptoms and chosen acupoint combinations. Data mining approach can be useful to reveal the complex relationships between diseases and acupoints from clinical data. Combining the clinical information and the bodily sensation map, the spatial patterns of acupoint indication can be further estimated. Interoperable medical data should be collected for medical knowledge discovery and clinical decision support system. In the era of artificial intelligence, machine learning can reveal the associations between diseases and prescribed acupoints from large scale clinical data warehouse.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.4
• /
• pp.130-133
• /
• 2021

Recently, as the expansion of the metaverse accelerated due to the spread of the non-face-to-face trend after the COVID-19 pandemic, various metaverse platforms using it have appeared. In this study, we propose research and development of a virtual reality spatial psychological counseling service platform utilizing the advantages of metaverse. A counseling service platform was developed through virtual reality hardware including Unity 3D game engine and Head Mounted Display. Counseling participants create and participate in their own avatars, and counseling facilitators respond to the situation and environment of the counseling target in various virtual environments. It was attempted to improve the efficiency of the counseling service by allowing the space and counselor avatar to be selected. Furthermore, various interactions were implemented, and development was carried out so that it could be extended and utilized for social activities such as group counseling and general meetings and presentations. In the future, through additional research and development, we will prove the practical effectiveness of the psychological counseling service platform developed by conducting clinical trials under the support of psychological counseling experts and participation in actual counseling.