• Korean Journal of Remote Sensing
• /
• v.36 no.3
• /
• pp.449-460
• /
• 2020

Super-resolution is a technique used to reconstruct an image with low-resolution into that of high-resolution. Recently, deep-learning based super resolution has become the mainstream, and applications of these methods are widely used in the remote sensing field. In this paper, we propose a super-resolution method based on the deep back-projection network model to improve the satellite image resolution by the factor of four. In the process, we customized the loss function with the edge loss to result in a more detailed feature of the boundary of each object and to improve the stability of the model training using generative adversarial network based on Wasserstein distance loss. Also, we have applied the detail preserving image down-scaling method to enhance the naturalness of the training output. Finally, by including the modified-residual learning with a panchromatic feature in the final step of the training process. Our proposed method is able to reconstruct fine features and high frequency information. Comparing the results of our method with that of the others, we propose that the super-resolution method improves the sharpness and the clarity of WorldView-3 and KOMPSAT-2 images.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2004.05a
• /
• pp.44-45
• /
• 2004

With the development of informational machinery and tools in the modern industrial society, the image is expressed diversely as tools of informational transmission and artistic communication. This image is revival equipment and transmissional media in which sound and light are comprehensively formed. The image's intuitive and sensational expressivity can revive subjects and express a fiction, a reality, a nonfiction, and a virtual reality as a communication tool that has synchronicity and the medium of meaning. Because of this, the domain of the image will be gradually extended in the future, and the world of cognizance that can be detected across our living space will absorb the image diversely and react. In this context, the investigator examined what influence image media and equipments have in space as spatial equipments, based on the recognition of cerrelation among the image, space, and mankind, namely, the environmental meaning the mage and the space contain. Therefore, this study was conducted from the aspects of relationship establishment between image equipments that are ever expansive to a variety of domains and the space that accommodates the equipments. As study findings, the influences the image equipments have on space and their expressional features are presented in three aspects: 'the expressional medium of mutual synergy','metaphysical ultra-epithelial space constituent',' and 'object'. This study seems to be meaningful in that we can expect the spatial approach method by purposes and spatial layout of image structures, with this study, through analyzing the meaning of relationship between image equipments and space.

• Science of Emotion and Sensibility
• /
• v.18 no.4
• /
• pp.3-14
• /
• 2015

This study has extracted observation data by spatial factor for the analysis of subjects' selective attention with the objects of public space at the entrance of subway stations. The methods extracting observation data can be summarized as the following. First, the frequency analysis by lattice was prevalent for those methods, but there is a limitation to the analysis of the observation data. On the contrary, the method extracting observation data by factor applied in this study can make it clear if any sight is concentrated on any particular factors in a space. Second, the results from the extracted data corresponding to the observation area can be objectified while the method setting up the observation area by applying the radius of fovea. Third, time-sequential trace of observation results of relevant factors was possible through hourly analysis of spatial factors. The consideration of the results of "corresponding spatial scope" which is the object of this study will reveal that the more the observation time, the less the degree of attention it receives. Fourth, the frequency of observation superiority was applied for the analysis of the sections with selective attention by time scope; this revealed that men and women had intensive observation in time scope I (52.4 %) and in time scope IV (24.0 %), respectively.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.658-670
• /
• 2018

Busan Citizen Park has been taken as the research object in this paper to learn about the categories and types of resting facilities such as seats and Pergolas in the park and analyze the visitors' use patterns of bench and Pergolas. In addition, the analysis of the cultural features and preferences of bench and Pergolas will provide the basic data for the future design of resting facilities. After the research on the categories and types of bench and Pergolas and the evaluation factors through literature surveys, the type, location, and number of resting facilities including bench, Pergolas, sheds, etc. in the entire park have been investigated through field surveys. In addition, the behavioral map analysis has been created through the observation of the use patterns of bench and Pergolas in the morning and afternoon of each month, and the degree of preference and satisfaction of park bench and Pergolas has been grasped through questionnaires. The research results are as follows. Among the ten types of bench and Pergolas, the citizens like the mats and awnings + mats best. The environment is the most important factor for the mats with highest score, followed by the functional and regional factors. In addition, various activities such as eating in mats and sheds that block sunlight are Korean use patterns, which is very common in Korean daily life. These results show that bench and Pergolas in urban parks are not placed arbitrarily and the layout and design of bench and Pergolas should be completed based on behavior and preferences, which are influenced by cultural characteristics.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.592-597
• /
• 2020

Currently, river survey data is mainly performed by acquiring longitudinal and cross-sectional data of rivers using total stations or the GNSS(Global Navigation Satellite System). There is not much research that addresses the use of LiDAR(Light Detection and Ranging)systems for surveying rivers. This study evaluates the applicability of using LiDAR data for surveying rivers The Ministry of Land, Infrastructure and Transport recently launched a drone-based river fluctuation survey. Pilot survey projects were conducted in major rivers nationwide. Studies related to river surveying were performed using the ground LiDAR(Light Detection And Ranging)system.Accuracy was ensured by extracting the linearity of the object and comparing it with the total station survey performance. Data on trees and other features were extracted to generate three-dimensional geospatial information for the point-cloud data on the ground.Deviations were 0.008~0.048m. and compared with the results of surveying GNSS and the use of drone LiDAR data. Drone LiDAR provided accurate three-dimensional spatial information on the entire target area. It was able to reduce the shaded area caused by the lack of surveying results of the target area. Analyses such as those of area and slope of the target sites are possible. Uses of drones may therefore be anticipated for terrain analyses in the future.

• Journal of KIISE
• /
• v.44 no.8
• /
• pp.813-821
• /
• 2017

Entity Linking find the meaning of an entity mention, which indicate the entity using different expressions, in a user's query by linking the entity mention and the entity in the knowledge base. This task has four challenges, including the difficult knowledge base construction problem, multiple presentation of the entity mention, ambiguity of entity linking, and NIL entity recognition. In this paper, we first construct the entity name dictionary based on Wikipedia to build a knowledge base and solve the multiple presentation problem. We then propose various methods for NIL entity recognition and solve the ambiguity of entity linking by training the support vector machine based on several features, including the similarity of the context, semantic relevance, clue word score, named entity type similarity of the mansion, entity name matching score, and object popularity score. We sequentially use the proposed two methods based on the constructed knowledge base, to obtain the good performance in the entity linking. In the result of the experiment, our system achieved 83.66% and 90.81% F1 score, which is the performance of the NIL entity recognition to solve the ambiguity of the entity linking.

• Cartoon and Animation Studies
• /
• s.34
• /
• pp.263-292
• /
• 2014

This research explores websites of comics museum provided by the Korean Manhwa Museum and the Kyoto International Manga Museum and is supposed to analyze the type of content and finding out features. Since both museums specialize in comics and provide diverse information related to comics and their museums, this research analyze them on the basis of three types of categories, which are public relations content, professional content, and exhibition/education content The result shows that both museums generally provide similar type of information and content even though there are small differences. Especially, they have common points in the way that both offer detailed information of museum facilities and about exhibition schedules and education programs. However, the goal they are aiming at shows a difference. Korea Manhwa Museum tries to have interactive communication with its site visitors using the bulletin board system and to update newly published comics and events frequently managing separate websites. Kyoto International Manga Museum seems to focus on promoting itself in order to have more museum visitors. It provides detailed information such as history of the museum building, the object of setting up the museum and so on. Also, it provides four different foreign language websites.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.3
• /
• pp.57-67
• /
• 2007

Researchers in mobile AR systems have so far put the value on the technical challenges involved in the limitations imposed from mobility. Beyond such immediate technical questions, however, are questions regarding the possible contents that are to be used for the user’s interaction in ubiquitous computing environment. Various aspects of context of user and environment can be utilized easily as well as effectively. Moreover, the environment will be equipped with lots of pervasive but invisible computing resources. However, it is difficult for users to have access to those computing resources. At the same time, as the smart appliances get to have more features, their user interfaces tend to become harder to use. Thus, in this paper, we propose Context-Aware Mobile Augmented Reality (CAMAR) system. In our system, users only need to take a picture of smart appliances with a built-in camera in a mobile device when they intend to control the appliances. It lets users interact with the smart appliances through personalized control interfaces on their mobile devices. Also, it supports enabling contents to be not only personalized but also shared selectively and interactively among user communities.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.30 no.2
• /
• pp.108-120
• /
• 2004

Object : Patients with facial asymmetry accompanying mandibular prognathism have various causes and clinical features. So, it is difficult to find a satisfactory treatment method functionally and esthetically. Every traditional classification and interpretation to find etiopathogenesis and/or to establish ideal surgical modality has many limitations because it can't be applied simply to various conditions of patients with facial asymmetry accompanying mandibular prognathism. Therefore, we employ a new classification to interpret more details of the morphologic change of mandible and the spatial change of mandible and maxilla. Materials and Methods : Using panoramic X-ray films, PA cephalograms and submentovertex films of 126 patients diagnosed with facial asymmetry accompanying mandibular prognathism as resources, the following results were gathered after analyzing each characteristics through distributing the patterns according to the morphological mandibular asymmetry and mandibular and maxillary spatial asymmetry. Results : Almost frequency of morphological mandibular asymmetry was shown. In case of condyle-ramus elongation and body elongation group, it's frequency was the highest. Higher frequency of compensating vertical growth was shown on the side of over growing maxilla in case of vertical length difference between left and right condyle-ramus. On the other hand, higher frequency of no compensating vertical growth difference between left and right side was shown in case of no vertical length difference in condyle-ramus. Spatial mandibular asymmetry generally occurred when there was no morphological mandibular asymmetry. Correlation between condyle length difference and condyle-ramus length difference between left and right side was very high, but correlation between condyle length difference and body length difference, and correlation between condyle length difference and body vertical length difference was low. Conclusion : In case of patients with facial asymmetry accompanying mandibular prognathism, it is suggested that various pattern of facial asymmetry is occurred by the independent growth of each unit rather than dependent growth of other unit by major growth unit abnormality. Due to the untypical pattern and the various asymmetry occurring according to the changes of each mandibular growth unit, it is considered that an appropriate surgical method should be searched based on the accurate recognition of the each pattern for patients with facial asymmetry accompanying mandibular prognathism.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.9
• /
• pp.794-806
• /
• 2017

It is essential to protect the national space assets and space environment safely as a space development country from the continuously increasing space debris. And Active Debris Removal(ADR) is the most active way to solve this problem. In this paper, we studied the Artificial Neural Network(ANN) for a stable recognition model of vision-based space debris tracking system. We obtained the simulated image of the space environment by the KARICAT which is the ground-based space debris clearing satellite testbed developed by the Korea Aerospace Research Institute, and created the vector which encodes structure and color-based features of each object after image segmentation by depth discontinuity. The Feature Vector consists of 3D surface area, principle vector of point cloud, 2D shape and color information. We designed artificial neural network model based on the separated Feature Vector. In order to improve the performance of the artificial neural network, the model is divided according to the categories of the input feature vectors, and the ensemble technique is applied to each model. As a result, we confirmed the performance improvement of recognition model by ensemble technique.