• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.194-203
• /
• 2021

Virtual reality is being increasingly used for healing and therapy for mental health. In this study, we developed VR-based immersive content that enables virtual travel without the limitations of time and physical conditions. We aim to develop and produce VR content for relaxation and meditation using the beautiful natural scenery. To make realistic and immersive content, we took a video of natural sceneries with a small UAV connected to a VR camera. The content was developed through stitching, video editing and post-processing of the initially captured video data, and then the created VR video was inserted into the VR device. The produced content will be helpful for stress and used to heal the mind and body of exhausted modern people by providing the place with great scenery and sound in an immersive way at any time.

• International Journal of Contents
• /
• v.18 no.1
• /
• pp.98-104
• /
• 2022

With Unity creating footage is possible by using 3D motion, 2D motion, particular, and sound. Even post-production video editing is possible by combining the footage. In particular, Cinemachine, a suite of camera tools for Unity, that greatly affects screen layout and the flow of video images, can implement most of the functions of a physical camera. Visual aesthetics can be achieved through it. However, as it is a part of a game engine. Thus, the understanding of the game engine should come first. Also doubts may arise as to how similar it is to a physical camera. Accordingly, the purpose of this study is to examine the advantages and cautions of virtual cameras in Cinemachine, and explore the potential for development by implementing storytelling directly.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.699-706
• /
• 2015

In recent years, as near-duplicate image has been increasing explosively by the spread of Internet and image-editing technology that allows easy access to image contents, related research has been done briskly. However, BoF (Bag-of-Feature), the most frequently used method for near-duplicate image detection, can cause problems that distinguish the same features from different features or the different features from same features in the quantization process of approximating a high-level local features to low-level. Therefore, a post-verification method for BoF is required to overcome the limitation of vector quantization. In this paper, we proposed and analyzed the performance of a post-verification method for BoF, which converts SIFT (Scale Invariant Feature Transform) descriptors into 128 bits binary codes and compares binary distance regarding of a short ranked list by BoF using the codes. Through an experiment using 1500 original images, it was shown that the near-duplicate detection accuracy was improved by approximately 4% over the previous BoF method.

• Journal of Fashion Business
• /
• v.24 no.1
• /
• pp.75-87
• /
• 2020

The purpose of this study is to find trends in new media fashion content by analyzing the fashion content of the official Instagram accounts of domestic fashion magazines that are being transformed by digital media. The framework for these analysis of fashion content type and methods of production is based on one used in an earlier research project. Empirical analysis is conducted on Vogue Korea's official Instagram accounts, using the highest number of major views as the secondary measure of interest. After screening for fashion content in posts on the Vogue Korea account for four months, 291 short video postings were extracted to analyze the number of views the postings received. The results were categorized as 'star', 'show/exhibition', 'product', 'shop', 'fashion film', 'designer', or 'event', included in the data are the number of postings by type and the number of views by post. Based on the characteristics of the creator and the editing, the posts were classified into 'professional production highlight', 'professional production private', 'UCC' or 'GIF' videos, the number of views per post were also collected. The research results show different levels of interest depending on the type of fashion content, and also on the way the videos were produced. The study also investigated how the combination of these two factors affects interest. When producing a new media fashion content, combining a 'star' type post with 'professional production private' video content was most popular. The selection of production method is therefore important even given the same type of content.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.393-402
• /
• 2022

Effective data management of underground facilities is very important in terms of human life. For this, input of up-to-date and high-accuracy data should be preceded. Therefore, it is important to have an efficient data input method. In this study, by developing a sewage facility site survey program using open source software, paper drawings could be replaced with tablet PCs. By using a tablet PC, figures and property information acquired from the field are transmitted in real time through a database server. PostGIS query is developed to automate structured editing to minimize manual work in constructing a GIS (Geographic Information System) database for sewage facilities. did. In addition, the database was built using the sewage facility GIS database building program. As a result of comparing and analyzing the existing sewage facility database construction, work process, and work time, the work process was simplified and work time was shortened. In addition, through simple customization of open source software, it will be able to be used for field surveys and database construction in other fields.

• Spatial Information Research
• /
• v.22 no.4
• /
• pp.39-47
• /
• 2014

The Yeongsan river estuary has a serious water quality problem due to the water stagnation and it is imperative to predict the changes of water quality for mitigating water pollution. EFDC(Environmental Fluid Dynamics Code) model was mainly utilized to predict the changes of water quality for the estuary. The EFDC modeling normally accompanies the large volume of modeling output. For checking the spatial distribution of the modeling results, post-processing for converting of the output is prerequisite and mainly post-processing program is EFDC_Explorer. However, EFDC_Explorer only shows the spatial distribution of the time series and this doesn't support overlay function with other thematic maps. This means the impossible to the connection analysis with a various GIS data and high dimensional analysis. Therefore, this study aims to develop a post-processing system of a EFDC output to use them as GIS layers. For achieving this purpose, a editing module for main input files, and a module for converting binary format into an ASCII format, and a module for converting it into a layer format to use in a GIS based environment, and a module for visualizing the reconfigured model result efficiently were developed. Using the developed system, result file is possible to automatically convert the GIS based layer and it is possible to utilize for water quality management.

• Journal of the Korea Computer Graphics Society
• /
• v.18 no.1
• /
• pp.23-28
• /
• 2012

In this paper, we present a new method for automatically synchronize captured facial expression data with its corresponding motion data. In a usual optical motion capture set-up, a detailed facial expression can not be captured simultaneously in the motion capture session because its resolution requirement is higher than that of the motion capture. Therefore, those are captured in two separate sessions and need to be synchronized in the post-process to be used for generating a convincing character animation. Based on the patterns of the actor's neck movement extracted from those two data, we present a non-linear time warping method for the automatic synchronization. We justify our method with the actual examples to show the viability of the method.

• Journal of Korean Elementary Science Education
• /
• v.36 no.4
• /
• pp.428-438
• /
• 2017

The purpose of this study is to analyze the visual attention of elementary school students according to the editorial design of the 2007 2009 revised elementary science textbook 'Structure and function of our body'. For this purpose, eye movements were collected while elementary school students were watching real textbooks wearing mobile eye tracker. The BeGaze 3.7 program of SMI company was used analyzing eye movements. Twenty-six elementary school students participated voluntarily in mobile tracking research. Elementary students learned the contents of textbook related to 'digestive organ' and 'respiratory organ' by using double reading learning strategy. The results of this study are as follows. First, as a result of pre- and post-knowledge tests, there was no statistically significant difference in learning effect between 2007 revised and 2009 revised textbook editing design. Second, elementary school students tended to give more visual attention to text than textbook illustrations. Third, the selective attention and persistent attention of elementary students showed a very strong positive correlation (.940), but the selective attention and self-control showed a strong positive correlation (.499). Fourth, students with high level of attention and low level showed high visual occupancy in text than in illustrations. Fifth, elementary school students preferred the 2009 revised science textbook to the 2007 revised.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.145-150
• /
• 2020

최근 음성인식 분야에서 신경망 기반의 종단간 모델이 제안되고 있다. 해당 모델들은 음성을 직접 입력받아 전사된 문장을 생성한다. 음성을 직접 입력받는 모델의 특성상 데이터의 품질이 모델의 성능에 많은 영향을 준다. 본 논문에서는 이러한 종단간 모델의 문제점을 해결하고자 음성인식 결과를 후처리하기 위한 멀티모달 기반 모델을 제안한다. 제안 모델은 음성과 전사된 문장을 입력 받는다. 입력된 각각의 데이터는 Encoder를 통해 자질을 추출하고 주의집중 메커니즘을 통해 Decoder로 추출된 정보를 전달한다. Decoder에서는 전달받은 주의집중 메커니즘의 결과를 바탕으로 후처리된 토큰을 생성한다. 본 논문에서는 후처리 모델의 성능을 평가하기 위해 word error rate를 사용했으며, 실험결과 Google cloud speech to text모델에 비해 word error rate가 8% 감소한 것을 확인했다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.3-8
• /
• 2021

인공지능 기술이 발달함에 따라 기계번역 기술도 많은 진보를 이루었지만 여전히 기계번역을 통한 번역문 내에는 사람이 교정해야 하는 오류가 다수 포함되어있다. 이렇게 번역 모델에서 생성되는 오류를 교정하는 전문인력의 요구를 경감시키기 위하여 기계번역 사후교정 연구가 등장하였고, 해당 연구는 현재 WMT를 주축으로 활발하게 연구되고 있다. 이러한 사후교정 연구는 최근 도메인 특화 관점에서 주로 연구가 이루어지고 있으며 현재 많은 도메인에서 유의미한 성과를 내고 있다. 하지만 이런 연구들은 기존 번역문의 품질을 얼만큼 향상시켰는가에 초점을 맞출 뿐, 다른 도메인 특화 번역모델의 성능과 비교했을 때 얼마나 뛰어난지는 밝히지 않기 때문에 사후교정 연구가 도메인 특화에서 효과적으로 작용하는지 명확하게 알 수 없다. 이에 본 연구에서는 도메인 특화 번역 모델과 도메인 특화 사후교정 모델간의 성능을 비교함으로써, 도메인 특화에서 사후교정을 통해 얻을 수 있는 실제적인 성능을 검증한다. 이를 통해 사후교정이 도메인 특화 번역모델과 비교했을 때 미미한 수준의 성능을 보임을 실험적으로 확인하였고, 해당 실험 결과를 분석함으로써 향후 도메인특화 사후교정 연구의 방향을 제안하였다.