• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1403-1410
• /
• 2020

Recently, as interest in non-face-to-face experiences and services increases, the demand for web video contents that can be easily consumed using mobile devices such as smartphones or tablets is rapidly increasing. To cope with these requirements, in this paper we propose a technique to efficiently produce video contents that can provide experience of visiting famous places (i.e., stage tour) in animation or movies. To this end, an image dataset was established by collecting images of stage areas using Google Maps and Google Street View APIs. Afterwards, a deep learning-based style transfer method to apply the unique style of animation videos to the collected street view images and generate the video contents from the style-transferred images was presented. Finally, we showed that the proposed method could produce more interesting stage-tour video contents through various experiments.

• Electronics and Telecommunications Trends
• /
• v.35 no.4
• /
• pp.91-102
• /
• 2020

Recently, generative adversarial networks (GANs) is a field of research that has rapidly emerged wherein many studies conducted shows overwhelming results. Initially, this was at the level of imitating the training dataset. However, the GAN is currently useful in many fields, such as transformation of data categories, restoration of erased parts of images, copying facial expressions of humans, and creation of artworks depicting a dead painter's style. Although many outstanding research achievements have been attracting attention recently, GANs have encountered many challenges. First, they require a large memory facility for research. Second, there are still technical limitations in processing high-resolution images over 4K. Third, many GAN learning methods have a problem of instability in the training stage. However, recent research results show images that are difficult to distinguish whether they are real or fake, even with the naked eye, and the resolution of 4K and above is being developed. With the increase in image quality and resolution, many applications in the field of design and image and video editing are now available, including those that draw a photorealistic image as a simple sketch or easily modify unnecessary parts of an image or a video. In this paper, we discuss how GANs started, including the base architecture and latest technologies of GANs used in high-resolution, high-quality image creation, image and video editing, style translation, content transfer, and technology.

• Publications of The Korean Astronomical Society
• /
• v.13 no.1 s.14
• /
• pp.39-54
• /
• 1998

We have developed solar observational system in the department of Astronomy & Space Sciences of KyungHee University, in order to monitor solar activities and construct solar database for space weather forecasting at maximum of 23rd solar cycle, as well as an solar education and exercise for undergraduate students. Our solar observational system consists of the full disk monitoring system and the regional observation system for H a fine structure. Full disk monitoring system is made of an energy rejection filter, 16cm refractor, video CCD camera and monitor. Monitored data are recorded to VHS video tape and analog output of video CCD can be captured as digital images by the computer with video graphic card. Another system for regional observation of the sun is made of energy rejection filter, 21cm Schmidt-Cassegrain reflector, H a filter with 1.6A pass band width and $375\times242$ CCD camera. We can observe H a fine structure in active regions of solar disk and solar limb, by using this system. We have carried out intense solar observations for a test of our system. It is found that Quality of our H a image is as good as that of solar images provided by Space Environmental Center. In this paper, we introduce the basic characteristics of the KyungHee Solar Observation System and result of our solar observations. We hope that our data should be used for space weather forecasting with domestic data of RRL(Radio Research Laboratory) and SOFT(SOlar Flare Telescope).

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.1057-1060
• /
• 1999

For efficient storage and retrieval of large video data sets, automatic video scene change detection is a necessary tool. Video scene changes fall into two categories, namely fast and gradual scene changes. The gradual scene change effects include, dissolves, wipes, fades, etc. Although currently existing algorithms are able to detect fast scene changes quite accurately, the detection of gradual scene changes continue to remain a difficult problem. In this paper, among various gradual scene changes, we focus on dissolves. The algorithm uses a subset of the entire video, namely the sequence of DC images, for improvement of detection velocity

• Journal of Korea Multimedia Society
• /
• v.21 no.7
• /
• pp.795-801
• /
• 2018

In these days, various technologies to provide a service of high quality of 360 VR media contents is being studied and developed. However, rendering high-quality of media images is very difficult with the limited resources of HMD (Head Mount Display). In this paper, we designed and implemented a 360 VR Player for high quality 360 tiled video image render to HMD. Furthermore, we developed multi-resolution-based Foveated Rendering technology. By conducting several experiments, We have confirmed that it improved the performance of video rendering far more than existing tiled video rendering technology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.4
• /
• pp.1128-1139
• /
• 2012

With the development of three-dimensional display and related technologies, depth video coding becomes a new topic and attracts great attention from industries and research institutes. Because (1) the depth video is not a sequence of images for final viewing by end users but an aid for rendering, and (2) depth video is simpler than the corresponding color video, fast algorithm for depth video is necessary and possible to reduce the computational burden of the encoder. This paper proposes a fast mode decision algorithm for depth video coding based on depth segmentation. Firstly, based on depth perception, the depth video is segmented into three regions: edge, foreground and background. Then, different mode candidates are searched to decide the encoding macroblock mode. Finally, encoding time, bit rate and video quality of virtual view of the proposed algorithm are tested. Experimental results show that the proposed algorithm save encoding time ranging from 82.49% to 93.21% with negligible quality degradation of rendered virtual view image and bit rate increment.

• Journal of Broadcast Engineering
• /
• v.18 no.6
• /
• pp.850-858
• /
• 2013

In this paper, we propose a method of frame synchronization for stereoscopic 3D video to solve the viewing problem caused by synchronization errors between a left video and a right video using the temporal frame difference image depending on the movement of objects. Firstly, we compute two temporal frame difference images from the left video and the right video which are corrected the vertical parallax between two videos using rectification, and calculate two horizontal projection profiles of two temporal frame difference images. Then, we find a pair of synchronized frames of the two videos by measuring the mean of absolute difference (MAD) of two horizontal projection profiles. Experimental results show that the proposed method can be used for stereoscopic 3D video, and is robust against Gaussian noise and video compression by H.264/AVC.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10B
• /
• pp.1093-1103
• /
• 2009

In this paper, we propose a new depth map based distributed multi-view video coding algorithm through an efficient side information generation. A distributed video coding scheme corrects errors between an original image and side information generated at a decoder by using channel coding techniques. Therefore, the more accurate side information is generated, the better performance of distributed video coding scheme is achieved. In the proposed algorithm, a distributed video coding scheme is applied to multi-view video coding based on depth map. Side information is also generated from images of adjacent views through 3D warping by using a depth map and is also combined with MCTI(motion compensated temporal interpolation) which uses images on a temporal axis, and 3D warping. Experimental results show that side information generated by using the proposed algorithm has 0.97dB better average PSNR compared with using MCTI and 3D warping separated. In addition, 8.01% of average bit-rate has been decreased while the same PSNR in R-D curves is kept.

• Journal of IKEEE
• /
• v.19 no.1
• /
• pp.1-9
• /
• 2015

This paper proposes the design of sub-pixel interpolation circuit for real-time multi-decoder supporting 4K-UHD video images. The proposed sub-pixel interpolation circuit supports H.264, MPEG-4, VC-1 and new video compression standard HEVC. The common part of the interpolation algorithm used in each video compression standard is shared to reduce the circuit size. An intermediate buffer is effectively used to reduce the circuit size and optimize the performance. The proposed sub-pixel interpolation circuit was synthesised by using 130nm standard cell library. The synthesized gate-level circuit consists of 122,564 gates and processes 35~86 image frames per second for 4K-UHD video at the maximum operation frequency of 200MHz. Therefore, the proposed circuit can process 4K-UHD video in real time.

• The Research Journal of the Costume Culture
• /
• v.18 no.6
• /
• pp.1318-1330
• /
• 2010

The 21st century is the age when a sensational image has more explanatory power and can deliver a more powerful message than a message consisting of logical thinking. Powerful visual images create a big impact on many people throughout the world, overcoming linguistic barriers and even replacing language as a means of communication. In the fashion field, the concept and power of visual images within the new multimedia of the 21st century are becoming increasingly important. In recent years, other than the above methods, videos, movies and animation features have been produced directly to enhance visual effects and attempts are increasing to use these new tools as communication methods. This study focuses on animation contents that have been used in the fashion industry to overcome prejudice of luxury international brands that feature images that emphasize value, quality and heritage. The purpose of this study is to focus on the specific character of fashion animation in order to overview the concept of 21st video fashion communication and to show how the collection concept that includes color and detail places an emphasis on visual images. Analysis of previous research, theoretical research through literature and case study on Prada fashion animation led to the following conclusion. The common features of two different Prada fashion animation show that both animation have the following features in common : realism, dramatic impact and convergence for expression methods, and creativeness, hybrid and a happy ending for contents. Beginning with this study, I believe that various angles of interest and concern about communication in the fashion world, which is a social and cultural phenomenon that changes rapidly, can be will be looked at and learned from.