• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.85-92
• /
• 2021

In a face, there is much information of person's identity. Because of this property, various tasks such as expression recognition, identity recognition and deepfake have been actively conducted. Most of them use the exact frontal view of the given face. However, various directions of the face can be observed rather than the exact frontal image in real situation. The profile (side view) lacks information when comparing with the frontal view image. Therefore, if we can generate the frontal face from other directions, we can obtain more information on the given face. In this paper, we propose a combined style model based the conditional generative adversarial network (cGAN) for generating the frontal face from multi-view images that consist of characteristics that not only includes the style around the face (hair and beard) but also detailed areas (eye, nose, and mouth).

• ETRI Journal
• /
• v.36 no.2
• /
• pp.242-252
• /
• 2014

Since July of 2012, the 3D video extension of H.264/AVC has been under development to support the multi-view video plus depth format. In 3D video applications such as multi-view and free-view point applications, synthesized views are generated using coded texture video and coded depth video. Such synthesized views can be distorted by quantization noise and inaccuracy of 3D wrapping positions, thus it is important to improve their quality where possible. To achieve this, the relationship among the depth video, texture video, and synthesized view is investigated herein. Based on this investigation, an edge noise suppression filtering process to preserve the edges of the depth video and a method based on a total variation approach to maximum a posteriori probability estimates for reducing the quantization noise of the coded texture video. The experiment results show that the proposed methods improve the peak signal-to-noise ratio and visual quality of a synthesized view compared to a synthesized view without post processing methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.3A
• /
• pp.337-344
• /
• 2006

In this paper, we propose a multi-view video codec for 3DTV system. The proposed algorithm is not only to reduce the temporal and spatial redundancy but also to reduce the redundancy among each view. With these results, we can improve the coding efficiency for multi-view video sequences. In order to reduce the redundancy of each view more efficiently, we define the assembled image(AI) that is generated by the global disparity compensation of each view. In addition, the proposed algorithm is based on MPEG-2 structure so that we can easily implement 3DTV system without changing the conventional 2D digital TV system. Experimental results show that the proposed algorithm performs very well. It also performs better than MPEG-2 simulcast coding method. The newly proposed codec also supports the view scalability, accurate temporal synchronization among multiple views and random access capability in view dimension.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.954-964
• /
• 2020

In immersive media, the most important factor that provides immersion is depth information. Therefore, it is essential to obtain high quality depth information in order to produce high quality immersive media. In this paper we propose an algorithm to improve depth map, considering the segmentation of images and the relationship between multiple views in multi-view systems. The proposed algorithm uses a super-pixel segmentation technique to divide the depth map of the reference view into several segments, and project each segment into adjacent view. Subsequently, the depth map of the adjacent view is improved using plane estimation using the information of the projected segment, and then reversed to the reference view. This process is repeated for several adjacent views to improve the reference depth map by updating the values of the improved adjacent views and the initial depth map of the reference view. Through simulation, the proposed algorithm is shown to surpass the conventional algorithm subjectively and objectively.

• Journal of Power Electronics
• /
• v.14 no.5
• /
• pp.1069-1078
• /
• 2014

This study presents the design and implementation of a web-based remote laboratory for a multi-mode single-leg power converter, which is a topic in advanced power electronics course. The proposed laboratory includes an experimental test rig with a multi-mode single-leg power converter and its driver circuits, a measurement board, a control platform, and a LabVIEW-based user interface program that is operated in the server computer. Given that the proposed web-based remote laboratory is based on client/server architecture, the experimental test rig can be controlled by a client computer with Internet connection and a standard web browser. Although the multi-mode single-leg power converter can work at four different modes (main boost, buck-boost, boost-boost, and battery boost modes), only the buck-boost mode is used in the experiment because of page limit. Users can choose the control structure, control parameters, and reference values, as well as obtain graphical results from the user interface software. Consequently, the feedbacks received from students who conducted remote laboratory studies indicate that the proposed laboratory is a useful tool for both remote and traditional education.

• Broadcasting and Media Magazine
• /
• v.19 no.2
• /
• pp.80-89
• /
• 2014

기존 HD TV에 비해 더 높은 화질과 몰입감을 시청자에게 제공하는 UHD TV는 차세대 방송 시장의 성장을 주도하고 있다. 따라서 UHD 방송 시스템을 구축하기 위해 고효율 압축 부호화 기술인 HEVC 표준화, 5G 전송 기술 표준화 등 차세대 기술 연구가 콘텐츠 압축, 전송 분야에서 활발하게 진행되었다. 이러한 콘텐츠 압축, 전송 기술 분야의 괄목할 만한 연구 성과에 의해, UHD 방송을 제공하기 위한 기술적 문제는 많은 부분 해결되었다. 하지만 현재 기존 HD 방송과 차별화 되는 UHD 방송 시스템 기반의 방송 서비스 기술에 대한 연구는 많이 진행되지 않고 있다. 따라서 본 논문에서는 한 화면에서 여러 채널을 동시 시청할 수 있는 Multi-Channel View 서비스 기술에 대해서 알아보고, 이를 통해 UHD 방송의 고해상도 영상을 이용한 차별화된 사용자 맞춤형 Multi-Channel View 서비스를 구현하기 위한 연구 방향을 제시하고자 한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.266-272
• /
• 2012

This paper presents a parking assistant system of multi-view using vehicle data. Proposed system provides the driver with three direction of the scenes surrounding vehicle. Depending on the handle rotation, the proposed system displays views from multiple wide-angle CCD cameras on the laptop screen to reduce blind spots, support smooth parallel or garage parking, and support comfortable and safe driving. The handle angle and gear position are obtained from ABS ECU through OBD-II port. The performance of proposed system is validated by vehicle experiments.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.187-190
• /
• 2003

In this paper, we propose an extrinsic calibration method for a multi-view camera to get an optimal pose in 3D space. Conventional calibration algorithms do not guarantee the calibration accuracy at a mid/long distance because pixel errors increase as the distance between camera and pattern goes far. To compensate for the calibration errors, firstly, we apply the Tsai's algorithm to each lens so that we obtain initial extrinsic parameters Then, we estimate extrinsic parameters by using distance vectors obtained from structural cues of a multi-view camera. After we get the estimated extrinsic parameters of each lens, we carry out a non-linear optimization using the relationship between camera coordinate and world coordinate iteratively. The optimal camera parameters can be used in generating 3D panoramic virtual environment and supporting AR applications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.5A
• /
• pp.688-695
• /
• 2000

We present a multi-view autostereoscopic display system based on volume holographic storage technique. In this proposed system, the interference pattern of spatial multiplexed plane reference and angular multiplexed plane object beams are recorded into a photorefractive crystal, which plays a role of guiding object beams of multi-view images into the desired persfective directions. For reconstruction, object beams containing the desired multi-view image information, which satisfy Bragg matching condition, are illuminated in the time-division multiplexed manner onto the crystal. Then multiple stereoscopic images are Projected to the display plane for autostereoscopic 3D viewing.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.3
• /
• pp.21-28
• /
• 2018

As computer performance and needs of user convenience increase, computer user interface are also changing. This changes had great effects on software development environment. In past, text editors like vi or emacs on UNIX OS were the main development environment. These editors are very strong to edit source code, but difficult and not intuitive compared to GUI(Graphical User Interface) based environment and were used by only some experts. Moreover, the trends of software development environment was changed from command line to GUI environment and GUI Editor provides usability and efficiency. As a result, the usage of text based editor had decreased. However, because GUI based editor use a lot of computer resources, computer performance and efficiency are decreasing. The more contents are, the more time to verify and display the contents it takes. In this paper, we provide a new parser that provide multi view editing, incremental parsing and multiple entry of abstract syntax tree.