• ETRI Journal
• /
• v.27 no.6
• /
• pp.806-809
• /
• 2005

The main goal of this research is automatic video analysis using a face recognition technique. In this paper, an automatic video management system is introduced with a variety of functions enabled, such as index, edit, summarize, and retrieve multimedia data. The automatic management tool utilizes MPEG-7 visual descriptors to generate a video index for creating a summary. The resulting index generates a preview of a movie, and allows non-linear access with thumbnails. In addition, the index supports the searching of shots similar to a desired one within saved video sequences. Moreover, a face recognition technique is utilized to personalbased video summarization and indexing in stored video data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.213-214
• /
• 2013

본 논문에서는 다중화면 분할 제작 콘텐츠 효과에 대해서 제안한다. 다중화면 분할 영상은 기존의 단일 영상 제공에 비해 2개, 3개, 4개, 9개의 화면을 각각 분할하여 다양한 영상들을 제공함으로써 보다 풍부한 정보 제공과 영상의 화려함과 미학을 제공한다. 이와 반대로 여러 화면의 정보들을 동시에 제공함으로써 한 화면에 집중하지 못함으로 여러 다양한 정보들을 수용하지 못하는 단점도 있다. 그러나 단일 화면보다는 다중 분할 화면으로 다양한 정보를 제공함으로써 얻는 효과가 더 크다고 사료한다. 이러한 다중화면 효과는 시청자들에게는 더 흥미로운 영상으로 충족 될 것이라고 사료한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.147-151
• /
• 2008

Since the first HDV(High Definition Video) camcoder, HDR-FX1 with 1080i resolution, had been launched at 2004, the image capture and record with HD resolution have been possible by the various types of camcoder and recorder which can support the HDV format. At a present day, a non-linear editing system, which is composed of only one computer, can capture, edit and export the image with HDV format. The HDV format has the same class of resolution with HD and the same data transfer bit rate of DV(Digital Video). Additionally, the image with HDV format can be recorded in 6mm DV cassette tape. It is possible because the HDV format uses the concept of Long GOP(Gorup of pictures) method for its compression. In this paper, the characteristic feature of HDV format, the essential factors in editing with HDV format and the concept of Long GOP method for its compression have been studied for the way of effective HDV editing.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.3
• /
• pp.9-17
• /
• 2014

This paper presents a method to retarget a source motion to the rig-space parameter for a target character that can be equipped with a complex rig structure as used in traditional animation pipelines. Our solution allows the animators to edit the retargeted motion easily and intuitively as they can work with the same rig parameters that have been used for keyframe animation. To acheive this, we analyze the correspondence between the source motion space and the target rig-space, followed by performing non-linear optimization for the motion retargeting to target rig-space. We observed the general workflow practiced by animators and apply this process to the optimization step.