• ICROS
• /
• v.10 no.5
• /
• pp.18-21
• /
• 2004

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.489-494
• /
• 2002

컴퓨터 통신 서비스나 인터넷의 비약적인 발전으로 복잡해진 지식 체계에 따른 다양해진 정보를 신속 정확하게 이용할 수 있고, 전 세계의 모든 정보와 문화를 쉽게 접할 수 있게 되었다. 본 논문에서는 모션캡쳐를 이용하여, 교육용 타이틀, 애니메이션 및 게임 등의 제작을 위한 멀티미디어 디지털 라이브러리를 구축하고, 여러 사용자들이 쉽고 빠르게 동영상 및 영화, CF, 게임 등에 응응함으로써, 다양한 디지털 컨텐츠 개발을 목적으로 한다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.257-269
• /
• 2023

There is currently a burgeoning demand for image synthesis from photos and videos using deep learning models. Existing video synthesis models solely extract motion information from the provided video to generate animation effects on photos. However, these synthesis models encounter challenges in achieving accurate lip synchronization with the audio and maintaining the image quality of the synthesized output. To tackle these issues, this paper introduces a novel framework based on an image animation approach. Within this framework, upon receiving a photo, a video, and audio input, it produces an output that not only retains the unique characteristics of the individuals in the photo but also synchronizes their movements with the provided video, achieving lip synchronization with the audio. Furthermore, a super-resolution model is employed to enhance the quality and resolution of the synthesized output.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.631-636
• /
• 2007

Promotion websites of companies have several advantages: They can publicize the brand image in various ways by using the character of web environment; they enable consumers to learn the information of products in the round with interests; they can stretch out their marketing targets to the whole world. In order to make an effective delivery of their information in such promotion websites, interaction with their consumers is an important factor, for which understanding Interactive Storytelling is essential. The purpose of this thesis is to study Interactive Storytelling which enables us to have effective interaction with consumers in making promotion websites of companies. For this, this thesis analyzes examples of Interact Storytelling focused on it have story promotion websites on the basis of the five steps for internet marketing promotions: attraction of visitors, attraction of interests and participations, acquisition of the information of customers, grasp of the needs of customers, and an offer of values classified by customers.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.8
• /
• pp.407-415
• /
• 2008

This paper presents novel segmentation and transition techniques for dancing motion synthesis. The segmentation method for dancing motions is based on Laban Movement Analysis (LMA). We assume a dance sequence as a set of small dancing motions. To segment a dancing motion is a subjective, psychological, and complex problem, so we extract the shape factor of LMA from a dance motion and observe shape's changes to find the boundaries of dance segments. We also introduce a transition method that meets constraints on the feet. This method that is based on a linear interpolation modifies the intermediate posture motion after analyzing footprint positions. The posture could be a key-frame between source motion and target motion on the transition. With the proposed techniques, it would be easy for multimedia applications to generate plausible dance motions.

• Korean journal of communication and information
• /
• v.72
• /
• pp.52-91
• /
• 2015

The purpose of this study is to examine the effects of attribute agenda-setting and priming through content analysis and a survey about Particulate Matter($PM_{10}$ & $PM_{2.5}$) using both promotional news and general news. The study results were as follows. First, promotional news and general news were found to showcase similar cognitive attributes. Second, the results did not show a significant relationship between highlighted attributes in media coverage and the public's salient attributes, but media attributes had been generally reflected in the public's perception because the public was highly aware of the importance of all media attributes. Third, the recognition of the public's attribute importance affected the direction of public opinion, which resulted in the acceptance of priming effects. Meanwhile, the recognition of the public's attribute importance towards economic damage, international cooperation, individual response, and the recognition of promotional news had affected risk perception. Furthermore, the recognition of promotional news and involvement appeared to have an interaction effect on risk perception.

• The Journal of the Korea Contents Association
• /
• v.16 no.1
• /
• pp.521-529
• /
• 2016

This paper presents the historical development process and expressive style of motion graphics which are intended to artistic expression, and discusses the value of artistic expressions in motion graphics through the works and activities of F5 and Semi-Permanent which are the representative organization of that. Commercial use of digital motion graphics has been rapidly widespread and used in most of the picture contents by changes in the digital video production environment with the development of the computer. Motion graphics begins with a graphic design applied to the motion graphic content and is transferred from the abstract representation of the animation at the same time. Since then motion graphics have been developed as an independent genre on the basis of graphic design and animation, and take the important position for the understanding and development of the contemporary design and content industry. Moreover, the motion graphics which present the experiment of various techniques and the aspect of mixed genres contribute to the development and diversification of the visual image. This paper is covered on not only F5 and Semi-Permanent that have published experimental artistic motion graphics but also the analysis of the developed ways and expressive patters to produce experimental motion graphics of their works. Furthermore, it discusses the experimental artistic value of these works.

• The Journal of the Korea Contents Association
• /
• v.15 no.5
• /
• pp.18-26
• /
• 2015

In this paper, we presented a design and control method of multi-stage with wagon and lift stage. Multi-stage system has 4 degree-of-freedom(DOF), i.e., forward/backward/left/right/rotate and up/down motion. Wagon mechanism in the type of two wheel and steering is proposed in order to improve for the maneuverability compared to the existing differential-type wagons. Also, the lift mechanism is designed by interlocking type in order to make the maximum height bigger than 10 times of the original height. We also proposed a path planning algorithm. The performance of the propped system is validated via multi motion experiments, so that the multi-stage system is useful for various performances production.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.334-335
• /
• 2023

본 논문에서는 이미지 데이터와 각종 텍스트 기반의 데이터를 적절히 결합하여 유용한 데이터를 만들어 내는 방법을 제안한다. 그 사례로 편의점 상품 이미지와 편의점 프로모션 데이터, 사용자 위치정보 데이터를 적절히 결합하여 사용자가 편의점 상품 전면 이미지를 제공했을 때, 해당 상품이 어떤 편의점 브랜드에서 어떤 프로모션을 진행하고 있는지, 그리고 현재 위치에서 가까운 점포가 어디인지를 사용자에게 제공하는 시스템을 구현한다. 이미지를 어떤 데이터와 결합하는지에 따라 다양한 요구사항에 대응할 수 있다.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.305-310
• /
• 2010

In this paper, we propose a heuristic algorithm for motion correspondence based on a point series similarity. A point series is a sequence of points which are sorted in the ascending order of their x-coordinate values. The proposed algorithm clusters the points of a previous frame based on their local adjacency. For each group, we construct several potential point series by permuting the points in it, each of which is compared to the point series of the following frame in order to match the set of points through their similarity based on a proximity constraint. The longest common subsequence between two point series is used as global information to resolve the local ambiguity. Experimental results show an accuracy of more than 90% on two image sequences from the PETS 2009 and the CAVIAR data sets.