• IEMEK Journal of Embedded Systems and Applications
• /
• v.4 no.2
• /
• pp.79-83
• /
• 2009

Streaming Technology can support the real-time playback without downloading and storing multimedia data in local HDD. So, client browser or plug-in can represent multimedia data before the end of file transmission using streaming technology. Recently, the demand for efficient real-time playback and transmission of large amounts of multimedia data is growing rapidly. But most users' connections over network are not fast and stable enough to download large chunks of multimedia data. In this paper, we propose an intelligent IP streaming system based on personalized media service. The proposed IP streaming system enables users to get an intelligent recommendation of multimedia contents based on the user preference information stored on the streaming server or the home media server. The supposed intelligent IP streaming system consists of Server Metadata Agent, Pumping Server, Contents Storage Server, Client Metadata Agent and Streaming Player. And in order to implement the personalized media service, the user information, user preference information and client device information are managed under database concept. Moreover, users are assured of seamless access of streamed content event if they switch to another client device by implementing streaming system based on user identification and device information. We evaluate our approach with manufacturing home server system and simulation results.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06b
• /
• pp.67-71
• /
• 1996

We have developed an MPEG2 realtime codec system and ATM interface, and evaluated the performance and characteristics of the audio-visual communication in terms of Interoperability specification of The ATM Forum, ITU-T H.310 draft recommendation [1] and the reference points of DAVIC specification through the experiments using the experimental public ATM network.

• The Journal of the Korea Contents Association
• /
• v.16 no.12
• /
• pp.181-191
• /
• 2016

We analyzed the search word of the media content in the IPTV service, and as a result we found that an important factor is general meta information as well as content(material, plot, etc.) and emotion information in the media content selection criteria of customers. Therefore, in this research, in order to efficiently provide various media contents of IPTV to users, we designed the emotion classification system for utilizing the emotion information of the media content. Next, we proposed 'personalized media contents curation system based on emotion information' for organizing the media contents, through the various processing steps. Finally, to demonstrate the effectiveness of this system, we conducted a user satisfaction survey(72.0 points). In addition, the results of comparing the results based on popularity and the results of the proposed system showed that the ratio leading to the actual users' viewing behavior was 10 times higher.

• Broadcasting and Media Magazine
• /
• v.19 no.4
• /
• pp.50-59
• /
• 2014

사용자들이 미디어를 접하는 디바이스 환경이 다양화되고 그 속에서 접할 수 있는 콘텐츠의 양은 많아졌다. 특히 급속도로 발전한 모바일 환경에서 사용자들은 개인화된 기기를 사용하여 콘텐츠를 소비하고 주변 사용자들과 경험을 공유한다. 콘텐츠 제공 서비스에서는 이러한 개인의 콘텐츠 소비 이력 및 SNS 관계에서 발생한 데이터를 분석하여 활용함으로써 콘텐츠 소비를 활성화하고자 한다. KBS에서도 이러한 동향에 맞추어 방송콘텐츠 추천검색 연구와 실시간 TV캡처 및 소셜 공유 연구를 진행하였으며, 그 과정에서 많은 양의 데이터를 효율적으로 처리하기 위한 방법의 필요성을 절감하게 되었다. 데이터 분석이 필요한 두 과제에서 진행한 내용을 기술하고 대용량 데이터 처리기법을 활용하여 상용화 서비스를 구축할 계획을 소개한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10a
• /
• pp.433-435
• /
• 1999

The Synchronized Multimedia Integration Language (SMIL) is a recommendation from the W3C that makes authoring of TV-like multimedia presentations on the Web easier. It uses the eXtensible Markup Language (XML) to define a set of markup tags to synchronize the timing and positioning relationships between multimedia objects. We present the design and implementation of JAVA-based SMIL player, SSP(Sejong SMIL Player). SSP processes different types of media objects using multiple threads. Moreover, its cache engine detects the mediatype and allocates the proper cache memory for the corresponding media object.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.184-185
• /
• 2022

인터넷 환경의 변화에 따라 텍스트 기반의 정보 전달에서 멀티미디어 기반의 스트리밍 방식으로 바뀌어가고 있다. 또한 대용량의 동영상 데이터뿐 아니라 Shorts, Clip Reels 또는 등 다양한 방식의 동영상 형태로 배포되고 있으며 서비스 플랫폼에서는 손쉽게 편집할 수 있도록 기능을 제공하고 있다. 대용량 콘텐츠, TV, Youtue 콘텐츠를 포함하여 소용량 동영상 편집에 필요한 영상 제작 기술에서 가장 인력과 시간이 많이 소요되는 부분은 편집 단계로 딥러닝 기반 인공지능 기술을 활용하여 자동화하고 있으며 영상편집에서 가장 기본이 되는 단위인 씬검출 기법을 개발하였다. 키프레임 검출 기법과 유사도 기법을 이용하여 씬을 추출하였으며 블록 Cost Function을 이용하여 최적화하여 0.5214의 정확도를 도출하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.39-41
• /
• 2023

본 논문에서는 대학생들의 스터디 활동을 돕는 앱의 구현 내용을 앱에서 핵심적으로 사용되는 관심도 기반 추천 알고리즘을 중점으로 소개하였다. 해당 알고리즘을 통해 이 앱은 사용자에게 더욱 높은 접근성을 제공한다. 본 논문에서는 이 알고리즘의 설계와 적용 방식을 서술하였고, 이를 통한 앱의 기대효과를 작성하였다. 본 연구의 과정은 해당 앱을 개발하는 과정을 서술하여 유사한 앱 또는 유사한 알고리즘을 활용하는 앱을 개발하는 프로젝트에서 사례로 활용될 수 있다.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.125-133
• /
• 2023

Traditional attire has assumed a pivotal role within the contemporary fashion industry. The objective of this study is to construct a computer vision model tailored to the recognition of traditional costumes originating from five distinct countries, namely India, Korea, Japan, Tanzania, and Vietnam. Leveraging a dataset comprising 1,608 images, we proceeded to train the cutting-edge computer vision model YOLOv8. The model yielded an impressive overall mean average precision (MAP) of 96%. Notably, the Indian sari exhibited a remarkable MAP of 99%, the Tanzanian kitenge 98%, the Japanese kimono 92%, the Korean hanbok 89%, and the Vietnamese ao dai 83%. Furthermore, the model demonstrated a commendable overall box precision score of 94.7% and a recall rate of 84.3%. Within the realm of the fashion industry, this model possesses considerable utility for trend projection and the facilitation of personalized recommendation systems.

• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.86-93
• /
• 2012

The emergence of cable TV, satellite broadcasting and IPTV provides viewers with a variety of TV programs. However, viewers' desire for watching their favorite TV program at convenient time has increased because of insufficient spare time. As an increase in smart phone market has accelerated an entry into "the age of smart network media" since 2009, mobile media suggests services connected to other digital devices. Recently, there has been growing interest in TV controling system of smart phone. Therefore, the present study aims to provide an concept of the smart phone application which recommends contents of TV program by analyzing personal watching pattern. To suggest detailed direction of the interaction and UI design, we analyzed previous research and examples of TV controlling applications and products. In addition, public opinion survey was carried out to rationalize this study and suggest suitable UI structure.

• Journal of the Korea Convergence Society
• /
• v.11 no.3
• /
• pp.181-186
• /
• 2020

The purpose of this study is to empirically examine the factors affecting the binge-watching behaviors of OTT service users by using a multi-layer perceptron (MLP) artificial neural network. All samples (n=1,000) were collected from 'A survey on user awareness in OTT service' published by a Media Research Center of the Korea Press Foundation in 2018. Our research model includes one dependent variable which is binge-watching behaviors on OTT service and five independent variables such as gender, age, frequency of service usage, users' satisfaction with content recommendation algorithm, and content types mainly consumed. Our findings demonstrate that age, frequency of service usage, users' satisfaction with content recommendation algorithms, and certain types of contents (e.g., Korean dramas, Korean films, and foreign dramas) were found to be highly related to binge-watching behavior on OTT services.