• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.59-63
• /
• 2014

최근 미디어 간 컨버전스가 가속화되면서 그 사이를 흐르는 콘텐츠 유형이 방송과 인터넷 양쪽을 충족시키고 또한 모바일 환경에 최적화된 서비스를 위해 클립화 되어 가고 있다. 다수의 미디어 콘텐츠를 공급하는 방송사의 입장에서는 콘텐츠서비스를 위한 콘텐츠 관리방안이 중요한 이슈가 되고 있으며 ID, 메타데이터 등 관리를 위한 체계를 잡는 것의 중요성도 증대되고 있으며 또한 분절된 동영상을 어떻게 만들고 어떻게 서비스 할것인가도 중요한 이슈이다. 이번연구는 대표적인 방송용 콘텐츠 메타데이터 표준인 EBU Core, PB Core와 우리나라 KBS 메타데이터의 분절형동영상 관련하여 메타데이터 구조를 파악하고 어떻게 구성되어 있는지 비교분석하여 보았다. 분석결과 메타데이터가 근간을 이루는 기본구조는 거의 유사하였고 각각 관점의 차이에 따라 추가되는 항목이 존재함을 발견할 수 있었다. 그리고 최근 미디어 환경변화에 따라 분절형동영상을 표현하는 메타데이터 항목에 대한 개선방향을 몇가지 제안하였다.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.45-54
• /
• 2018

This paper presents a vision-based fall detection system to automatically monitor and detect people's fall accidents, particularly those of elderly people or patients. For video analysis, the system should be able to extract both spatial and temporal features so that the model captures appearance and motion information simultaneously. Our approach is based on 3-dimensional convolutional neural networks, which can learn spatiotemporal features. In addition, we adopts a thermal camera in order to handle several issues regarding usability, day and night surveillance and privacy concerns. We design a pan-tilt camera with two actuators to extend the range of view. Performance is evaluated on our thermal dataset: TCL Fall Detection Dataset. The proposed model achieves 90.2% average clip accuracy which is better than other approaches.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.716-719
• /
• 2010

비디오 클립은 최근 온라인 상에서 흔히 볼 수 있는 짧은 동영상으로 이러한 동영상 클립의 대규모 유입으로 유사한 비디오 클립을 검색하는 동영상 검색 엔진의 필요성이 크게 증가하였다. BCS은 최초의 단일 비디오 클립 표현 모델로 비디오 클립을 주성분 분석을 통해 얻어진 좌표축들을 그 위로 사상된 데이터들로 제한한 것들로 이루어진 좌표계로 요약한다. 그러나 BCS 은 영상의 순서를 무시한 벡터로 표현되므로 세밀한 유사도 구별이 불가능하다. 본 논문에서는 유사한 동영상에 대한 사람의 판단은 서로 유사한 일부분이 많이 존재하는 것을 기반으로 하는 점에 착안하여 하나의 동영상 클립을 샷 단위로 나누어 여러 개의 BCS 으로 나타낸 다음, 이들간의 유사도 측정을 통해 검색의 성능을 높이고자 하였다. 실험 결과 만족할 만한 정확도로 유사한 동영상 클립을 검색해 내는 것을 확인할 수 있다.

• 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.

• Convergence Security Journal
• /
• v.15 no.2
• /
• pp.3-9
• /
• 2015

The development of the digital compression technology and the broadcasting receiver's processing power make it possible to apply a multi-view function to the broadcasting services. The multi-view function is usually utilized to provide simultaneously several programs to viewers or to implement a multi-angle service of a sports program that allows a viewer to choose a video of his/her prefer viewpoint. The paper proposes an integrated method for utilizing a multi-view function in the digital broadcasting environment in which more than 100 programs are on air and there may be various data services which want to use multi-view video clips. For the purpose, a method of composing and transmitting multi-view videos and related information has been devised and a Java API to utilize the rapid editing function of a decoding chip-set has been implemented to clip, resize, and display parts of the multi-view videos.

• Journal of Engineering Education Research
• /
• v.24 no.1
• /
• pp.34-45
• /
• 2021

This research is a case study about "Critical Thinking and Debate Education" class which was done for freshmen at the engineering college of "S" Women's University. Real time remote classes through LMS and ZOOM were the most effective tools under on-line circumstances, considering the fact that video lectures only cannot cultivate students' capabilities of critical thinking and communication. Throughout the analysis on students' self-reflection journals and lecture evaluations, this paper examined considerable future points and the pros and cons of "Critical Thinking and Debate Education" under online presentation and discussion situation. As research outputs, students told they could feel less nervousness and anxiety when they exercise and have a presentation because they could choose familiar space for them. In addition, students also told that they feel comfortable about both self-feedback and peer evaluation, repeatedly seeing the recorded video clip. However, on the contrary, sometimes students felt uncomfortable due to unstable internet connection through the online classes, and they also were regretful about the missing chances of interaction between a teacher and students and of intimate exchanges among students. They also told they had felt a kind of limit of enhancing their presentation skills just in front of the monitor. Considering these outcomes, this research paper points out that online education needs to be proceeded by strengthening multi layered feedback to students with the build-up of a non-face-to-face stable educational infrastructure, application of online instructional strategy, and utilization of YouTube platform and video contents. Through this research paper, I hope the new system of encompassing on/off line "Critical Thinking and Debate Education" and effective teaching and learning method can be developed soon by strengthening the strength of online education.

• Science of Emotion and Sensibility
• /
• v.9 no.spc3
• /
• pp.167-177
• /
• 2006

In this study, we developed a tool for measuring user's emotions expressed while using a product in the natural and accessible environment for the design field. Also, using emotional word logging software VideoTAME, we measured a user's emotions expressed while using a product. In the testing module of VideoTAME, participants evaluate their emotional changes through playing and watching the video clips of their performing tasks in the experiment room. In the analyzing module, the researchers replay the results created by participants during the experiment and analyze the results using Microsoft Excel. In this research, we have asked users to examine their emotional changes while watching the recorded video clip of them in the experiment room performing a series of tasks using a cellular phone. In this experiment, there were no big differences in the representative emotions expressed for each characteristics of task. The reason for this can be assumed it is because of the emotional changes occurred while facing specific situations when performing a task rather than the task itself. If more data is collected and concrete statistical analysis is done, it is expected that we can clarify what effect a product's usability has on user's emotions.

• Archives of design research
• /
• v.19 no.5 s.67
• /
• pp.373-382
• /
• 2006

In this study, emotional word logging software,'VideoTAME' was developed as an effective measurement tool for complementing the current psychological measuring methods. With the software, we measured the user's emotional changes while they interact with a product. The main goal of this study is to reveal the influence of usability on human emotions by analyzing the user's emotional changes while using a product. In this research, we asked 30 subjects to examine their emotional changes with watching the video clip recorded when they performed a series of tasks with a cellular phone in the experiment room. The results of this research indicated that negative emotion such as 'Uncomfortalbeness' was elicited mostly while they performed tasks which were difficult due to usability problems. On the other hand, positive emotion such as 'Satisfaction in Usability' was elicited for tasks which were easy to perform because of good usability. The reason for the user's emotional changes while they interact with a product can be assumed that the emotional changes were caused by specific situations they face when performing a task rather than the characteristics of task itself. We expect to clarify how usability of a product impact user's emotions in depth with more data collected and analyzed with the help of 'VideTAME'.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.514-528
• /
• 2004

An emotion-based video scene retrieval algorithm is proposed in this paper. First, abrupt/gradual shot boundaries are detected in the video clip representing a specific story Then, five video features such as 'average color histogram' 'average brightness', 'average edge histogram', 'average shot duration', and 'gradual change rate' are extracted from each of the videos and mapping between these features and the emotional space that user has in mind is achieved by an interactive genetic algorithm. Once the proposed algorithm has selected videos that contain the corresponding emotion from initial population of videos, feature vectors from the selected videos are regarded as chromosomes and a genetic crossover is applied over them. Next, new chromosomes after crossover and feature vectors in the database videos are compared based on the similarity function to obtain the most similar videos as solutions of the next generation. By iterating above procedures, new population of videos that user has in mind are retrieved. In order to show the validity of the proposed method, six example categories such as 'action', 'excitement', 'suspense', 'quietness', 'relaxation', 'happiness' are used as emotions for experiments. Over 300 commercial videos, retrieval results show 70% effectiveness in average.

• Journal of the Korean Society of Safety
• /
• v.35 no.1
• /
• pp.45-52
• /
• 2020

Construction industry has a relatively higher industrial accident rate than other domestic industries. Thus, to reduce the accident rate, researches on the methodology of worker's safety education combined with new technologies like IT technology have increased. In the light of workers' safety information provision, this study develops a VR(Virtual Reality)-based construction site using the BIM(Building Information Modeling) data. The target structures and geographical features are included in the VR-based construction site where the construction machinery model and worker model are also created using a game engine. For highly effective provision of safety information, video clips with suitable captions corresponding to working processes were made with proper screen directing. They should be appropriately connected to correct worker's operations to improve the work commitment level, sense of reality and inducement of interest. From this scenario, the 3D VR-based construction site, which can be experienced through a VR equipment, was created and in the same platform, the safety information was provided by the video clip combined with the suitable captions. Although the real construction site involves various requirements depending on field situation and the expertness and experience of workers are not consistent, the developed safety information provision based on the VR construction site is expected to effectively reduce the incomplete factors leading to construction accidents by improving the worker's perception of workplace safety.