• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.986-1005
• /
• 2020

In this paper, we propose AnoVid, an automated video annotation tool based on deep neural networks, that automatically generates various meta data for each scene or shot in a long drama video containing rich elements. To this end, a novel meta data schema for drama video is designed. Based on this schema, the AnoVid video annotation tool has a total of six deep neural network models for object detection, place recognition, time zone recognition, person recognition, activity detection, and description generation. Using these models, the AnoVid can generate rich video annotation data. In addition, AnoVid provides not only the ability to automatically generate a JSON-type video annotation data file, but also provides various visualization facilities to check the video content analysis results. Through experiments using a real drama video, "Misaeing", we show the practical effectiveness and performance of the proposed video annotation tool, AnoVid.

• 융합신호처리학회논문지
• /
• 제7권1호
• /
• pp.11-16
• /
• 2006

To manipulate large video databases, effective video indexing and retrieval are required. A large number of video indexing and retrieval algorithms have been presented for frame-w]so user query or video content query whereas a relatively few video sequence matching algorithms have been proposed for video sequence query. In this paper, we propose an efficient algorithm to extract key frames using color histograms and to match the video sequences using edge features. To effectively match video sequences with low computational load, we make use of the key frames extracted by the cumulative measure and the distance between key frames, and compare two sets of key frames using the modified Hausdorff distance. Experimental results with several real sequences show that the proposed video retrieval algorithm using color and edge features yields the higher accuracy and performance than conventional methods such as histogram difference, Euclidean metric, Battachaya distance, and directed divergence methods.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.87-96
• /
• 2021

The demand for e-learning through video lectures is rapidly increasing due to its diverse advantages over the traditional learning methods. This led to massive volumes of web-based lecture videos. Indexing and retrieval of a lecture video or a lecture video topic has thus proved to be an exceptionally challenging problem. Many techniques listed by literature were either visual or audio based, but not both. Since the effects of both the visual and audio components are equally important for the content-based indexing and retrieval, the current work is focused on both these components. A framework for automatic topic-based indexing and search depending on the innate content of the lecture videos is presented. The text from the slides is extracted using the proposed Merged Bounding Box (MBB) text detector. The audio component text extraction is done using Google Speech Recognition (GSR) technology. This hybrid approach generates the indexing keywords from the merged transcripts of both the video and audio component extractors. The search within the indexed documents is optimized based on the Naïve Bayes (NB) Classification and K-Means Clustering models. This optimized search retrieves results by searching only the relevant document cluster in the predefined categories and not the whole lecture video corpus. The work is carried out on the dataset generated by assigning categories to the lecture video transcripts gathered from e-learning portals. The performance of search is assessed based on the accuracy and time taken. Further the improved accuracy of the proposed indexing technique is compared with the accepted chain indexing technique.

• Journal of Korea Trade
• /
• 제26권7호
• /
• pp.145-166
• /
• 2022

Purpose - The field of online videos has seen rapid changes in information and communications technology (ICT) development. Despite active academic research on the use of online platforms, few studies have analyzed the relative importance among the factors determined. In this study, the relative importance of factors found in previous studies was identified for users of online video platforms in China and Korea. Through this, factors that should be considered first in research on online video use were derived. In addition, the quality level of online video platforms currently used in China and Korea was measured and used for analysis. The analysis results can provide information for companies to enter Chinese and Korean markets and also be useful to platform providers aiming to increase usage. Design/methodology - Among the factors of Online Video Usage identified in previous studies, 13 factors to be studied were selected through focus group interviews and hierarchized into 2 layers. For the analytic hierarchy process (AHP), each factor was designed as a pairwise comparison questionnaire. The survey included questions on the quality of online video platform currently in use. Data collection was conducted on 16 platforms in China and 11 platforms in Korea, and the relative importance of factors and user perspectives was compared and analyzed using importance performance analysis (IPA). In the analytical process, platforms were divided into over-the-top (OTT) group and Creator group according to the weight of user-generated content, and data analysis focused on these groups. Findings - As a result of AHP, China and Korea showed both "Fun" and "Interests" factors at the top, while the importance of the Entertainment factor "Vicarious satisfaction" was very different for China and Korea. "Relationship with content creators" was the most important factor in China, but it ranked the lowest in Korea. The IPA showed that the factors with high importance and performance were fun, interests, and easy accessibility for both China and Korea. In contrast, the factors that showed low performance compared to high importance in China were relationship with content creators, relationship with acquaintances/friends, and trustworthiness. As for Korea, vicarious satisfaction was observed; thus, this study has raised the need for academic and industrial interest in vicarious satisfaction. The results show that fun, interests, vicarious satisfaction, and easy accessibility of the platform are factors that must be included in further studies on online videos. Originality/value - Existing studies related to the use of online platforms have derived factors or focused on the influence relationship between factors and performance. However, few studies have analyzed the relative importance among the determined factors. This paper explores factors to be considered in future studies by deriving the relative importance between these factors from the perspective of users in China and Korea.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(3)
• /
• pp.133-136
• /
• 2001

Numerous challenges have been made to retrieve video using the contents. Recently MPEG-7 had set up a set of visual descriptors for such purpose of searching and retrieving multimedia data. Among them, color and motion descriptors are employed to develop a content-based video retrieval system to search for videos that have similar characteristics in terms of color and motion features of the video sequence. In this paper, the performance of the proposed system is analyzed and evaluated. Experimental results indicate that the processing time required for a retrieval using MPEG-7 descriptors is relatively short at the expense of the retrieval accuracy.

• 인터넷정보학회논문지
• /
• 제10권6호
• /
• pp.173-189
• /
• 2009

최근 UCC를 중심으로 동영상 데이터에 대해 사람들의 관심이 증가하고 있다. 따라서 동영상 데이터의 내용-기반 검색을 지원하는 효율적인 색인 기법이 요구된다. 그러나 Hybrid Spill-Tree를 제외한 대부분의 색인 기법들은 대용량의 고차원 데이터를 다루는데 비효율적이다. 본 논문에서는 동영상 데이터의 내용-기반 검색을 지원하기 위한 효율적인 고차원 색인 기법을 제안한다. 제안하는 고차원 색인 기법은 기존 Hybrid Spill-Tree을 기반으로 새롭게 제안하는 클러스터링 방법과 시그니쳐를 이용한 데이터 저장 방법을 결합하여 확장된 색인 기법이다. 또한 제안하는 시그니쳐-기반 고차원 색인 기법이 기존 M-Tree 및 Hybrid Spill-Tree에 비해 성능이 우수함을 보인다.

• 한국인터넷방송통신학회논문지
• /
• 제12권4호
• /
• pp.111-118
• /
• 2012

다양한 방송사와 서로 다른 CP(Contents Provider)가 분산되어 있는 Data Center서버에서 VOD 서비스를 하고자 할 때, 서로 다른 CP 플랫폼들이 고화질 HD, 3DTV 비디오 등의 영상파일을 교환하기 위해 고성능 네트워크를 통하여 빠르게 전송할 수 있는 망을 빠르게 구성해야 한다. 본 논문은 Public망의 QoS와 보안성을 보완하는 선택적인 암호화 방안을 이용하여, 고속의 안전한 VPN(Virtual Privatr Network)을 생성하고 콘텐츠를 고속으로 대용량 영상파일을 전송하는 프로토콜을 제안한다. End to End의 Device가 대용량의 영상파일을 Parallel 전송으로 가용한 자원을 최대한 사용하면서 안전한 콘텐츠 전송이 가능한 고성능의 VPN을 구성하는 모델을 제안한다.

• ETRI Journal
• /
• 제35권6호
• /
• pp.960-968
• /
• 2013

To implement a cloud game service platform supporting multiple users and devices based on real-time streaming, there are many technical needs, including game screen and sound capturing, audio/video encoding in real time created by a high-performance server-generated game screen, and real-time streaming to client devices, such as low-cost PCs, smart devices, and set-top boxes. We therefore present a game service platform for the running and management of the game screen, as well as running the sound on the server, in which the captured and encoded game screen and sound separately provide client devices through real-time streaming. The proposed platform offers Web-based services that allow game play on smaller end devices without requiring the games to be installed locally.

• 전기학회논문지P
• /
• 제66권3호
• /
• pp.135-138
• /
• 2017

This study analyzed with the case analysis of a series of processes from job analysis survey and results analysis, and academic achievement in order to transform the curriculum of existing courses of the NCS-based video broadcasting. Also this study analysed the existing curriculum and analyzed the trend of workforce trends and needs of the broadcasting content industry. Also through a needs analysis for the industry and alumni and students, video graphics, video editing and video directing were selected. In this paper it dealt mainly with respect to the video graphics in a dual job. Modeling capability into the unit through a job analysis, animation, effects and lighting were chosen accordingly based introduction of graphics and application of graphics were derived two courses and selected profiles and performance criteria. This training according to the NCS curriculum for students was evaluated based on the student's job was to investigate the learning ability.

• ETRI Journal
• /
• 제32권3호
• /
• pp.490-492
• /
• 2010

This letter proposes a robust feature extraction method using a spatially normalized mean for temporal ordinal measurement. Before computing a rank matrix from the mean values of non-overlapped blocks, each block mean is normalized so that it obeys the invariance property against linear additive and subtractive noise effects and is insensitive against multiplied and divided noise effects. Then, the temporal ordinal measures of spatially normalized mean values are computed for the feature matching. The performance of the proposed method showed about 95% accuracy in both precision and recall rates on various distortion environments, which represents the 2.7% higher performance on average compared to the temporal ordinal measurement.