• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.217-228
• /
• 2023

Video instance segmentation is an intelligent visual task with high complexity because it not only requires object instance segmentation for each image frame constituting a video, but also requires accurate tracking of instances throughout the frame sequence of the video. In special, human instance segmentation in drama videos has an unique characteristic that requires accurate tracking of several main characters interacting in various places and times. Also, it is also characterized by a kind of the class imbalance problem because there is a significant difference between the frequency of main characters and that of supporting or auxiliary characters in drama videos. In this paper, we introduce a new human instance datatset called MHIS, which is built upon drama videos, Miseang, and then propose a novel video data augmentation method, CDVA, in order to overcome the data imbalance problem between character classes. Different from the previous video data augmentation methods, the proposed CDVA generates more realistic augmented videos by deciding the optimal location within the background clip for a target human instance to be inserted with taking rich spatio-temporal context embedded in videos into account. Therefore, the proposed augmentation method, CDVA, can improve the performance of a deep neural network model for video instance segmentation. Conducting both quantitative and qualitative experiments using the MHIS dataset, we prove the usefulness and effectiveness of the proposed video data augmentation method.

• Journal of Korea Multimedia Society
• /
• v.9 no.5
• /
• pp.576-584
• /
• 2006

Content-based video matching is measuring a similarity of video signature compared to the original clip and copies of media. Specially, it is very important to match the exact frame position, but it depends on frame rate, noise condition and compression format of video. Ordinal signature shows good performance than other video signatures under normal condition but the previous didn't try to find the uniqueness and robustness. Hua et al. performed a uniqueness test under compressed in different formats or frame size. However, they used other compression format image instead of noise in robustness test. This paper proposes robustness test method using several noise models and analyzes the performance of robustness and uniqueness.

• Journal of KIISE:Databases
• /
• v.37 no.3
• /
• pp.127-136
• /
• 2010

With rapid growth of information and computer communication technologies, the numbers of digital documents including multimedia data have been recently exploded. In particular, news video database and news video mining have became the subject of extensive research, to develop effective and efficient tools for manipulation and analysis of news videos, because of their information richness. However, many research focus on browsing, retrieval and summarization of news videos. Up to date, it is a relatively early state to discover and to analyse the plentiful latent semantic knowledge from news videos. In this paper, we propose the news video mining system based on multi-modal approach and text mining, which uses the visual-textual information of news video clips and their scripts. The proposed system systematically constructs a taxonomy of news video stories in automatic manner with hierarchical clustering algorithm which is one of text mining methods. Then, it multilaterally analyzes the topics of news video stories by means of time-cluster trend graph, weighted cluster growth index, and network analysis. To clarify the validity of our approach, we analyzed the news videos on "The Second Summit of South and North Korea in 2007".

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.101-109
• /
• 2002

In this paper, multiple object tracking system in a known environment is proposed. It extracts moving areas shaped on objects in video sequences and detects racks of moving objects. Color invariant co-occurrence matrices are exploited to extract the plausible object blocks and the correspondences between adjacent video frames. The measures of class separability derived from the features of co-occurrence matrices are used to improve the performance of tracking. The experimented results are presented.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06d
• /
• pp.92-96
• /
• 2008

모바일 인터넷 사용자가 급속히 늘어남에 따라 모바일 콘텐츠의 수요도 증가하고 있다. MP3, 온라인 게임, 비디오 클립 등 지적재산권이 있는 유료 콘텐츠를 보호하기 위해 일반적으로 모바일 DRM과 같은 암호화 방식이 적용된다. 하지만, 자원이 제한된 모바일 환경에서 AES 알고리즘 등으로 콘텐츠 전체를 암호화할 경우, 응답시간 지연과 전력소비 증가로 효율적 모바일 콘텐츠 서비스를 제공하기 어렵다. 이러한 문제를 해결하기 위해, 본 논문에서는 모바일 콘텐츠를 고정크기 분할(fragment)들로 나눈 다음 각 분할의 앞 뒤 부분만 암호화하는 효율적인 부분 암호화(partial encryption) 기법을 제안한다. 또한, 부분 암호화로 인한 안전성 감소 가능성을 보완하기 위하여 분할들에 대해 뒤섞기(shuffling)를 적용한다. 제안한 개념을 모바일 DRM 표준 블록 암호화 알고리즘인 AES를 사용하여 ARM 기반 임베디드 보드에서 구현하여 실험하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.2
• /
• pp.21-28
• /
• 2008

This paper proposes a novel reduced-reference assessment method for video quality assessment, in which one-dimensional (1-D) histograms of motion vectors (MVs) are used as features of videos. The proposed method is more efficient than the conventional methods in view of computation time, because the proposed quality metric decodes MVs directly from video stream in the parsing process instead of reconstructing the distorted video at the receiver. Moreover, in view of data size, the propose method is efficient because a sender transmits 1-D histograms of MVs accumulated over whole input video sequences. Here, we use 1-D histograms of MVs accumulated over the whole video sequences, which is different from the conventional methods that assessed each image independently. For testing the similarity between histograms, we use histogram intersection and histogram difference methods. We compare the proposed method with the conventional methods for 52 video clips, which are coded under varying bit rate, image size, and frame rate. Experimental results show that the proposed method is more efficient than the conventional methods and that the proposed method is more similar to the mean opinion score (MOS) than conventional algorithms.

• Journal of Broadcast Engineering
• /
• v.12 no.5
• /
• pp.435-444
• /
• 2007

In this paper, we presented the concept and some methods to watch online video clips related to a TV program on atelevision which is called lean-back media, and we simulated our concept on a PC system. The key point of this research is suggesting a new service model to TV viewers and the TV industry, which the model provides simple and easy ways to watch online video clips on a TV screen. The paper defined new tags for metadata and algorithm for the model, then showed simple example using those metadata. At the end, it mentioned the usage of the model in the digital broadcasting environment and discuss about the issues which should handle as future works.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.4
• /
• pp.71-83
• /
• 2003

This study is aimed to develop and evaluate different approaches for cyber education. The project involved the development of sample cyber education programs using different design approaches, with built-in evaluation mechanisms. The different design approaches depend on what delivery technologies are involved. In the First Generation, the delivery technologies use text, flash and animation, whereas the synchronized content to video and audio are used in the Second and the Third Generations but the difference is the delivery method used by the videoclip. Tests were carried out through self-assessment to measure and analyze the efficient teaching. The results show that the Third generation technologies were the most effective method for cyber education. However, since the Third generation program is developed in multimedia, it tends 10 require higher development costs, and more advanced hardware and software as well as a higher bandwidth for network. Therefore, the research indicates that the development of technical supports, like loading speed, has to be solved simultaneously with the development of multimedia products for effective cyber education.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.1013-1016
• /
• 2017

본 논문에서는 사각형의 형태를 벗어나 임의의 다각형 평면에 원하는 "카메라 입력 영상", "비디오 클립", 혹은 "3차원 그래픽 실시간 렌더링 영상"등을 보다 쉽게 매핑 시킬 수 있는 인터랙티브 프로젝션 매핑 소프트웨어 시스템을 설계 구현하였다. 제안 시스템은 얼굴 인식 기능을 통하여 사용자 혹은 관객이 프로젝션 매핑 작품 앞에 등장하였음을 인식하고, 관객의 모습이 미디어 콘텐츠의 일부로 실시간 포함되어 임의의 평면에 매핑하는 기능을 포함하고 있다. 제안 시스템은 프로젝션 매핑의 초보자가 쉽게 사용할 수 있도록 텍스트 기반의 구성 파일 (Configuration File)에 매핑 평면과 미디어 콘텐츠의 형태 및 내용을 정의해 주도록 하는 구조로 구성하였다. 제안 시스템의 유용성을 확인하기 위하여, 육면체, 원구형, 사각 평면 형태의 실제의 객체에 다양한 형태의 미디어 콘텐츠를 매핑 한 미디어 작품을 제작하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.7
• /
• pp.467-476
• /
• 2014

Recently, various services which use the fused form of broadcasting and communication are being offered over the Internet globally. To provide various interactive services through connected smart TV on wired or wireless network, the seamless multimedia service is key feature. In this paper, Dynamic Adaptive Streaming over HTTP (DASH)is adopted to develop cost-effective adaptive streaming system for Open Hybrid TV(OHTV) service. This system can provide seamless adaptive streaming service for IP VOD, Video Clips, Ad insertion which are defined in OHTV.