• Proceedings of the Korea Database Society Conference
• /
• 1995.12a
• /
• pp.165-168
• /
• 1995

본 논문은 비디오 연속 영상에서 얼굴의 위치를 추적하는 알고리즘에 관하여 기술한다. 컴퓨터 비젼에서 대량의 비디오 연속 영상내 물체 추적은 실시간에 처리되는 빠른 알고리즘이 요구된다. 기존의 방법은 형태에 기반한 알고리즘으로 물체의 회전, 크기 변화, 겹침 등에 대한 문제에 민감하여 여러 가지 어려움이 발생한다. 그러나 칼라를 이용한 알고리즘은 이러한 문제에 대하여 둔감하여 훨씬 효과적이다. 본 논문은 칼라 3D 히스토그램을 이용한 Swain과 Ballard의 역 투사(backprojection) 방법을 적용하여 비디오 연속 영상에서 얼굴의 위치를 빠르고 정확히 추적하는 알고리즘을 제안한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.12
• /
• pp.5856-5864
• /
• 2011

In this paper, we propose a moving object detection method in road video sequences acquired from a stationary camera. Our proposed method is based on the background subtraction method using Gaussian pyramids in both the background images and input video frames. It is more effective than pixel based subtraction approaches to reduce false detections which come from the mis-registration between current frames and the background image. And to determine a threshold value automatically in subtracted images, we calculate the threshold value using Otsu's method in each frame and then apply a scalar Kalman filtering to the threshold value. Experimental results show that the proposed method effectively detects moving objects in road video images.

• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.87-100
• /
• 2011

In this paper, we address a video summarization task as generating both visually salient and semantically important video segments. In order to find salient data points, one can use the OC-SVM (One-class Support Vector Machine), which is well known for novelty detection problems. It is, however, hard to incorporate into the OC-SVM process the importance measure of data points, which is crucial for video summarization. In order to integrate the importance of each point in the OC-SVM process, we propose a fuzzy version of OC-SVM. The Importance-based Fuzzy OC-SVM weights data points according to the importance measure of the video segments and then estimates the support of a distribution of the weighted feature vectors. The estimated support vectors form the descriptive segments that best delineate the underlying video content in terms of the importance and salience of video segments. We demonstrate the performance of our algorithm on several synthesized data sets and different types of videos in order to show the efficacy of the proposed algorithm. Experimental results showed that our approach outperformed the well known traditional method.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.743-754
• /
• 2019

System for three degrees of freedom plus (3DoF+) and 6DoF requires multi-view high resolution 360 video transmission to provide user viewport adaptive 360 video streaming. In this paper, we implement 3DoF+ 360 video compression system which removes the redundancy between multi-view videos and merges the residual into one video to provide high quality 360 video corresponding to an user's head movement efficiently. Implementations about 3D warping based redundancy removal method between 3DoF+ 360 videos and residual extraction and merger are explained in this paper. With the proposed system, 20.14% of BD-rate reduction in maximum is shown compared to traditional high-efficiency video coding (HEVC) based system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.219-222
• /
• 2009

자유시점 비디오는 단순히 수동적으로 비디오를 보는 것이 아니라 원하는 시점을 자유로이 선택하여 보는 능동형 비디오이다. 일반적으로 다양한 위치 및 다양한 각도에 위치하는 다수의 카메라로부터 촬영된 영상을 이용하여 제작하는데, 이 기술은 박물관 투어, 엔터테인먼트 등의 다양한 분야에서 활용된다. 본 논문에서는 자유시점 비디오의 새로운 분야로 한 장의 영상을 가상 카메라와 깊이맵을 이용하여 영상 내부를 네비게이션하는 자유시점 입체 Tour-Into-Picture (TIP)을 제안한다. 오래전부터 TIP가 연구되어 왔는데, 이 분야는 한 장의 사진 내부를 탐험하면서 애니메이션으로 볼 수 있게 하는 기술이다. 제안 방법은 전처리과정으로 전경 마스크, 배경영상, 및 깊이맵을 자동 및 수동 방법으로 구한다. 다음에는 영상 내부를 항해하면서 투영 영상들을 획득한다. 배경영상과 전객객체의 3D 모델링 데이터를 기반으로 가상 카메라의 3차원 공간 이동, yaw, pitch, rolling의 회전, look-around effect, 줌인 등의 다양한 카메라 기능을 활용하여 자유시점 비디오를 구현한다. 또한 깊이정보의 특성 및 구조에 따라 놀라운 시청효과를 전달하는 카메라 기능의 설정 방법을 소개한다. 소프트웨어는 OpenGL 및 MFC Visual C++ 기반으로 구축되었으며, 실험영상으로 조선시대의 작품인 신윤복의 단오풍정을 사용하였고, 입체 애니메이션으로 제작되어 보다 실감있는 콘텐츠를 제공한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.1
• /
• pp.46-57
• /
• 2001

To access the multimedia data, such as video data with temporal properties, the content-based image retrieval technique is required. Moreover, one of the basic techniques for content-based image retrieval is an extraction of representative key-frames. Not only did we implement this method, but also by analyzing the video data, we have proven the proposed method to be both effective and accurate. In addition, this method is expected to solve the real world problem of building video databases, as it is very useful in building an index.

• The Journal of the Korea Contents Association
• /
• v.15 no.2
• /
• pp.31-39
• /
• 2015

2D-to-3D video conversion vests 3D effects in a 2D video by generating stereoscopic views using depth cues inherent in the 2D video. This technology would be a good solution to resolve the problem of 3D content shortage during the transition period to the full ripe 3D video era. In this paper, a low-complexity depth generation method for 2D-to-3D video conversion is presented. For temporal consistency in global depth, a pattern-based depth generation method is newly introduced. A low-complexity refinement algorithm for local depth is also provided to improve 3D perception in object regions. Experimental results show that the proposed method outperforms conventional methods in terms of complexity and subjective quality.

• Journal of Internet Computing and Services
• /
• v.2 no.1
• /
• pp.49-61
• /
• 2001

Internet has been becoming widely popular and making rapid progress and network technologies is showing extension in data transmission speeds. Rapid and convenient multimedia services supplied with high quality and high speed are being needed, This paper treats of the design and implement method of clip-based video retrieval system on the world-wide-web environments. The implemented system consists of the content-based indexing system supporting convenient services for video contents providers and the web-based retrieval system in order to make it easy and various information retrieval for users on the world-wide-web. Three important methods were used in the content-based indexing system. Key frame extracting method by dividing video data, clip file creation method by clustering related information and video database build method by using clip unit, In web-based retrieval system, retrieval method by using a key word, two dimension browsing method of key frame and real-time display method of the clip were used. As a result. the proposed methodologies showed a usefulness of video content providing. and provided an easy method for searching intented video content.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.55-61
• /
• 2020

With the development of deep learning technology and advances in computing power, video-based research is now gaining more and more attention. Video data contains a large amount of temporal and spatial information, which is the biggest difference compared with image data. It has a larger amount of data. It has attracted intense attention in computer vision. Among them, motion recognition is one of the research focuses. However, the action recognition of human in the video is extremely complex and challenging subject. Based on many research in human beings, we have found that artificial intelligence-like attention mechanisms are an efficient model for cognition. This efficient model is ideal for processing image information and complex continuous video information. We introduce this attention mechanism into video action recognition, paying attention to human actions in video and effectively improving recognition efficiency. In this paper, we propose a new 3D residual attention network using convolutional neural network based on two attention models to identify human action behavior in the video. An evaluation result of our model showed up to 90.7% accuracy.

• Korea Multimedia Society
• /
• v.2 no.1
• /
• pp.46-56
• /
• 1998