• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2010년도 하계학술대회
• /
• pp.42-45
• /
• 2010

This paper proposes an intelligent video surveillance system for human object tracking. The proposed system integrates the object extraction, human object recognition, face detection, and camera control. First, the object in the video signals is extracted using the background subtraction. Then, the object region is examined whether it is human or not. For this recognition, the region-based shape descriptor, angular radial transform (ART) in MPEG-7, is used to learn and train the shapes of human bodies. When it is decided that the object is human or something to be investigated, the face region is detected. Finally, the face or object region is tracked in the video, and the pan/tilt/zoom (PTZ) controllable camera tracks the moving object with the motion information of the object. This paper performs the simulation with the real CCTV cameras and their communication protocol. According to the experiments, the proposed system is able to track the moving object(human) automatically not only in the image domain but also in the real 3-D space. The proposed system reduces the human supervisors and improves the surveillance efficiency with the computer vision techniques.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.17-19
• /
• 2007

This paper describe an interactive video object segmentation tool which can be used to generate MPEG-4 video object planes for multimedia broadcasting and enables content based functionalities. In order to apply these functionalities, each frame of video sequence should be represented in terms of video objects. Semiautomatic segmentation can be thought of as a user-assisted segmentation technique. A user can initially mark objects of interest around the real object boundaries. Then the user-guided and selected objects are continuously separated from the unselected areas though time evolution in the image sequences. We proposed method shows very promising result and this encourages the development of object based video editing system.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.433-436
• /
• 2000

In this paper, we present two types of digital image stabilization (DIS) schemes for mobile video communications. In the first scheme, the DIS system, which is used as a preprocessor of the video encoder, compensates the camera’s undesirable shakes before encoding. This method can reduce the bit rate of encoded video sequence by attenuating the prediction error to be encoded. In the second proposed scheme, the DIS system is coupled with the video decoder. The second scheme uses the K-means clustering algorithm to estimate the camera motion using motion vectors decoded from the received video stream. Simulation results show that the first scheme improves coding efficiency, while the second scheme is computationally efficient since it does not require motion estimation.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 춘계종합학술대회
• /
• pp.81-85
• /
• 2002

원격화상강의시스템(Video Lecturing System)에 의한 강의수업의 장점 및 단점 그리고 문제점의 해결방안을 설문조사를 통해 분석하였다. 본 논문에서는 원격화상강의 수강자들의 설문결과로 인한 수업의 만족도 및 효율성결과를 일반강의와 비교 분석하여 원격화상강의의 우수성을 입증하여 미래의 대체교육법으로서 제시하고자 한다.

• 한국정보처리학회논문지
• /
• 제3권3호
• /
• pp.608-616
• /
• 1996

본 논문에서는 영상회의를 위한 멀티미디어 하드웨어 구조를 입 출력 중심으로 제안 하고, 구조를 대기모델로 표현하여 시스템의 동작을 분석하였으며, 설계와구현 을 통해 분석결과를 고찰하였다. 영상회의시에 발생되는 멀티미디어 데이타의 병목 현상 과 비디오 데이타의 크기, 프레임 수, 화자의 수 및 압축율의 변화를 모의실험하여 가능한 영상회의 수준과 문제점을 분석하였다. 또 분석된 내용의 요구를 .근사적으로 반영하는 시스팀을 구현하고 시험하여 멀티미디어 시스팀 입축력 설계시에 고려해야 할 사항들을 기술하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 학술대회지
• /
• pp.600-607
• /
• 2004

The paper describes the implementation of the video conferencing system using public key infrastructure which is used for user authentication and media stream encryption. Using public key infrastructure, we are able to reinforce the authentication for conference participant and block several malicious hacking while protecting conference control information. The paper shows the implementation of the transportation layer secure protocol in conformity with Korea public key authentication algorithm standard and symmetric key encryption algorithm (RC2, SEED, DES and 3DES) for media stream encryption. The feature of the paper is transportation layer secure protocol that is implemented for protection of information on a user authentication and video conference and the media streaming encryption algorithm also can be envisioned with another block encryption algorithm. The key for media streaming encryption may be safely distributed by the transportation layer secure protocol.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.484-486
• /
• 2005

Passenger safety is a primary concern of railway system but, it has been urgent issue that dozens of people are killed every year when they falloff from train platforms. Recently, advancements in IT have enabled applying vision sensors to railway environments, such as CCTV and stereo camera sensors. In this paper, we propose a stereoscopic video coding scheme for subway accident monitoring system. The proposed scheme is designed for providing flexible video among various displays, such as control center, station employees and train driver. We uses MPEG-2 standard for coding the left-view sequence and IBMDC for predicting the P- and B-types of frames of the right-view sequence. IBMDC predicts matching block by interpolating both motion and disparity predicted macroblocks. To provide efficient stereoscopic video service. we define both temporally and spatially scalable layers for each eye's-view by using the concept of Spatio-Temporal scalability. According to the experimental results. we expect the proposed functionalities will play a key role in establishing highly flexible stereoscopic video codec for ubiquitous display environment where devices and network connections are heterogeneous.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.169-174
• /
• 2002

In this paper, we suggest a new spatial information system called video GIS where video is used for spatial data construction and is integrated with map. We develop a prototype system of video GIS and apply it to roadside facility management. The main functions supported by the suggested system are data collection, coordinate calculation and conversion, data construction, analysis, searching, and browsing. The stereo images and corresponding position data are collected by a vehicle named 4S-Van that has GPS, IMU, and cameras. The 3-D coordinates of the objects in the images, such as road sign, signal lamp, and building, can be calculated and constructed from the collected data. The spatial objects are displayed on both image and map, and can be searched and browsed, which enables visual and realistic browsing and management of spatial objects. Compared to conventional field survey used in roadside facility management, the method enables faster, easier, and more efficient construction of spatial data. The suggested video GIS can be applied not only to roadside facility management but also to many similar projects of central or local governments that are related to GIS.

• 한국정보처리학회논문지
• /
• 제4권12호
• /
• pp.3097-3110
• /
• 1997

초고속 통신망의 구축과 컴퓨터 기술의 발전으로, 컴퓨터 기술과 통신망이 통합된 정보통신 인프라 (Infra-structure)를 객체 지향 소프트웨어 구조의 시스템으로 모델화한 개방형 정보 통신망 구조위에서 멀티미디어 서비스를 제공하는 연구 활동이 활발히 전개되고 있다. 본 논문에서는 멀티미디어 서비스의 기본이 되는 화상 회의 서비스를 선정하여, 개방형 정보 통신망 구조에서 서비스 세션 관리 기능을 객체 모델링 하였다. 또한 화상 회의 서비스를 통하여 서비스 세션 객체와 물리적 통신망을 제어하는 연결 관리 객체간 접속을 세션 그래프와 연결 그래프로 개념화 하였으며, 이들 간의 세션 관리 객체 모델링과 매핑 및 객체 정보 공유에 대한 기술을 검증하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.801-803
• /
• 2003

In this paper, we present a method for generating and providing spatially encoded video data that can be effectively used by GIS applications. We collect the video data by a mobile mapping system called 4S-Van that is equipped by GPS, INS, CCD camera, and DVR system. The information about spatial object appearing in video, such as occupied region in each frame, attribute value, and geo-coordinate, are generated and encoded. We suggest methods that can generate such data for each frame in semi-automatic manner. We adopt standard MPEG-7 metadata format for representation of the spatially encoded video data to be generally used by GIS application. The spatial and attribute information encoded to each video frame can make visual browsing between map and video possible. The generated video data can be provided and applied to various GIS applications where location and visual data are both important.