대한전자공학회:학술대회논문집 (Proceedings of the IEEK Conference)

대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지

얼굴 인식과 추적을 이용한 ROI 기반 영상 통화 코덱 설계 및 구현

ROI-based Encoding using Face Detection and Tracking for mobile video telephony

  • 이유선 (한국정보통신대학교 공학부) ;
  • 김창희 (한국정보통신대학교 공학부) ;
  • 나태영 (한국정보통신대학교 공학부) ;
  • 임정연 (SK 텔레콤 네트웍 기술원, 코어망 개발팀) ;
  • 주영호 (SK 텔레콤 네트웍 기술원, 코어망 개발팀) ;
  • 김기문 (SK 텔레콤 네트웍 기술원, 코어망 개발팀) ;
  • 변재완 (SK 텔레콤 네트웍 기술원, 코어망 개발팀) ;
  • 김문철 (한국정보통신대학교 공학부)
  • Lee, You-Sun (School of Engineering, Information and Communication University) ;
  • Kim, Chang-Hee (School of Engineering, Information and Communication University) ;
  • Na, Tae-Young (School of Engineering, Information and Communication University) ;
  • Lim, Jeong-Yeon (Core Network Development Team, Institute of Network Technology, SK Telecom) ;
  • Joo, Young-Ho (Core Network Development Team, Institute of Network Technology, SK Telecom) ;
  • Kim, Ki-Mun (Core Network Development Team, Institute of Network Technology, SK Telecom) ;
  • Byun, Jae-Woan (Core Network Development Team, Institute of Network Technology, SK Telecom) ;
  • Kim, Mun-Churl (School of Engineering, Information and Communication University)
  • 발행 : 2008.06.18
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

With advent of 3G mobile communication services, video telephony becomes one of the major services. However, due to a narrow channel bandwidth, the current video telephony services have not yet reached a satisfied level. In this paper, we propose an ROI (Region-Of-Interest) based improvement of visual quality for video telephony services with the H.264|MPEG-4 Part 10 (AVC: Advanced Video Coding) codec. To this end, we propose a face detection and tracking method to define ROI for the AVC codec based video telephony. Experiment results show that our proposed ROI based method allowed for improved visual quality in both objective and subjective perspectives.

키워드