Performance Comparison of Background Estimation in the Video

영상에서의 배경추정알고리즘 성능 비교

  • Do, Jin-Kyu (Convergence of IT Devices Institute Busan, Dongeui University) ;
  • Kim, Gyu-Yeong (Convergence of IT Devices Institute Busan, Dongeui University) ;
  • Park, Jang-Sik (Division of Electronics Engineering, Kyungsung University) ;
  • Kim, Hyun-Tae (Convergence of IT Devices Institute Busan, Dongeui University) ;
  • Yu, Yun-Sik (Convergence of IT Devices Institute Busan, Dongeui University)
  • 도진규 (동의대학교 부산IT융합부품연구소) ;
  • 김규영 (동의대학교 부산IT융합부품연구소) ;
  • 박장식 (경성대학교 전자공학과) ;
  • 김현태 (동의대학교 부산IT융합부품연구소) ;
  • 유윤식 (동의대학교 부산IT융합부품연구소)
  • Published : 2011.05.26

Abstract

The background estimation algorithms had a significant impact on the performance of image processing and recognition. In this paper, background estimation algorithms were analysis of complexity and performance as preprocessing of image recognition. It was evaluated the performance of Gaussian Running Average, Mixture of Gaussian, and KDE algorithm. The simulation results show that KDE algorithm outperforms compared to the other algorithms.

Acknowledgement

Grant : IT특화연구소:"부산IT융합부품연구소" 설립 및 운영

Supported by : 정보통신산업진흥원, 부산광역시, 동의대학교