Title   name
2007년 KSIAM 봄 학술대회
 
  Title
  Speaker   Woo, Hyenkyun  
  Date 2007-05-25
  Host
  Place KAIST
  File  의 1 번째 Real Media 동영상입니다. 의 1 번째 강연자료입니다.
 
Abstract : This paper presents a real-time motion detection algorithm for surveillance application basedon a new level set-based energy functional. The proposed algorithm for minimizing the energyfunctional combines automatically motion segmentation and denoising operation in real time,and it provides robust and efficient motion detection at various noise levels of image sequences.Experimental results using surveillance camera show that it is very efficient in segmenting movingobjects regardless of environment conditions. It has a very low false alarm rate even at night,when relatively few motion occur.