상세정보
학술대회
Background Generation using Mean-Shift and Fast Marching Method
- 저자
- 조상현, 강행봉, 유장희
- 발행일
- 200912
- 출처
- International Conference on Computer Science and Its Applications (CSA) 2009, pp.1-6
- 협약과제
- 09MS5500, 개인신변 안전보장을 위한 영상보안 기술개발, 한종욱
- 초록
- Background generation is very important for accurate object tracking in the video surveillance system. Traditional background generation techniques cause some problems when there have been non-moving objects for a long time. To overcome this problem, we propose a new background generation method using mean-shift and Fast Marching Method (FMM) that fuse pixel information along temporal and spatial dimensions. The mode of pixel value density along time axis is estimated by mean-shift algorithm and spatial information is evaluated by FMM, and then they are fused together to generate desirable background for nonmoving objects for a certain period. Experimental results show that our proposed method is more efficient than the traditional method. © 2009 IEEE.
- KSP 제안 키워드
- Background generation, Fast Marching method, Long Time, Mean-shift(MS), Moving Object, Pixel Value, Traditional methods, Video surveillance system, mean-shift algorithm, object Tracking, spatial information