Coarse to Fine Optical flow Detection

Heeman Lee; Seo Jeong-Man

Journal of The Korea Society of Computer and Information

Abbr : JKSCI
2005, 10(1), pp.223-229
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science

Heeman Lee ¹, Seo Jeong-Man ²

¹서원대학교
²한국재활복지대학

ABSTRACT

In this paper, a coarse-to-fine optical flow detection method is proposed. Provided that optical flow gives reliable approximation to two-dimensional image motion, it can be used to recover the three-dimensional motion, but usually to get the reliable optical flows are difficult. The proposed algorithm uses Horn's algorithm for detecting initial optical flow, then Thin Plate Spline is introduced to warp a image frame of the initial optical flow to the next image frame. The optical flow for the warped image frame is again used iteratively until the mean square error between two image sequence frames is lowered. The proposed method is experimented for the real moving picture image sequence. The proposed algorithm gives dense optical flow vectors.
KEYWORDS

Optical Flow, Thin Plate Spline, Warphing
REFERENCES (10)

[journal] / 1995. / “The Computing of Optical Flow” 27(3) : 433~467

[journal] / 1994. / “Performance of Optical Flow” : 43~12 77

[journal] / nips2001. / Approximate Thin Plate Spline Mapping / “Approximate Thin Plate Spline Mapping”

[journal] / 1989. / Thin-plate splines and decomposition of deformation” / “Principal Warps 11(6) : 567~585

[journal] / 2002. / “Eleastic Minutiae Matching by Means of Thin-Plate Spline Model” : 985~988

[journal] / 2004 / “전역 탐색 알고리듬을 이용한 이동 무선 통신 네트워크의 최적화에 대한 연구” 9(1) : 88~89

[journal] / 1999 / 가상현실용 3차원 시뮬레이터

[journal] / 2000 / “비디오 압축을 위한 고속 블록 정합 알고리즘에 관한 연구” / 세종대학교 대학원 : 13~

[journal] / 2003. / “모션벡터를 이용한 가상현실 체험 시스템의 구현 8 : 87~88

[journal] / 2004. / “TPS를 이용한 광류의 검출방법 ” 과학과 문화 1(1) : 355~360
KCI Citation (0)

KJC Korea
Journal Central

Statistics

Tools