Fast Optical Flow Estimation Based on Multi-Grid

被引：0

作者：

Li, Xiuzhi ^{[1
]}

Jia, Songmin ^{[1
]}

Tan, Jun ^{[1
]}

Yin, Xiaolin ^{[1
]}

机构：

[1] Beijing Univ Technol, Coll Elect Informat & Control Engn, Beijing, Peoples R China

来源：

SIXTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2013) | 2013年 / 9067卷

关键词：

Optical flow; Multi-grid; Real-time processing; Iteration; REAL-TIME; COMPUTATION;

D O I：

10.1117/12.2051203

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Estimation efficiency is one of key topics in computationally intense optical flow algorithm. Traditional numerical iterative methods are effective at eliminating the high frequency components of the estimation error, while keeping most of low frequency components unchanged. In this paper, we consider the multi-grid based real-time implementation of dense optical flow computation by classical Horn-Schunck model. For this purpose, establishing of the linear set of equation, which is required in linear multi-grid model, is carefully studied, and the overall multi-grid framework is presented. Efficiency and effectiveness of the proposed algorithm is validated by experimental results.

引用

页数：5

共 8 条

[1] Variational optical flow computation in real time [J].

Bruhn, A ;

Weickert, J ;

Feddern, C ;

Kohlberger, T ;

Schnörr, C .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2005, 14 (05) :608-615

[2] A multigrid platform for real-time motion computation with discontinuity-preserving variational methods [J].

Bruhn, Andres ;

Weickert, Joachim ;

Kohlberger, Timo ;

Schnoerr, Christoph .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2006, 70 (03) :257-277

[3]

Chang M., 1999, J SE U, V29, P101

[4] DETERMINING OPTICAL-FLOW [J].

HORN, BKP ;

SCHUNCK, BG .

ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) :185-203

[5] NONLINEAR TOTAL VARIATION BASED NOISE REMOVAL ALGORITHMS [J].

RUDIN, LI ;

OSHER, S ;

FATEMI, E .

PHYSICA D, 1992, 60 (1-4) :259-268

[6] Three-dimensional scene flow [J].

Vedula, S ;

Baker, S ;

Rander, P ;

Collins, R ;

Kanade, T .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (03) :475-480

[7] Stereoscopic Scene Flow Computation for 3D Motion Understanding [J].

Wedel, Andreas ;

Brox, Thomas ;

Vaudrey, Tobi ;

Rabe, Clemens ;

Franke, Uwe ;

Cremers, Daniel .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2011, 95 (01) :29-51

[8] An Improved Algorithm for TV-L1 Optical Flow [J].

Wedel, Andreas ;

Pock, Thomas ;

Zach, Christopher ;

Bischof, Horst ;

Cremers, Daniel .

STATISTICAL AND GEOMETRICAL APPROACHES TO VISUAL MOTION ANALYSIS, 2009, 5604 :23-+

← 1 →