Variational optical flow computation in real time
- 18 April 2005
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 14 (5), 608-615
- https://doi.org/10.1109/tip.2005.846018
Abstract
This paper investigates the usefulness of bidirectional multigrid methods for variational optical flow computations. Although these numerical schemes are among the fastest methods for solving equation systems, they are rarely applied in the field of computer vision. We demonstrate how to employ those numerical methods for the treatment of variational optical flow formulations and show that the efficiency of this approach even allows for real-time performance on standard PCs. As a representative for variational optic flow methods, we consider the recently introduced combined local-global method. It can be considered as a noise-robust generalization of the Horn and Schunck technique. We present a decoupled, as well as a coupled, version of the classical Gau/spl szlig/-Seidel solver, and we develop several multigrid implementations based on a discretization coarse grid approximation. In contrast, with standard bidirectional multigrid algorithms, we take advantage of intergrid transfer operators that allow for nondyadic grid hierarchies. As a consequence, no restrictions concerning the image size or the number of traversed levels have to be imposed. In the experimental section, we juxtapose the developed multigrid schemes and demonstrate their superior performance when compared to unidirectional multigrid methods and nonhierachical solvers. For the well-known 316/spl times/252 Yosemite sequence, we succeeded in computing the complete set of dense flow fields in three quarters of a second on a 3.06-GHz Pentium4 PC. This corresponds to a frame rate of 18 flow fields per second which outperforms the widely-used Gau/spl szlig/-Seidel method by almost three orders of magnitude.Keywords
This publication has 23 references indexed in Scilit:
- Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow MethodsInternational Journal of Computer Vision, 2005
- Optimal Control Formulation for Determining Optical FlowSIAM Journal on Scientific Computing, 2003
- Dense estimation and object-based segmentation of the optical flow with robust techniquesIEEE Transactions on Image Processing, 1998
- A fast scalable algorithm for discontinuous optical flow estimationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Estimation of optical flow based on higher-order spatiotemporal derivatives in interlaced and non-interlaced image sequencesArtificial Intelligence, 1995
- Efficient multiscale regularization with applications to the computation of optical flowIEEE Transactions on Image Processing, 1994
- Computing oriented texture fieldsCVGIP: Graphical Models and Image Processing, 1991
- Investigations of multigrid algorithms for the estimation of optical flow fields in image sequencesComputer Vision, Graphics, and Image Processing, 1988
- DETERMINING OPTICAL-FLOWArtificial Intelligence, 1980
- Multi-Level Adaptive Solutions to Boundary-Value ProblemsMathematics of Computation, 1977