International Journal of Computer Vision
A Segmentation Based Variational Model for Accurate Optical Flow Estimation
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Stereo Image Analysis of Non-Lambertian Surfaces
International Journal of Computer Vision
EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
GPU-based multigrid: real-time performance in high resolution nonlinear image processing
ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Dense point trajectories by GPU-accelerated large displacement optical flow
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Joint estimation of motion, structure and geometry from stereo sequences
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Dense, robust, and accurate motion field estimation from stereo image sequences in real-time
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
International Journal of Computer Vision
TV-L1 optical flow for vector valued images
EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
A robust multigrid approach for variational image registration models
Journal of Computational and Applied Mathematics
Video motion estimation with temporal coherence
Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry
Improving sub-pixel correspondence through upsampling
Computer Vision and Image Understanding
Variational motion segmentation with level sets
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Improving motion estimation using image-driven functions and hybrid scheme
PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
Improving the robustness of variational optical flow through tensor voting
Computer Vision and Image Understanding
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
Optical flow estimation in cardiac CT images using the steered Hermite transform
Image Communication
Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles
International Journal of Computer Vision
Adaptive integration of feature matches into variational optical flow methods
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
On improving the robustness of variational optical flow against illumination changes
Proceedings of the 4th ACM/IEEE international workshop on Analysis and retrieval of tracked events and motion in imagery stream
International Journal of Computer Vision
A Framework for Moving Least Squares Method with Total Variation Minimizing Regularization
Journal of Mathematical Imaging and Vision
Hi-index | 0.00 |
Although variational methods are among the most accurate techniques for estimating the optical flow, they have not yet entered the field of real-time vision. Main reason is the great popularity of standard numerical schemes that are easy to implement, however, at the expense of being too slow for real-time performance. In our paper we address this problem in two ways: (i) We present an improved version of the highly accurate technique of Brox et al. [9]. Thereby we show that a separate robustification of the constancy assumptions is very useful, in particular if the 1-norm is used as penalizer. As a result, a method is obtained that yields the lowest angular errors in the literature. (ii) We develop an efficient numerical scheme for the proposed approach that allows real-time performance for sequences of size 160 脳 120. To this end, we combine two hierarchical strategies: A coarse-to-fine warping strategy as implementation of a fixed point iteration for a non-convex optimisation problem and a nonlinear full multigrid method 驴 a so called full approximation scheme (FAS) 驴 for solving the highly nonlinear equation systems at each warping level. In the experimental section the advantage of the proposed approach becomes obvious: Outperforming standard numerical schemes by two orders of magnitude frame rates of six high quality flow fields per second are obtained on a 3.06 GHz Pentium4 PC.