A Statistical Confidence Measure for Optical Flows

Authors:
Claudia Kondermann;Rudolf Mester;Christoph Garbe
Affiliations:
Interdisciplinary Center for Scientific Computing, University of Heidelberg, Germany;Visual Sensorics and Information Processing Lab, University of Frankfurt, Germany;Interdisciplinary Center for Scientific Computing, University of Heidelberg, Germany
Venue:
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Year:
2008

Citing 0
Cited 8

Reconstructing Optical Flow Fields by Motion Inpainting

EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Control of the Effects of Regularization on Variational Optic Flow Computations

Journal of Mathematical Imaging and Vision
Optical flow reliability model approximated with RBF

IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part II
Error analysis for lucas-kanade based schemes

ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part I
A loop-consistency measure for dense correspondences in multi-view video

Image and Vision Computing
On performance analysis of optical flow algorithms

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
A complete confidence framework for optical flow

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
When is a confidence measure good enough?

ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Confidence measures are crucial to the interpretation of any optical flow measurement. Even though numerous methods for estimating optical flow have been proposed over the last three decades, a sound, universal, and statistically motivated confidence measure for optical flow measurements is still missing. We aim at filling this gap with this contribution, where such a confidence measure is derived, using statistical test theory and measurable statistics of flow fields from the regarded domain. The new confidence measure is computed from merely the results of the optical flow estimator and hence can be applied to any optical flow estimation method, covering the range from local parametric to global variational approaches. Experimental results using state-of-the-art optical flow estimators and various test sequences demonstrate the superiority of the proposed technique compared to existing 'confidence' measures.