Dense optic flow with a bayesian occlusion model

Authors:
Kevin Koeser;Christian Perwass;Gerald Sommer
Affiliations:
Institute of Computer Science and Applied Mathematics, Christian-Albrechts-University of Kiel, Kiel, Germany;Institute of Computer Science and Applied Mathematics, Christian-Albrechts-University of Kiel, Kiel, Germany;Institute of Computer Science and Applied Mathematics, Christian-Albrechts-University of Kiel, Kiel, Germany
Venue:
SCVMA'04 Proceedings of the First international conference on Spatial Coherence for Visual Motion Analysis
Year:
2004

Citing 10
Cited 0

Bayesian Estimation of Motion Vector Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Bayesian approach to binocular stereopsis

International Journal of Computer Vision
On the unification of line processes, outlier rejection, and robust statistics with applications in early vision

International Journal of Computer Vision
Stereo Matching with Nonlinear Diffusion

International Journal of Computer Vision
Empirical Bayesian Motion Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Integrated Bayesian Approach to Layer Extraction from Image Sequences

IEEE Transactions on Pattern Analysis and Machine Intelligence
Gauss-Markov Measure Field Models for Low-Level Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Cooperative Algorithm for Stereo Matching and Occlusion Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dense estimation and object-based segmentation of the optical flow with robust techniques

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a dense optic flow algorithm based on quite simple local probability assumptions. Due to the explicit derivation of the correspondence concept in a probability-theoretical framework, occlusion probability evolves straight-forwardly from the model for each pixel. Initialized with a similarity measure based on single pixels, an iterated diffusion step propagates local information across the image, while occlusion probability is used to inhibit flow information transfer across depth discontinuities, which prevents flow smoothing at 3d object boundaries. The inhibition is thereby not artificially modelled by some heuristically chosen parameters, but arises directly from the Bayesian correspondence model. The algorithm structure can be interpreted as a recurrent neural network, where matched points have reached a stable state, while others (e.g. those in homogeneous areas) keep receiving information from regions more and more far away until they converge, this way overcoming the aperture problem. The massive parallel structure allows for and demands a real hardware implementation of the system.