Estimation of Occlusion and Dense Motion Fields in a Bidirectional Bayesian Framework

Authors:
Keng Pang Lim;Amitabha Das;Man Nang Chong
Affiliations:
Nanyang Technological Univ., Singapore;Nanyang Technological Univ., Singapore;GDC Technology Limited, Queensway, Hong Kong
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2002

Citing 8
Cited 4

Image segmentation based on object oriented mapping parameter estimation

Signal Processing
Bayesian Estimation of Motion Vector Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital video processing

Digital video processing
Markov random field modeling in computer vision

Markov random field modeling in computer vision
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields

Computer Vision and Image Understanding
Multimodal Estimation of Discontinuous Optical Flow using Markov Random Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Bayes decision test for detecting uncovered-background and moving pixels in image sequences

IEEE Transactions on Image Processing
The application of mean field theory to image motion estimation

IEEE Transactions on Image Processing

Estimating Piecewise-Smooth Optical Flow with Global Matching and Graduated Optimization

IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking multiple objects through occlusion with online sampling and position estimation

Pattern Recognition
A surface-volume matching process using a markov random field model for cardiac motion extraction in MSCT imaging

FIMH'05 Proceedings of the Third international conference on Functional Imaging and Modeling of the Heart
Sparse Occlusion Detection with Optical Flow

International Journal of Computer Vision

Quantified Score

Hi-index	0.14

Visualization

Abstract

This paper presents new MRF models in a bidirectional Bayesian framework for accurate motion and occlusion fields estimation. With careful selection of the five free parameters required by the models, good experimental results have been obtained. The resultant computational speed is also 5.5 times faster compared with the conventional Iterated Conditional Mode relaxation using the proposed fast bidirectional relaxation.