Comparison of the Efficiency of Deterministic and Stochastic Algorithms for Visual Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Boundary Detection by Constrained Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computational strategies for object recognition
ACM Computing Surveys (CSUR)
A Three-Frame Algorithm for Estimating Two-Component Image Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian Estimation of Motion Vector Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
A decomposition-based simulated annealing technique for data clustering
PODS '94 Proceedings of the thirteenth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
The computation of optical flow
ACM Computing Surveys (CSUR)
IEEE Transactions on Pattern Analysis and Machine Intelligence
A General Motion Model and Spatio-Temporal Filters forComputing Optical Flow
International Journal of Computer Vision
Exploiting Discontinuities in Optical Flow
International Journal of Computer Vision
Robust Optical Flow Computation Based on Least-Median-of-Squares Regression
International Journal of Computer Vision
Structure from Motion: Beyond the Epipolar Constraint
International Journal of Computer Vision
Empirical Bayesian Motion Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Fourier Properties of Discontinuous Motion
Journal of Mathematical Imaging and Vision
A Theoretical Framework for Convex Regularizers in PDE-Based Computation of Image Motion
International Journal of Computer Vision
Variational Optic Flow Computation with a Spatio-Temporal Smoothness Constraint
Journal of Mathematical Imaging and Vision
Video sequence segmentation using genetic algorithms
Pattern Recognition Letters
Probabilistic Detection and Tracking of Motion Boundaries
International Journal of Computer Vision - Special issue on Genomic Signal Processing
Hierarchical Estimation and Segmentation of Dense Motion Fields
International Journal of Computer Vision
Multimodal Estimation of Discontinuous Optical Flow using Markov Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optic Flow Field Segmentation and Motion Estimation Using a Robust Genetic Partitioning Algorithm
IEEE Transactions on Pattern Analysis and Machine Intelligence
Foreground Segmentation Using Motion Vectors in Sports Video
PCM '02 Proceedings of the Third IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Bayesian inference of visual motion boundaries
Exploring artificial intelligence in the new millennium
Estimating Piecewise-Smooth Optical Flow with Global Matching and Graduated Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Layered Motion Segmentation and Depth Ordering by Tracking Edges
IEEE Transactions on Pattern Analysis and Machine Intelligence
Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods
International Journal of Computer Vision
Highly Accurate Optic Flow Computation with Theoretically Justified Warping
International Journal of Computer Vision
On the Spatial Statistics of Optical Flow
International Journal of Computer Vision
EURASIP Journal on Applied Signal Processing
Automatic video object segmentation using volume growing and hierarchical clustering
EURASIP Journal on Applied Signal Processing
Particle Video: Long-Range Motion Estimation Using Point Trajectories
International Journal of Computer Vision
Dynamic Texture Detection Based on Motion Analysis
International Journal of Computer Vision
EURASIP Journal on Advances in Signal Processing
Comparison of stochastic and deterministic solution methods in Bayesian estimation of 2D motion
Image and Vision Computing
Segmentation and free space detection using Gabor filters
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Detection of vehicles using Gabor filters and affine moment invariants from an image
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Detecting regions of dynamic texture
SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Optimal dominant motion estimation using adaptive search of transformation space
Proceedings of the 29th DAGM conference on Pattern recognition
OSCAR: object segmentation using correspondence and relaxation
3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
Spatially coherent clustering using graph cuts
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
A Database and Evaluation Methodology for Optical Flow
International Journal of Computer Vision
International Journal of Computer Vision
Motion segmentation using an occlusion detector
WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision
ICIAR'05 Proceedings of the Second international conference on Image Analysis and Recognition
2D motion description and contextual motion analysis: issues and new models
SCVMA'04 Proceedings of the First international conference on Spatial Coherence for Visual Motion Analysis
Hi-index | 0.15 |
This paper presents results from computer experiments with an algorithm to perform scene disposition and motion segmentation from visual motion or optic flow. The maximum a posteriori (MAP) criterion is used to formulate what the best segmentation or interpretation of the scene should be, where the scene is assumed to be made up of some fixed number of moving planar surface patches. The Bayesian approach requires, first, specification of prior expectations for the optic flow field, which here is modeled as spatial and temporal Markov random fields; and, secondly, a way of measuring how well the segmentation predicts the measured flow field. The Markov random fields incorporate the physical constraints that objects and their images are probably spatially continuous, and that their images are likely to move quite smoothly across the image plane. To compute the flow predicted by the segmentation, a recent method for reconstructing the motion and orientation of planar surface facets is used. The search for the globally optimal segmentation is performed using simulated annealing.