Heuristics: intelligent search strategies for computer problem solving
Heuristics: intelligent search strategies for computer problem solving
Optimal orientations of cells in slicing floorplan designs
Information and Control
IEEE Transactions on Pattern Analysis and Machine Intelligence
Information Processing Letters
Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
The design and analysis of spatial data structures
The design and analysis of spatial data structures
MPEG: a video compression standard for multimedia applications
Communications of the ACM - Special issue on digital multimedia systems
Matching Two Perspective Views
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Three-Frame Algorithm for Estimating Two-Component Image Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance of optical flow techniques
International Journal of Computer Vision
Picture Segmentation by a Tree Traversal Algorithm
Journal of the ACM (JACM)
Robot Vision
Machine Learning
Detecting and Tracking Multiple Moving Objects Using Temporal Integration
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Hierarchical Model-Based Motion Estimation
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Cell Migration Analysis After In Vitro WoundingInjury with a Multi-Agent Approach
Artificial Intelligence Review
Axiomatic Approach to Feature Subset Selection Based on Relevance
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Distributed Algorithm for Content Based Indexing of Images by Projections on Ritz Primary Images
Data Mining and Knowledge Discovery
Hi-index | 0.14 |
The standard approach to computing motion relies on pixel correspondence. Computational schemes impose additional constraints, such as smoothness and continuity of the motion vector field, even though these are not directly related to pixel correspondence. This paper proposes an alternative to the multiple constraints approach. By drawing analogy with machine learning, motion is computed as a function that accurately predicts frames. The Occam-Razor principle suggests that among all functions that accurately predict the second frame from the first frame, the best predictor is the 驴simplest,驴 and simplicity can be rigorously defined in terms of encoding length. An implementation of a practical algorithm is described. Experiments with real video sequences verify the algorithm assumptions by showing that motion in typical sequences can be accurately described in terms of a few parameters. Our particular choice of predictors produces results that compare very favorably with other image flow algorithms in terms of accuracy and compactness. It may, however, be too constrained to enable accurate recovery of 3D motion and structure.