In 18th IEEE International Conference on Image Processing. IEEE (2011)
AbstractWe present a minimum message length (MML) framework for trajectory partitioning by point selection, and use it to automatically select the tolerance parameter ε for Douglas-Peucker partitioning, adapting to local trajectory complexity. By examining a range of ε for synthetic and real trajectories, it is easy to see that the best ε does vary by trajectory, and that the MML encoding makes sensible choices and is robust against Gaussian noise. We use it to explore the identification of micro-activities within a longer trajectory. This MML metric is comparable to the TRACLUS metric – and shares the constraint of abstracting only by omission of points – but is a true lossless encoding. Such encoding has several theoretical advantages – particularly with very small segments (high frame rates) – but actual performance interacts strongly with the search algorithm. Both differ from unconstrained piecewise linear approximations, including other MML formulations.
Similar books and articles
Bayes Not Bust! Why Simplicity Is No Problem for Bayesians.David L. Dowe, Steve Gardner & and Graham Oppy - 2007 - British Journal for the Philosophy of Science 58 (4):709 - 754.
Empirical Data Sets Are Algorithmically Compressible: Reply to McAllister.Charles Twardy, Steve Gardner & David Dowe - 2005 - Studies in the History and Philosophy of Science, Part A 36 (2):391-402.
Minimum Propositional Proof Length is NP-Hard to Linearly Approximate.Michael Alekhnovich, Sam Buss, Shlomo Moran & Toniann Pitassi - 2001 - Journal of Symbolic Logic 66 (1):171-191.
Universal Bayesian Inference?David Dowe & Graham Oppy - 2001 - Behavioral and Brain Sciences 24 (4):662-663.
The Ethics and Economics of the Minimum Wage.T. M. Wilkinson - 2004 - Economics and Philosophy 20 (2):351-374.
The Status of the Minimum Principle in the Theoretical Analysis of Visual Perception.Gary Hatfield & William Epstein - 1985 - Psychological Bulletin 97 (2):155–186.
What is Complexity? - The Philosophy of Complexity Per Se with Application to Some Examples in Evolution.Bruce Edmonds - 1995 - In [Book Chapter] (in Press).
Thermodynamic Study of Motor Behaviour Optimization.Patrick Cordier, Michel Mendès France, Philippe Bolon & Jean Pailhous - 1994 - Acta Biotheoretica 42 (2-3):187-201.
Review: Michael Alekhnovich, Sam Buss, Shlomo Moran, Toniann Pitassi, Minimum Propositional Proof Length Is NP-Hard to Linearly Approximate. [REVIEW]Alexander Razborov - 2002 - Bulletin of Symbolic Logic 8 (2):301-302.
MDLChunker: A MDL-Based Cognitive Model of Inductive Learning.Vivien Robinet, Benoît Lemaire & Mirta B. Gordon - 2011 - Cognitive Science 35 (7):1352-1389.
Following a Trajectory: On "Tracing a Trajectory" and "Explaining and Valuing," by James M. Gustafson.Melvin Konner - 1995 - Zygon 30 (2):191-200.
Added to PP
Historical graph of downloads