Method for visual tracking using switching linear dynamic system models
作者： Vladimir Pavlović , James Matthew Rehg
DOI:
关键词: Trajectory 、 Viterbi algorithm 、 Eye tracking 、 Model fitting 、 Set (abstract data type) 、 Control theory 、 Dynamic models 、 Mathematics 、 Sequence 、 State (functional analysis)
摘要: A target in a sequence of measurements is tracked by modeling the with switching linear dynamic system (SLDS) having plurality models. Each model associated state such that selected when its true. set continuous estimates determined for given measurement, and each possible state. transition record then determining recording, measurement state, an optimal previous based on sequence, where optimizes probability estimates. fitted to sequence. The description influence measurement. It couples what observed estimated target. Finally, trajectory from fitting, parameters SLDS, which correspond preferably obtained through Viterbi prediction. can be prior or posterior
google.com.mx 参考文章(28)
Michael I Jordan, Zoubin Ghahramani, Tommi S Jaakkola, Lawrence K Saul, None, An introduction to variational methods for graphical models Machine Learning. ,vol. 37, pp. 105- 161 ,(1999) , 10.1023/A:1007665907178
Gregory A. Watson, Theodore R. Rice, William D. Blair, Interacting multiple bias model filter system for tracking maneuvering targets ,(1993)
Kathleen Knobe, James Mathew Rehg, Umakishore Ramachandran, Rishiyur S. Nikhil, System for integrating task and data parallelism in dynamic applications ,(1998)
Roberto Cusani, Enzo Baccarelli, MAP receiver for high-speed numerical transmissions through rayleigh channels noisy and dispersive in time and frequency ,(1997)
Vladimir Pavlovic, Robert R. Leyendecker, Desmond Wai M. Yan, Claudio G. Rey, Armando C. Garrido, Yan Guo, Jay J.-C. Chen, Method and apparatus for linear transmission by direct inverse modeling ,(1998)
Peter S. Maybeck, Stochastic Models, Estimation And Control ,(2012)
Zoubin Ghahramani, Learning Dynamic Bayesian Networks Adaptive Processing of Sequences and Data Structures, International Summer School on Neural Networks, "E.R. Caianiello"-Tutorial Lectures. pp. 168- 197 ,(1997) , 10.1007/BFB0053999
Kevin P. Murphy, Inference and Learning in Hybrid Bayesian Networks University of California at Berkeley. ,(1998)
Xavier Boyen, Daphne Koller, Tractable inference for complex stochastic processes uncertainty in artificial intelligence. pp. 33- 42 ,(1998)
Zoubin Ghahramani, Geoffrey E Hinton, None, Parameter estimation for linear dynamical systems University of Toronto: Department of Computer Science. ,(1996)