Multicue HMM-UKF for real-time contour tracking

Author

Yunqiang Chen ; Yong Rui ; Huang, T.S.

Author_Institution

Siemens Corp. Res., Princeton, NJ

Volume

28

Issue

9

fYear

2006

Firstpage

1525

Lastpage

1529

Abstract

We propose an HMM model for contour detection based on multiple visual cues in spatial domain and improve it by joint probabilistic matching to reduce background clutter. It is further integrated with unscented Kalman filter to exploit object dynamics in nonlinear systems for robust contour tracking

Keywords

Kalman filters; clutter; edge detection; hidden Markov models; image matching; nonlinear systems; HMM model; background clutter; contour detection; joint probabilistic matching; multiple visual cues; nonlinear systems; real-time contour tracking; unscented Kalman filter; Application software; Hidden Markov models; Human computer interaction; Nonlinear dynamical systems; Nonlinear systems; Object detection; Particle filters; Robustness; Shape; State-space methods; HMM; Parametric contour; joint probabilistic matching.; unscented Kalman filters; Algorithms; Artificial Intelligence; Computer Simulation; Computer Systems; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Markov Chains; Models, Statistical; Motion; Pattern Recognition, Automated;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.2006.190

Filename

1661554