Interacting Multiple Model LK Tracking

Hong Wang; Jia Deng

doi:10.4028/www.scientific.net/AMM.644-650.1733

Paper Titles

An Algorithm for Mining Weighted Negative Sequence Pattern
p.1717

Study on Multidimensional Negative Association Rules
p.1721

Visual Growth Model Research of Gramineous Adventitious Root System
p.1725

Digital Growth Model Research on Repent Stem of Grasses
p.1729

Interacting Multiple Model LK Tracking
p.1733

The Optimization Algorithm and Applied in Soil Fertility Evaluation Based on Data Mining
p.1737

Simulation Analysis of the Three-Dimensional Ball Motion
p.1741

Application of Three-Dimensional Virtual Model in the Field of Architectural Design
p.1745

The Effective Classification Process Analysis of the Big Data in Construction Project
p.1749

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 644-650Interacting Multiple Model LK Tracking

Interacting Multiple Model LK Tracking

Abstract:

The nonlinear motion state of object seriously affects the object tracking characteristics in complex motion scene. In this paper, we propose an interacting multiple model LK (IMM-LK) tracking algorithm to enhance the performance of tracking nonlinear moving object. LK tracking approach is based on the localized gradient obtaining stable optical-flow feature, based on LK, we build several motion models of the tracked object that interact with each other in the tracking process. The method extracts different model's object features, estimates the object state and calculates the matching rate of each model with the current motion model using theory of minimum variance. Combining with the optimal transfer matrix then we can track the nonlinear moving object. The proposed IMM-LK algorithm performs favorably against conventional LK tracking on the performance of tracking nonlinear moving object.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 644-650)

Pages:

1733-1736

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.644-650.1733

Citation:

Cite this paper

Online since:

September 2014

Authors:

Hong Wang*, Jia Deng

Keywords:

Constant Acceleration (CA), Constant Velocity (CV), Interacting Multiple Model (IMM), Lucas-Kanade (LK) Method, Optical Flow

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Magill D. Optimal adaptive estimation of sampled stochastic processes [J]. Automatic Control, IEEE Transactions on, 1965, 10(4): 434-439.

DOI: 10.1109/tac.1965.1098191

Google Scholar

[2] Blom P. An efficient filter for abruptly changing systems[C]/The 23rd IEEE Conference on Decision and Control. 1984, 23: 656-658.

DOI: 10.1109/cdc.1984.272089

Google Scholar

[3] Li X R, Bar-Shalom Y. Multiple-model estimation with variable structure [J]. Automatic Control, IEEE Transactions on, 1996, 41(4): 478-493.

DOI: 10.1109/9.489270

Google Scholar

[4] Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[C]/IJCAI. 1981, 81: 674-679.

Google Scholar

[5] Nagel H H, Enkelmann W. An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1986 (5): 565-593.

DOI: 10.1109/tpami.1986.4767833

Google Scholar

[6] Horn B K, Schunck B G. Determining optical flow[C]/1981 Technical Symposium East. International Society for Optics and Photonics, 1981: 319-331.

Google Scholar