The Publication Database hosted by SPL
|
All Publications
Upload
Advanced Search
Gallery View
Download Statistics
Help
Import
Log in
A Generic Framework for Tracking using Particle Filter with Dynamic Shape Prior
|
|
Institution: |
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA. |
Publisher: |
IEEE Trans Image Process |
Publication Date: |
May-2007 |
Volume Number: |
16 |
Issue Number: |
5 |
Pages: |
1370-1382 |
Citation: |
IEEE Trans Image Process. 2007 May;16(5):1370-82. |
PubMed ID: |
17491466 |
PMCID: |
PMC3654013 |
Keywords: |
Dynamic shape prior, geometric active contours, particle filters (PFs), tracking, unscented Kalman filter |
Appears in Collections: |
NA-MIC, NAC |
Sponsors: |
NIH P41 RR13218 U54 EB005149 |
Generated Citation: |
Rathi Y., Vaswani N., Tannenbaum A. A Generic Framework for Tracking using Particle Filter with Dynamic Shape Prior. IEEE Trans Image Process. 2007 May;16(5):1370-82. PMID: 17491466. PMCID: PMC3654013. |
| Downloaded: | 2052 times. [view map] |
| Paper: | Download, View online |
| Export citation: |
Tracking deforming objects involves estimating the global motion of the object and its local deformations as functions of time. Tracking algorithms using Kalman filters or particle filters (PFs) have been proposed for tracking such objects, but these have limitations due to the lack of dynamic shape information. In this paper, we propose a novel method based on employing a locally linear embedding in order to incorporate dynamic shape information into the particle filtering framework for tracking highly deformable objects in the presence of noise and clutter. The PF also models image statistics such as mean and variance of the given data which can be useful in obtaining proper separation of object and background.
Additional Material
1 File (307.077kB)
Rathi-IEEETIP2007-fig.jpg (307.077kB)