Fragment-based Visual Tracking with Multiple Representations
Journal Title: American Journal of Engineering and Applied Sciences - Year 2016, Vol 9, Issue 2
Abstract
Fragment-based Visual Tracking with Multiple Representations Junqiu Wang and Yasushi Yagi DOI : 10.3844/ajeassp.2016.187.194 American Journal of Engineering and Applied Sciences Volume 9, Issue 2 Pages 187-194 Abstract We present a fragment-based tracking algorithm that considers appearance information characterized by a non-parametric distribution and spatial information described by a parametric representation. We segment an input object into several fragments based on the appearance similarity and spatial distribution. Spatial distribution and appearance are important for distinguishing different fragments. We employee such information for separating an object from its background: Appearance information is described by nonparametric representation such as kernels; spatial information is characterized by Gaussians with spatial distribution of fragments. We integrate appearance and spatial information for target localization in images. The overall motion is estimated by the mean shift algorithm. This motion can deviate from the true position in the overall motion estimation because of the mean-shift drifting. We refine the estimated position based on the foreground probabilities. The proposed tracker gives better target localization results and better foreground probability images. Our experimental results demonstrate that the integration of appearance and spatial information by combining parametric and non-parametric representation is effective for tracking targets in difficult sequences. Copyright © 2016 Junqiu Wang and Yasushi Yagi. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. http://thescipub.com/abstract/10.3844/ajeassp.2016.187.194
Authors and Affiliations
Junqiu Wang, Yasushi Yagi
Keywords
Related Articles
- EP ID EP203571
- DOI 10.3844/ajeassp.2016.187.194
- Views 105
- Downloads 0
A Methodology for Continuous Evaluation of Cloud Resiliency
A Methodology for Continuous Evaluation of Cloud Resiliency Long Wang, Tiancheng Liu, Yue Zhang and Xiaoyong Yuan DOI : 10.3844/ajeassp.2016.264.273 American Journal of Engineering and Applied Sciences Volume 9, Issue...
Integration of Human Factor in Design Ergonomics: Example of a High Speed Train Cabin Design
Abstract The development of new technologies and technical progress has accelerated man/machine substitution. Work is disappearing in its human form. This technical progress has not avoided certain catastrophes occurrin...
Stiffened Panels Damage Tolerance Determination using an Optimization Procedure based on a Linear Delamination Growth Approach
Abstract The damage tolerance of delaminated composite panels under compressive load is usually numerically evaluated by means of computationally expensive non-linear approaches. In this study, an alternative numerical...
Effect of Parameters of Selection and Replacement Drilling Bits Based on Geo-Mechanical Factors: (Case Study: Gas and Oil Reservoir in the Southwest of Iran)
Effect of Parameters of Selection and Replacement Drilling Bits Based on Geo-Mechanical Factors: (Case Study: Gas and Oil Reservoir in the Southwest of Iran) Arzhang Nabilou DOI : 10.3844/ajeassp.2016.380.395 American...
George (Gogu) Constantinescu
George (Gogu) Constantinescu Relly Victoria Virgil Petrescu, Raffaella Aversa, Antonio Apicella, MirMilad Mirsayar, Samuel Kozaitis, Taher Abu-Lebdeh and Florian Ion Tiberiu Petrescu DOI : 10.3844/ajeassp.2017.965.979...