CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Robust Visual Object Tracking using Multi-Mode Anisotropic Mean Shift and Particle Filters

Zulfiqar H. Khan (Institutionen för signaler och system, Signalbehandling) ; Irene Y.H. Gu (Institutionen för signaler och system, Signalbehandling) ; Andrew Backhouse
IEEE Transactions on Circuits and Systems for Video Technology (1051-8215). Vol. 21 (2011), 1, p. 74-87.
[Artikel, refereegranskad vetenskaplig]

This paper addresses issues in object tracking where videos contain complex scenarios. We propose a novel tracking scheme that jointly employs particle filters and multi-mode anisotropic mean shift. The tracker estimates the dynamic shape and appearance of objects, and also performs online learning of reference object. Several partition prototypes and fully tunable parameters are applied to the rectangular object bounding box for improving the estimates of shape and multiple appearance modes in the object. The main contributions of the proposed scheme include: (a) use a novel approach for online learning of reference object distributions; (b) use a five parameter set (2D central location, width, height, and orientation) of rectangular bounding box as tunable variables in the joint tracking scheme; (c) derive the multi-mode anisotropic mean shift related to a partitioned rectangular bounding box and several partition prototypes; (d) relate the bounding box parameter computation with the multi-mode mean shift estimates by combining eigen-decomposition, geometry of subareas and weighted average. This has led to more accurate and efficient tracking where only small number of particles (<20) is required. Experiments have been conducted for a range of videos captured by a dynamic or stationary camera, where the target object may experience long-term partial occlusions, intersections with other objects with similar color distributions, deformable object accompanied with shape, pose or abrupt motion speed changes, and cluttered background. Comparisons with existing methods and performance evaluations are also performed. Test results have shown marked improvement of the proposed method in terms of robustness to occlusions, tracking drifts and tightness and accuracy of tracked bounding box. Limitations of the method are also mentioned.

Nyckelord: Visual object tracking, anisotropic mean shift, particle filters, multiple modes,multiple parts, partial object occlusion, object intersection, online learning.

Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2010-09-20. Senast ändrad 2011-03-21.
CPL Pubid: 126617


Läs direkt!

Länk till annan sajt (kan kräva inloggning)

Institutioner (Chalmers)

Institutionen för signaler och system, Signalbehandling (1900-2017)


Informations- och kommunikationsteknik

Chalmers infrastruktur

Relaterade publikationer

Denna publikation ingår i:

Stochastic Modeling for Video Object Tracking and Online Learning: manifolds and particle filters