Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Multiple-cue-based visual object contour tracking with incremental learning

Wang, Aiping, Cheng, Zhi-Quan, Martin, Ralph Robert and Li, Sikun 2013. Multiple-cue-based visual object contour tracking with incremental learning. Pan, Zhigeng, Cheok, Adrian David, Müller, Wolfgang and Liarokapis, Fotis, eds. Transactions on Edutainment IX, Lecture Notes in Computer Science, vol. 7544. Springer Berlin Heidelberg, pp. 225-243. (10.1007/978-3-642-37042-7_16)

[thumbnail of Tracking.pdf]
PDF - Submitted Pre-Print Version
Download (602kB) | Preview


This paper proposes a visual object contour tracking algorithm using a multi-cue fusion particle filter. A novel contour evolution energy is proposed which integrates an incrementally learnt model of object appearance with a parametric snake model. This energy function is combined with a mixed cascade particle filter tracking algorithm which fuses multiple observation models for object contour tracking. Bending energy due to contour evolution is modelled using a thin plate spline (TPS). Multiple order graph matching is performed between contours in consecutive frames. Both of the above are taken as observation models for contour deformation; these models are fused efficiently using a mixed cascade sampling process. The dynamic model used in our tracking method is further improved by the use of optical flow. Experiments on real videos show that our approach provides high performance object contour tracking.

Item Type: Book Section
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Uncontrolled Keywords: Tracking; Snake model; Particle filter; Mixed cascade
Additional Information: PDF uploaded in accordance with publisher's policy [accessed 29/05/2015] The final publication is available at Springer via
Publisher: Springer Berlin Heidelberg
ISBN: 9783642370410
ISSN: 03029743
Related URLs:
Last Modified: 04 Jun 2017 04:48

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics