Evaluation of on-line quality estimators for object tracking
Metadatos
Title:
Evaluation of on-line quality estimators for object tracking
Author:
Sanmiguel, Juan Carlos; Cavallaro, Andrea; Martínez, José M.
Entity:
UAM. Departamento de Tecnología Electrónica y de las Comunicaciones
Publisher:
Institute of Electrical and Electronics Engineers
Date:
2010
Citation:
10.1109/ICIP.2010.5653449
17th IEEE International Conference on Image Processing, ICIP 2010. IEEE, 2010. 825-828
ISSN:
1522-4880
ISBN:
978-1-4244-7993-1 (online); 978-1-4244-7992-4 (print)
DOI:
10.1109/ICIP.2010.5653449
Funded by:
Work partially supported by the Spanish Government (TEC2007- 65400 SemanticVideo), Cátedra Infoglobal-UAM for “Nuevas
Tecnologías de video aplicadas a la seguridad”, Consejería de Educación of the Comunidad de Madrid and European Social Fund. Part of
the work reported in this paper was done during a research stay of the first author under a research grant (funded by UAM) at Queen Mary
University of London (UK).
Editor's Version:
http://dx.doi.org/10.1109/ICIP.2010.5653449
Subjects:
Performance evaluation without groundtruth; Video surveillance; Visual tracking quality; Telecomunicaciones
Note:
Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. J. C. SanMiguel, A. Cavallaro, and J. M. Martínez, "Evaluation of on-line quality estimators for object tracking", in 17th IEEE International Conference on Image Processing, ICIP 2010, p. 825-828
Rights:
© 2010 IEEE
Abstract:
Failure of tracking algorithms is inevitable in real and on-line tracking systems. The online estimation of the track quality is therefore desirable for detecting tracking failures while the algorithm is operating. In this paper, we propose a taxonomy and present a comparative evaluation of online quality estimators for video object tracking. The measures are compared over a heterogeneous video dataset with standard sequences. Among other results, the experiments show, that the Observation Likelihood (OL) measure is an appropriate quality measure for overall tracking performance evaluation, while the Template Inverse Matching (TIM) measure is appropriate to detect the start and the end instants of tracking failures.
Show full item record
Save this on Delicious