On the evaluation of background subtraction algorithms without ground-truth
Metadatos
Title:
On the evaluation of background subtraction algorithms without ground-truth
Author:
Sanmiguel, Juan Carlos; 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/AVSS.2010.21
2010 Seventh IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2010. IEEE 2010. 180-187
ISBN:
978-1-4244-8310-5
DOI:
10.1109/AVSS.2010.21
Funded by:
This work is partially supported by the Spanish
Government (TEC2007- 65400 SemanticVideo), by
Cátedra Infoglobal-UAM for “Nuevas Tecnologías de
video aplicadas a la seguridad”, by the Consejería de
Educación of the Comunidad de Madrid and by the
European Social Fund.
Editor's Version:
http://dx.doi.org/10.1109/AVSS.2010.21
Subjects:
Informática; 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. San Miguel, and J. M. Martínez, "On the evaluation of background subtraction algorithms without ground-truth" in 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, 2013, 180 - 187
Rights:
© 2010 IEEE
Abstract:
In video-surveillance systems, the moving object segmentation stage (commonly based on background subtraction) has to deal with several issues like noise, shadows and multimodal backgrounds. Hence, its failure is inevitable and its automatic evaluation is a desirable requirement for online analysis. In this paper, we propose a hierarchy of existing performance measures not-based on ground-truth for video object segmentation. Then, four measures based on color and motion are selected and examined in detail with different segmentation algorithms and standard test sequences for video object segmentation. Experimental results show that color-based measures perform better than motion-based measures and background multimodality heavily reduces the accuracy of all obtained evaluation results.
Show full item record