A systematic fire detection approach based on sparse least-squares SVMs

Zhang, Jingjing ORCID: https://orcid.org/0000-0002-8970-7568, Li, Kang, Zhao, Wanqing ORCID: https://orcid.org/0000-0001-6160-9547, Fei, Minrui and Wang, Yigang 2014. A systematic fire detection approach based on sparse least-squares SVMs. Presented at: International Conference on Intelligent Computing for Sustainable Energy and Environment and International Conference on Life System Modeling and Simulation, Shanghai, China, 20 -23 September 2014. Published in: Fei, M., Peng, C., Su, Z., Song, Y. and Han, Q. eds. Computational Intelligence, Networked Systems and Their Applications. Communications in Computer and Information Science. Communications in Computer and Information Science , vol.462 (462) Berlin: Springer, pp. 351-362. 10.1007/978-3-662-45261-5_37

Full text not available from this repository.

Abstract

In this paper, a systematic approach adopting sparse least-squares SVMs (LS-SVMs) is proposed to automatically detect fire using vision-based systems with fast speed and good performance. Within this framework, the features are first extracted from input images using wavelet analysis. The LS-SVM is then trained on the obtained dataset with global support vectors (GSVs) selected by a fast subset selection method, in the end of which the classifier parameters can be directly calculated rather than updated during the training process, leading to a significant saving of computing time. This sparse classifier only depends on the GSVs rather than all the patterns, which helps to reduce the complexity of the classifier and improve the generalization performance. Detection results on real fire images show the effectiveness and efficiency of the proposed approach.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Engineering
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Publisher:	Springer
ISBN:	978-3-662-45260-8
ISSN:	1865-0929
Last Modified:	28 Oct 2022 09:45
URI:	https://orca.cardiff.ac.uk/id/eprint/75633

Citation Data

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

Actions (repository staff only)

Edit Item