Proceedings of the 2017 2nd International Conference on Machinery, Electronics and Control Simulation (MECS 2017)

Smoke Classification based on curve transform

Authors
Tiantian Tang, Linhan Dai, Zhijian Yin
Corresponding Author
Tiantian Tang
Available Online June 2016.
DOI
https://doi.org/10.2991/mecs-17.2017.148How to use a DOI?
Keywords
Smoke classification, Curvelet transform, Curvelet coefficients, Support Vector Machine
Abstract
Smoke classification based on video image plays an important role in the performance of fire warning system. This paper presents a smoke classification algorithm based on frequency domain information processing. It is a feature in the video stream image region, which is based on the frequency domain analysis of smoke characteristics. In this paper, a method of extracting features based on Curvelet transform is proposed. Firstly, the multi-scale decomposition of the smoke pattern is preprocessed, and then the effective Curvelet coefficients are extracted as far as possible. At the same time, the selected coefficients as a feature, and finally to the Support Vector Machine classifier to achieve the identification of smoke. The experimental results show that the method can effectively classify the smoke in the frequency domain.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Cite this article

TY  - CONF
AU  - Tiantian Tang
AU  - Linhan Dai
AU  - Zhijian Yin
PY  - 2016/06
DA  - 2016/06
TI  - Smoke Classification based on curve transform
BT  - Proceedings of the 2017 2nd International Conference on Machinery, Electronics and Control Simulation (MECS 2017)
PB  - Atlantis Press
SP  - 277
EP  - 282
SN  - 2352-5401
UR  - https://doi.org/10.2991/mecs-17.2017.148
DO  - https://doi.org/10.2991/mecs-17.2017.148
ID  - Tang2016/06
ER  -