Smoke Image Recognition Based on Local Binary pattern

DOI

10.2991/icmmcce-17.2017.199How to use a DOI?

Keywords

Background Subtraction; Local Binary Pattern (LBP); Support Vector Machines (SVM)

Abstract

Smoke accurate detection, for the real-time fire detection and early warning has an important role. In order to overcome the problem that the smoke is low when the fire is burned, the video smoke detection method based on the local binary mode is proposed under the condition of disturbing the wind speed and other factors. In this method, the motion region is extracted by the background subtraction method, and each piece of motion area is processed to obtain local information. Then, the texture feature of each block is extracted by using the local binary model. Finally, the texture features of the smoke texture are used to obtain the texture feature. To achieve smoke image extraction. Finally, the support vector machine is used to classify the extracted features. Experiments show that the local binary pattern texture features show good attribute characteristics in the texture, and the correlation test data and the comparison result show that the texture feature is effective for the detection of smoke.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tiantian Tang
AU  - Linhan Dai
AU  - Zhijian Yin
PY  - 2017/09
DA  - 2017/09
TI  - Smoke Image Recognition Based on Local Binary pattern
BT  - Proceedings of the 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2017)
PB  - Atlantis Press
SP  - 1118
EP  - 1123
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmcce-17.2017.199
DO  - 10.2991/icmmcce-17.2017.199
ID  - Tang2017/09
ER  -