Application of Gaussian Mixture Model in Identification of Oil Spill on Sea

DOI

10.2991/mmebc-16.2016.256How to use a DOI?

Keywords

oil spill identification, Gaussian mixture model, image segmentation and unsupervised clustering

Abstract

Aiming at the phenomena of evaporating, emitting, dripping or leaking of offshore oil platform, optical image acquisition device is used to carry out continuous unattended monitoring and effective oil spill identification algorithm is utilized to monitor and identify offshore oil spill. This paper focuses on exploring the study on application of Gaussian mixture model in segmentation and recognition of offshore oil spill image, describes specific algorithm and build an offshore oil spill model by using the expectation-maximization (EM) algorithm and minimum description length (MDL) principle of Gaussian mixture model and combines sequential maximum a posteriori (SMAP) algorithm to segment and identify oil spill image. The research result shows that this method can be used to effectively acquire oil spill information and effectively segment and identify oil spill image.

Copyright

© 2016, 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  - Weiwei Jin
AU  - Yupeng Zhao
AU  - Wei An
AU  - Jianwei Li
PY  - 2016/06
DA  - 2016/06
TI  - Application of Gaussian Mixture Model in Identification of Oil Spill on Sea
BT  - Proceedings of the 2016 6th International Conference on Machinery, Materials, Environment, Biotechnology and Computer
PB  - Atlantis Press
SP  - 1257
EP  - 1262
SN  - 2352-5401
UR  - https://doi.org/10.2991/mmebc-16.2016.256
DO  - 10.2991/mmebc-16.2016.256
ID  - Jin2016/06
ER  -