Research on Target Polarization Recognition and Classification Based on BP Neural Network

DOI

10.2991/icsd-16.2017.99How to use a DOI?

Keywords

Polarization Detection; Stokes Parameter, BP neural network; Recognition.

Abstract

Polarization detection technology has become an important means of detection technology. This paper discusses the principle and measuring method of polarization detection, typical features and the polarization characteristics, such as rock, concrete, soil, vegetation and military targets. According to the feature of polarization information, the model of target polarization recognition and classification based on BP neural network is constructed. And to validate the precision of this recognition and classification method t the experiment is organized. The results show that the scattering light polarization information as the classification basis is reliable and the model accuracy reached more than 85%, which have a good performance and can be used in many areas.

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  - Bang Wu
AU  - Qi Jia
AU  - Wei-Dong Xu
AU  - Xu-Liang Lv
AU  - Jiang-Hua Hu
PY  - 2016/12
DA  - 2016/12
TI  - Research on Target Polarization Recognition and Classification Based on BP Neural Network
BT  - Proceedings of the 2nd 2016 International Conference on Sustainable Development (ICSD 2016)
PB  - Atlantis Press
SP  - 453
EP  - 455
SN  - 2352-5401
UR  - https://doi.org/10.2991/icsd-16.2017.99
DO  - 10.2991/icsd-16.2017.99
ID  - Wu2016/12
ER  -