A Waterway Monitoring Method of Unmanned Surface Vehicle Based on Deep Learning

DOI

10.2991/cnci-19.2019.70How to use a DOI?

Keywords

Waterway Monitoring Method, RPN network.

Abstract

A waterway monitoring method of unmanned surface vehicle based on deep learning is proposed to help identify ship accidents in real time. Compared with the traditional waterway monitoring method, the use of unmanned surface vehicle is more flexible and the recognition method of deep learning is more real-time. First, we build a dataset of ship accidents, and then use this dataset to train the Faster R-CNN network, we optimize the RPN in the fast R-CNN framework for the problem of missed detection at the same time, and finally obtain the target detection model. Experiments show that the method can effectively improve the efficiency of the waterway monitoring, greatly reduce the labour cost, and facilitate the management personnel to grasp the waterway situation in real time.

Copyright

© 2019, 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  - Yiheng Wu
AU  - Xing Li
AU  - Zhangjie Yin
AU  - Jian Li
AU  - Yan Zhou
PY  - 2019/05
DA  - 2019/05
TI  - A Waterway Monitoring Method of Unmanned Surface Vehicle Based on Deep Learning
BT  - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)
PB  - Atlantis Press
SP  - 510
EP  - 514
SN  - 2352-538X
UR  - https://doi.org/10.2991/cnci-19.2019.70
DO  - 10.2991/cnci-19.2019.70
ID  - Wu2019/05
ER  -