Application of Convolutional Neural Network (CNN) to Recognize Ship Structures

Jae-Jun Lim; Dae-Won Kim; Woon-Hee Hong; Min Kim; Dong-Hoon Lee; Sun-Young Kim; Jae-Hoon Jeong

doi:10.3390/s22103824

Application of Convolutional Neural Network (CNN) to Recognize Ship Structures

Sensors (Basel). 2022 May 18;22(10):3824. doi: 10.3390/s22103824.

Authors

Jae-Jun Lim¹, Dae-Won Kim², Woon-Hee Hong³, Min Kim¹, Dong-Hoon Lee⁴, Sun-Young Kim⁵, Jae-Hoon Jeong⁶

Affiliations

¹ The Department of Control and Instrumentation Engineering, Pukyong National University, Busan 48513, Korea.
² The School of Interdisciplinary Management, Ulsan National Institute of Science and Technology, Ulsan 44919, Korea.
³ The Department of Radio Engineering, Korea Maritime & Ocean University, Busan 49112, Korea.
⁴ The Department of Energy Transport System Engineering, Major of Mechanical System Engineering, Pukyong National University, Busan 48513, Korea.
⁵ The School of Mechanical Engineering, Kunsan National University, Gunsan 54150, Korea.
⁶ The School of IT, Information and Control Engineering, Kunsan National University, Gunsan 54150, Korea.

Abstract

The purpose of this paper is to study the recognition of ships and their structures to improve the safety of drone operations engaged in shore-to-ship drone delivery service. This study has developed a system that can distinguish between ships and their structures by using a convolutional neural network (CNN). First, the dataset of the Marine Traffic Management Net is described and CNN's object sensing based on the Detectron2 platform is discussed. There will also be a description of the experiment and performance. In addition, this study has been conducted based on actual drone delivery operations-the first air delivery service by drones in Korea.

Keywords: convolutional neural network (CNN); faster R-CNN; mask R-CNN; recognize ship structures.

MeSH terms

Neural Networks, Computer*
Republic of Korea
Ships*

Grants and funding

S3050712/Korea Technology and Information Promotion Agency