비전 센서 및 딥러닝 기반 선박 접안을 위한 어라운드뷰 모니터링 시스템
Vision Sensor and Deep Learning-based Around View Monitoring System for Ship Berthing
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This paper proposes vision sensors and deep learning-based around view monitoringsystem for ship berthing. Ship berthing to the port requires precise relative position and relativespeed information between the mooring facility and the ship. For ships of Handysize or higher,the vesselships must be docked with the help of pilots and tugboats. In the case of ships handlingdangerous cargo, tug boats push the ship and dock it in the port, using the distance and velocityinformation receiving from the berthing aid system (BAS). However, the existing BAS is veryexpensive and there is a limit on the size of the vessel that can be measured. Also, there is alimitation that it is difficult to measure distance and speed when there are obstacles near theport. This paper proposes a relative distance and speed estimation system that can be used as aship berthing assist system. The proposed system is verified by comparing the performance withthe existing laser-based distance and speed measurement system through the field tests at theactual port.
Abstract
This paper proposes vision sensors and deep learning-based around view monitoringsystem for ship berthing. Ship berthing to the port requires precise relative position and relativespeed information between the mooring facility and the ship. For ships of Handysize or higher,the vesselships must be docked with the help of pilots and tugboats. In the case of ships handlingdangerous cargo, tug boats push the ship and dock it in the port, using the distance and velocityinformation receiving from the berthing aid system (BAS). However, the existing BAS is veryexpensive and there is a limit on the size of the vessel that can be measured. Also, there is alimitation that it is difficult to measure distance and speed when there are obstacles near theport. This paper proposes a relative distance and speed estimation system that can be used as aship berthing assist system. The proposed system is verified by comparing the performance withthe existing laser-based distance and speed measurement system through the field tests at theactual port.
참고문헌 (10)
- Korea Coast Guard, "Statistical Yearbook of Maritime Distress in 2018"
- Status of Marine Accidents by Ship Use, "Korean Statistical Information Service", ~
- "AVISS Sensor Module, Seadronix"[URL]
- H. Kim, "Vision-based Real-time Obstacle Segmentation Algorithm for Autonomous Surface Vehicle", Journal of IEEE Access, 7, pp.179420~179428 (2019)
- A. G. Howard, "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications", pp.1~9 (2017)
- A. Pazke, "ENet: A Deep Neural Network Architecture for Real-time Semantic Segmentation", pp.1~10 (2017)
- L. -C. Chen, "Encoder-decoder with Atrous Separable Convolution for Semantic Image Segmentation", Proceedings of European Conference on Computer Cision, pp.833~851 (2018)
- 정호열, "딥러닝 기반 3차원 라이다의 반사율 세기 신호를 이용한 흑백 영상 생성 기법", 대한임베디드공학회논문지, 14(1), pp.1~9 (2019), 대한임베디드공학회[DOI]
- 김영백, "웨이블릿 퓨전에 의한 딥러닝 색상화의 성능 향상", 대한임베디드공학회논문지, 13(6), pp.313~319 (2018), 대한임베디드공학회[DOI]
- K. He, "Single Image Haze Removal Using Dark Channel Prior", Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12), pp.2341~2353 (2011)