Journal - 남권우, 노명일, 이혜원, 이원재, "자율 운항 선박을 위한 딥 러닝 기반 선박 이미지 분류 방법", 한국CDE학회 논문집, Vol. 26, No. 2, pp. 144-153, 2021.06.01

Atachment
첨부 '1'	KCDE(202106).pdf,

Extra Form
Abstract	In the last few years, researches on autonomous ships have attracted attention. One of the essential techniques required for autonomous ships is the awareness of surroundings, including detection and classification of objects. Although researches on computer vision regarding the classification of ship images are still making progress, it is challenging to encounter a lack of enough database that was adequately labeled for ship classification. In this study, data obtained from Singapore Maritime Dataset (SMD) and public datasets such as MARVEL, FleetMon, and VesselFinder were labeled and integrated into a unified dataset for further study for ship classification. The ship image dataset was classified into seven classes, including bulk carrier, container ship, cruise ship, naval surface ship, tanker, tug boat, and buoy. Subsequently, Convolutional Neural Networks (CNNs) based on GoogleNet, VGG16, and ResNet were implemented for ship image classification, and a comparative test was done. As a result, the CNNs which were trained with the unified dataset showed high accuracy. The classification results were analyzed by the heatmap visualization with Grad-CAM, which indicates critical features best activating each class of ships, and further discussion was made.
Publication Date	2021-06-01
Role	Corresponding Author
Category	KCI

Abstract

In the last few years, researches on autonomous ships have attracted attention. One of the essential techniques required for autonomous ships is the awareness of surroundings, including detection and classification of objects. Although researches on computer vision regarding the classification of ship images are still making progress, it is challenging to encounter a lack of enough database that was adequately labeled for ship classification. In this study, data obtained from Singapore Maritime Dataset (SMD) and public datasets such as MARVEL, FleetMon, and VesselFinder were labeled and integrated into a unified dataset for further study for ship classification. The ship image dataset was classified into seven classes, including bulk carrier, container ship, cruise ship, naval surface ship, tanker, tug boat, and buoy. Subsequently, Convolutional Neural Networks (CNNs) based on GoogleNet, VGG16, and ResNet were implemented for ship image classification, and a comparative test was done. As a result, the CNNs which were trained with the unified dataset showed high accuracy. The classification results were analyzed by the heatmap visualization with Grad-CAM, which indicates critical features best activating each class of ships, and further discussion was made.

Publication Date

2021-06-01

Role

Corresponding Author

Category

KCI

남권우, 노명일, 이혜원, 이원재, "자율 운항 선박을 위한 딥 러닝 기반 선박 이미지 분류 방법", 한국CDE학회 논문집, Vol. 26, No. 2, pp. 144-153, 2021.06.01

List of Articles
번호	분류	제목	Publication Date
172	International Journal	Do-Hyun Chun, Myung-Il Roh, Hye-Won Lee, "Automation of Crane Control for Block Lifting Based on Deep Reinforcement Learning", accepted for publication in Journal of Computational Design and Engineering, 2022.07.11	2022-07-11
171	International Journal	Min-Chul Kong, Myung-Il Roh, Ki-Su Kim, Jeongyoul Lee, Jongoh Kim, Gapheon Lee, "Object Detection Method for Ship Safety Plans Using Deep Learning", Ocean Engineering, 2022.02.15	2022-02-15
170	International Journal	Ki-Su Kim, Myung-Il Roh, Seung-Min Lee, "Quasi-static Flooding Analysis Method of a Damaged Ship Considering Oil Spill and Cargo Load", Journal of Ship Production and Design, 2022.02.10	2022-02-10
169	International Journal	Won-Jae Lee, Myung-Il Roh, Hye-Won Lee, Jisang Ha, Yeong-Min Cho, Nam-Sun Son, “Detection and Tracking for the Awareness of Surroundings of a Ship Based on Deep Learning”, Journal of Computational Design and Engineering, Vo. 8, No. 5	2021-10-01
168	International Journal	Hye-Won Lee, Joo-Hyun Woo, Myung-Il Roh, Seung-Ho Ham, et al., "Integrated Simulation of Virtual Prototypes and Control Algorithms of Unmanned Surface Vehicles Based on a Robot Operating System", Journal of Marine Science and Technology (Taiwan)	2021-09-03
167	International Journal	Do-Hyun Chun, Myung-Il Roh, Hye-Won Lee, Jisang Ha, Donghun Yu, “Deep Reinforcement Learning-based Collision Avoidance for an Autonomous Ship”, Ocean Engineering, Vol. 234, pp. 1-20, 2021.08.15	2021-08-15
166	International Journal	Hye-Won Lee, Myung-Il Roh, Ki-Su Kim, “Ship Route Planning in Arctic Ocean Based on POLARIS”, Ocean Engineering, Vol. 234, pp. 109297.1-14, 2021.08.15	2021-08-15
165	International Journal	June-Beom Lee, Myung-Il Roh, Ki-Su Kim, “Prediction of Ship Power Based on Variation in Deep Feed-forward Neural Network”, International Journal of Naval Architecture and Ocean Engineering, 2021.08.07	2021-08-12
164	International Journal	Jisang Ha, Myung-Il Roh, Seung-Ho Ham, Sung-Jun Lee, “Optimum Design of the Underwater Discharge System Based on Surrogate Modeling”, Journal of Marine Science and Technology (Taiwan), Vol. 29, No. 3, pp. 338-353, 2021.06.01	2021-06-01
163	International Journal	Jisang Ha, Myung-Il Roh, Hye-Won Lee, “Quantitative Calculation Method of the Collision Risk for Collision Avoidance in Ship Navigation Using the CPA and Ship Domain”, Journal of Computational Design and Engineering, Vol. 8, No. 3, 2021.06.01	2021-06-01
»	Domestic Journal	남권우, 노명일, 이혜원, 이원재, "자율 운항 선박을 위한 딥 러닝 기반 선박 이미지 분류 방법", 한국CDE학회 논문집, Vol. 26, No. 2, pp. 144-153, 2021.06.01	2021-06-01
161	International Journal	Beom-Soo Kim, Min-Jae Oh, Jae-Hoon Lee, Yonghwan Kim, Myung-Il Roh, "Study on Hull Optimization Process Considering Operational Efficiency in Waves", Processes, Vol. 9, No. 5, pp. 898.1-21, 2021.05.19	2021-05-19
160	International Journal	Min-Jae Oh, Myung-Il Roh, Sung-Woo Park, Do-Hyun Chun, Myeong-Jo Son, Jeong-Youl Lee, “Operational Analysis of Container Ships by Using Maritime Big Data”, Journal of Marine Science and Engineering, Vol. 9, No. 4, pp. 438: 1-21, 2021.04.18	2021-04-18
159	International Journal	Hye-Won Lee, Myung-Il Roh, Seung-Ho Ham, "Underactuated Crane Control for the Automation of Block Erection in Shipbuilding", Automation in Construction, Vol. 124, pp. 1-28, 2021.04.01	2021-04-01
158	International Journal	Seung-Min Lee, Jong-Hyeok Lee, Myung-Il Roh, Ki-Su Kim, Seung-Ho Ham, Hye-Won Lee, "An Optimization Model of Tugboat Operation for Conveying a Large Surface Vessel", Journal of Computational Design and Engineering, Vol. 8, No. 2, 2021.04.01	2021-04-01
157	International Journal	Seung-Ho Ham, Myung-Il Roh, “Time-domain Structural Analysis During Block Turnover and Lifting Using 2D Flexible Multibody Dynamics”, Marine Structures, Vol. 75, pp. 102841.1-26, 2021.01.01	2021-01-01
156	International Journal	Ki-Su Kim, Myung-Il Roh, "Dynamic Flooding Analysis Method for Intermediate Flooding Process of a Ship", Ocean Engineering, Vol. 218, pp. 108173.1-33, 2020.12.15	2020-12-15
155	International Journal	Joo-Pil Lee, Myung-Il Roh, Hye-Won Lee, Seung-Ho Ham, "Design of a Wreck Removal Method Considering Safety and Economy", Ships and Offshore Structures, Vol. 15, No. 10, pp. 1037-1056, 2020.12.01	2020-12-01
154	International Journal	Hye-Won Lee, Myung-Il Roh, Seung-Ho Ham, "Block Erection Simulation Considering Frictional Contact with Wire Ropes", Ocean Engineering, Vol. 217, pp. 1-24, 2020.12.01	2020-12-01
153	International Journal	Sung-Jun Lee, Myung-Il Roh, Min-Jae Oh, "Image-based Ship Detection Using Deep Learning", Ocean Systems Engineering, Vol. 10, No. 4, pp. 415-434, 2020.12.01	2020-12-01

번호

분류

제목

Publication Date

172

International Journal

Do-Hyun Chun, Myung-Il Roh, Hye-Won Lee, "Automation of Crane Control for Block Lifting Based on Deep Reinforcement Learning", accepted for publication in Journal of Computational Design and Engineering, 2022.07.11

2022-07-11

171

International Journal

Min-Chul Kong, Myung-Il Roh, Ki-Su Kim, Jeongyoul Lee, Jongoh Kim, Gapheon Lee, "Object Detection Method for Ship Safety Plans Using Deep Learning", Ocean Engineering, 2022.02.15 file