Thesis - Won-Jae Lee, "Image-based Object Detection and Tracking Method for the Awareness around the Ship", M.Sc. Thesis, Seoul National University, 2021.02.26

Atachment
첨부 '1'	(202102)이원재석사학위논문.pdf,

Extra Form
Abstract	For the safe operation of autonomous ships, a system that automatically detects the ship's surroundings is required. AIS (Automatic Identification System), RADAR (RAdio Detection And Ranging), and LIDAR (LIght Detection And Ranging) are typical equipment for detecting the ship's surroundings. However, those sensors have limits. AIS cannot detect a ship without AIS equipment. RADAR has a slow update rate, and a blind zone is created depending on the installation location. LIDAR has a short detection range. Therefore, it is necessary to use a camera to supplement existing equipment. In this study, an image-based object recognition technology was developed. Object recognition technology was divided into three categories: detection, localization, and tracking. Detection is a technique that determines the existence and location of objects on the image. Recently, with the rapid development of deep learning, especially Convolutional Neural Network (CNN), deep learning-based object detection technology made remarkable progress. To use the detection model based on deep learning, training data is required. This study compared the open-source data set Singapore Maritime Dataset (SMD) and virtual image data set (Unity Dataset). Localization is a technique that converts the detected bounding box on the image into spatial coordinates through a camera model. Horizontal line information on the image is required. In this study, a gyro sensor was used to detect the horizontal line. Finally, tracking is the task of estimating the position and speed of objects over time. To set the Kalman filter's initial value, the target ship's headings were identified as left/right using deep learning and set as the initial value. The results of tracking target ships were compared with the AIS data to evaluate the tracking accuracy.
Publication Date	2021-02-26

Abstract

For the safe operation of autonomous ships, a system that automatically detects the ship's surroundings is required. AIS (Automatic Identification System), RADAR (RAdio Detection And Ranging), and LIDAR (LIght Detection And Ranging) are typical equipment for detecting the ship's surroundings. However, those sensors have limits. AIS cannot detect a ship without AIS equipment. RADAR has a slow update rate, and a blind zone is created depending on the installation location. LIDAR has a short detection range. Therefore, it is necessary to use a camera to supplement existing equipment.
In this study, an image-based object recognition technology was developed. Object recognition technology was divided into three categories: detection, localization, and tracking. Detection is a technique that determines the existence and location of objects on the image. Recently, with the rapid development of deep learning, especially Convolutional Neural Network (CNN), deep learning-based object detection technology made remarkable progress. To use the detection model based on deep learning, training data is required. This study compared the open-source data set Singapore Maritime Dataset (SMD) and virtual image data set (Unity Dataset). Localization is a technique that converts the detected bounding box on the image into spatial coordinates through a camera model. Horizontal line information on the image is required. In this study, a gyro sensor was used to detect the horizontal line. Finally, tracking is the task of estimating the position and speed of objects over time. To set the Kalman filter's initial value, the target ship's headings were identified as left/right using deep learning and set as the initial value. The results of tracking target ships were compared with the AIS data to evaluate the tracking accuracy.

Publication Date

2021-02-26

Won-Jae Lee, "Image-based Object Detection and Tracking Method for the Awareness around the Ship", M.Sc. Thesis, Seoul National University, 2021.02.26

이원재, "선박 주변 인지를 위한 영상 기반 장애물 탐지 및 추적 방법", 석사학위논문, 서울대학교, 2021.02.26

List of Articles
번호	분류	제목	Publication Date
29	M.Sc. Thesis	Yun-Sik Kim, "An Improved Method for Detection and Tracking of Maritime Obstacles Based on Multiple Sensor Fusion", M.Sc. Thesis, Seoul National University, 2026.02.25	2026-02-25
28	M.Sc. Thesis	Seong-Won Choi, "An Improved Method for Ship Collision Avoidance Based on Deep Reinforcement Learning Using Attention Module and Mixture-of-Experts", M.Sc. Thesis, Seoul National University, 2026.02.25	2026-02-25
27	Ph.D. Thesis	Do-Hyun Chun, "A Method for Collision Avoidance of a Ship Based on Reinforcement Learning in Complex Maritime Situations", Ph.D. Thesis, Seoul National University, 2024.02.29	2024-02-29
26	M.Sc. Thesis	Dong-Gyu Park, "An Optimization Method of Initial Principal Particulars of Small Naval Ships Considering Design Requirements", M.Sc. Thesis, Seoul National University, 2025.02.26	2025-02-26
25	M.Sc. Thesis	In-Su Han, "A Method for Searching Ship Regulations Based on Generative AI Considering the Intent of User’s Query", M.Sc. Thesis, Seoul National University, 2025.02.26	2025-02-26
24	M.Sc. Thesis	Ha-Yun Kim, "An Improved Method for Tracking of Maritime Obstacles Using Sensor Data", M.Sc. Thesis, Seoul National University, 2024.02.26	2024-02-26
23	Ph.D. Thesis	Jisang Ha, "Optimal Arrangement Method of Equipment and Pipes in the Engine Room of a Ship", Ph.D. Thesis, Seoul National University, 2023.08.29	2023-08-29
22	M.Sc. Thesis	Dong-Geun Jeong, "A Method for Hierarchical Route Planning of Small ships in Coastal Area Using Quadtree Chart", M.Sc. Thesis, Seoul National University, 2023.02.24	2023-02-24
21	M.Sc. Thesis	Jeong-Ho Park, "A Method for Detection and Tracking of Maritime Obstacles Based on Multi-Video", M.Sc. Thesis, Seoul National University, 2023.02.24	2023-02-24
20	M.Sc. Thesis	Hamin Song, "Optimization of Crew Manning Considering Operation Scenarios of a Naval Ship", M.Sc. Thesis, Seoul National University, 2023.02.24	2023-02-24
19	M.Sc. Thesis	Yeongmin Jo, "A Method for the Path Tracking of Surrounding Ships Using Multiple Sensors", M.Sc. Thesis, Seoul National University, 2022.02.25	2022-02-25
»	M.Sc. Thesis	Won-Jae Lee, "Image-based Object Detection and Tracking Method for the Awareness around the Ship", M.Sc. Thesis, Seoul National University, 2021.02.26	2021-02-26
17	M.Sc. Thesis	June-Beom Lee, "Development of Prediction Models of Ship Power and Ocean Environmental Data Based on Deep Learning", M.Sc. Thesis, Seoul National University, 2021.02.26	2021-02-26
16	Ph.D. Thesis	Hye-Won Lee, "Wire Rope Contact Model and Crane Control Method for the Advanced Simulation and Automation of Block Erection", Ph.D. Thesis, Seoul National University, 2020.02.26	2020-02-26
15	Ph.D. Thesis	Ki-Su Kim, "Assessment Method of the Fitness of Initial Arrangement Design of a Naval Ship", Ph.D. Thesis, Seoul National University, 2019.08.29	2019-08-29
14	M.Sc. Thesis	Sung-Woo Park, "Data Mining Method for Offshore Structures based on Big Data Technology", M.Sc. Thesis, Seoul National University, 2019.02.26	2019-02-26
13	Ph.D. Thesis	Luman Zhao, "Simulation Method to Support Autonomous Navigation and Installation Operation of an Offshore Support Vessel", Ph.D. Thesis, Seoul National University, 2019.02.26	2019-02-01
12	M.Sc. Thesis	Joo-Pil Lee, "Design of Wreck Removal Considering Safety and Economy", M.Sc. Thesis, Seoul National University, 2019.02.26	2019-02-26
11	Ph.D. Thesis	Seung-Ho Ham, "Integrated Simulation Method Based on Multibody Dynamics for Production Design Verification in Ships and Offshore Structures", Ph.D. Thesis, Seoul National University, 2018.08.29	2018-08-29
10	M.Sc. Thesis	Sang-Hyun Lee, "Integrated Method for Layout Design of LNG FPSO Based on Optimization Technique and Expert System", M.Sc. Thesis, Seoul National University, 2018.02.26	2018-02-26

번호

분류

제목

Publication Date

M.Sc. Thesis

Yun-Sik Kim, "An Improved Method for Detection and Tracking of Maritime Obstacles Based on Multiple Sensor Fusion", M.Sc. Thesis, Seoul National University, 2026.02.25 file