4.7 Article

Detection and tracking for the awareness of surroundings of a ship based on deep learning

Journal

JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
Volume 8, Issue 5, Pages 1407-1430

Publisher

OXFORD UNIV PRESS
DOI: 10.1093/jcde/qwab053

Keywords

ship awareness; object detection; deep learning; object tracking; Kalman filter

Funding

  1. Korea Research Institute of Ships and Ocean Engineering (KRISO) [PES3880]
  2. Ministry of Science and ICT, Republic of Korea [1711097744]
  3. Research Institute of Marine Systems Engineering of Seoul National University, Republic of Korea
  4. Institute of Engineering Research of Seoul National University, Republic of Korea

Ask authors/readers for more resources

In this study, ship awareness was achieved through ship detection using YOLO(v3), constructing a virtual image dataset using Unity, calculating the position of the horizon in ship images, tracking target ships' positions and speeds, and proposing a deep learning model to determine ship headings. The proposed method for ship awareness based on camera images was successfully validated in various scenarios, demonstrating good detection, localization, and tracking performance.
To prevent maritime accidents, it is crucial to be aware of the surrounding environment near ships. The images recorded by a camera mounted on a ship could be used for the awareness of other ships surrounding it. In this study, ship awareness was performed using three procedures: detection, localization, and tracking. Initially, ship detection was performed using the deep learning-based detection model, YOLO (You Only Look Once) v3, based on the camera image. A virtual image dataset was constructed using Unity to overcome the difficulty of obtaining camera images onboard with various sizes of ships, and to improve the detection performance. This was followed by the localization procedure in which the position of the horizon on the image was calculated using the orientation information from the ship. Subsequently, the position of the detected ship in the spatial coordinate system was calculated using the horizon information. Following this, the position, course over ground, and speed over ground of the target ships were tracked in the time domain using the extended Kalman filter. A deep learning model that determines the heading of the ship in the image was proposed to utilize abundant information of cameras, and it was used to set the initial value of the Kalman filter. Finally, the proposed method for the awareness of ships was validated using an actual video captured from a camera installed on an actual ship with various encountering scenarios. The tracking results were compared with actual automatic identification system data obtained from other ships. As a result, the entire detection, localization, and tracking procedures showed good performance, and it was estimated that the proposed method for the awareness of the surroundings of a ship, based on camera images, could be used in the future.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available