| Abstract | Manually converting the information of objects existing in the ship safety plan into digital data requires significant effort and time. To overcome this problem, a technique is required for automatically extracting the location and information of the object in the plan. However, owing to the characteristics of the ship safety plan, there are frequent cases in which the detection target overlaps with noise (figure, text, etc.), which lowers the detection accuracy. In this study, an object detection model based on a convolutional neural network is proposed to extract the number and location of objects effectively in a ship safety plan while incorporating noise. Among various deep learning models, suitable models for object detection in ship safety plans were compared and analyzed. In addition, an algorithm to generate the data necessary for training the object detection model was proposed. Subsequently, a specialized detection algorithm to rapidly process a large ship safety plan was proposed. The method proposed in this study was applied to 15 ship safety plans. Consequently, an average recall of 0.85 was achieved, confirming the effectiveness of the proposed method. |
|---|---|
| Publication Date | 2022-02-15 |
| Role | Corresponding Author |
| Category | SCI |
| Impact Factor | 3.795 |
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, Vol. 246, pp. 110587.1-15, 2022.02.15
https://doi.org/10.1016/j.oceaneng.2022.110587