닫기
216.73.216.214
216.73.216.214
close menu
KCI 등재
Object detection for various types of vessels using the YOLO algorithm
박민호, 최재혁, 이원주
DOI http://dx.doi.org/10.5916/jamet.2024.48.2.81

Owing to the development of computer vision technology, much effort is being conducted to apply it in the maritime field. In this study, we developed a model that can detect various types of ships using object detection. Nine types of ship images were downloaded, and bounding box processing of the ships in the images was performed. Among the You Only Look Once (YOLO) model versions for object detection, YOLO v3 and YOLO v5s were used to train the training set, and predictions were made on the validation and testing sets. For the validation and testing sets, both models made good predictions. However, as some mispredictions occurred in the testing set, recommendations for these are given in the last section.

×