Young-Min Kim, Ki-Won Kwon, Tae-Ho Im, Journal of Internet Computing and Services, Vol. 25, No. 5, pp. 131-140, Oct. 2024
10.7472/jksii.2024.25.5.131, Full Text:
Keywords: Horizontal line detection, vessel detection, Binarization, route sign, Image Segmentation

Abstract

Aids to navigation, such as buoys used in maritime environments, play a crucial role in providing accurate information to navigating vessels, enabling them to precisely determine their position and maintain safe routes by marking surrounding hazardous areas. However, collisions between ships and these aids result in substantial costs for buoy damage and repair. While high-end equipment is currently used to prevent such accidents, its widespread adoption is hindered by cost concerns. This paper presents research on a maritime object detection algorithm utilizing embedded systems to address this issue. Previous studies employed the Hough transform for horizon detection, but its high computational demands posed challenges for real-time processing. To overcome this limitation, our approach first performs image segmentation, followed by an optimized Otsu algorithm for horizon detection. Subsequently, we establish a Region of Interest (ROI) based on the detected horizon, focusing on areas with a high risk of ship collision. Within this ROI, particularly below the horizon line, maritime objects are detected. A Convolutional Neural Network (CNN) model is then applied to determine whether the detected objects are ships. Objects classified as ships within the ROI are considered potential collision risks.

Statistics
Cite this article