Berthing Monitoring System Based on Ship Size Estimation Using LiDAR and Camera Fusion

Berthing accidents are serious problems that can cause damage to the ship and port facilities. Accident prevention and management are critical challenges in port operations and maritime safety. This study proposes a ship berthing monitoring system that combines camera image data and LiDAR point cloud data. The camera recognizes the ship and estimates its size. The LiDAR sensor uses the iterative closest point (ICP) algorithm to calculate the distance between the ship, the quay wall, and the ship's approach direction. Additionally, to overcome the short detection range of LiDAR, we propose a sensor fusion method that predicts the berthing direction and size of the ship and creates a new point cloud to expand the detection range. Field tests are conducted in a real port to validate the performance of the proposed camera and LiDAR fusion-based monitoring system. The estimation results of the proposed monitoring system are compared with the ship's Automatic Identification System (AIS) results to validate its performance.