Petković Miro, Vujović Igor, Kaštelan Nediljko, Šoda Joško
Faculty of Maritime Studies, University of Split, Ruđera Boškovića 37, 21000 Split, Croatia.
Sensors (Basel). 2023 Jul 28;23(15):6777. doi: 10.3390/s23156777.
Monitoring and counting maritime traffic is important for efficient port operations and comprehensive maritime research. However, conventional systems such as the Automatic Identification System (AIS) and Vessel Traffic Services (VTS) often do not provide comprehensive data, especially for the diverse maritime traffic in Mediterranean ports. The paper proposes a real-time vessel counting system using land-based cameras is proposed for maritime traffic monitoring in ports, such as the Port of Split, Croatia. The system consists of a YOLOv4 Convolutional Neural Network (NN), trained and validated on the new SPSCD dataset, that classifies the vessels into 12 categories. Further, the Kalman tracker with Hungarian Assignment (HA) algorithm is used as a multi-target tracker. A stability assessment is proposed to complement the tracking algorithm to reduce false positives by unwanted objects (non-vessels). The evaluation results show that the system has an average counting accuracy of 97.76% and an average processing speed of 31.78 frames per second, highlighting its speed, robustness, and effectiveness. In addition, the proposed system captured 386% more maritime traffic data than conventional AIS systems, highlighting its immense potential for supporting comprehensive maritime research.
监测和统计海上交通对高效港口运营和全面的海洋研究至关重要。然而，诸如自动识别系统（AIS）和船舶交通服务（VTS）等传统系统往往无法提供全面的数据，尤其是对于地中海港口多样化的海上交通。本文提出了一种使用陆基摄像头的实时船舶计数系统，用于克罗地亚斯普利特港等港口的海上交通监测。该系统由一个在新的SPSCD数据集上进行训练和验证的YOLOv4卷积神经网络（NN）组成，该网络将船舶分为12类。此外，采用带有匈牙利分配（HA）算法的卡尔曼跟踪器作为多目标跟踪器。提出了一种稳定性评估方法来补充跟踪算法，以减少由不需要的物体（非船舶）产生的误报。评估结果表明，该系统的平均计数准确率为97.76%，平均处理速度为每秒31.78帧，突出了其速度、鲁棒性和有效性。此外，所提出的系统比传统AIS系统捕获的海上交通数据多386%，突出了其在支持全面海洋研究方面的巨大潜力。
