An approximate system for evaluating real-time port operations based on remote sensing images

As an important transportation infrastructure and a strong support for foreign trades, ports play an indispensable role in economic development. However, the acquisition of operating data has a certain hysteresis, making it difficult to analyse and evaluate in real-time. To solve this problem, in this paper, we proposed a new perspective where the number of vessels was used to replace the traditional operation data, which are not easily available, to reflect the health of the economy. We designed an approximate system for evaluating real-time port operations based on remote sensing images. First, the port's remote sensing images were acquired and pre-processed in real-time. Then, the vessels in the remote sensing images were identified using object detection technology. Finally, the correlation between the vessels and the port's operating indicators were established to analyse and predict the port operating conditions. The result demonstrated that the number of ships reflected the change of the port throughput to a certain extent and the predicted accuracy was within 10%. This system effectively solved the problems of operating data hysteresis and the difficulty in acquiring, and it opens large prospects for practical applications.