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

ABSTRACT 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.

[1]  Chao Li,et al.  Measuring economic activity in China with mobile big data , 2017, EPJ Data Science.

[2]  Weiwei Sun,et al.  R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery , 2019, Remote. Sens..

[3]  F. Billari,et al.  Leveraging mobile phones to attain sustainable development , 2020, Proceedings of the National Academy of Sciences.

[4]  Ying Chang,et al.  A Novel Method of Evaluating Highway Traffic Prosperity Based on Nighttime Light Remote Sensing , 2019, Remote. Sens..

[5]  Xiao Xiang Zhu,et al.  Hierarchical Region Based Convolution Neural Network for Multiscale Object Detection in Remote Sensing Images , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[6]  Bruno Aragon,et al.  CubeSats Enable High Spatiotemporal Retrievals of Crop-Water Use for Precision Agriculture , 2018, Remote. Sens..

[7]  Zhenwei Shi,et al.  Fully Convolutional Network With Task Partitioning for Inshore Ship Detection in Optical Remote Sensing Images , 2017, IEEE Geoscience and Remote Sensing Letters.

[8]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Chao Fan,et al.  Time series evaluation of landscape dynamics using annual Landsat imagery and spatial statistical modeling: Evidence from the Phoenix metropolitan region , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[10]  R. Emmanuel.  Urban Vegetational Change as an Indicator of Demographic Trends in Cities: The Case of Detroit , 1997, Environment and planning. B, Planning & design.

[11]  Jian Yao,et al.  S-CNN-BASED SHIP DETECTION FROM HIGH-RESOLUTION REMOTE SENSING IMAGES , 2016 .

[12]  Anne Helmond,et al.  The like economy: Social buttons and the data-intensive web , 2013, New Media Soc..

[13]  A. Cottam,et al.  Using Social Media to Measure the Contribution of Red List Species to the Nature-Based Tourism Potential of African Protected Areas , 2015, PloS one.

[14]  R. Benedetti,et al.  Mapping Poverty of Latin American and Caribbean Countries from Heaven Through Night-Light Satellite Images , 2020 .

[15]  Fu-yuan Li,et al.  A Research on the Combination of Oblique Photography and Mobile Applications Based on the Sustainable Development of Tourism , 2020, Sustainability.

[16]  Baojun Zhao,et al.  Compressed-Domain Ship Detection on Spaceborne Optical Image Using Deep Neural Network and Extreme Learning Machine , 2015, IEEE Transactions on Geoscience and Remote Sensing.