期刊
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
卷 10, 期 4, 页码 -出版社
MDPI
DOI: 10.3390/ijgi10040250
关键词
trajectory classification; deep learning; neural networks; computer vision; distributed processing; stream processing; real-time vessel monitoring; trajectory compression; AIS
资金
- European Union (European Social Fund (ESF)) through the Operational Programme Human Resources Development, Education and Lifelong Learning 2014-2020 [MIS 5049026]
- MASTER Project through the European Union's Horizon 2020 research and innovation program under Marie-Sklodowska Curie Grant [777695]
- SmartShip Project through the European Union's Horizon 2020 research and innovation program under Marie-Sklodowska Curie Grant [823916]
With the proliferation of tracking sensors, high-frequency vessel tracking data is generated daily. This study presents a novel approach that transforms vessel trajectory patterns into images and uses deep learning algorithms to accurately classify vessel activities in near real time, achieving over 96% accuracy in classification performance.
Due to the vast amount of available tracking sensors in recent years, high-frequency and high-volume streams of data are generated every day. The maritime domain is no different as all larger vessels are obliged to be equipped with a vessel tracking system that transmits their location periodically. Consequently, automated methodologies able to extract meaningful information from high-frequency, large volumes of vessel tracking data need to be developed. The automatic identification of vessel mobility patterns from such data in real time is of utmost importance since it can reveal abnormal or illegal vessel activities in due time. Therefore, in this work, we present a novel approach that transforms streaming vessel trajectory patterns into images and employs deep learning algorithms to accurately classify vessel activities in near real time tackling the Big Data challenges of volume and velocity. Two real-world data sets collected from terrestrial, vessel-tracking receivers were used to evaluate the proposed methodology in terms of both classification and streaming execution performance. Experimental results demonstrated that the vessel activity classification performance can reach an accuracy of over 96% while achieving sub-second latencies in streaming execution performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据