GPU加速的海上大型船舶轨迹压缩和可视化IoT Industries
GPU-Accelerated Compression and Visualization of Large-Scale Vessel Trajectories in Maritime IoT Industries
摘要：
自动识别系统（AIS）是一种自动船舶跟踪系统，已被广泛用于海上物联网（IoT）行业的智能交通管理和避碰服务。随着海上交通的快速发展，大量基于AIS的船舶航迹数据被采集，使得航迹数据压缩成为迫切需要和具有挑战性的问题。本文主要研究大规模血管轨迹的压缩和可视化及其图形处理单元（GPU）加速实现。通过可视化研究了压缩对血管轨迹数据质量的影响。特别是，Douglas-Peucker（DP）和核密度估计（KDE）算法，分别用于轨迹压缩和可视化，通过GPU架构的大规模并行计算能力显着加速。本文对三个不同水域的大规模AIS船舶运动数据进行了轨迹压缩和可视化的综合实验，长江口南港、成山角和舟山群岛。实验结果表明：（1）所提出的基于GPU的并行实现框架可以显著减少轨迹压缩和可视化的计算时间;（2）如果选择合适的压缩阈值，压缩血管轨迹对轨迹可视化的影响可以忽略不计;（3）通过与其他7种核函数的比较，发现高斯核函数能够产生更合适的基于KDE的可视化性能。
英文摘要：
The automatic identification system (AIS), an automatic vessel-tracking system, has been widely adopted to perform intelligent traffic management and collision avoidance services in maritime Internet of Things (IoT) industries. With the rapid development of maritime transportation, tremendous numbers of AIS-based vessel trajectory data have been collected, which make trajectory data compression imperative and challenging. This paper mainly focuses on the compression and visualization of large-scale vessel trajectories and their Graphics Processing Unit (GPU)-accelerated implementations. The visualization was implemented to investigate the influence of compression on vessel trajectory data quality. In particular, the Douglas-Peucker (DP) and Kernel Density Estimation (KDE) algorithms, respectively utilized for trajectory compression and visualization, were significantly accelerated through the massively parallel computation capabilities of GPU architecture. Comprehensive experiments on trajectory compression and visualization have been conducted on large-scale AIS data of recording ship movements collected from 3 different water areas, i.e., the South Channel of Yangtze River Estuary, the Chengshan Jiao Promontory, and the Zhoushan Islands. Experimental results illustrated that (1) the proposed GPU-based parallel implementation frameworks could significantly reduce the computational time for both trajectory compression and visualization; (2) the influence of compressed vessel trajectories on trajectory visualization could be negligible if the compression threshold was selected suitably; (3) the Gaussian kernel was capable of generating more appropriate KDE-based visualization performance by comparing with other seven kernel functions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
