Trajectory compression-guided visualization of spatio-temporal AIS vessel density

As an automatic tracking system, the shipboard Automatic Identification System (AIS) has been widely adopted to identify and locate the vessels by electronically exchanging data with other nearby ships. With the development of computer technology, AIS-based visualization of vessel traffic has attracted increasing attention during the past several years. The vessel density visualization can be used as an appropriate computer-aided method to better understand the maritime traffic situation and (abnormal) vessel behaviors. However, it often suffers from high computational cost due to the massive sample size of spatio-temporal AIS trajectories datasets. To handle the problem of high computational cost, the Douglas-Peucker (DP) algorithm was firstly introduced to simplify the massive AIS trajectories. The final Kernel Density Estimation (KDE)-based vessel density visualization was implemented based on the simplified trajectory datasets to shorten the visualization time. To guarantee a good balance between AIS trajectory simplification and visualization performance, numerous experiments haven been conducted to optimally select an appropriate threshold for DP-based AIS trajectory simplification. Comprehensive experiments on realistic spatio-temporal datasets have illustrated that our proposed method can achieve a satisfactory visualization of AIS vessel density while reducing the visualization time.