TY - JOUR
T1 - Development of denoising and compression algorithms for AIS-based vessel trajectories
AU - Yan, Ran
AU - Mo, Haoyu
AU - Yang, Dong
AU - Wang, Shuaian
N1 - Funding Information:
This research is supported by the National Natural Science Foundation of China under Grant number of 71971185 , the Department of Science and Technology of Guangdong Province under Project Number of 2021A1515010699 .
Publisher Copyright:
© 2022 Elsevier Ltd
PY - 2022/5/15
Y1 - 2022/5/15
N2 - Ship navigation information derived from the Automatic Identification System (AIS) is widely used in the shipping industry. As AIS reports are featured with huge volume and noises, preprocessing of AIS data is essential before its further application. This study aims to develop effective algorithms to denoise and compress raw trajectories derived from AIS reports. Specifically, an effective noise detection method based on statistical theory and sliding window is first proposed to identify glitches in a given trajectory. Linear interpolation is further used to rectify the glitches detected. Then, two modes of algorithms are proposed for trajectory compression: static mode with preset threshold for compression and dynamic mode considering the distance between trajectory points and the coastline in a real-time manner. Numerical experiments show that the noise detection and rectification algorithms and the trajectory compression algorithms are accurate and highly efficient considering compression rate, information loss, and computation time. The main innovation of this research includes developing an accurate and robust trajectory glitch detection and rectification algorithm, proposing two modes of trajectory compression algorithms, and combining the two tasks in a holistic robust framework. Especially, the dynamic compression mode can overcome a major problem encountered in static compression where the compressed trajectories may go across land. It can also deal with more flexible compression requirements and thus should be more applicable in practice.
AB - Ship navigation information derived from the Automatic Identification System (AIS) is widely used in the shipping industry. As AIS reports are featured with huge volume and noises, preprocessing of AIS data is essential before its further application. This study aims to develop effective algorithms to denoise and compress raw trajectories derived from AIS reports. Specifically, an effective noise detection method based on statistical theory and sliding window is first proposed to identify glitches in a given trajectory. Linear interpolation is further used to rectify the glitches detected. Then, two modes of algorithms are proposed for trajectory compression: static mode with preset threshold for compression and dynamic mode considering the distance between trajectory points and the coastline in a real-time manner. Numerical experiments show that the noise detection and rectification algorithms and the trajectory compression algorithms are accurate and highly efficient considering compression rate, information loss, and computation time. The main innovation of this research includes developing an accurate and robust trajectory glitch detection and rectification algorithm, proposing two modes of trajectory compression algorithms, and combining the two tasks in a holistic robust framework. Especially, the dynamic compression mode can overcome a major problem encountered in static compression where the compressed trajectories may go across land. It can also deal with more flexible compression requirements and thus should be more applicable in practice.
KW - Automatic identification system (AIS)
KW - Dynamic threshold
KW - Trajectory compression
KW - Trajectory denoising
KW - Trajectory point-coastline distance
UR - http://www.scopus.com/inward/record.url?scp=85127493868&partnerID=8YFLogxK
U2 - 10.1016/j.oceaneng.2022.111207
DO - 10.1016/j.oceaneng.2022.111207
M3 - Journal article
AN - SCOPUS:85127493868
SN - 0029-8018
VL - 252
JO - Ocean Engineering
JF - Ocean Engineering
M1 - 111207
ER -