Abstract: A large amount of vessel trajectory data with a wide coverage and strong timeliness has been accumulated in the big data era, whose spatio-temporal and semantic state changes can be represented by some trajectory points. To increase trajectory retrieval efficiency and reduce storage and transmission burden, this paper proposes a trajectory compression method upon trajectory spatio-temporal features and navigation semantic features. First, spatio-temporal and semantic features of vessel trajectory are analyzed, and a trajectory data compression method is proposed. Then, trajectory points with significant spatio-temporal and semantic features are extracted by Douglas-Peucker and sliding window methods to construct spatio-temporal and semantic ranks, respectively. To synthesize these features, the weighted fusion method is introduced to combine these ranks, thus ranking the trajectory points in order. Finally, vessel trajectory can be compressed by calculating reserved point number from compression ratio. The proposed method is verified through comparative analysis of efficiency and quality, and a compression case. The experiments indicate that the method could not only reduce redundancy significantly, but also retain the dynamic semantics and spatio-temporal morphological features of driving, thus providing a solid foundation for trajectory mining.

Key words: data compression, trajectory data compression, spatio-temporal features, semantic features, vessel trajectory