Semantic Trajectory Compression

In the light of rapidly growing repositories capturing the movement trajectories of people in spacetime, the need for trajectory compression becomes obvious. This paper argues for semantic trajectory compression (STC) as a means of substantially compressing the movement trajectories in an urban environment with acceptable information loss. STC exploits that human urban movement and its large-scale use (LBS, navigation) is embedded in some geographic context, typically defined by transportation networks. STC achieves its compression rate by replacing raw, highly redundant position information from, for example, GPS sensors with a semantic representation of the trajectory consisting of a sequence of events. The paper explains the underlying principles of STC and presents an example use case.