A dissimilarity measure estimation for analyzing trajectory data

抄録

Quantifying dissimilarity between two trajectories is a challenging problem yet it is a fundamental task with a wide range of applications. Existing dissimilarity measures are computationally expensive to calculate. We proposed a dissimilarity measure estimate for trajectory data based on deep learning methodology. One advantage of the proposed method is that it can get executed on GPU, which can significantly reduce the execution time for processing a large number of data. The proposed network is trained using synthetic data. A trajectory simulator that generates random trajectories is proposed. We used a publicly available dataset to evaluate the proposed method for the task of trajectory clustering. Our experiments show the performance of the proposed dissimilarity estimation method is comparable with well-known methods while our method is substantially faster to compute.