‘Bag of segments’ for motion trajectory analysis

We propose a novel method to represent motion trajectory - ´bag of segments´. Motivated by the ´bag of words´ approach in text mining and more recently in image categorization, we represent each trajectory as a collection of segments, each assigned a membership to a codeword of a dictionary. The trajectory segments are represented by their shape and motion information while the inter-segment relationship is ignored. In the ´bag of trajectory segments´ representation, the trajectories are transformed to a vector in the codeword space. The codebook is generated by clustering a large amount of trajectory segments using expectation maximization (EM) algorithm and each codeword is a weighted regression model. Given the codebook, trajectories are segmented and associated with a soft-frequency vector in codeword space as an intermediate representation. With the ´bag of segments´ representation, trajectory analysis can be carried out in vector space as traditional data. Experiments show the ´bag of segments´ method is very effective in trajectory similarity search and classification.