New paper published at ARXIV by MASTER researchers from Harokopio University and Federal University of Santa Catarina. Title of the paper is “TraClets: Harnessing the power of computer vision for trajectory classification”.
In the paper authors exploit image representations of trajectories, called TraClets, in order to classify trajectories through computer vision techniques. Experimental results demonstrate that TraClets achieves a classification performance that is comparable to, or in most cases, better than the state-of-the-art, acting as a universal, high-accuracy approach for trajectory classification.
Paper can be found at