TraClets: A trajectory representation and classification library

Abstract

Due to the advent of new mobile devices and tracking sensors in recent years, huge amounts of data are being produced every day. Therefore, novel methodologies need to emerge that dive through this vast sea of information and generate insights and meaningful information. To this end, researchers have developed several trajectory classification algorithms over the years that are able to annotate tracking data. Similarly, we propose a software that exploits image representations of trajectories, called TraClets, in order to classify trajectories in an intuitive to the human way, through computer vision techniques. The proposed software has been evaluated in three real-world datasets and is currently used in a live vessel tracking terrestrial base station.

Keywords

• Trajectory classification
• Deep learning
• Convolutional neural networks
• Computer vision