Efficient Point-Based Pattern Search in 3D Motion Capture Databases

Abstract

3D motion capture data is a specific type of data arising in the Internet of Things. It is widely used in science and industry for recording the movements of humans, animals, or objects over time. In order to facilitate efficient spatio-temporal access into large 3D motion capture databases collected via internet-of-things technology, we propose an efficient 2-Phase Point-based Trajectory Search Algorithm (2PPTSA) which is built on top of a compact in-memory spatial access method. The 2PPTSA is fundamental to any type of pattern-based investigation and enables fast and scalable point-based pattern search in 3D motion capture databases. Our empirical evaluation shows that the 2PPTSA is able to retrieve the most similar trajectories for a given point-based query pattern in a few milliseconds with a comparatively low number of I/O accesses.