QSRlib: a software library for online acquisition of qualitative spatial relations from video
Yiannis Gatsoulis, Muhannad Alomari, Chris Burbridge, Christian Dondrup, Paul Duckworth, P. Lightbody, Marc Hanheide, Nick Hawes, David Hogg, Anthony G. Cohn · Lincoln Repository (University of Lincoln) · 2016
There is increasing interest in using Qualitative Spatial Relations as a formalism to abstract from noisy and large amounts of video data in order to form high level conceptualisations, e.g. of activities present in video. We present a library to support such work. It is compatible with the Robot Operating System (ROS) but can also be used stand alone. A number of QSRs are built in; others can be easily added.