A GIS-Centric Optical Tracking System and Lap Simulator for Short Track Speed Skating

This paper presents a GIS-centric computer vision system for tracking high-speed skaters in competition and training situations. This system outputs spatio-temporal trajectories that are analyzed through presented geometric, physical and power-based models in order to evaluate sports performance. Through spatial SQL and shared database access, the GIS enables the manipulation of the trajectories and offer, amongst other, selection, fusion and completion of tracks, as well as automatic computation of distances between competitors. We propose a new method for (1) calibrating the cameras using a GIS-like image rectification method; 2) simulating trajectories and their associated power profiles to model the sport´s domain; 3) incorporating the instant center of rotation in both the particle filter´s dynamic model and the simulator and 4) leveraging several GIS advanced capabilities in a client-server application. Experimental results show that our rectification methology is very precise, that our tracking performance is acceptable and that the proposed power balance model is very close to the state of the art.