Classification of sports types using thermal imagery

Abstract

In this chapter we propose a method for automatic classification of five different sports types. The approach is based only on occupancy heatmaps produced from position data and is robust to detection noise. To overcome privacy issues when capturing video in public sports arenas we use thermal imaging only. This image modality also facilitates easier detection of humans; the detection algorithm is based on automatic thresholding of the image. After a few occlusion handling procedures, the positions of people on the court are calculated using homography. Heatmaps are produced by summarising Gaussian distributions representing people over 10-minute periods. Before classification the heatmaps are projected to a lowdimensional discriminative space using the principle of Fisherfaces. We test our approach on 2weeks of video and get promising results with a correct classification of 89.64%. In addition, we get correct classification on a publicly available handball dataset.