*Application of Deep Learning Methods for Detection and Tracking of Players DOI: http://dx.doi.org/10.5772/intechopen.96308*

is gathering enough training data, which can be facilitated by methods that reduce the manual effort of labeling ground truth data. To that end, the experiments for automatic temporal segmentation of the raw footage and a method for detecting the active player in a sequence using low level visual features were presented.

Advances in deep learning methods promise continued improvement in the analysis of dynamic sports scenes, in order to recognize more complex activities, plan competitive tactics and monitor player progress.
