Question about the model data

[HelveticaScenario]

How are the .tracker files created? do they have anything to do with the xml haarcascade files in the opencv repo https://github.com/Itseez/opencv/tree/master/data/haarcascades? if they are specially trained models, what would be the best way of turning them into xml haarcascade files for use with opencv's CascadeClassifier class http://docs.opencv.org/master/d1/de5/classcv_1_1CascadeClassifier.html#gsc.tab=0?