Human tracking based on Soft Decision Feature and online real boosting

Online boosting is an effective incremental learning method which can update weak classifiers efficiently according to the object being tracked. It is a promising technique for online object tracking to adapt to the appearance variations of objects during tracking process. However, proposed online-boosting based tracking methods update and select weak classifiers from fixed the offline learned weak classifiers, which might not be an optimal selection for object appearance variations. In this paper, we propose a new feature adjusting strategy for online boosting called soft decision feature. We combine it with online real AdaBoost to achieve better tracking performance in scenes with human pose and posture variations. Experiment result demonstrates that it can successfully deal with the human posture variation scenes that conventional online boosting tracking methods fails to deal with.