Online Human-AssistedLearning using Random Ferns

摘要

We present an Online Random Ferns (ORFs) classifierthatprogressivelylearnsandbuildsenhancedmodelsofobjectappearances. Duringthelearningprocess, we allow the human intervention to assist the classifier and discard false positive training samples. The amount of human intervention is minimized and integrated within the online learning, such that in a few seconds,complexobjectappearancescanbelearned. Aftertheassistedlearningstage,theclassifierisable to detect the object under severe changing conditions. The system runs at a few frames per second, and has been validated for face and object detection tasks on a mobile robot platform. We show that with minimal humanassistanceweareabletobuildadetectorrobustto viewpoint changes, partial occlusions, varying lighting andclutteredbackgrounds. 1