Learning Features for Tracking

We treat tracking as a matching problem of detected keypoints between successive frames. The novelty of this paper is to learn classifier-based keypoint descriptions allowing to incorporate background information. Contrary to existing approaches, we are able to start tracking of the object from scratch requiring no off-line training phase before tracking. The tracker is initialized by a region of interest in the first frame. Afterwards an on-line boosting technique is used for learning descriptions of detected keypoints lying within the region of interest. New frames provide new samples for updating the classifiers which increases their stability. A simple mechanism incorporates temporal information for selecting stable features. In order to ensure correct updates a verification step based on estimating homographies using RANSAC is performed. The approach can be used for real-time applications since on-line updating and evaluating classifiers can be done efficiently.

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Michael Grabner, Helmut Grabner, Horst Bischof
• Keywords: Classifier-based Keypoint Descriptions, Computer Vision, CVPR 2007, Off-line Training Phase, On-line Boosting Technique, On-line Updating, Successive Frames