Adaptive visual tracking with reacquisition ability for arbitrary objects

This paper introduces a novel tracking framework for robots that can adapt various appearance changes of object and also owns the ability of reacquisition after drift. Two classifiers, LaRank and Online Random Ferns, are adopted to realize this tracking algorithm. The former one maintains the adaptive tracking using a Condensation-based method with an online support vector machine (SVM) as observation model, which also provides the reliable image patch samples to detector for updating. The other one is in charge of the task of detection in order to redetect the object when the target drifts. We also present a refinement strategy to improve the tracker's performance by discarding the support vector corresponding to possible wrong updates by a matching template after re-initialization. The experiments on benchmark dataset compare our tracking method with several other state-of-the-art algorithms, demonstrating a promising performance of the proposed framework.

Authors

• Tianyu Yang
• Baopu Li
• Chao Hu
• Max Q. -H. Meng

Keywords

• Support vector machines
• Laboratories
• TV
• Reliability
• Videos
• Adaptive Tracking
• Support Vector Machine
• Tracking Performance
• Changes In Appearance
• Image Patches
• Tracking Algorithm
• Reliability In Sample
• Template Matching
• Detection In Order
• Tracking Framework
• Linear Discriminant Analysis
• Pedestrian
• Online Learning
• Motion Model
• Training Examples
• Object Position
• Particle Filter
• Global Search
• Illumination Changes
• Particle Weight
• Offline Learning
• Tracking Failure
• Positive Patch
• Histogram Of Oriented Gradients
• Online Learning Algorithm
• Online Learning Methods