A novel region-based multiple object tracking framework based on Kalman filtering and elastic matching is proposed. The proposed Kalman filtering-elastic matching model is genera...
We propose a novel tracking algorithm for the target of which geometric appearance changes drastically over time. To track it, we present a local patch-based appearance model and p...
Junseok Kwon (Seoul National University), Kyoung M...
Most motion-based tracking algorithms assume that objects undergo rigid motion, which is most likely disobeyed in real world. In this paper, we present a novel motionbased trackin...
Online Boosting is an effective incremental learning method which can update weak classifiers efficiently according to the object being trackedt. It is a promising technique for o...
Online learned tracking is widely used for it’s adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of erro...