Online object tracking is a challenging problem as it entails learning an effective model to account for appearance change caused by intrinsic and extrinsic factors. In this paper, we propose a novel online object tracking algorithm with sparse prototypes, which exploits both classic principal component analysis (PCA) algorithms with recent sparse representation schemes for learning effective appearance models.
We introduce L1 regularization into the PCA reconstruction, and develop a novel algorithm to represent an object by sparse prototypes that account explicitly for data and noise. For tracking, objects are represented by the sparse prototypes learned online with update. In order to reduce tracking drift, we present a method that takes occlusion and motion blur into account rather than simply includes image observations for model update.
Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods.
★ A novel representation model: The tracked target is represented by sparse prototypes that consist of a set of PCA basis vectors and trivial templates.
★ An iterative algorithm to solve the representation model.
★ A novel likelihood function that considers occlusions as well as mis-alignments.
★ Outlier recovery or rejection for online updating.
Paper and Code
IEEE Transaction on Image Processing (to appear).
We appreciate that you can cite our work if you use our code.