Robust Visual Tracking via Structured Multi-Task Sparse Learning

Tianzhu Zhang      Bernard Ghanem      Si Liu      Narendra Ahuja

National Lab of Pattern Recognition
Institute of Automation, Chinese Academy of Sciences

Abstract

In this paper, we formulate object tracking in a particle filter framework as a structured multi-task sparse learning problem, which we denote as Structured Multi-Task Tracking (S-MTT). Since we model particles as linear combinations of dictionary templates that are updated dynamically, learning the representation of each particle is considered a single task in Multi-Task Tracking (MTT). By employing popular sparsity-inducing p,q mixed norms (specificallyp ∈ {2,∞} and q = 1), we regularize the representation problem to enforce joint sparsity and learn the particle representations together. As compared to previous methods that handle particles independently, our results demonstrate that mining the interdependencies between particles improves tracking.

Figure 1 - (Color online) Schematic example of the L21 tracker. The representation C of all particles X w.r.t. dictionary B (set of target and occlusion templates) is learned by solving Eq.(9) with p = 2 and q = 1. Notice that the columns of C are jointly sparse, i.e. a few (but the same) dictionary templates are used to represent all the particles together. The particle xi is selected among all other particles as the tracking result, since xi is represented the best by object templates only.

Video Results