Visual learning is expected to be a continuous and robust process, which treats input images and pixels selectively. In this paper we present a method for subspace learning, which...
This paper introduces a hierarchical approach for multicomponent tracking, where the object-to-be-tracked is modeled as a group of spatial related parts. We propose to use a robus...
In this paper, we propose a novel and robust method for extracting motion layers in video sequences. Taking advantage of temporal continuity, our framework considers both the visi...
In this paper we describe a robust approach to segment text from color images. The proposed approach mainly includes four steps. Firstly, a preprocessing step is utilized to enhan...
A vital task in sports video annotation is to detect and segment areas of the playfield. This is an important first step in player or ball tracking and detecting the location of t...