Scene understanding is an important problem in intelligent robotics. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the...
Action recognition is a popular and important research topic in computer vision. However, it is challenging when facing viewpoint variance. So far, most researches in action recogn...
It is difficult to recognize sign language in different viewpoint. The HMM method is hindered by the difficulty of extracting view invariant features. The general template matchin...
We propose textural features, which are invariant to illumination spectrum and extremely robust to illumination direction. They require only a single training image per texture an...
We present a method for live grouping of feature points into persistent 3D clusters as a single camera browses a static scene, with no additional assumptions, training or infrastr...