In this work, we present a combined approach to tracking and reconstruction. An implicit feedback of 3d information to the tracking process is achieved by optimizing a single error...
This paper demonstrates how a simple, yet effective, set of features enables to integrate ensemble classifiers in optical flow based tracking. In particular, gray value differences...
Mean-Shift tracking gained a lot of popularity in computer vision community. This is due to its simplicity and robustness. However, the original formulation does not estimate the o...
In this paper, we address the problem of recovering the camera radial distortion coefficients from one image. The approach that we propose uses a special kind of snakes called rad...
—This paper presents a fast part-based subspace selection algorithm, termed the binary sparse nonnegative matrix factorization (B-SNMF). Both the training process and the testing...