Abstract— Least-squares policy iteration is a useful reinforcement learning method in robotics due to its computational efficiency. However, it tends to be sensitive to outliers...
Object recognition forms a ubiquitous problem in digital image processing. The detection of robust image features of high distinctiveness is one important key in this regard. We p...
We propose a new robust estimator for camera pose estimation based on a recently developed nonlinear mean shift algorithm. This allows us to treat pose estimation as a clustering ...
A robust linear method for auto-calibration of a moving camera from image sequences is presented. Known techniques for auto-calibration have problems with critical motion sequences...
We propose a scheme for building peer-to-peer overlay networks for broadcasting using network coding. The scheme addresses many practical issues such as scalability, robustness, c...