Abstract. Approaches to visual navigation, e.g. used in robotics, require computationally efficient, numerically stable, and robust methods for the estimation of ego-motion. One of...
In this paper we propose an approach for action recognition based on a vocabulary of local motion-appearance features and fast approximate search in a large number of trees. Large...
We present an interactive system for generating photorealistic, textured, piecewise-planar 3D models of architectural structures and urban scenes from unordered sets of photograph...
Sudipta N. Sinha, Drew Steedly, Richard Szeliski, ...
We present a template-based approach to detecting human silhouettes in a specific walking pose. Our templates consist of short sequences of 2D silhouettes obtained from motion cap...
In this work, we solve the pose estimation problem for robot motion by placing multiple cameras on the robot. In particular, we use four cameras arranged as two back-to-back stere...
Mohammad Ehab Ragab, King Hong Wong, Jun Zhou Chen...