Toshihiko Misu

Distributed Particle Filtering for Multiocular Soccer-Ball Tracking

This paper proposes a distributed state estimation architecture for multi-sensor fusion. The system consists of networked subsystems that cooperatively estimate the state of a common target from their own observations. Each subsystem is equipped with a self-contained particle filter that can operate in stand-alone as well as in network mode with a particle exchange function. We applied this flexible architecture to 3D soccer-ball tracking by modeling the imaging processes related to the centroid, size, and motion-blur of a target, and by modeling the dynamics with ballistic motion, bounce, and rolling. To evaluate the precision and robustness of the system, we conducted experiments using multiocular images of a professional soccer match.

Terrain shape recognition for celestial landing/rover missions from shade information

Abstract This paper proposes a direct geographic recognition scheme from a gray-scale image without shape reconstruction. Several geographic categories are expressed in 3x3-arrays of normal-vector directions. Only by looking up a table, observed pixel-values (intensities) in a window are transformed into indeces of conformity whether the scene in the window is due to each geographic category or not. The recognition is accomplished by multi-resolution interpretation and fuzzy-logical operations. The results of recognition has shown the feasibility and robustness of the proposed method.

Image-based topographic recognition on natural terrain

This paper proposes a direct geographic recognition scheme from a gray-scale image without shape reconstruction. Several geographic categories are expressed in 3 /spl times/ 3-arrays of normal-vector directions. Only by looking up a table, the observed pixel-values (intensities) in a window are transformed into indices of conformity whether the scene in the window is due to each geographic category or not. Geographical features are extracted by multi-resolution interpretation and fuzzy-logical operations. The feasibility and robustness of the proposed method is shown by some computer simulations.

Recognition and extraction of topographic features from gray-scale image of a celestial body

A method of recognition and extraction of geographical features from a grayscale image of the surface of a celestial body is proposed. The scheme is based on direct recognition from the image taken by a camera on a spacecraft without shape reconstruction, which usually entails a large amount of computation. By preparing templates of geographical categories such as mountains and valleys, indices of the membership of each pixel in these categories are efficiently calculated. With some logical operations, geographic features are automatically extracted on demand. The scheme is applied to synthesized images and natural ones to show its feasibility and robustness.