Learn More
This paper describes a method for image classification and retrieval for natural and urban scenes. The proposed algorithm is based on hierarchical image contents analysis. First image is classified as urban or natural according to color and edge distribution properties. Additionally scene is classified according to its conditions: illumination, weather,(More)
Localization and mapping is important in autonomous navigation of mobile robot. In this paper, we deal with localization using 2D laser range finder and IR positioning sensor. 2D grid map is built in local coordinate using data from laser range finder. And it is integrated into global coordinate using information from IR landmark. It can provide consistent(More)
Recently, self-calibration algorithms that use only the information in the image have been actively researched. But most algorithms require bundle adjustment in the projective reconstruction or in the nonlinear minimization. We propose a practical self-calibration algorithm that only requires a linear projective reconstruction. We overcome the sensitivity(More)
In this paper, we present an algorithm for the extrinsic calibration method of rotating laser range finder (LRF). LRF is rotated about one axis using a motor therefore it is required to find the transformation between the motor and LRF to register scanned datum into one coordinate. We use calibration structure consisted of two planes to recover the(More)
In this paper, we propose a robust motion estimation algorithm using uncalibrated 3D motion model considering depth discontinuity. Most of the previous direct motion estimation algorithms with 3D motion model compute the depth value through the local smoothing, which result in erroneous results at depth discontinuity. In this paper, we overcome this problem(More)