Integration of Multi-view Panoramic Range Data Using Global Features

In this paper, we propose a robust and efficient method to integrate the multi-view panoramic range data using the global features acquired from panorama range data. In our approach, the planes with similar normal vectors are handled as one group, and multiple plane groups are extracted from the multi-view panoramic range data. Next, the transformation ( r e tation and translation) parameters between viewpoints are estimated by matching the plane groups in multiple viewpoints based on the global statistical features of each plane group. Since our method carries out the integration using the global features of panoramic range data, there is no necessity to consider the initial p e sition, and it is robust to noise. Experimental results on real panoramic range data show the effectiveness of the proposed method. (rotation and translation) parameters between viewpoints are estimated by matching the plane groups in multiple viewpoints based on the global statistical features of each plane group. Since our method carries out the integration using the global features of panoramic range data, there is no necessity to consider the initial position, and it is robust to noise. Experimental results on real panoramic range data show the effectiveness of the proposed method. 2 Plane groups and global statistical features In our approach, the transformation parameters between viewpoints are estimated by matching the plane groups in multiple viewpoints based on each plane group's global statistical features. Then, the plane groups and the global statistical features are extracted from multi-view panorama range data.