ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-5/W2, 127-132, 2013
http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-5-W2/127/2013/
doi:10.5194/isprsannals-II-5-W2-127-2013
© Author(s) 2013. This work is distributed
under the Creative Commons Attribution 3.0 License.
 
16 Oct 2013
Generation and weighting of 3D point correspondences for improved registration of RGB-D data
K. Khoshelham1, D. R. Dos Santos2, and G. Vosselman1 1Faculty of Geo-Information Science and Earth Observation, University of Twente, the Netherlands
2Federal University of Parana, Curitiba, Brazil
Keywords: Alignment, Indoor Mapping, Kinect, Loop Closing, Point Cloud, RGB-D, SLAM Abstract. Registration of RGB-D data using visual features is often influenced by errors in the transformation of visual features to 3D space as well as the random error of individual 3D points. In a long sequence, these errors accumulate and lead to inaccurate and deformed point clouds, particularly in situations where loop closing is not feasible. We present an epipolar search method for accurate transformation of the keypoints from 2D to 3D space, and define weights for the 3D points based on the theoretical random error of depth measurements. Our results show that the epipolar search method results in more accurate 3D correspondences. We also demonstrate that weighting the 3D points improves the accuracy of sensor pose estimates along the trajectory.
Conference paper (PDF, 683 KB)


Citation: Khoshelham, K., Dos Santos, D. R., and Vosselman, G.: Generation and weighting of 3D point correspondences for improved registration of RGB-D data, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-5/W2, 127-132, doi:10.5194/isprsannals-II-5-W2-127-2013, 2013.

BibTeX EndNote Reference Manager XML