Volume II-5/W2
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-5/W2, 127-132, 2013
https://doi.org/10.5194/isprsannals-II-5-W2-127-2013
© Author(s) 2013. This work is distributed under
the Creative Commons Attribution 3.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-5/W2, 127-132, 2013
https://doi.org/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

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 K. Khoshelham et al.
  • 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.