Abstract
We present two algorithms for aligning two colored point clouds. The two algorithms are designed to minimize a probabilistic cost based on the color-supported soft matching of points in a point cloud to their K-closest points in the other point cloud. The first algorithm, like prior iterative closest point algorithms, refines the pose parameters to minimize the cost. Assuming that the point clouds are obtained from RGB-depth images, our second algorithm regards the measured depth values as variables and minimizes the cost to obtain refined depth values. Experiments with our synthetic dataset show that our pose refinement algorithm gives better results compared to the existing algorithms. Our depth refinement algorithm is shown to achieve more accurate alignments from the outputs of the pose refinement step. Our algorithms are applied to a real-world dataset, providing accurate and visually improved results.
Highlights
RGB-depth (RGB-D) cameras have recently been used in many application areas in robotics and RGB-D video of an environment and aligning the point clouds obtained from the RGB-D images [1,2].An object’s 3D model can be obtained by using a multi-view system consisting of multiple calibratedRGB-D cameras [3,4]
An advanced algorithm based on pose-graph optimization exists [37], we present a simpler method that is adequate for evaluating the robustness of the pairwise registration algorithm
The multi-view performance of the pose and depth refinement algorithms is evaluated on the same dataset
Summary
RGB-depth (RGB-D) cameras have recently been used in many application areas in robotics and. The depth values measured by RGB-D cameras suffer from errors [14,15,16], which hinder obtaining accurate one-to-one correspondences. The cost is minimized by refining the depth values so that the two point clouds get aligned more closely. No publicly available RGB-D dataset in this multi-view setting provides ground truth pose parameters and depth values. Building such a dataset will require several high-end laser scanners accurately calibrated with the RGB-D cameras. Another contribution of this paper is a synthetic multi-view RGB-D dataset used for in-depth evaluation of our algorithms.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
