Fast and Accurate Reconstruction of Pan-Tilt RGB-D Scans via Axis Bound Registration (1812.00240v3)

Abstract: A fast and accurate algorithm is presented for registering scans from an RGB-D camera on a pan-tilt platform. The pan-tilt RGB-D camera rotates and scans the entire scene in an automated fashion. The proposed algorithm exploits the movement of the camera that is bound by the two rotation axes of the servo motors so as to realize fast and accurate registration of acquired point clouds. The rotation parameters, including the rotation axes, pan-tilt transformations and the servo control mechanism, are calibrated beforehand. Subsequently, fast global registration can be performed during online operation with transformation matrices formed by the calibrated rotation axes and angles. In local registration, features are extracted and matched between two scenes. False-positive correspondences, whose distances to the rotation trajectories exceed a threshold, are rejected. Then, a more accurate registration can be achieved by minimizing the residual distances between corresponding points, while transformations are bound to the rotation axes. Finally, the preliminary alignment result is input to the iterative closed point algorithm to compute the final transformation. Results of comparative experiments validate that the proposed method outperforms state-of-the-art algorithms of various approaches based on camera calibration, global registration, and simultaneous-localization-and-mapping in terms of root-mean-square error and computation time.