A Novel Sketch-Based Registration Framework for Point Cloud Frames

Automatic registration of point clouds is a fundamental research problem in 3-D computer vision. In this letter, a sketch-based registration framework is proposed targeting 3-D scenarios. It consists of two major modules: pairwise alignment and multiview alignment. For the pairwise alignment, a point cloud is first abstracted into a sketch which greatly preserves the contour information in the scene; then an entropy point pair feature (EPPF) method that integrates contour shape features and point pair geometric features is applied to estimate transformation. For the multiview alignment, the key is to combine the voting-based pairwise method with simultaneous localization and mapping (SLAM) system, which ensures the robustness of the proposed framework in different scenarios. Experiments show that the proposed sketch-based method clearly outperforms the state-of-the-art methods.