Super Edge 4-Points Congruent Sets-Based Point Cloud Global Registration

Abstract

With the acceleration in three-dimensional (3D) high-frame-rate sensing technologies, dense point clouds collected from multiple standpoints pose a great challenge for the accuracy and efficiency of registration. The combination of coarse registration and fine registration has been extensively promoted. Unlike the requirement of small movements between scan pairs in fine registration, coarse registration can match scans with arbitrary initial poses. The state-of-the-art coarse methods, Super 4-Points Congruent Sets algorithm based on the 4-Points Congruent Sets, improves the speed of registration to a linear order via smart indexing. However, the lack of reduction in the scale of original point clouds limits the application. Besides, the coplanarity of registration bases prevents further reduction of search space. This paper proposes a novel registration method called the Super Edge 4-Points Congruent Sets to address the above problems. The proposed algorithm follows a three-step procedure, including boundary segmentation, overlapping regions extraction, and bases selection. Firstly, an improved method based on vector angle is used to segment the original point clouds aiming to thin out the scale of the initial point clouds. Furthermore, overlapping regions extraction is executed to find out the overlapping regions on the contour. Finally, the proposed method selects registration bases conforming to the distance constraints from the candidate set without consideration about coplanarity. Experiments on various datasets with different characteristics have demonstrated that the average time complexity of the proposed algorithm is improved by 89.76%, and the accuracy is improved by 5 mm on average than the Super 4-Points Congruent Sets algorithm. More encouragingly, the experimental results show that the proposed algorithm can be applied to various restrictive cases, such as few overlapping regions and massive noise. Therefore, the algorithm proposed in this paper is a faster and more robust method than Super 4-Points Congruent Sets under the guarantee of the promised quality.

Korean Cattle 3D Reconstruction from Multi-View 3D-Camera System in Real Environment

“…Another reconstruction method is using multi-view cameras. A system of cameras is built to synchronously scan data and then align all frames to create the point cloud [ 16 , 17 , 18 , 19 ]. However, in paper [ 16 , 17 ], the fence size must be small, or the registration algorithm used (Super4PCS) can not work with small overlapping point clouds.…”

“…However, if the overlap between a pair of cameras is small or there is no data because of occlusion from fences leading to alignment by ICP, the algorithm can fail. The global alignment method for the cloud from all cameras in paper [ 18 , 19 ] used information on building a set of co-planar points to register.…”

2PNS++ point-cloud registration via hash of invariants and local compatibility check

“…Sun et al introduced a more flexible congruent base extracting method and raised A4PCS, which is based on V4PCS and outperforms other variants of 4PCS in most cases [25]. Li et al proposed an improved method call Super Edge 4PCS [26], which extracts boundary segmentation, overlapping regions of boundary segments and selects bases from them to register point clouds with obvious edges.…”

Edge detection for 3D point clouds via locally max-angular gaps descriptor

“…With the boost of 3D sensing techniques, point clouds have become a popular 3D representation format, and abundant point-cloud-based tasks are now underway. Tasks such as reconstruction [2], simplification [3], normal estimation [4], registration [5], and so on, have urgent demand for point cloud * Author to whom any correspondence should be addressed. edge features.…”