[Paper] Double Sparse Representation for Point Cloud Registration

Abstract

Point cloud registration is an important part of 3-dimensional information processing. Low overlap ratio, noise, outliers, and missing points considerably influence the registration results. In this paper, we propose a fast and robust point cloud registration method to reduce the impact of these factors. First, the point groups are resampled by point clouds as basic elements for point cloud registration. Second, singular value decomposition is used to decompose the point groups. Third, the depth image of the point groups is calculated, and the sparse feature is obtained using the depth image. Finally, the sparse feature is used to obtain registration results through sparse representation. Under the premise of robustness to low overlap ratio, noise, outliers, and missing points, experimental results show that our algorithm is faster and more accurate than extant methods.

Accurate 3D to 2D Object Distance Estimation from the Mapped Point Cloud Data

“…Using LiDAR point clouds has various advantages because they are dispersed throughout the measurement area. In addition, point clouds are sparse with varied densities, and the processing of point clouds cannot be affected by basic transformations [ 5 ]. LiDAR sensors can be used to calculate distance in three different ways: Triangulation measurement systems consist of a camera and laser transmitter positioned at a fixed angle.…”