A non-parametric inference technique for shape boundaries in noisy point clouds

This study explores the non-parametric estimation of a shape boundary from noisy points in 2D when the sensor characteristics are known. As the underlying shape information is not known, the offered algorithm estimates points on the shape boundary by using the statistics of the subsets of point cloud data. The novel approach proposed in this paper is able to find corner points in a local geometry by only using sample mean and covariance matrices of the subsets of the point cloud. While the proposed approach can be used for any class of boundary functions that demonstrates symmetry; for this paper, the analysis and experiments are performed on a connected line segment.