Research on Segmentation of Pear Shape from Unorganized Point Clouds

Abstract

With the advent of 3D scanner, accurate segmentation of 3D fruit shape from unorganized point clouds has been turned out to be the most challenging task in scientists and engineers in reverse engineering. This paper herein proposes efficient and robust approach to extract pear shape from background. At first, an interactive, non-local denoising algorithm is employed to efficient denoise the pear scans; Second, geometric properties, including normal, variation and curvature, are estimated by covariance analysis; Third, a Recursive Region Increment (RRI) is proposed to add the geometric similarity points to a base set, to generate an ultimate set only including the points of pear shape; Forth, point clouds is linearized for rapidly rending in the post processing. Finally, segmentation algorithm applied on ten range scans of a pear demonstrates that our algorithm reduces the number of pear point clouds by 88.3%, proves the validity and practicability of this method in pear segmentation

High-efficiency texture coding and synthesis on point-based pear surface

“…However, according to our previous result [23], the maximum units number of the biggest scans is no more than 8000, which means only 3.05% of the units are valuable, or 96.95% of coding is redundancy. Furthermore, the segmentation process in this paper makes the most of the units stop segmentation before 6-level.…”

“…(1) Texture organization: based on point-octree segmentation cell-surfel [23], we convert 2D texture to three-dimensional space by developing an adaptive point quadtree for texture division and organization.…”

“…(2-4), in which, θ is /2, rotation angle along x-axis. Based on the thin convex shell of point and idea of conventional quartering [24], by taking the splitting parameters of point cloud as condition [23], color value in Eq. (2-3) as input data, we proposed a point-quadtree division process QT_div(P,C).…”

“…(3-1 a). According to the previous partition rules on the fruit [23], the digit of texton data coding is 6 at most, whose 6-digit Morton code corresponding to leaf node is given in Eq. in which q i -the node code of each division ,value range is: 0, … ,7.…”