US 12,094,153 B2
Point cloud analysis device, method, and program
Hitoshi Niigaki, Tokyo (JP); Yasuhiro Yao, Tokyo (JP); Masaaki Inoue, Tokyo (JP); Tomoya Shimizu, Tokyo (JP); Yukihiro Goto, Tokyo (JP); Shigehiro Matsuda, Tokyo (JP); Ryuji Honda, Tokyo (JP); Hiroyuki Oshida, Tokyo (JP); Kana Kurata, Tokyo (JP); Shingo Ando, Tokyo (JP); and Atsushi Sagata, Tokyo (JP)
Assigned to NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
Appl. No. 17/608,963
Filed by NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
PCT Filed May 8, 2019, PCT No. PCT/JP2019/018449
§ 371(c)(1), (2) Date Nov. 4, 2021,
PCT Pub. No. WO2020/225886, PCT Pub. Date Nov. 12, 2020.
Prior Publication US 2022/0215572 A1, Jul. 7, 2022
Int. Cl. G06T 7/70 (2017.01); G06T 7/00 (2017.01)
CPC G06T 7/70 (2017.01) [G06T 7/0002 (2013.01); G06T 2207/10028 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A point cloud analysis device for estimating presence or absence of a linear structure or/and a region in which the linear structure is present from point cloud data obtained by measuring a real space, the point cloud analysis device comprising:
a linear structure estimator configured to estimate the presence or absence of the linear structure or/and the region in which the linear structure is present from the point cloud data using a property in the real space common to the linear structure,
wherein the property includes a length of the linear structure and a relationship between divided regions when the linear structure is divided into predetermined units,
a three-dimensional data store configured to store a point cloud representing three-dimensional points;
a cluster configured to cluster the point clouds to obtain a point cloud cluster;
a central axis direction estimator configured to estimate a central axis direction based on the point cloud cluster; and
a direction-dependent local effective length estimator configured to estimate a local effective length for each of the point cloud clusters and the estimated central axis direction, the local effective length being a length when a length of projection of a point cloud belonging to the point cloud cluster in the central axis direction is interpolated by an amount of a loss part of the point cloud,
wherein the linear structure estimator uses the local effective length as a length of the linear structure to estimate a model parameter representing a region in which the linear structure is present.