Processing apparatus, processing method, and computer readable medium

Patent metadata

Field	Value
Publication number	US-2022343628-A1
Application number	US-201917637132-A
Country	US
Kind code	A1
Filing date	Aug 28, 2019
Priority date	Aug 28, 2019
Publication date	Oct 27, 2022
Grant date	—

Abstract

A processing apparatus (10) includes classification means (12) for classifying three-dimensional point group data acquired based on a reflected light from a structure to be inspected illuminated by light into clusters, which are units of a shape that corresponds to the structure to be inspected, based on positional information at each point of the data; and cluster association means (13) for determining whether a first cluster and a second cluster included in the classified clusters correspond to one structure to be inspected based on a positional relation between the classified clusters.

First claim

What is claimed is:

1 . A processing apparatus comprising:
at least one memory storing instructions, and at least one processor configured to execute the instructions to: classify three-dimensional point group data acquired based on a reflected light from a structure to be inspected illuminated by light into clusters, which are units of a shape that corresponds to the structure, based on positional information at each point of the data; and determine whether a first cluster and a second cluster included in the classified clusters correspond to one structure based on a positional relation between the classified clusters.

2 . The processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions to:
generate a first projection cluster obtained by projecting the first cluster onto a predetermined first plane and a second projection cluster obtained by projecting the second cluster onto the first plane, the first plane being vertical to a line that connects the center of gravity of the first cluster to the center of gravity of the second cluster; and take into account a result of a determination regarding whether the first projection cluster matches the second projection cluster in the association between the first cluster and the second cluster.

3 . The processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions to:
generate a first projection cluster obtained by projecting the first cluster onto a predetermined first plane and a second projection cluster obtained by projecting the second cluster onto the first plane; detect, for each of all the clusters classified, the longest direction in which the largest number of points are aligned, the first plane being vertical to the longest direction; and take into account a result of a determination regarding whether the first projection cluster matches the second projection cluster in the association between the first cluster and the second cluster.

4 . The processing apparatus according to claim 2 , wherein the at least one processor is further configured to execute the instructions to:
extract, for each of all the clusters classified, a plurality of contour lines that are present; compare, for a first cluster and a second cluster included in all the clusters, a first contour line group, which is a plurality of contour lines extracted from the first cluster, with a second contour line group, which is a plurality of contour lines extracted from the second cluster, and calculating the number of contour lines in the first contour line group that match contour lines in the second contour line group; and take into account the number of contour lines that match each other in the association between the first cluster and the second cluster.

5 . The processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions to:
detect, for each of all the clusters classified, the shortest direction in which the least number of points being aligned; calculate one of the angles between the shortest direction detected by the first cluster and the shortest direction detected by the second cluster that is smaller than the other one; calculate the difference between a first average distance, which is the average of distances between respective points included in the first cluster and a second plane, and a second average distance, which is the average of distances between respective points included in the second cluster and the second plane, the second plane being a plane vertical to the shortest direction detected by the first cluster; and take into account the angle and the difference in the association between the first cluster and the second cluster.

6 . The processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions to:
determine whether there is a third cluster including points whose number is equal to or larger than a predetermined number in a position in front of a structure to be inspected between the first cluster and the second cluster with respect to a three-dimensional sensor that irradiates light on the structure to be inspected, and not associate the first cluster with the second cluster when there is no third cluster.

7 . The processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions to:
generate a distance image from point group data and calculating the average of pixel values of pixels included in a region between the first cluster and the second cluster in the distance image that has been generated; and not associate the first cluster with the second cluster when the average is larger than a predetermined threshold.

8 . The processing apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions to
complement a point group between the first cluster and the second cluster when it has been determined that the first cluster will be associated with the second cluster.

9 . A processing method comprising the steps of:
classifying three-dimensional point group data acquired based on a reflected light from a structure to be inspected illuminated by light into clusters, which are units of a shape that corresponds to the structure, based on positional information at each point of the data; and determining whether a first cluster and a second cluster included in the classified clusters correspond to one structure based on a positional relation between the classified clusters.

10 . A non-transitory computer readable medium storing a program for causing a computer to execute the following steps of:
classifying three-dimensional point group data acquired based on a reflected light from a structure to be inspected illuminated by light into clusters, which are units of a shape that corresponds to the structure, based on positional information at each point of the data; and determining whether a first cluster and a second cluster included in the classified clusters correspond to one structure based on a positional relation between the classified clusters.

Assignees

• Nec Corp

Inventors

• Ono Yoshimasa
• Tsuji Akira
• Abe Junichi

Classifications

• G06V10/762 Primary

  using clustering, e.g. of similar faces in social networks · CPC title

• G06V10/764 Primary

  using classification, e.g. of video objects · CPC title

• G06T7/00

  Image analysis · CPC title