A proposal of 3D feature based on occupancy of point cloud in multi-scale shell region

Shoichi Takei, Shuichi Akizuki, Manabu Hashimoto

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose a novel keypoint detection and feature description method called "SHORT" (Shell Histograms and Occupancy from Radial Transform) for fast 3D object recognition. Conventional keypoint detection and feature description methods such as the SHOT method have been necessary to calculate many normal vectors or other statistical values from the point cloud data in local regions, so its computational costs are expensive. By contrast, the SHORT method consists of a fast keypoint detector that does not calculate statistics and a fast feature descriptor that uses a small number of points in the restricted local regions. The keypoint detector uses the occupancy measure which can be estimated by only counting the number of points in multiple spherical shell regions. Also the feature descriptor uses a small number of points included in distinctive shell regions of multiple scales. Experimental results in 3D object recognition using real dataset show that the processing speed of the proposed method is approximately nine times faster than that of comparative methods.

Original languageEnglish
Pages (from-to)1078-1084
Number of pages7
JournalIEEJ Transactions on Electronics, Information and Systems
Volume136
Issue number8
DOIs
Publication statusPublished - 2016
Externally publishedYes

Fingerprint

Object recognition
Detectors
Statistics
Mathematical transformations
Processing
Costs

Keywords

  • 3D feature description
  • 3D object recognition
  • Multiple scale shell
  • Occupancy
  • Robot vision

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

A proposal of 3D feature based on occupancy of point cloud in multi-scale shell region. / Takei, Shoichi; Akizuki, Shuichi; Hashimoto, Manabu.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 136, No. 8, 2016, p. 1078-1084.

Research output: Contribution to journalArticle

Takei, Shoichi ; Akizuki, Shuichi ; Hashimoto, Manabu. / A proposal of 3D feature based on occupancy of point cloud in multi-scale shell region. In: IEEJ Transactions on Electronics, Information and Systems. 2016 ; Vol. 136, No. 8. pp. 1078-1084.
@article{6a4ca4ac05e341f4932174376eaee1ed,
title = "A proposal of 3D feature based on occupancy of point cloud in multi-scale shell region",
abstract = "In this paper, we propose a novel keypoint detection and feature description method called {"}SHORT{"} (Shell Histograms and Occupancy from Radial Transform) for fast 3D object recognition. Conventional keypoint detection and feature description methods such as the SHOT method have been necessary to calculate many normal vectors or other statistical values from the point cloud data in local regions, so its computational costs are expensive. By contrast, the SHORT method consists of a fast keypoint detector that does not calculate statistics and a fast feature descriptor that uses a small number of points in the restricted local regions. The keypoint detector uses the occupancy measure which can be estimated by only counting the number of points in multiple spherical shell regions. Also the feature descriptor uses a small number of points included in distinctive shell regions of multiple scales. Experimental results in 3D object recognition using real dataset show that the processing speed of the proposed method is approximately nine times faster than that of comparative methods.",
keywords = "3D feature description, 3D object recognition, Multiple scale shell, Occupancy, Robot vision",
author = "Shoichi Takei and Shuichi Akizuki and Manabu Hashimoto",
year = "2016",
doi = "10.1541/ieejeiss.136.1078",
language = "English",
volume = "136",
pages = "1078--1084",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "8",

}

TY - JOUR

T1 - A proposal of 3D feature based on occupancy of point cloud in multi-scale shell region

AU - Takei, Shoichi

AU - Akizuki, Shuichi

AU - Hashimoto, Manabu

PY - 2016

Y1 - 2016

N2 - In this paper, we propose a novel keypoint detection and feature description method called "SHORT" (Shell Histograms and Occupancy from Radial Transform) for fast 3D object recognition. Conventional keypoint detection and feature description methods such as the SHOT method have been necessary to calculate many normal vectors or other statistical values from the point cloud data in local regions, so its computational costs are expensive. By contrast, the SHORT method consists of a fast keypoint detector that does not calculate statistics and a fast feature descriptor that uses a small number of points in the restricted local regions. The keypoint detector uses the occupancy measure which can be estimated by only counting the number of points in multiple spherical shell regions. Also the feature descriptor uses a small number of points included in distinctive shell regions of multiple scales. Experimental results in 3D object recognition using real dataset show that the processing speed of the proposed method is approximately nine times faster than that of comparative methods.

AB - In this paper, we propose a novel keypoint detection and feature description method called "SHORT" (Shell Histograms and Occupancy from Radial Transform) for fast 3D object recognition. Conventional keypoint detection and feature description methods such as the SHOT method have been necessary to calculate many normal vectors or other statistical values from the point cloud data in local regions, so its computational costs are expensive. By contrast, the SHORT method consists of a fast keypoint detector that does not calculate statistics and a fast feature descriptor that uses a small number of points in the restricted local regions. The keypoint detector uses the occupancy measure which can be estimated by only counting the number of points in multiple spherical shell regions. Also the feature descriptor uses a small number of points included in distinctive shell regions of multiple scales. Experimental results in 3D object recognition using real dataset show that the processing speed of the proposed method is approximately nine times faster than that of comparative methods.

KW - 3D feature description

KW - 3D object recognition

KW - Multiple scale shell

KW - Occupancy

KW - Robot vision

UR - http://www.scopus.com/inward/record.url?scp=84980378665&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84980378665&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.136.1078

DO - 10.1541/ieejeiss.136.1078

M3 - Article

AN - SCOPUS:84980378665

VL - 136

SP - 1078

EP - 1084

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 8

ER -