New compact 3-dimensional shape descriptor for a depth camera in indoor environments

Hyukdoo Choi, Euntai Kim

Research output: Contribution to journalArticle

Abstract

This study questions why existing local shape descriptors have high dimensionalities (up to hundreds) despite simplicity of local shapes. We derived an answer from a historical context and provided an alternative solution by proposing a new compact descriptor. Although existing descriptors can express complicated shapes and depth sensors have been improved, complex shapes are rarely observed in an ordinary environment and a depth sensor only captures a single side of a surface with noise. Therefore, we designed a new descriptor based on principal curvatures, which is compact but practically useful. For verification, the CoRBS dataset, the RGB-D Scenes dataset and the RGB-D Object dataset were used to compare the proposed descriptor with existing descriptors in terms of shape, instance, and category recognition rate. The proposed descriptor showed a comparable performance with existing descriptors despite its low dimensionality of 4.

Original languageEnglish
Article number876
JournalSensors (Switzerland)
Volume17
Issue number4
DOIs
Publication statusPublished - 2017 Apr 16

Fingerprint

Cameras
cameras
Sensors
Noise
sensors
curvature
Datasets

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Biochemistry
  • Atomic and Molecular Physics, and Optics
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

@article{d48d3e993ab44e80a526d3991f4ecb07,
title = "New compact 3-dimensional shape descriptor for a depth camera in indoor environments",
abstract = "This study questions why existing local shape descriptors have high dimensionalities (up to hundreds) despite simplicity of local shapes. We derived an answer from a historical context and provided an alternative solution by proposing a new compact descriptor. Although existing descriptors can express complicated shapes and depth sensors have been improved, complex shapes are rarely observed in an ordinary environment and a depth sensor only captures a single side of a surface with noise. Therefore, we designed a new descriptor based on principal curvatures, which is compact but practically useful. For verification, the CoRBS dataset, the RGB-D Scenes dataset and the RGB-D Object dataset were used to compare the proposed descriptor with existing descriptors in terms of shape, instance, and category recognition rate. The proposed descriptor showed a comparable performance with existing descriptors despite its low dimensionality of 4.",
author = "Hyukdoo Choi and Euntai Kim",
year = "2017",
month = "4",
day = "16",
doi = "10.3390/s17040876",
language = "English",
volume = "17",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

New compact 3-dimensional shape descriptor for a depth camera in indoor environments. / Choi, Hyukdoo; Kim, Euntai.

In: Sensors (Switzerland), Vol. 17, No. 4, 876, 16.04.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - New compact 3-dimensional shape descriptor for a depth camera in indoor environments

AU - Choi, Hyukdoo

AU - Kim, Euntai

PY - 2017/4/16

Y1 - 2017/4/16

N2 - This study questions why existing local shape descriptors have high dimensionalities (up to hundreds) despite simplicity of local shapes. We derived an answer from a historical context and provided an alternative solution by proposing a new compact descriptor. Although existing descriptors can express complicated shapes and depth sensors have been improved, complex shapes are rarely observed in an ordinary environment and a depth sensor only captures a single side of a surface with noise. Therefore, we designed a new descriptor based on principal curvatures, which is compact but practically useful. For verification, the CoRBS dataset, the RGB-D Scenes dataset and the RGB-D Object dataset were used to compare the proposed descriptor with existing descriptors in terms of shape, instance, and category recognition rate. The proposed descriptor showed a comparable performance with existing descriptors despite its low dimensionality of 4.

AB - This study questions why existing local shape descriptors have high dimensionalities (up to hundreds) despite simplicity of local shapes. We derived an answer from a historical context and provided an alternative solution by proposing a new compact descriptor. Although existing descriptors can express complicated shapes and depth sensors have been improved, complex shapes are rarely observed in an ordinary environment and a depth sensor only captures a single side of a surface with noise. Therefore, we designed a new descriptor based on principal curvatures, which is compact but practically useful. For verification, the CoRBS dataset, the RGB-D Scenes dataset and the RGB-D Object dataset were used to compare the proposed descriptor with existing descriptors in terms of shape, instance, and category recognition rate. The proposed descriptor showed a comparable performance with existing descriptors despite its low dimensionality of 4.

UR - http://www.scopus.com/inward/record.url?scp=85018505021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018505021&partnerID=8YFLogxK

U2 - 10.3390/s17040876

DO - 10.3390/s17040876

M3 - Article

AN - SCOPUS:85018505021

VL - 17

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 4

M1 - 876

ER -