A comparative study of image feature detection and description methods for robot vision

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Detection and description of local features in images is an essential task in robot vision. This task allows to identify and uniquely specify stable and invariant regions in a observed scene. Many successful detectors and descriptors have been proposed. However, the proper combination of a detector and a descriptor is not trivial because there is a trade-off among different performance criteria. This work presents a comparative study of successful image feature detection and description methods in the context of the simultaneous localization and mapping problem. The considered methods are exhaustively evaluated in terms of accuracy, robustness, and processing time.

Original languageEnglish
Title of host publicationOptics and Photonics for Information Processing XIII
EditorsKhan M. Iftekharuddin, Abdul A. S. Awwal, Victor H. Diaz-Ramirez, Andres Marquez
PublisherSPIE
ISBN (Electronic)9781510629653
DOIs
StatePublished - 1 Jan 2019
EventOptics and Photonics for Information Processing XIII 2019 - San Diego, United States
Duration: 13 Aug 201914 Aug 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11136
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceOptics and Photonics for Information Processing XIII 2019
CountryUnited States
CitySan Diego
Period13/08/1914/08/19

Fingerprint

Robot Vision
Feature Detection
robots
Computer vision
Descriptors
Comparative Study
Detector
Invariant Region
Detectors
Simultaneous Localization and Mapping
Local Features
detectors
Trivial
Trade-offs
Robustness
Processing
Context

Keywords

  • Image matching
  • Local feature descriptor
  • Local feature detector
  • Simultaneous Localization and Mapping

Cite this

Gonzalez-Ruiz, M., Diaz-Ramirez, V. H., & Juarez-Salazar, R. (2019). A comparative study of image feature detection and description methods for robot vision. In K. M. Iftekharuddin, A. A. S. Awwal, V. H. Diaz-Ramirez, & A. Marquez (Eds.), Optics and Photonics for Information Processing XIII [111360P] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11136). SPIE. https://doi.org/10.1117/12.2528581
Gonzalez-Ruiz, Martin ; Diaz-Ramirez, Victor H. ; Juarez-Salazar, Rigoberto. / A comparative study of image feature detection and description methods for robot vision. Optics and Photonics for Information Processing XIII. editor / Khan M. Iftekharuddin ; Abdul A. S. Awwal ; Victor H. Diaz-Ramirez ; Andres Marquez. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{5acd7623fe2d429caf6a58abac37087e,
title = "A comparative study of image feature detection and description methods for robot vision",
abstract = "Detection and description of local features in images is an essential task in robot vision. This task allows to identify and uniquely specify stable and invariant regions in a observed scene. Many successful detectors and descriptors have been proposed. However, the proper combination of a detector and a descriptor is not trivial because there is a trade-off among different performance criteria. This work presents a comparative study of successful image feature detection and description methods in the context of the simultaneous localization and mapping problem. The considered methods are exhaustively evaluated in terms of accuracy, robustness, and processing time.",
keywords = "Image matching, Local feature descriptor, Local feature detector, Simultaneous Localization and Mapping",
author = "Martin Gonzalez-Ruiz and Diaz-Ramirez, {Victor H.} and Rigoberto Juarez-Salazar",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2528581",
language = "Ingl{\'e}s",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Iftekharuddin, {Khan M.} and Awwal, {Abdul A. S.} and Diaz-Ramirez, {Victor H.} and Andres Marquez",
booktitle = "Optics and Photonics for Information Processing XIII",
address = "Estados Unidos",

}

Gonzalez-Ruiz, M, Diaz-Ramirez, VH & Juarez-Salazar, R 2019, A comparative study of image feature detection and description methods for robot vision. in KM Iftekharuddin, AAS Awwal, VH Diaz-Ramirez & A Marquez (eds), Optics and Photonics for Information Processing XIII., 111360P, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11136, SPIE, Optics and Photonics for Information Processing XIII 2019, San Diego, United States, 13/08/19. https://doi.org/10.1117/12.2528581

A comparative study of image feature detection and description methods for robot vision. / Gonzalez-Ruiz, Martin; Diaz-Ramirez, Victor H.; Juarez-Salazar, Rigoberto.

Optics and Photonics for Information Processing XIII. ed. / Khan M. Iftekharuddin; Abdul A. S. Awwal; Victor H. Diaz-Ramirez; Andres Marquez. SPIE, 2019. 111360P (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11136).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A comparative study of image feature detection and description methods for robot vision

AU - Gonzalez-Ruiz, Martin

AU - Diaz-Ramirez, Victor H.

AU - Juarez-Salazar, Rigoberto

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Detection and description of local features in images is an essential task in robot vision. This task allows to identify and uniquely specify stable and invariant regions in a observed scene. Many successful detectors and descriptors have been proposed. However, the proper combination of a detector and a descriptor is not trivial because there is a trade-off among different performance criteria. This work presents a comparative study of successful image feature detection and description methods in the context of the simultaneous localization and mapping problem. The considered methods are exhaustively evaluated in terms of accuracy, robustness, and processing time.

AB - Detection and description of local features in images is an essential task in robot vision. This task allows to identify and uniquely specify stable and invariant regions in a observed scene. Many successful detectors and descriptors have been proposed. However, the proper combination of a detector and a descriptor is not trivial because there is a trade-off among different performance criteria. This work presents a comparative study of successful image feature detection and description methods in the context of the simultaneous localization and mapping problem. The considered methods are exhaustively evaluated in terms of accuracy, robustness, and processing time.

KW - Image matching

KW - Local feature descriptor

KW - Local feature detector

KW - Simultaneous Localization and Mapping

UR - http://www.scopus.com/inward/record.url?scp=85075780840&partnerID=8YFLogxK

U2 - 10.1117/12.2528581

DO - 10.1117/12.2528581

M3 - Contribución a la conferencia

AN - SCOPUS:85075780840

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Optics and Photonics for Information Processing XIII

A2 - Iftekharuddin, Khan M.

A2 - Awwal, Abdul A. S.

A2 - Diaz-Ramirez, Victor H.

A2 - Marquez, Andres

PB - SPIE

ER -

Gonzalez-Ruiz M, Diaz-Ramirez VH, Juarez-Salazar R. A comparative study of image feature detection and description methods for robot vision. In Iftekharuddin KM, Awwal AAS, Diaz-Ramirez VH, Marquez A, editors, Optics and Photonics for Information Processing XIII. SPIE. 2019. 111360P. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2528581