Fast feature matching for detailed point cloud generation

Berjón Díez, Daniel and Pages Scasso, Rafael and García Santos, Narciso (2016). Fast feature matching for detailed point cloud generation. In: "6th International Conference on Image Processing Theory, Tools and Applications, IPTA2016", 12/12/2016 - 15/12/2016, Oulu, Finlandia. ISBN 978-1-4673-8910-5. pp. 1-6. https://doi.org/10.1109/IPTA.2016.7820978.

Description

Title: Fast feature matching for detailed point cloud generation
Author/s:
  • Berjón Díez, Daniel
  • Pages Scasso, Rafael
  • García Santos, Narciso
Item Type: Presentation at Congress or Conference (Article)
Event Title: 6th International Conference on Image Processing Theory, Tools and Applications, IPTA2016
Event Dates: 12/12/2016 - 15/12/2016
Event Location: Oulu, Finlandia
Title of Book: Proceedings of 6th International Conference on Image Processing Theory Tools and Applications (IPTA), 2016
Date: 15 December 2016
ISBN: 978-1-4673-8910-5
Subjects:
Freetext Keywords: Feature extraction, Three-dimensional displays, Cameras, Image reconstruction, Detectors, Graphics processing units, Instruction sets
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

Structure from motion is a very popular technique for obtaining three-dimensional point cloud-based reconstructions of objects from un-organised sets of images by analysing the correspondences between feature points detected in those images. However, the point clouds stemming from usual feature point extractors such as SIFT are frequently too sparse for reliable surface recovery. In this paper we show that alternate feature descriptors such as A-KAZE, which provide denser coverage of images, yield better results and more detailed point clouds. Unfortunately, the use of a dramatically increased number of points per image poses a computational challenge. We propose a technique based on epipolar geometry restrictions to significantly cut down on processing time and an efficient implementation thereof on a GPU.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainTEC2013-48453project MR-UHDTVUnspecifiedUnspecified
FP7grant 610691BRIDGETUnspecifiedUnspecified

More information

Item ID: 46505
DC Identifier: http://oa.upm.es/46505/
OAI Identifier: oai:oa.upm.es:46505
DOI: 10.1109/IPTA.2016.7820978
Official URL: http://ieeexplore.ieee.org/document/7820978/
Deposited by: Memoria Investigacion
Deposited on: 04 Sep 2017 16:39
Last Modified: 04 Sep 2017 16:39
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM