Feature evaluation for building facade images - An empirical study

M. Y. Yang, W. Förstner, D. Chai

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

5 Citations (Scopus)
1 Downloads (Pure)

Abstract

The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.
Original languageEnglish
Title of host publicationInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Science
Subtitle of host publicationXXII ISPRS Congress
Pages513-518
Number of pages6
VolumeXXXIX-B3
DOIs
Publication statusPublished - 1 Sep 2012
Externally publishedYes
Event22nd Congress of the International Society for Photogrammetry and Remote Sensing, ISPRS 2012 - Melbourne, Australia
Duration: 25 Aug 20121 Sep 2012
Conference number: 22

Publication series

NameInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
PublisherCopernicus
ISSN (Print)1682-1750

Conference

Conference22nd Congress of the International Society for Photogrammetry and Remote Sensing, ISPRS 2012
Abbreviated titleISPRS 2012
CountryAustralia
CityMelbourne
Period25/08/121/09/12

Fingerprint

Facades
Image classification
Photogrammetry
Pavements
Labeling
Classifiers
Railroad cars
Textures
Color
Experiments

Keywords

  • ITC-GOLD

Cite this

Yang, M. Y., Förstner, W., & Chai, D. (2012). Feature evaluation for building facade images - An empirical study. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Science: XXII ISPRS Congress (Vol. XXXIX-B3, pp. 513-518). (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences). https://doi.org/10.5194/isprsarchives-XXXIX-B3-513-2012
Yang, M. Y. ; Förstner, W. ; Chai, D. / Feature evaluation for building facade images - An empirical study. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Science: XXII ISPRS Congress. Vol. XXXIX-B3 2012. pp. 513-518 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences).
@inproceedings{e5d2667fd68640ec97461dbed29c768d,
title = "Feature evaluation for building facade images - An empirical study",
abstract = "The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.",
keywords = "ITC-GOLD",
author = "Yang, {M. Y.} and W. F{\"o}rstner and D. Chai",
year = "2012",
month = "9",
day = "1",
doi = "10.5194/isprsarchives-XXXIX-B3-513-2012",
language = "English",
volume = "XXXIX-B3",
series = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
publisher = "Copernicus",
pages = "513--518",
booktitle = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Science",

}

Yang, MY, Förstner, W & Chai, D 2012, Feature evaluation for building facade images - An empirical study. in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Science: XXII ISPRS Congress. vol. XXXIX-B3, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp. 513-518, 22nd Congress of the International Society for Photogrammetry and Remote Sensing, ISPRS 2012, Melbourne, Australia, 25/08/12. https://doi.org/10.5194/isprsarchives-XXXIX-B3-513-2012

Feature evaluation for building facade images - An empirical study. / Yang, M. Y.; Förstner, W.; Chai, D.

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Science: XXII ISPRS Congress. Vol. XXXIX-B3 2012. p. 513-518 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Feature evaluation for building facade images - An empirical study

AU - Yang, M. Y.

AU - Förstner, W.

AU - Chai, D.

PY - 2012/9/1

Y1 - 2012/9/1

N2 - The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.

AB - The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.

KW - ITC-GOLD

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2012/chap/yang_fea.pdf

U2 - 10.5194/isprsarchives-XXXIX-B3-513-2012

DO - 10.5194/isprsarchives-XXXIX-B3-513-2012

M3 - Conference contribution

VL - XXXIX-B3

T3 - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SP - 513

EP - 518

BT - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Science

ER -

Yang MY, Förstner W, Chai D. Feature evaluation for building facade images - An empirical study. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Science: XXII ISPRS Congress. Vol. XXXIX-B3. 2012. p. 513-518. (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences). https://doi.org/10.5194/isprsarchives-XXXIX-B3-513-2012