Analysis of oblique aerial images for land cover and point cloud classification in an Urban environment

Jiann Yeou Rau, Jyun Ping Jhan, Ya Ching Hsu

研究成果: Article

44 引文 (Scopus)

摘要

In addition to aerial imagery, point clouds are important remote sensing data in urban environment studies. It is essential to extract semantic information from both images and point clouds for such purposes; thus, this study aims to automatically classify 3-D point clouds generated using oblique aerial imagery (OAI)/vertical aerial imagery (VAI) into various urban object classes, such as roof, facade, road, tree, and grass. A multicamera airborne imaging system that can simultaneously acquire VAI and OAI is suggested. The acquired small-format images contain only three RGB spectral bands and are used to generate photogrammetric point clouds through a multiview-stereo dense matching technique. To assign each 3-D point cloud to a corresponding urban object class, we first analyzed the original OAI through object-based image analyses. A rule-based hierarchical semantic classification scheme that utilizes spectral information and geometry-and topology-related features was developed, in which the object height and gradient features were derived from the photogrammetric point clouds to assist in the detection of elevated objects, particularly for the roof and facade. Finally, the photogrammetric point clouds were classified into the aforementioned five classes. The classification accuracy was assessed on the image space, and four experimental results showed that the overall accuracy is between 82.47% and 91.8%. In addition, visual and consistency analyses were performed to demonstrate the proposed classification scheme's feasibility, transferability, and reliability, particularly for distinguishing elevated objects from OAI, which has a severe occlusion effect, image-scale variation, and ambiguous spectral characteristics.

原文English
文章編號6870455
頁(從 - 到)1304-1319
頁數16
期刊IEEE Transactions on Geoscience and Remote Sensing
53
發行號3
DOIs
出版狀態Published - 2015 三月 1

指紋

cloud classification
land cover
imagery
Antennas
Facades
Roofs
roof
Semantics
analysis
Imaging systems
topology
Remote sensing
Topology
grass
road
remote sensing
geometry
Geometry

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Earth and Planetary Sciences(all)

引用此文

@article{3da7f38d582148ed92735ac238df4b05,
title = "Analysis of oblique aerial images for land cover and point cloud classification in an Urban environment",
abstract = "In addition to aerial imagery, point clouds are important remote sensing data in urban environment studies. It is essential to extract semantic information from both images and point clouds for such purposes; thus, this study aims to automatically classify 3-D point clouds generated using oblique aerial imagery (OAI)/vertical aerial imagery (VAI) into various urban object classes, such as roof, facade, road, tree, and grass. A multicamera airborne imaging system that can simultaneously acquire VAI and OAI is suggested. The acquired small-format images contain only three RGB spectral bands and are used to generate photogrammetric point clouds through a multiview-stereo dense matching technique. To assign each 3-D point cloud to a corresponding urban object class, we first analyzed the original OAI through object-based image analyses. A rule-based hierarchical semantic classification scheme that utilizes spectral information and geometry-and topology-related features was developed, in which the object height and gradient features were derived from the photogrammetric point clouds to assist in the detection of elevated objects, particularly for the roof and facade. Finally, the photogrammetric point clouds were classified into the aforementioned five classes. The classification accuracy was assessed on the image space, and four experimental results showed that the overall accuracy is between 82.47{\%} and 91.8{\%}. In addition, visual and consistency analyses were performed to demonstrate the proposed classification scheme's feasibility, transferability, and reliability, particularly for distinguishing elevated objects from OAI, which has a severe occlusion effect, image-scale variation, and ambiguous spectral characteristics.",
author = "Rau, {Jiann Yeou} and Jhan, {Jyun Ping} and Hsu, {Ya Ching}",
year = "2015",
month = "3",
day = "1",
doi = "10.1109/TGRS.2014.2337658",
language = "English",
volume = "53",
pages = "1304--1319",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

Analysis of oblique aerial images for land cover and point cloud classification in an Urban environment. / Rau, Jiann Yeou; Jhan, Jyun Ping; Hsu, Ya Ching.

於: IEEE Transactions on Geoscience and Remote Sensing, 卷 53, 編號 3, 6870455, 01.03.2015, p. 1304-1319.

研究成果: Article

TY - JOUR

T1 - Analysis of oblique aerial images for land cover and point cloud classification in an Urban environment

AU - Rau, Jiann Yeou

AU - Jhan, Jyun Ping

AU - Hsu, Ya Ching

PY - 2015/3/1

Y1 - 2015/3/1

N2 - In addition to aerial imagery, point clouds are important remote sensing data in urban environment studies. It is essential to extract semantic information from both images and point clouds for such purposes; thus, this study aims to automatically classify 3-D point clouds generated using oblique aerial imagery (OAI)/vertical aerial imagery (VAI) into various urban object classes, such as roof, facade, road, tree, and grass. A multicamera airborne imaging system that can simultaneously acquire VAI and OAI is suggested. The acquired small-format images contain only three RGB spectral bands and are used to generate photogrammetric point clouds through a multiview-stereo dense matching technique. To assign each 3-D point cloud to a corresponding urban object class, we first analyzed the original OAI through object-based image analyses. A rule-based hierarchical semantic classification scheme that utilizes spectral information and geometry-and topology-related features was developed, in which the object height and gradient features were derived from the photogrammetric point clouds to assist in the detection of elevated objects, particularly for the roof and facade. Finally, the photogrammetric point clouds were classified into the aforementioned five classes. The classification accuracy was assessed on the image space, and four experimental results showed that the overall accuracy is between 82.47% and 91.8%. In addition, visual and consistency analyses were performed to demonstrate the proposed classification scheme's feasibility, transferability, and reliability, particularly for distinguishing elevated objects from OAI, which has a severe occlusion effect, image-scale variation, and ambiguous spectral characteristics.

AB - In addition to aerial imagery, point clouds are important remote sensing data in urban environment studies. It is essential to extract semantic information from both images and point clouds for such purposes; thus, this study aims to automatically classify 3-D point clouds generated using oblique aerial imagery (OAI)/vertical aerial imagery (VAI) into various urban object classes, such as roof, facade, road, tree, and grass. A multicamera airborne imaging system that can simultaneously acquire VAI and OAI is suggested. The acquired small-format images contain only three RGB spectral bands and are used to generate photogrammetric point clouds through a multiview-stereo dense matching technique. To assign each 3-D point cloud to a corresponding urban object class, we first analyzed the original OAI through object-based image analyses. A rule-based hierarchical semantic classification scheme that utilizes spectral information and geometry-and topology-related features was developed, in which the object height and gradient features were derived from the photogrammetric point clouds to assist in the detection of elevated objects, particularly for the roof and facade. Finally, the photogrammetric point clouds were classified into the aforementioned five classes. The classification accuracy was assessed on the image space, and four experimental results showed that the overall accuracy is between 82.47% and 91.8%. In addition, visual and consistency analyses were performed to demonstrate the proposed classification scheme's feasibility, transferability, and reliability, particularly for distinguishing elevated objects from OAI, which has a severe occlusion effect, image-scale variation, and ambiguous spectral characteristics.

UR - http://www.scopus.com/inward/record.url?scp=84907522905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907522905&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2014.2337658

DO - 10.1109/TGRS.2014.2337658

M3 - Article

AN - SCOPUS:84907522905

VL - 53

SP - 1304

EP - 1319

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 3

M1 - 6870455

ER -