The Ascender System

Automated Site Modeling from Multiple Aerial Images

Robert Collins, Christopher O. Jaynes, Yong Qing Cheng, Xiaoguang Wang, Frank Stolle, Edward M. Riseman, Allen R. Hanson

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

The Ascender system acquires, extends, and refines 3D geometric site models from calibrated aerial imagery. To acquire a new site model, an automated building detector is run on one image to hypothesize potential building rooftops. Supporting evidence is located in other images via epipolar line segment matching in constrained search regions. The precise 3D shape and location of each building is then determined by multiimage triangulation under geometric constraints of 3D orthogonality, parallelness, colinearity, and coplanarity of lines and surfaces. Projective mapping of image intensity information onto these polyhedral building models results in a realistic site model that can be rendered using virtual "fly-through" graphics. As new images of the site become available, model extension and refinement procedures are performed to add previously unseen buildings and to improve the geometric accuracy of the existing 3D building models. In this way, the system gradually accumulates evidence over time to make the site model more complete and more accurate. An extensive performance evaluation of component algorithms and the full system has been carried out. Two-dimensional building detection accuracy, as well as accuracy of the three-dimensional building reconstruction, are presented for a representative data set.

Original languageEnglish (US)
Pages (from-to)143-162
Number of pages20
JournalComputer Vision and Image Understanding
Volume72
Issue number2
DOIs
StatePublished - Jan 1 1998

Fingerprint

Antennas
Triangulation
Detectors

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Collins, R., Jaynes, C. O., Cheng, Y. Q., Wang, X., Stolle, F., Riseman, E. M., & Hanson, A. R. (1998). The Ascender System: Automated Site Modeling from Multiple Aerial Images. Computer Vision and Image Understanding, 72(2), 143-162. https://doi.org/10.1006/cviu.1998.0729
Collins, Robert ; Jaynes, Christopher O. ; Cheng, Yong Qing ; Wang, Xiaoguang ; Stolle, Frank ; Riseman, Edward M. ; Hanson, Allen R. / The Ascender System : Automated Site Modeling from Multiple Aerial Images. In: Computer Vision and Image Understanding. 1998 ; Vol. 72, No. 2. pp. 143-162.
@article{0b8146bcc38347c0be919f0cd102523b,
title = "The Ascender System: Automated Site Modeling from Multiple Aerial Images",
abstract = "The Ascender system acquires, extends, and refines 3D geometric site models from calibrated aerial imagery. To acquire a new site model, an automated building detector is run on one image to hypothesize potential building rooftops. Supporting evidence is located in other images via epipolar line segment matching in constrained search regions. The precise 3D shape and location of each building is then determined by multiimage triangulation under geometric constraints of 3D orthogonality, parallelness, colinearity, and coplanarity of lines and surfaces. Projective mapping of image intensity information onto these polyhedral building models results in a realistic site model that can be rendered using virtual {"}fly-through{"} graphics. As new images of the site become available, model extension and refinement procedures are performed to add previously unseen buildings and to improve the geometric accuracy of the existing 3D building models. In this way, the system gradually accumulates evidence over time to make the site model more complete and more accurate. An extensive performance evaluation of component algorithms and the full system has been carried out. Two-dimensional building detection accuracy, as well as accuracy of the three-dimensional building reconstruction, are presented for a representative data set.",
author = "Robert Collins and Jaynes, {Christopher O.} and Cheng, {Yong Qing} and Xiaoguang Wang and Frank Stolle and Riseman, {Edward M.} and Hanson, {Allen R.}",
year = "1998",
month = "1",
day = "1",
doi = "10.1006/cviu.1998.0729",
language = "English (US)",
volume = "72",
pages = "143--162",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",
number = "2",

}

Collins, R, Jaynes, CO, Cheng, YQ, Wang, X, Stolle, F, Riseman, EM & Hanson, AR 1998, 'The Ascender System: Automated Site Modeling from Multiple Aerial Images', Computer Vision and Image Understanding, vol. 72, no. 2, pp. 143-162. https://doi.org/10.1006/cviu.1998.0729

The Ascender System : Automated Site Modeling from Multiple Aerial Images. / Collins, Robert; Jaynes, Christopher O.; Cheng, Yong Qing; Wang, Xiaoguang; Stolle, Frank; Riseman, Edward M.; Hanson, Allen R.

In: Computer Vision and Image Understanding, Vol. 72, No. 2, 01.01.1998, p. 143-162.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The Ascender System

T2 - Automated Site Modeling from Multiple Aerial Images

AU - Collins, Robert

AU - Jaynes, Christopher O.

AU - Cheng, Yong Qing

AU - Wang, Xiaoguang

AU - Stolle, Frank

AU - Riseman, Edward M.

AU - Hanson, Allen R.

PY - 1998/1/1

Y1 - 1998/1/1

N2 - The Ascender system acquires, extends, and refines 3D geometric site models from calibrated aerial imagery. To acquire a new site model, an automated building detector is run on one image to hypothesize potential building rooftops. Supporting evidence is located in other images via epipolar line segment matching in constrained search regions. The precise 3D shape and location of each building is then determined by multiimage triangulation under geometric constraints of 3D orthogonality, parallelness, colinearity, and coplanarity of lines and surfaces. Projective mapping of image intensity information onto these polyhedral building models results in a realistic site model that can be rendered using virtual "fly-through" graphics. As new images of the site become available, model extension and refinement procedures are performed to add previously unseen buildings and to improve the geometric accuracy of the existing 3D building models. In this way, the system gradually accumulates evidence over time to make the site model more complete and more accurate. An extensive performance evaluation of component algorithms and the full system has been carried out. Two-dimensional building detection accuracy, as well as accuracy of the three-dimensional building reconstruction, are presented for a representative data set.

AB - The Ascender system acquires, extends, and refines 3D geometric site models from calibrated aerial imagery. To acquire a new site model, an automated building detector is run on one image to hypothesize potential building rooftops. Supporting evidence is located in other images via epipolar line segment matching in constrained search regions. The precise 3D shape and location of each building is then determined by multiimage triangulation under geometric constraints of 3D orthogonality, parallelness, colinearity, and coplanarity of lines and surfaces. Projective mapping of image intensity information onto these polyhedral building models results in a realistic site model that can be rendered using virtual "fly-through" graphics. As new images of the site become available, model extension and refinement procedures are performed to add previously unseen buildings and to improve the geometric accuracy of the existing 3D building models. In this way, the system gradually accumulates evidence over time to make the site model more complete and more accurate. An extensive performance evaluation of component algorithms and the full system has been carried out. Two-dimensional building detection accuracy, as well as accuracy of the three-dimensional building reconstruction, are presented for a representative data set.

UR - http://www.scopus.com/inward/record.url?scp=0032207498&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032207498&partnerID=8YFLogxK

U2 - 10.1006/cviu.1998.0729

DO - 10.1006/cviu.1998.0729

M3 - Article

VL - 72

SP - 143

EP - 162

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

IS - 2

ER -