KIT | KIT-Bibliothek | Impressum | Datenschutz

Deep Cross-Domain Building Extraction for Selective Depth Estimation from Oblique Aerial Imagery

Ruf, Boitumelo; Thiel, Laurenz; Weinmann, Martin

Abstract (englisch):
With the technological advancements of aerial imagery and accurate 3d reconstruction of urban environments, more and more attention has been paid to the automated analyses of urban areas. In our work, we examine two important aspects that allow online analysis of building structures in city models given oblique aerial image sequences, namely automatic building extraction with convolutional neural networks (CNNs) and selective real-time depth estimation from aerial imagery. We use transfer learning to train the Faster R-CNN method for real-time deep object detection, by combining a large ground-based dataset for urban scene understanding with a smaller number of images from an aerial dataset. We achieve an average precision (AP) of about 80% for the task of building extraction on a selected evaluation dataset. Our evaluation focuses on both dataset-specific learning and transfer learning. Furthermore, we present an algorithm that allows for multi-view depth estimation from aerial image sequences in real-time. We adopt the semi-global matching (SGM) optimization strategy to preserve sharp edges at object boundaries. In combination with the Faster R-CNN, it allows a selective reconstruction of buildings, identified with regions of interest (RoIs), from oblique aerial imagery.

Open Access Logo

Verlagsausgabe §
DOI: 10.5445/IR/1000086558
Veröffentlicht am 15.10.2018
DOI: 10.5194/isprs-annals-IV-1-125-2018
Zitationen: 1
Cover der Publikation
Zugehörige Institution(en) am KIT Fakultät für Bauingenieur-, Geo- und Umweltwissenschaften (BGU)
Institut für Photogrammetrie und Fernerkundung (IPF)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2018
Sprache Englisch
Identifikator urn:nbn:de:swb:90-865580
KITopen-ID: 1000086558
Erschienen in ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences
Band IV-1
Seiten 125–132
Nachgewiesen in Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page