KIT | KIT-Bibliothek | Impressum | Datenschutz

A classification-segmentation framework for the detection of individual trees in dense MMS point cloud data acquired in urban areas

Weinmann, Martin; Weinmann, Michael; Mallet, Clément; Brédif, Mathieu

In this paper, we present a novel framework for detecting individual trees in densely sampled 3D point cloud data acquired in urban areas. Given a 3D point cloud, the objective is to assign point-wise labels that are both class-aware and instance-aware, a task that is known as instance-level segmentation. To achieve this, our framework addresses two successive steps. The first step of our framework is given by the use of geometric features for a binary point-wise semantic classification with the objective of assigning semantic class labels to irregularly distributed 3D points, whereby the labels are defined as “tree points” and “other points”. The second step of our framework is given by a semantic segmentation with the objective of separating individual trees within the “tree points”. This is achieved by applying an efficient adaptation of the mean shift algorithm and a subsequent segment-based shape analysis relying on semantic rules to only retain plausible tree segments. We demonstrate the performance of our framework on a publicly available benchmark dataset, which has been acquired with a mobile mapping system in the city of Delft in the Netherlands. ... mehr

Open Access Logo

Volltext §
DOI: 10.5445/IR/1000070399
DOI: 10.3390/rs9030277
Zitationen: 41
Web of Science
Zitationen: 36
Zitationen: 41
Cover der Publikation
Zugehörige Institution(en) am KIT Fakultät für Bauingenieur-, Geo- und Umweltwissenschaften (BGU)
Institut für Photogrammetrie und Fernerkundung (IPF)
KIT-Zentrum Klima und Umwelt (ZKU)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2017
Sprache Englisch
Identifikator ISSN: 2072-4292
KITopen-ID: 1000070399
HGF-Programm 12.03 (POF III, LK 01) Tropospheric trace substances
Erschienen in Remote sensing
Verlag MDPI
Band 9
Heft 3
Seiten Art.Nr. 277
Bemerkung zur Veröffentlichung Gefördert durch den KIT-Publikationsfonds
Schlagwörter mobile mapping systems; 3D point cloud; feature extraction; feature selection; semantic classification; semantic segmentation; instance-level segmentation; tree-like objects
Nachgewiesen in Web of Science
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page