Outdoor scene building extraction method based on multi-feature constraint

The invention discloses an outdoor scene building extraction method based on multi-feature constraint, and the method comprises the steps: firstly carrying out the down-sampling of a large-scale point cloud scene through employing a voxel grid filtering method, and removing ground points from the sc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SUN ZEQIAN, WANG LANLAN, WANG LIN, WANG YINGHUI, NING XIAOJUAN, JIN HAIYAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses an outdoor scene building extraction method based on multi-feature constraint, and the method comprises the steps: firstly carrying out the down-sampling of a large-scale point cloud scene through employing a voxel grid filtering method, and removing ground points from the scene after the down-sampling through employing a cloth filtering algorithm; then, non-ground points are clustered based on a density clustering algorithm and a KD tree, and the non-ground points are clustered into different point clusters; and finally, combining the height, volume, direction, dimension and color features of the point cloud to separate the building point cloud from the non-building point cloud, and finally extracting the building point cloud from the outdoor scene. According to the method, the problem of low extraction precision of a traditional method is effectively solved, most buildings in an outdoor scene can be successfully extracted, and a corresponding processing thought is provided for buildi