Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers

• Published in: ISPRS journal of photogrammetry and remote sensing Vol. 105; pp. 286 - 304
• Main Authors: Weinmann, Martin, Jutzi, Boris, Hinz, Stefan, Mallet, Clément
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.07.2015; Elsevier
• Subjects: 3D scene analysis; Classification; Computer Science; computer vision; Computer Vision and Pattern Recognition; data collection; expert opinion; Feature extraction; Feature selection; Neighborhood selection; photogrammetry; Point cloud; remote sensing; robots; Neighborhood selection; Feature extraction; Feature selection; Point cloud; 3D scene analysis; Classification

3D scene analysis in terms of automatically assigning 3D points a respective semantic label has become a topic of great importance in photogrammetry, remote sensing, computer vision and robotics. In this paper, we address the issue of how to increase the distinctiveness of geometric features and sel...