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
• ISSN: 0924-2716; 1872-8235
• DOI: 10.1016/j.isprsjprs.2015.01.016

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 select the most relevant ones among these for 3D scene analysis. We present a new, fully automated and versatile framework composed of four components: (i) neighborhood selection, (ii) feature extraction, (iii) feature selection and (iv) classification. For each component, we consider a variety of approaches which allow applicability in terms of simplicity, efficiency and reproducibility, so that end-users can easily apply the different components and do not require expert knowledge in the respective domains. In a detailed evaluation involving 7 neighborhood definitions, 21 geometric features, 7 approaches for feature selection, 10 classifiers and 2 benchmark datasets, we demonstrate that the selection of optimal neighborhoods for individual 3D points significantly improves the results of 3D scene analysis. Additionally, we show that the selection of adequate feature subsets may even further increase the quality of the derived results while significantly reducing both processing time and memory consumption.