TY - JOUR

T1 - Contextual classification of point cloud data by exploiting individual 3D neigbourhoods

AU - Weinmann, M.

AU - Schmidt, A.

AU - Mallet, C.

AU - Hinz, S.

AU - Rottensteiner, F.

AU - Jutzi, B.

PY - 2015/3/12

Y1 - 2015/3/12

N2 - The fully automated analysis of 3D point clouds is of great importance in photogrammetry, remote sensing and computer vision. For reliably extracting objects such as buildings, road inventory or vegetation, many approaches rely on the results of a point cloud classification, where each 3D point is assigned a respective semantic class label. Such an assignment, in turn, typically involves statistical methods for feature extraction and machine learning. Whereas the different components in the processing workflow have extensively, but separately been investigated in recent years, the respective connection by sharing the results of crucial tasks across all components has not yet been addressed. This connection not only encapsulates the interrelated issues of neighborhood selection and feature extraction, but also the issue of how to involve spatial context in the classification step. In this paper, we present a novel and generic approach for 3D scene analysis which relies on (i) individually optimized 3D neighborhoods for (ii) the extraction of distinctive geometric features and (iii) the contextual classification of point cloud data. For a labeled benchmark dataset, we demonstrate the beneficial impact of involving contextual information in the classification process and that using individual 3D neighborhoods of optimal size significantly increases the quality of the results for both pointwise and contextual classification.

AB - The fully automated analysis of 3D point clouds is of great importance in photogrammetry, remote sensing and computer vision. For reliably extracting objects such as buildings, road inventory or vegetation, many approaches rely on the results of a point cloud classification, where each 3D point is assigned a respective semantic class label. Such an assignment, in turn, typically involves statistical methods for feature extraction and machine learning. Whereas the different components in the processing workflow have extensively, but separately been investigated in recent years, the respective connection by sharing the results of crucial tasks across all components has not yet been addressed. This connection not only encapsulates the interrelated issues of neighborhood selection and feature extraction, but also the issue of how to involve spatial context in the classification step. In this paper, we present a novel and generic approach for 3D scene analysis which relies on (i) individually optimized 3D neighborhoods for (ii) the extraction of distinctive geometric features and (iii) the contextual classification of point cloud data. For a labeled benchmark dataset, we demonstrate the beneficial impact of involving contextual information in the classification process and that using individual 3D neighborhoods of optimal size significantly increases the quality of the results for both pointwise and contextual classification.

KW - 3D Scene Analysis

KW - Classification

KW - Contextual Learning

KW - Features

KW - Laser Scanning

KW - Lidar

KW - Point Cloud

KW - Urban

UR - http://www.scopus.com/inward/record.url?scp=84969193116&partnerID=8YFLogxK

U2 - 10.5194/isprsannals-II-3-W4-271-2015

DO - 10.5194/isprsannals-II-3-W4-271-2015

M3 - Conference article

AN - SCOPUS:84969193116

VL - 2

SP - 271

EP - 278

JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SN - 2194-9042

IS - 3W4

T2 - Joint ISPRS workshops on Photogrammetric Image Analysis, PIA 2015 and High Resolution Earth Imaging for Geospatial Information, HRIGI 2015

Y2 - 25 March 2015 through 27 March 2015

ER -