ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-3, 325-332, 2016
https://doi.org/10.5194/isprs-annals-III-3-325-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
 
06 Jun 2016
FAST PROBABILISTIC FUSION OF 3D POINT CLOUDS VIA OCCUPANCY GRIDS FOR SCENE CLASSIFICATION
Andreas Kuhn1,2, Hai Huang1, Martin Drauschke1,2, and Helmut Mayer1 1Bundeswehr University Munich, Munich, Germany
2German Aerospace Center, Oberpfaffenhofen-Weßling, Germany
Keywords: Scene Classification, Point Cloud Fusion, Multi-View Stereo Abstract. High resolution consumer cameras on Unmanned Aerial Vehicles (UAVs) allow for cheap acquisition of highly detailed images, e.g., of urban regions. Via image registration by means of Structure from Motion (SfM) and Multi View Stereo (MVS) the automatic generation of huge amounts of 3D points with a relative accuracy in the centimeter range is possible. Applications such as semantic classification have a need for accurate 3D point clouds, but do not benefit from an extremely high resolution/density. In this paper, we, therefore, propose a fast fusion of high resolution 3D point clouds based on occupancy grids. The result is used for semantic classification. In contrast to state-of-the-art classification methods, we accept a certain percentage of outliers, arguing that they can be considered in the classification process when a per point belief is determined in the fusion process. To this end, we employ an octree-based fusion which allows for the derivation of outlier probabilities. The probabilities give a belief for every 3D point, which is essential for the semantic classification to consider measurement noise. For an example point cloud with half a billion 3D points (cf. Figure 1), we show that our method can reduce runtime as well as improve classification accuracy and offers high scalability for large datasets.
Conference paper (PDF, 9709 KB)


Citation: Kuhn, A., Huang, H., Drauschke, M., and Mayer, H.: FAST PROBABILISTIC FUSION OF 3D POINT CLOUDS VIA OCCUPANCY GRIDS FOR SCENE CLASSIFICATION, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-3, 325-332, https://doi.org/10.5194/isprs-annals-III-3-325-2016, 2016.

BibTeX EndNote Reference Manager XML