Implicit shape models for object detection in 3D point clouds

TitleImplicit shape models for object detection in 3D point clouds
Publication TypeConference Paper
Year of Publication2012
AuthorsVelizhev A, Shapovalov R, Schindler K
Refereed DesignationUnknown
Conference NameInternational Society of Photogrammetry and Remote Sensing Congress
Publication LanguageEnglish
KeywordsLaser Scanning, LIDAR, Point Cloud, Recognition

We present a method for automatic object localization and recognition in 3D point clouds representing outdoor urban scenes. The method is based on the implicit shape models (ISM) framework, which recognizes objects by voting for their center locations. It requires only few training examples per class, which is an important property for practical use. We also introduce and evaluate an improved version of the spin image descriptor, more robust to point density variation and uncertainty in normal direction estimation. Our experiments reveal a significant impact of these modifications on the recognition performance. We compare our results against the state-of-the-art method and get significant improvement in both precision and recall on the Ohio dataset, consisting of combined aerial and terrestrial LiDAR scans of 150,000 m² of urban area in total.

Citation Key689