Документ взят из кэша поисковой машины. Адрес
оригинального документа
: http://graphics.cs.msu.ru/en/node/689
Дата изменения: Sun Apr 10 00:17:26 2016 Дата индексирования: Sun Apr 10 00:17:26 2016 Кодировка: UTF-8 |
Title | Implicit shape models for object detection in 3D point clouds |
Publication Type | Conference Paper |
Year of Publication | 2012 |
Authors | Velizhev A, Shapovalov R, Schindler K |
Refereed Designation | Unknown |
Conference Name | International Society of Photogrammetry and Remote Sensing Congress |
Publication Language | English |
Keywords | Laser Scanning, LIDAR, Point Cloud, Recognition |
Abstract | 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 mќ of urban area in total. |
URL | http://shapovalov.ro/papers/ISM-Velizhev-et-al-ISPRS2012.pdf |
Citation Key | 689 |