KIT | KIT-Bibliothek | Impressum | Datenschutz

Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding

Wu, Chengzhi; Pfrommer, Julius; Beyerer, Jürgen; Li, Kangning; Neubert, Boris

Abstract:
We present an improved approach for 3D object detection in point clouds data based on the Frustum PointNet (F-PointNet). Compared to the original F-PointNet, our newly proposed method considers the point neighborhood when computing point features. The newly introduced local neighborhood embedding operation mimics the convolutional operations in 2D neural networks. Thus features of each point are not only computed with the features of its own or of the whole point cloud, but also computed especially with respect to the features of its neighbors. Experiments show that our proposed method achieves better performance than the F-Pointnet baseline on 3D object detection tasks.



Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Institut für Visualisierung und Datenanalyse (IVD)
Publikationstyp Proceedingsbeitrag
Publikationsmonat/-jahr 08.2020
Sprache Englisch
Identifikator KITopen-ID: 1000126362
Erschienen in Proceedings of 4th International Conference on Imaging, Vision & Pattern Recognition (IVPR 2020)
Veranstaltung 4th International Conference on Imaging, Vision & Pattern Recognition (IVPR 2020), Kitakyushu, Japan, 26.08.2020 – 29.09.2020
Bemerkung zur Veröffentlichung 9th ICIEV, 4th IVPR & 2nd ABC, 26-29 August, 2020, Kitakyushu, Japan
Schlagwörter 3D point clouds, object detection, deep learning, KNN-based embedding
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page