KIT | KIT-Bibliothek | Impressum | Datenschutz

Multimodal 3D Semantic Segmentation

Duerr, Fabian ORCID iD icon

Abstract (englisch):

Understanding and interpreting a scene is a key task of environment perception for autonomous driving, which is why autonomous vehicles are equipped with a wide range of different sensors. Semantic Segmentation of sensor data provides valuable information for this task and is often seen as key enabler. In this report, we’re presenting a deep learning approach for 3D semantic segmentation of lidar point clouds. The proposed architecture uses the lidar’s native range view and additionally exploits camera features to increase accuracy and robustness. Lidar and camera feature maps of different scales are fused iteratively inside the network architecture. We evaluate our deep fusion approach on a large benchmark dataset and demonstrate its benefits compared to other state-of-the-art approaches, which rely only on lidar.

Verlagsausgabe §
DOI: 10.5445/IR/1000126693
Veröffentlicht am 30.11.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator ISBN: 978-3-7315-1028-4
ISSN: 1863-6489
KITopen-ID: 1000126693
Erschienen in Proceedings of the 2019 Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory. Hrsg.: J. Beyerer; T. Zander
Verlag KIT Scientific Publishing
Seiten 39-52
Serie Karlsruher Schriften zur Anthropomatik / Lehrstuhl für Interaktive Echtzeitsysteme, Karlsruher Institut für Technologie ; Fraunhofer-Inst. für Optronik, Systemtechnik und Bildauswertung IOSB Karlsruhe ; 45
Bemerkung zur Veröffentlichung IES-2019-06
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page