Range adaptation for 3d object detection in LiDAR

Published

Journal Article

© 2019 IEEE. LiDAR-based 3D object detection plays a crucial role in modern autonomous driving systems. LiDAR data often exhibit severe changes in properties across different observation ranges. In this paper, we explore cross-range adaptation for 3D object detection using LiDAR, i.e., far-range observations are adapted to near-range. This way, far-range detection is optimized for similar performance to near-range one. We adopt a bird-eyes view (BEV) detection framework to perform the proposed model adaptation. Our model adaptation consists of an adversarial global adaptation, and a fine-grained local adaptation. The proposed cross-range adaptation framework is validated on three state-of-the-art LiDAR based object detection networks, and we consistently observe performance improvement on the far-range objects, without adding any auxiliary parameters to the model. To the best of our knowledge, this paper is the first attempt to study cross-range LiDAR adaptation for object detection in point clouds. To demonstrate the generality of the proposed adaptation framework, experiments on more challenging cross-device adaptation are further conducted, and a new LiDAR dataset with high-quality annotated point clouds is released to promote future research.

Full Text

Duke Authors

Cited Authors

  • Wang, Z; DIng, S; Li, Y; Zhao, M; Roychowdhury, S; Wallin, A; Sapiro, G; Qiu, Q

Published Date

  • October 1, 2019

Published In

  • Proceedings 2019 International Conference on Computer Vision Workshop, Iccvw 2019

Start / End Page

  • 2320 - 2328

Digital Object Identifier (DOI)

  • 10.1109/ICCVW.2019.00285

Citation Source

  • Scopus