.png){kind=icon}
Return
Dynamic graph transformer for 3D object detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2022.110085.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
LiDAR-based 3D detection is critical in autonomous driving perception systems. However, point-based 3D object detection that directly learns from point clouds is challenging owing to the sparsity and irregularity of LiDAR point clouds. Existing point-based methods are limited by fixed local relationships and the sparsity of distant and occluded objects. To address these issues, we propose a dynamic graph transformer 3D object detection network (DGT-Det3D) based on a dynamic graph transformer (DGT) module and a proposal-aware fusion (PAF) module. The DGT module is built on a dynamic graph and graph-aware self-attention module, which adaptively concentrates on the foreground points and encodes the graph to capture long-range dependencies. With the DGT module, DGT-Det3D has better capability to detect distant and occluded objects. To further refine the proposals, our PAF module fully integrates the proposal-aware spatial information and combines it with the point-wise semantic features from the first stage. Extensive experiments on the KITTI dataset demonstrate that our approach achieves state-of-the-art accuracy for point-based methods. In addition, DGT brings significant improvements when combined with state-of-the-art methods on the Waymo open dataset.(c) 2022 Elsevier B.V. All rights reserved.
Keywords:
3D object detection
Point cloud
Transformer
Graph structure learning
Automatic driving
Journal
K
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSave
View more