Loading...
Please wait, while we are loading the content...
Similar Documents
KDA3D: Key-Point Densification and Multi-Attention Guidance for 3D Object Detection
| Content Provider | MDPI |
|---|---|
| Author | Wang, Jiarong Zhu, Ming Wang, Bo Sun, Deyao Wei, Hua Liu, Changji Nie, Haitao |
| Copyright Year | 2020 |
| Description | In this paper, we propose a novel 3D object detector KDA3D, which achieves high-precision and robust classification, segmentation, and localization with the help of key-point densification and multi-attention guidance. The proposed end-to-end neural network architecture takes LIDAR point clouds as the main inputs that can be optionally complemented by RGB images. It consists of three parts: part-1 segments 3D foreground points and generates reliable proposals; part-2 (optional) enhances point cloud density and reconstructs the more compact full-point feature map; part-3 refines 3D bounding boxes and adds semantic segmentation as extra supervision. Our designed lightweight point-wise and channel-wise attention modules can adaptively strengthen the “skeleton” and “distinctiveness” point-features to help feature learning networks capture more representative or finer patterns. The proposed key-point densification component can generate pseudo-point clouds containing target information from monocular images through the distance preference strategy and K-means clustering so as to balance the density distribution and enrich sparse features. Extensive experiments on the KITTI and nuScenes 3D object detection benchmarks show that our KDA3D produces state-of-the-art results while running in near real-time with a low memory footprint. |
| Starting Page | 1895 |
| e-ISSN | 20724292 |
| DOI | 10.3390/rs12111895 |
| Journal | Remote Sensing |
| Issue Number | 11 |
| Volume Number | 12 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2020-06-11 |
| Access Restriction | Open |
| Subject Keyword | Remote Sensing Artificial Intelligence Imaging Science 3d Object Detection Multi-sensor Fusion Point Cloud Density Enhancement Attention Mechanism Autonomous Driving |
| Content Type | Text |
| Resource Type | Article |
