KDA3D: Key-Point Densification and Multi-Attention Guidance for 3D Object Detection
文献类型：期刊论文
| 作者 | J. R. Wang,M. Zhu,B. Wang,D. Y. Sun,H. Wei,C. J. Liu and H. T. Nie |
| 刊名 | Remote Sensing
 |
| 出版日期 | 2020 |
| 卷号 | 12期号:11页码:27 |
| DOI | 10.3390/rs12111895 |
| 英文摘要 | 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. |
| URL标识 | 查看原文 |
| 语种 | 英语 |
| 源URL | [http://ir.ciomp.ac.cn/handle/181722/64636]  |
| 专题 | 中国科学院长春光学精密机械与物理研究所 |
| 推荐引用方式 GB/T 7714 | J. R. Wang,M. Zhu,B. Wang,D. Y. Sun,H. Wei,C. J. Liu and H. T. Nie. KDA3D: Key-Point Densification and Multi-Attention Guidance for 3D Object Detection[J]. Remote Sensing,2020,12(11):27. |
| APA | J. R. Wang,M. Zhu,B. Wang,D. Y. Sun,H. Wei,C. J. Liu and H. T. Nie.(2020).KDA3D: Key-Point Densification and Multi-Attention Guidance for 3D Object Detection.Remote Sensing,12(11),27. |
| MLA | J. R. Wang,M. Zhu,B. Wang,D. Y. Sun,H. Wei,C. J. Liu and H. T. Nie."KDA3D: Key-Point Densification and Multi-Attention Guidance for 3D Object Detection".Remote Sensing 12.11(2020):27. |
入库方式： OAI收割
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。