Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss
文献类型：期刊论文
| 作者 | Chen, Yaran2,3 ; Li, Haoran2,3; Gao, Ruiyuan1; Zhao, Dongbin2,3
|
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2022-02-01 |
| 卷号 | 33期号:2页码:762-773 |
| 关键词 | 3-D object detection generalized Intersection of Union (GIoU) loss segmentation |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2020.3028964 |
| 通讯作者 | Zhao, Dongbin(dongbin.zhao@ia.ac.cn) |
| 英文摘要 | The 3-D object detection is crucial for many real-world applications, attracting many researchers' attention. Beyond 2-D object detection, 3-D object detection usually needs to extract appearance, depth, position, and orientation information from light detection and ranging (LiDAR) and camera sensors. However, due to more degrees of freedom and vertices, existing detection methods that directly transform from 2-D to 3-D still face several challenges, such as exploding increase of anchors' number and inefficient or hard-to-optimize objective. To this end, we present a fast segmentation method for 3-D point clouds to reduce anchors, which can largely decrease the computing cost. Moreover, taking advantage of 3-D generalized Intersection of Union (GIoU) and L-1 losses, we propose a fused loss to facilitate the optimization of 3-D object detection. A series of experiments show that the proposed method has alleviated the abovementioned issues effectively. |
| 资助项目 | National Natural Science Foundation of China (NSFC)[62006226] ; Natural Science Foundation of Beijing[L191002] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000752016400027 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China (NSFC) ; Natural Science Foundation of Beijing |
| 源URL | [http://ir.ia.ac.cn/handle/173211/47349]  |
| 专题 | 复杂系统管理与控制国家重点实验室_深度强化学习 |
| 通讯作者 | Zhao, Dongbin |
| 作者单位 | 1.Chinese Univ Hong Kong, Dept Comp Sci & Engn, Shatin, Hong Kong, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Coll Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, Yaran,Li, Haoran,Gao, Ruiyuan,et al. Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022,33(2):762-773. |
| APA | Chen, Yaran,Li, Haoran,Gao, Ruiyuan,&Zhao, Dongbin.(2022).Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,33(2),762-773. |
| MLA | Chen, Yaran,et al."Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 33.2(2022):762-773. |
入库方式： OAI收割
来源：自动化研究所
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。