中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
Patchlpr: a multi-level feature fusion transformer network for LiDAR-based place recognition

文献类型：期刊论文

作者Sun, Yang1,2; Guo, Jianhua1,3; Wang, Haiyang4; Zhang, Yuhang1,3; Zheng, Jiushuai1,3; Tian, Bin5
刊名SIGNAL IMAGE AND VIDEO PROCESSING
出版日期2024-04-07
页码9
关键词SLAM LiDAR Place recognition Deep learning Patch
ISSN号1863-1703
DOI10.1007/s11760-024-03138-9
通讯作者Guo, Jianhua(guojh2022@gmail.com)
英文摘要LiDAR-based place recognition plays a crucial role in autonomous vehicles, enabling the identification of locations in GPS-invalid environments that were previously accessed. Localization in place recognition can be achieved by searching for nearest neighbors in the database. Two common types of place recognition features are local descriptors and global descriptors. Local descriptors typically compactly represent regions or points, while global descriptors provide an overarching view of the data. Despite the significant progress made in recent years by both types of descriptors, any representation inevitably involves information loss. To overcome this limitation, we have developed PatchLPR, a Transformer network employing multi-level feature fusion for robust place recognition. PatchLPR integrates global and local feature information, focusing on meaningful regions on the feature map to generate an environmental representation. We propose a patch feature extraction module based on the Vision Transformer to fully leverage the information and correlations of different features. We evaluated our approach on the KITTI dataset and a self-collected dataset covering over 4.2 km. The experimental results demonstrate that our method effectively utilizes multi-level features to enhance place recognition performance.
WOS关键词VISION ; DEEP
资助项目Research on Key Technologies of Intelligent Equipment for Mine Powered by Pure Clean Energy, Natural Science Foundation of Hebei Province[F2021402011]
WOS研究方向Engineering ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:001197901800004
出版者SPRINGER LONDON LTD
资助机构Research on Key Technologies of Intelligent Equipment for Mine Powered by Pure Clean Energy, Natural Science Foundation of Hebei Province
源URL[http://ir.ia.ac.cn/handle/173211/58065]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者Guo, Jianhua
作者单位1.Hebei Univ Engn, Coll Mech & Equipment Engn, Handan 056038, Peoples R China
2.Key Lab Intelligent Ind Equipment Technol Hebei Pr, Handan, Hebei, Peoples R China
3.Handan Key Lab Intelligent Vehicles, Handan, Hebei, Peoples R China
4.Jizhong Energy Fengfeng Grp Co Ltd, 16 Unicom South Rd, Handan, Hebei, Peoples R China
5.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Sun, Yang,Guo, Jianhua,Wang, Haiyang,et al. Patchlpr: a multi-level feature fusion transformer network for LiDAR-based place recognition[J]. SIGNAL IMAGE AND VIDEO PROCESSING,2024:9.
APA Sun, Yang,Guo, Jianhua,Wang, Haiyang,Zhang, Yuhang,Zheng, Jiushuai,&Tian, Bin.(2024).Patchlpr: a multi-level feature fusion transformer network for LiDAR-based place recognition.SIGNAL IMAGE AND VIDEO PROCESSING,9.
MLA Sun, Yang,et al."Patchlpr: a multi-level feature fusion transformer network for LiDAR-based place recognition".SIGNAL IMAGE AND VIDEO PROCESSING (2024):9.

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。