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
LiDAR-Camera Fusion in Perspective View for 3D Object Detection in Surface Mine

文献类型：期刊论文

作者Ai, Yunfeng1,2; Yang, Xue2; Song, Ruiqi2,3,4; Cui, Chenglin1,2; Li, Xinqing1,2; Cheng, Qi5,6; Tian, Bin3; Chen, Long3
刊名IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
出版日期2024-02-01
卷号9期号:2页码:3721-3730
关键词Three-dimensional displays Feature extraction Laser radar Point cloud compression Cameras Object detection Fuses 3D object detection autonomous driving LiDAR-Camera fusion perspective view
ISSN号2379-8858
DOI10.1109/TIV.2023.3343377
通讯作者Yang, Xue(xue.yang@waytous.com)
英文摘要LiDAR-Camera fusion can effectively provide the complementary geometric and appearance information for 3D object detection task of autonomous driving system. However, current dominant methods designed for urban scenes often fuse multi-modal information into a Bird's-Eye-View (BEV) feature representation and have a relatively short perception range, which limits their application in surface mine. To achieve long-range perception in surface mine, we utilize a solid-state LiDAR (i.e. Livox Horizon) that has a large perception range (over 200 meters). Accordingly, we propose PVFusion, a novel 3D object detection method that only fuses LiDAR and camera information in Perspective View (PV). Specifically, we first generate the multi-channel depth map via point cloud projection and Depth Map Densification (DMD). Then, we extract visual-depth features and local geometry features from depth-enhanced camera image and point cloud respectively. To better fuse multi-modal information, we propose an Attentional Feature Fusion (AFF) module to dynamically fuse visual-depth features and local geometry features into fused PV features. Moreover, we design a three-branch detection head that leverages a Depth Decoupling Strategy (DDS) to improve the depth estimation for distant objects. We conduct extensive experiments on our surface mine dataset and verify the effectiveness of the proposed PVFusion.
资助项目National Key Research and Development Program of China Project 3
WOS研究方向Computer Science ; Engineering ; Transportation
语种英语
WOS记录号WOS:001215322100062
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China Project 3
源URL[http://ir.ia.ac.cn/handle/173211/59055]  
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Yang, Xue
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Waytous Inc, Qingdao 266109, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
4.Tongji Univ, Coll Surveying & Geoinformat, Shanghai 200092, Peoples R China
5.China Univ Min & Technol, Sch Mech & Elect Engn, Beijing 100083, Peoples R China
6.China Univ Min & Technol, Inner Mongolia Res Inst, Ordos 017000, Peoples R China
推荐引用方式
GB/T 7714		 Ai, Yunfeng,Yang, Xue,Song, Ruiqi,et al. LiDAR-Camera Fusion in Perspective View for 3D Object Detection in Surface Mine[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2024,9(2):3721-3730.
APA Ai, Yunfeng.,Yang, Xue.,Song, Ruiqi.,Cui, Chenglin.,Li, Xinqing.,...&Chen, Long.(2024).LiDAR-Camera Fusion in Perspective View for 3D Object Detection in Surface Mine.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,9(2),3721-3730.
MLA Ai, Yunfeng,et al."LiDAR-Camera Fusion in Perspective View for 3D Object Detection in Surface Mine".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 9.2(2024):3721-3730.

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。