电子学报2025，Vol.53Issue(6)：2131-2156,26.DOI:10.12263/DZXB.20250043
自动驾驶中的3D目标检测研究进展
Research Advances on 3D Object Detection in Autonomous Driving
摘要
Abstract
In recent years,autonomous driving has gained increasing attention due to its significant potential in im-proving road safety and enhancing traffic efficiency.The perception system plays a crucial role in modern autonomous driv-ing systems,aiming to accurately estimate the surrounding environment's state and provide reliable observations for predic-tion and planning.Among them,3D object detection serves as an important component of the perception system for predict-ing the positions,sizes,and categories of objects surrounding the autonomous vehicle.This paper provides a comprehensive overview of the research advancements in 3D object detection for autonomous driving in recent years.It discusses the ad-vantages and limitations of single-modal methods and multi-modal fusion methods using different sensors from the perspec-tives of single-modal detection and multi-modal fusion detection.Furthermore,the paper compares the performance of vari-ous representative algorithms on public datasets,summarizes the current commonly used training strategies,and discusses the future development directions in this field.关键词
自动驾驶/3D目标检测/单模态/多模态融合Key words
autonomous driving/3D object detection/single-modal/multi-modal fusion分类
信息技术与安全科学引用本文复制引用
陈建,苏思教,黄立勤,赵铁松..自动驾驶中的3D目标检测研究进展[J].电子学报,2025,53(6):2131-2156,26.基金项目
国家自然科学基金(No.62171134,No.62271149) （No.62171134,No.62271149）
福州市科技项目(No.2023-P-001) National Natural Science Foundation of China(No.62171134,No.62271149) （No.2023-P-001）
Science and Tech-nology Projects of Fuzhou City(No.2023-P-001) （No.2023-P-001）
