飞控与探测2025，Vol.8Issue(2)：82-92,11.DOI:10.20249/j.cnki.2096-5974.2025.02.010
基于Transformer的毫米波雷达/激光雷达/相机融合3D目标检测方法
Transformer-Based Radar/Lidar/Camera Fusion Solution for 3D Object Detection
摘要
Abstract
In response to the performance limitations of single sensors in environmental perception tasks,this paper proposes a transformer-based multimodal 3D object detection method that in-tegrates millimeter-wave radar,LiDAR,and camera data.The proposed framework consists of three key modules:1)Camera module,which combines image features with initial 3D object pre-dictions to enhance visual representation;2)Radar module,which addresses the sparsity issue of millimeter-wave radar point clouds by introducing a temporal multi-frame fusion algorithm that aggregates data from five consecutive frames.Additionally,a point cloud weighted fusion algo-rithm is proposed to construct an enhanced radar point cloud by leveraging the complementary characteristics of millimeter-wave radar and LiDAR;3)Fusion module,which employs a Trans-former decoder to effectively integrate radar point clouds and camera features,thereby improving 3D object detection performance.Experiments are conducted on a custom urban road dataset,and the proposed method is evaluated based on metrics from the nuScenes dataset.The results demon-strate that,compared to existing methods,the proposed approach achieves a 6.38％improvement in mAP and a 5.93％increase in NDS.关键词
环境感知/多模态融合/目标检测/变换器/注意力机制Key words
environment perception/multi-sensor fusion/object detection/transformer/attention mecha-nism分类
信息技术与安全科学引用本文复制引用
陈坤泽,刘晓晨,申冲..基于Transformer的毫米波雷达/激光雷达/相机融合3D目标检测方法[J].飞控与探测,2025,8(2):82-92,11.基金项目
山西省基础研究计划(202303021211150) （202303021211150）
航空科学基金(202400080U0001) （202400080U0001）
山西省量子传感、精密测量重点实验室基金(201905D121001) （201905D121001）
山西省研究生创新实践项目(2024SJ244) （2024SJ244）
