电讯技术2025，Vol.65Issue(4)：511-517,7.DOI:10.20079/j.issn.1001-893x.240105002
特征级监督的毫米波雷达和视觉融合的目标检测
Feature Level Supervised Millimeter Wave Radar and Vision Fusion for Target Detection
摘要
Abstract
To address the issue of lacking effective supervision in the feature fusion stage of millimeter-wave(MMW)radar and vision sensor fusion algorithms,a multimodal fusion-based 3D object detection algorithm called LRCFusion(Radar and Camera Fusion Based on LiDAR Supervision)is proposed.The algorithm first extracts data features separately from the vision sensor,LiDAR,and MMW radar.Then,with the method of knowledge distillation,it uses LiDAR features as the teacher model to supervise MMW radar features,in order to improve the expression level of millimeter wave radar features.Subsequently,an attention mechanism is introduced to fuse the MMW radar and vision features,and a point cloud-based 3D object detection method is employed to detect objects and predict 3D anchor boxes based on the fused features.Finally,the predicted 3D anchor boxes are used to update the 3D reference points before fusion.Compared with baseline algorithms,the LRCFusion algorithm achieves a 1.2%increase in average precision and a 1%improvement in normalized detection score.关键词
毫米波雷达/目标检测/特征级监督/激光雷达/视觉传感器Key words
millimeter wave radar/target detection/feature level supervision/LiDAR/vision sensor分类
信息技术与安全科学引用本文复制引用
黄晓红,何卿,田子然..特征级监督的毫米波雷达和视觉融合的目标检测[J].电讯技术,2025,65(4):511-517,7.基金项目
国家科技部重点研发专项(2017YFE0135700) （2017YFE0135700）
深圳市科技创新委员会项目(JCYJ20210324120002007) （JCYJ20210324120002007）
广东省科技厅先进智能感知技术重点实验室科技计划项目(2019B121203006) （2019B121203006）
