融合动态加权图卷积的三维目标检测  

3D Object Detection with Dynamic Weight Graph Convolution

作　　者：李宗民[1] 戎光彩 白云[1] 徐畅[1] 鲜世洋 LI Zongmin;RONG Guangcai;BAI Yun;XU Chang;XIAN Shiyang(Qingdao Institute of Software,College of Computer Science and Technology,China University of Petroleum(East China),Qingdao,Shandong 266580,China)

机构地区：[1]中国石油大学(华东)青岛软件学院、计算机科学与技术学院,山东青岛266580

出　　处：《计算机科学》2025年第3期104-111,共8页Computer Science

基　　金：国家重点研发计划(2019YFF0301800);国家自然科学基金(61379106);山东省自然科学基金(ZR2013FM036,ZR2015FM011)。

摘　　要：三维目标检测是自动驾驶中最关键的技术之一,基于激光雷达的三维目标检测通常在点云构建的场景中进行。目前的三维检测方法不能充分地利用点云的结构信息,这将导致目标物体的误检和漏检。为此,提出了基于动态加权图卷积的DEG R-CNN。首先,在RoI中对节点设置主邻点和次邻点,为目标物体构建点云的图结构,恢复物体的几何信息;然后,在图中利用Gaussian函数和一维卷积,高效地聚合点云的结构特征;最后,使用交叉注意力机制自适应地融合不同粒度的图像特征,为点云补充图像语义信息。在KITTI数据集上进行实验,验证了各个模块的有效性,三维目标检测的3D mAP达到88.80%,相比基线模型提高了1.22%。同时,对三维目标检测的结果进行了可视化,并对可视化结果进行了分析。3D object detection is one of the most critical technologies in autonomous driving,and 3D object detection based on LiDAR is usually carried out in the scene of point cloud construction.The current methods cannot fully use the point cloud’s structural information,leading to false and missed target detection.To solve this problem,we propose a DEG R-CNN based on dyna-mically weighted graph convolution.Firstly,the primary neighbour and subordinate neighbour are set for the node in RoI,and the graph structure of the point cloud is constructed.The geometric information of the object is restored.Then,Gaussian and 1D convolution are used in the graph to efficiently aggregate the point cloud’s structural features.Finally,the cross-attention mechanism adaptively fuses image features of different granularities to supplement the image semantic information.Experiments are conducted on KITTI dataset,and the effectiveness of modules is verified.The 3D mAP of the method reaches 88.80%,which is 1.22% higher than that of the baseline model.At the same time,the results of 3D object detection are visualized and analyzed in detail to understand performance and accuracy of the method better.

关 键 词：点云 三维目标检测 激光雷达 多模态融合 自动驾驶 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]