计算机工程与应用2025，Vol.61Issue(18)：132-141,10.DOI:10.3778/j.issn.1002-8331.2406-0146
全局形状关系约束的点云三维目标检测方法
Point Cloud 3D Object Detection Method with Global Shape Relation Constraints
摘要
Abstract
Voting-based method has shown great potential in indoor 3D object detection tasks,where voting directly deter-mines the quality of the detection results.However,seed points located in overlapping areas of objects are prone to errone-ous voting,mapping them near incorrect target object centers.Considering that these seed points are usually continuous on the geometric surface,introducing shape relations can improve this issue.Specifically,a shape relation extraction module is proposed,which constructs a 2D manifold and represents shape relations based on Euclidean distance on the manifold,then implements shape relation constraints on the point cloud through matrix multiplication.To obtain geometric surface continuity information,a binary tree Transformer module is designed.The point cloud constrained by shape rela-tions captures global context through an optimized Transformer network,thus learning the surface structure of objects.Comparative experiments using the ScanNet and SUN RGB-D datasets show that the proposed algorithm achieves mAP@0.25 scores of 65.1%and 62.7%,respectively,improving by 6.5 and 5 percentage points compared to baseline methods,and outperforming the current state-of-the-art methods by 0.6 and 1.1 percentage points,respectively.关键词
三维目标检测/点云/流形学习/Transformer/形状关系Key words
3D object detection/point cloud/manifold learning/Transformer/shape relation分类
信息技术与安全科学引用本文复制引用
鲜世洋,李宗民,公绪超,徐畅,张鹏,王文超,白云,戎光彩..全局形状关系约束的点云三维目标检测方法[J].计算机工程与应用,2025,61(18):132-141,10.基金项目
国家重点研发计划(2019YFF0301800) （2019YFF0301800）
国家自然科学基金(61379106,62207011) （61379106,62207011）
山东省自然科学基金(ZR2013FM036,ZR2015FM011) （ZR2013FM036,ZR2015FM011）
中石化博士后科研基金(YKB2411). （YKB2411）
