计算机应用与软件2026，Vol.43Issue(6)：147-154,221,9.DOI:10.3969/j.issn.1000-386x.2026.06.021
基于可变形多尺度卷积的三维点云目标检测方法
3D POINT CLOUD OBJECT DETECTION METHOD BASED ON DEFORMABLE MULTI-SCALE CONVOLUTION
摘要
Abstract
A deformable multi-scale convolutional 3D point cloud target detection method is proposed for the problem of difficult recognition of small targets such as pedestrians.The problem that PointPillars did not consider the contextual information of the point cloud neighborhood was solved by aggregating the corresponding scale point cloud neighborhood information through multilayer convolutional stacking and convolutional kernel setting to enhance the feature expression ability of the network.For the problem that the existing methods neglected the pedestrians' easy deformation characteristics during feature extraction,a two-branching strategy was used to introduce a two-dimensional offset in the shallow feature map,which enabled the network to adaptively learn the weights and improve the robustness to deformation targets.Multi-scale features were extracted using the feature pyramid structure,and the dual-branch features were spliced to obtain fusion information with richer expression.Experiments on the KITTI dataset show that compared with the PointPillars algorithm,this method improves the pedestrian detection accuracy in the bird's eye view mode by 7.83 and 7.38 percentage points for the medium and difficult levels,respectively,and in the 3D mode,the corresponding improvement is 9.91 and 5.42 percentage points.关键词
三维目标检测/可变形卷积/特征融合/点云/自动驾驶Key words
3D object detection/Deformable convolution/Feature fusion/Point cloud/Autopilot分类
信息技术与安全科学引用本文复制引用
王本源,朱勇建,刘淑莲,田世轩,欧阳博..基于可变形多尺度卷积的三维点云目标检测方法[J].计算机应用与软件,2026,43(6):147-154,221,9.基金项目
浙江省基础公益研究计划项目(LGG21E05000) （LGG21E05000）
教育部产学合作协同育人项目(220800006080308) （220800006080308）
上海应用技术大学科研启动项目(YJ2022-40) （YJ2022-40）
上海应用技术大学协同创新基金项目(XTCX2022-20). （XTCX2022-20）
