Scholarlink

<p>To address the impact of sparsity and disorder of point clouds on object detection accuracy, this paper proposes a multi-modal fusion network VPC-VoxelNet based on virtual point clouds. Firstly, virtual point clouds are constructed using image detection object information to increase the density of point clouds, thus improving the performance of object features; Secondly, increasing the dimensionality of point cloud features, distinguishing virtual point clouds and avoiding the accumulation of multi model errors; Finally, an optimized loss function such as the scale factor of the virtual point cloud is used to improve the training efficiency of the multi-modal network. The object detection network, VPC-VoxelNet, was tested on the KITTI dataset, and the detection accuracy was better than that of the classical 3D point cloud detection network and certain multi-modal information fusion networks, with a vehicle detection accuracy of 86.9%.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

VPC-VoxelNet: multi-modal fusion 3D object detection networks based on virtual point clouds

  • 期刊论文

  • 发表日期：

    2025年3月6日

查看全文
  • Qiang Zhang,
  • Qin Shi,
  • Teng Cheng,
  • Junning Zhang,
  • Jiong Chen

摘要

To address the impact of sparsity and disorder of point clouds on object detection accuracy, this paper proposes a multi-modal fusion network VPC-VoxelNet based on virtual point clouds. Firstly, virtual point clouds are constructed using image detection object information to increase the density of point clouds, thus improving the performance of object features; Secondly, increasing the dimensionality of point cloud features, distinguishing virtual point clouds and avoiding the accumulation of multi model errors; Finally, an optimized loss function such as the scale factor of the virtual point cloud is used to improve the training efficiency of the multi-modal network. The object detection network, VPC-VoxelNet, was tested on the KITTI dataset, and the detection accuracy was better than that of the classical 3D point cloud detection network and certain multi-modal information fusion networks, with a vehicle detection accuracy of 86.9%.