一种SAR三维目标识别方法

By employing a feature pyramid structure and a self-attention mechanism, the problems of sparse SAR 3D point clouds and uneven scattering were solved, improving the recognition accuracy and achieving high-precision SAR 3D target recognition.

CN118429960BActive Publication Date: 2026-07-17BEIJING INST OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING INST OF TECH
Filing Date
2024-05-10
Publication Date
2026-07-17

Smart Images

  • Figure CN118429960B_ABST
    Figure CN118429960B_ABST
Patent Text Reader

Abstract

本发明公开了一种SAR三维目标识别方法。本发明采用特征金字塔结构，提取SAR三维点云图像不同层级点云特征；通过充分融合浅层特征和深层特征，避免SAR三维点云稀疏导致的信息损失，提升目标识别准确率。在特征提取过程中，首先基于注意力算法，增强特征金字塔结构对强散射区域特征提取能力，降低弱散射区域特征信息干扰，解决SAR三维点云散射强度分布不均匀导致的弱散射区域特征降低网络目标识别精度的问题；其次，基于特征点局部邻域聚合实现了SAR三维点云的下采样和增强采样，基于三线性插值和跳跃连接信息实现了SAR三维点云的上采样，解决了传统金字塔卷积操作无法适用于无序三维点云的问题，有效实现特征金字塔不同层级特征点的提取。
Need to check novelty before this filing date? Find Prior Art