首页|多尺度特征融合的点云配准算法研究

多尺度特征融合的点云配准算法研究

扫码查看
原文链接
  • 万方数据
  • 维普
现有点云配准算法提取的特征不够丰富，导致配准精度很难进一步提升。针对该问题，本文提出一种基于深度学习的多尺度特征融合点云配准算法。首先，利用EdgeConv提取多个不同尺度的特征，该特征能够保持局部几何结构特性;接着，引入非线性极化注意力对其输出特征进行筛选，从而提高特征信息的有效性;然后，将以上多尺度特征进行融合并再次利用EdgeConv提取其特征，从而提高特征的表达能力;在刚体姿态估计阶段，采用线性李代数处理旋转变换以充分挖掘点云中的变换信息;最后，根据配准过程中提取点云特征的变化，动态调整损失函数各组成部分的权重，获得更准确的模型预测结果。在ModelNet40数据集上进行实验，本文算法在训练集和测试集样本种类相同时的旋转误差为1。826 7，位移误差为0。001 0;在训练集和测试集的样本种类不相同时(泛化实验)的旋转误差为2。979 4，位移误差为0。001 0。实验结果表明，本文算法的配准精度相比当前主流算法均有提高且泛化性能较好。
Research on Point Cloud Registration Algorithm Based on Multi-scale Feature Fusion
The features extracted by the existing point cloud registration algorithms are not so rich,which makes it difficult to further improve the accuracy of the registration.To address this problem,a deep learning-based multi-scale feature fusion point cloud registration algorithm is proposed.EdgeConv is employed to extract multiple features of different scales through the algorithm at first,which can maintain the local geometric structure characteristics.Then Non-linear Polarized Self-attention is introduced to filter its output features,and thus the effectiveness of feature information is improved.And later the above multi-scale features are fused and EdgeConv is employed again to extract their features,thereby improving the expression ability of the features.In the rigid pose estimation stage,Lie algebra is used to process the rotational transformation to fully exploit the transformation information of the point cloud.According to the changes of the extracted point cloud features during the registration process,the weight values of the components of the loss function are dynamically adjusted to evaluate the prediction results of the model more accurately.Tested on the ModelNet40 dataset,when the sample types of the train and test sets are the same,the rotation error of the proposed algorithm is 1.826 7 and the displacement error is 0.001 0,and when the sample types of the train and test sets are not the same(experiments on generalization),the rotation error of the proposed algorithm is 2.979 4 and the displacement error is 0.001 0.The experimental results show that the registration accuracy of the proposed algorithm has improved compared with the current mainstream algorithms,and it exhibits good generalization performance.

deep learningpoint cloud registrationfeature extractionrigid objectpose estimationLie algebra

易见兵、彭鑫、曹锋、李俊、谢唯嘉

展开 >

江西理工大学信息工程学院,江西赣州 341000

深度学习 点云配准 特征提取 刚体目标 姿态估计 李代数

国家自然科学基金国家自然科学基金江西省自然科学基金江西省教育厅科技项目江西省教育厅科技项目江西省教育厅科技项目江西省赣州市科技计划江西省研究生创新专项

620660187226101820181BAB202004GJJ210828GJJ200818GJJ180482YC2022-S640

2024

10.16088/j.issn.1001-6600.2023082502

广西师范大学学报(自然科学版)
广西师范大学

广西师范大学学报(自然科学版)

CSTPCD北大核心
影响因子：0.448
ISSN：1001-6600
年,卷(期)：2024.42(3)
  • 34