基于特征负反馈卷积的点云分析方法

Point Cloud Analysis Method Based on Feature Negative Feedback Convolution

针对不规则性、无序性和稀疏性给点云分析带来的困难与挑战,提出了融合局部信息提取与全局特征推理的点云分析方法。首先,为了更加有效地进行局部点分组,使用结构感知K近邻(KNN)搜索局部邻域点。其次,基于边卷积改进提出一种特征负反馈卷积模块,在映射的高维空间中提取更为准确的局部特征。此外,设计了基于注意力机制的全局语义推理模块,通过强调不同区域的分组点来避免潜在的信息冗余,从而全面地获取点云特征。通过在公开的点云数据集ModelNet40和ShapeNet上进行测试,该方法总体分类精度和总体平均交并比分别达到93.8%和86.4%,定量的评估指标以及定性的可视化实验证明了该方法的准确性和鲁棒性。

Aiming at the difficulties and challenges caused by the irregularity, disorder and sparsity to point cloud analysis, a point cloud analysis method that combines local information extraction and global feature reasoning is proposed. First, in order to group local points more effectively, the structure-aware K nearest neighbor(KNN) is used to search for local neighborhood points. Secondly, a feature negative feedback convolution module is improved based on edge convolution to extract more accurate local features in the mapped high-dimensional space. In addition, a global semantic reasoning module based on the attention mechanism is designed to avoid potential information redundancy by emphasizing the grouping point of different regions, so as to obtain point cloud features more comprehensively. Through tested on the public point cloud data sets ModelNet40 and ShapeNet, the overall classification accuracy and overall mean intersection over union(mIou) of the proposed method reach 93. 8% and 86. 4%, respectively. Quantitative evaluation indicators and qualitative visualization experiments prove the accuracy and robustness of the proposed method.