3D point cloud classification and segmentation based on dual attention and weighted dynamic graph convolution
In response to the deficiencies in local context information extraction and neighboring point fea-ture expression in deep learning-based point cloud classification and segmentation networks,as well as the problem of maxpooling leading to the loss of suboptimal information,a point cloud classification and seg-mentation algorithm that combines dual attention and weighted dynamic graph convolutional networks was proposed.Firstly,the weighted dynamic graph convolution used a weighted k-nearest neighbor algorithm to construct a robust local structure and introduced an enhanced edge convolution module to apply weights to point features,thereby obtaining enhanced edge features.Then,channel attention was used to con-struct channel correlations and unleash the potential of each channel,followed by spatial attention to per-ceive the spatial structure of 3D point clouds,enhancing the expression of local semantic features and ex-tracting effective contextual and deep semantic information.Finally,TopK pooling was employed to add suboptimal features.Experimental results show that the algorithm achieves an overall classification accura-cy of 93.36%on the ModelNet40 classification dataset and an average intersection over union of 85.96%on the ShapeNet Part segmentation dataset,effectively extracting contextual information and enhanced neighboring point feature expression,demonstrating the effectiveness of the algorithm.
classification and segmentation3D point cloudattention mechanismweighted dynamic graph convolutionK-nearest neighbor
万方数据
维普
