GCA-RDDGCN:基于动态图卷积的工件点云实例分割网络OA

To address the issues of incomplete point cloud features caused by mutual occlusion between stacked workpieces and the difficulty in distinguishing overlapping instances of the same category,a workpiece point cloud instance segmentation network(GCA-RDDGCN),which is based on the dynamic graph convolutional neural network(DGCNN)is proposed.The network constructs a new point cloud feature extraction module,GCA-RDDGC,which reconfigures the dynamic graph convolution into a residual structure to prevent network degradation.It introduces point cloud dilated convolution to expand the receptive field for capturing multi-scale contextual information and embeds a graph-channel attention module(GCAM)to aggregate local geometric features and channel information.Finally,a center-point-based fast point cloud clustering(FPCC)algorithm is employed to achieve rapid segmentation of workpiece instances.Experimental results on the Fraunhofer IPA and XA Bin-Picking datasets demonstrate that,compared with the mainstream FPCC-Net,the precision and recall of GCA-RDDGCN are improved by an average of 4.44 and 1.93 percentage points respectively,enabling the unordered grasping of common workpieces.