GCA-RDDGCN:基于动态图卷积的工件点云实例分割网络

GCA-RDDGCN: a workpiece point cloud instance segmentation network based on dynamic graph convolution

摘要

针对堆叠工件之间互相遮挡导致的点云特征不完整,且同类工件重叠部分实例难以区分的问题,提出一种基于动态图卷积神经网络(dynamic graph convolutional neural network, DGCNN)的工件点云实例分割网络GCA-RDDGCN(graph-channel attention-residual dilated dynamic graph convolutional network).该网络构建了新型点云特征提取模块GCA-RDDGC,通过将动态图卷积模块重构为残差结构避免网络退化问题,引入点云空洞卷积扩大感受野以捕捉多尺度上下文信息,嵌入图-通道联合注意力模块(graph-channel attention module, GCAM)用于聚合局部几何特征和通道信息.最后,采用基于中心点的快速聚类算法FPCC(fast point cloud clustering),实现工件实例的快速分割.在Fraunhofer IPA Bin-Pinking和XA Bin-Pinking数据集上的实验结果显示,相较于主流方法FPCC-Net, GCA-RDDGCN的精确率平均提高4.44百分点,召回率平均提高1.93百分点,可以实现普通工件的无序抓取.

Abstract

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.

关键词

无序抓取 / 点云实例分割 / 动态图卷积 / 注意力模块 / 快速聚类算法

Key words

unordered grasping / point cloud instance segmentation / dynamic graph convolution / attention module / fast clustering algorithm

参考文献

[1] QI C R, HAO S, MO K C, et al. PointNet: deep learning on point sets for 3D classification and segmentation[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 77-85.

[2] QI C R, YI L, SU H, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space[EB/OL]. [2024-03-19]. https://arxiv.org/abs/1706.02413v1.

[3] LI Y Y, BU R, SUN M C, et al. PointCNN: convolution on X-transformed points[C]// Advances in Neural Information Processing Systems 31. Red Hook, NY: Curran Associates Inc., 2018: 828-838.

[4] WANG Y, SUN Y B, LIU Z W, et al. Dynamic graph CNN for learning on point clouds[J]. ACM Transactions on Graphics, 2019, 38(5): 1-12.

[5] ZHANG K G, HAO M, WANG J, et al. Linked dynamic graph CNN: learning on point cloud via linking hierarchical features[EB/OL]. [2024-03-19]. https://arxiv.org/abs/1904.10014v2.

[6] HOU J, DAI A, NIEßNER M. 3D-SIS: 3D semantic instance segmentation of RGB-D scans[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 4421-4430.

[7] YI L, ZHAO W, WANG H, et al. GSPN: generative shape proposal network for 3D instance segmentation in point cloud[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 3947-3956.

[8] YANG B, WANG J N, CLARK R, et al. Learning object bounding boxes for 3D instance segmentation on point clouds[C]// 33rd Annual Conference on Neural Information Processing Systems. Vancouver: Neural Information Processing Systems Foundation, 2019: 6363-6372.

[9] WANG W Y, YU R, HUANG Q G, et al. SGPN: similarity group proposal network for 3D point cloud instance segmentation[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 2569-2578.

[10] WANG X L, LIU S, SHEN X Y, et al. Associatively segmenting instances and semantics in point clouds[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 4091-4100.

[11] JIANG L, ZHAO H S, SHI S S, et al. PointGroup: dual-set point grouping for 3D instance segmentation[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 4866-4875.

[12] CHEN S Y, FANG J M, ZHANG Q, et al. Hierarchical aggregation for 3D instance segmentation[C]// 2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 15447-15456.

[13] XU Y J, ARAI S, LIU D Y, et al. FPCC: fast point cloud clustering-based instance segmentation for industrial bin-picking[J]. Neurocomputing, 2022, 494: 255-268.

[14] KLEEBERGER K, LANDGRAF C, HUBER M F. Large-scale 6D object pose estimation dataset for industrial bin-picking[C]// 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems. Macao: IEEE, 2019: 2573-2578.

[15] XU Y J, ARAI S, TOKUDA F, et al. A convolutional neural network for point cloud instance segmentation in cluttered scene trained by synthetic data without color[J]. IEEE Access, 2020, 8: 70262-70269.

[16] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//FERRARI V, HEBERT M, SMINCHISESCU C, et al. Computer Vision: ECCV 2018. Cham: Springer International Publishing, 2018: 3-19.

[17] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.

[18] WANG L, HUANG Y C, HOU Y L, et al. Graph attention convolution for point cloud semantic segmentation[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 10288-10297.

[19] HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13708-13717.

[20] WANG Q L, WU B G, ZHU P F, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11531-11539.

基金资助

教育部产学研项目(231004983121903)