Adaptive Graph Convolutional 3D Point Cloud Recognition Algorithm Based on Attention Mechanism

doi:10.12068/j.issn.1005-3026.2024.06.004

Abstract

Abstract:

To better capture the local geometric structural information of 3D point clouds， an adaptive graph convolutional 3D point cloud recognition algorithm is proposed based on attention mechanism. To address the drawback of fixed convolutional kernels ignoring features， the algorithm first dynamically learns adaptive convolutional kernels based on graph structural features. Furthermore， to enhance the modeling capability of the model for local geometric structures， the weight distribution of the convolutional kernels using a vector attention mechanism is adjusted adaptively. Subsequently， a graph is constructed using the position features of the point cloud and perform convolution operations on the newly constructed graph structural features using the adaptive convolutional kernels. Finally， new point cloud features through pooling is obtained. Experimental results demonstrate that the proposed algorithm effectively extracts local geometric structural information and achieves higher accuracy in classification tasks even with a limited number of sampled points， outperforming previous point cloud convolutional algorithms. The proposed algorithm also exhibits certain advantages compared to existing methods for point cloud classification and segmentation， as evidenced by the performance evaluation on the ModelNet40， ScanObjectNN， and ShapeNetPart datasets.

Key words: 3D point clouds, attention mechanism, self?adaptation, graph convolution, dynamically learn

CLC Number:

TP 391.4

Yuan MA, Li-huang SHE, Jia-wei LI, Xi-rong BAO. Adaptive Graph Convolutional 3D Point Cloud Recognition Algorithm Based on Attention Mechanism[J]. Journal of Northeastern University(Natural Science), 2024, 45(6): 786-792.

Figures/Tables 11

References 19

1	Riegler G， Ulusoy A O， Geiger A.OctNet：learning deep 3D representations at high resolutions［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）.Honolulu，2017：6620-6629.
2	Klokov R， Lempitsky V.Escape from cells：deep KD-networks for the recognition of 3D point cloud models［C］//2017 IEEE International Conference on Computer Vision （ICCV）.Venice，2017：863-872.
3	Charles R Q， 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 （CVPR）.Honolulu，2017：77-85.
4	Shen Y R， Feng C， Yang Y Q，et al.Mining point cloud local structures by kernel correlation and graph pooling［C］//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City，2018：4548-4557.
5	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.
6	Devlin J， Chang M W， Lee K，et al.BERT：pre‐training of deep bidirectional transformers for language understanding［EB/OL］.2018：arXiv：1810.04805..
7	Hu H， Zhang Z， Xie Z D，et al.Local relation networks for image recognition［C］//2019 IEEE/CVF International Conference on Computer Vision （ICCV）.Seoul，2019：3463-3472.
8	Zhao H S， Jia J Y， Koltun V.Exploring self‐attention for image recognition［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）.Seattle，2020：10073-10082.
9	Zhao H S， Jiang L， Jia J Y，et al.Point transformer［C］//2021 IEEE/CVF International Conference on Computer Vision （ICCV）.Montreal，2021：16239-16248.
10	Liu Y C， Fan B， Xiang S M，et al.Relation‐shape convolutional neural network for point cloud analysis［C］//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）.Long Beach，2019：8887-8896.
11	Wu Z R， Song S R， Khosla A，et al.3D ShapeNets：a deep representation for volumetric shapes［C］//2015 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）.Boston，2015：1912-1920.
12	Loshchilov I， Hutter F.SGDR：stochastic gradient descent with warm restarts［EB/OL］.2016：arXiv：1608.03983..
13	Zhou Y， Tuzel O.VoxelNet：end‐to‐end learning for point cloud based 3D object detection［C］//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City，2018：4490-4499.
14	Li Y， Bu R， Sun M，et al.PointCNN：convolution on x‐transformed points［J］.Advances in Neural Information Processing Systems，2018.
15	Thomas H， Qi C R， Deschaud J E，et al.KPConv：flexible and deformable convolution for point clouds［C］//2019 IEEE/CVF International Conference on Computer Vision （ICCV）.Seoul，2019：6410-6419.
16	Guo M H， Cai J X， Liu Z N，et al.PCT：point cloud transformer［J］.Computational Visual Media，2021，7（2）：187-199.
17	Qian G， Li Y， Peng H，et al.PointNext：revisiting pointnet++ with improved training and scaling strategies［J］.Advances in Neural Information Processing Systems，2022，35：23192-23204.
18	Uy M A， Pham Q H， Hua B S，et al.Revisiting point cloud classification：a new benchmark dataset and classification model on real‐world data［C］//2019 IEEE/CVF International Conference on Computer Vision （ICCV）.Seoul，2019：1588-1597.
19	Cheng S L， Chen X W， He X W，et al.PRANet：point relation‑aware network for 3D point cloud analysis［J］.IEEE Transactions on Image Processing，2021，30：4436-4448.

方法	输入	点数量	mAcc/%	OA/%
VoxNet	voxel	—	83.0	85.9
PointNet	xyz	1 024	86.0	89.2
PointNet++	xyz	1 024	—	90.7
PointNet	xyz	5 120	—	91.9
PointCNN	xyz	1 024	88.1	92.5
KPConv	xyz	7 168	—	92.9
DGCNN	xyz	1 024	—	92.9
Point Trans	xyz	1 024	—	92.8
PCT	xyz	1 024	—	93.2
PointNext	xyz	1 024	—	93.2
本文	xyz	1 024	90.7	93.5

方法	输入	点数量	mAcc/%	OA/%
VoxNet	voxel	—	83.0	85.9
PointNet	xyz	1 024	86.0	89.2
PointNet++	xyz	1 024	—	90.7
PointNet	xyz	5 120	—	91.9
PointCNN	xyz	1 024	88.1	92.5
KPConv	xyz	7 168	—	92.9
DGCNN	xyz	1 024	—	92.9
Point Trans	xyz	1 024	—	92.8
PCT	xyz	1 024	—	93.2
PointNext	xyz	1 024	—	93.2
本文	xyz	1 024	90.7	93.5

方法	mAcc	OA
PointNet	63.4	68.2
PointNet++	75.4	77.9
PointCNN	75.1	78.5
DGCNN	73.6	78.1
PRANet^［19］	79.1	82.1
本文	79.3	82.7

方法	mAcc	OA
PointNet	63.4	68.2
PointNet++	75.4	77.9
PointCNN	75.1	78.5
DGCNN	73.6	78.1
PRANet^［19］	79.1	82.1
本文	79.3	82.7

算法	mcIoU	mIoU
PointNet	80.4	83.7
PointNet++	81.9	85.1
PointCNN	84.6	86.1
DGCNN	82.3	85.2
PRANet	85.1	86.4
本文	84.8	86.7