Opto-Electronic Engineering, Volume. 50, Issue 10, 230166-1(2023)
Multi-resolution feature fusion for point cloud classification and segmentation network
Figures & Tables(17)
Fig. 1. Multi-resolution graph convolution module algorithm flow chart
Fig. 2. Network framework. (a) Classification network; (b) Segmentation network
Fig. 4. The process of learning multi-resolution point cloud features
Fig. 6. The results of the part segmentation visualization. (a) Groud truth; (b) Ours
Fig. 7. Comparison of segmentation details. (a) Groud truth; (b) Ours; (c) Baseline
Table 1. Experimental parameter setting
View tableView in ArticleTable 1. Experimental parameter setting
参数项 分类网络 分割网络 输入点数 1024 2048 多分辨率点云点数 [896,768,640,512] [896,768,640] 图卷积分支k取值 20 20 训练周期 250 300 优化器 SGD SGD 训练批次 32 32 测试批次 16 16 初始学习速率 0.1 0.003
Table 2. Comparison of classification accuracy with different methods on ModelNet40 dataset
View tableView in ArticleTable 2. Comparison of classification accuracy with different methods on ModelNet40 dataset
方法 输入 点数/103 mAcc/% OA/% VoxNet[ 8 ]体素 - 83.0 85.9 MVCNN[ 11 ]多视图 - - 90.1 PointNet[ 12 ]坐标 1 86.0 89.2 PointNet++[ 13 ]坐标+法线 5 - 91.9 文献[ 24 ]坐标+法线 1 89.8 91.6 文献[ 25 ]坐标+法线 1 - 93.0 3D-GCN[ 26 ]坐标 1 - 92.1 DGCNN[ 15 ]坐标 1 90.2 92.9 LDGCNN[ 16 ]坐标 1 90.3 92.9 DDGCN[ 27 ]坐标 1 90.4 92.7 DRNet[ 28 ]坐标 1 - 93.1 DGANet[ 29 ]坐标 1 89.4 92.3 PCT[ 19 ]坐标 1 - 93.2 AFM-Net[ 30 ]坐标 1 89.4 92.85 文献[ 31 ]坐标 1 89.02 92.5 Our 坐标 1 91.2 93.4
Table 3. Comparison of classification accuracy with different methods on ScanObjectNN dataset
View tableView in ArticleTable 3. Comparison of classification accuracy with different methods on ScanObjectNN dataset
方法 输入 mAcc/% OA/% PointNet[ 12 ]坐标 63.4 68.2 PointNet++[ 13 ]坐标 75.4 77.9 DGCNN[ 15 ]坐标 73.6 78.1 DRNet[ 28 ]坐标 78.0 80.3 GBNet[ 32 ]坐标 77.8 80.5 PRANet[ 33 ]坐标 79.1 82.1 Ours 坐标 81.7 83.3
Table 4. Part segmentation results on the ShapeNet Part dataset
View tableView in ArticleTable 4. Part segmentation results on the ShapeNet Part dataset
方法 PointNet[ 12 ]PointNet++[ 13 ]文献[ 25 ]3D-GCN[ 26 ]LDGCNN[ 16 ]DGANet[ 29 ]DGCSA[ 34 ]DGCNN[ 15 ]本文 飞机 83.4 82.4 83.8 83.1 84.0 84.6 84.2 84.0 83.6 包 78.7 79.0 77.5 84.0 83.0 85.7 73.3 83.4 83.4 帐篷 82.5 87.7 87.9 86.6 84.9 87.8 82.3 86.7 88.4 ↑车 74.9 77.3 78.7 77.5 78.4 78.5 77.7 77.8 78.4↑ 椅子 89.6 90.8 90.8 90.3 90.6 91.0 91.0 90.6 89.7 耳机 73.0 71.8 77.3 74.1 74.4 77.3 75.3 74.7 80.5 ↑吉他 91.5 91.0 91.8 90.9 91.0 91.2 91.2 91.2 91.8 ↑刀 85.9 85.9 87.9 86.4 88.1 87.9 88.6 87.5 88.6 ↑台灯 80.8 83.7 84.2 83.8 83.4 82.4 85.3 82.8 81.6 手提电脑 95.3 95.3 95.9 95.6 95.8 95.8 95.9 95.7 95.8↑ 摩托 65.2 71.6 71.8 66.8 67.4 67.8 58.9 66.3 69.6↑ 马克杯 93.0 94.1 95.1 94.8 94.9 94.2 94.3 94.9 94.4 手枪 81.2 81.3 80.9 81.3 82.3 81.1 81.8 81.1 83.7 ↑火箭 57.9 58.7 59.6 59.6 59.2 59.7 56.9 63.5 62.5 滑板 72.8 76.4 76.6 75.7 76.0 75.7 75.4 74.5 82.0 ↑桌子 80.6 82.6 82.4 82.8 81.9 82.0 82.7 82.6 83.0 ↑mIoU 83.7 85.1 85.4 85.1 85.1 85.2 85.3 85.2 85.4 ↑
Table 5. Effect of different k values on model performance
View tableView in ArticleTable 5. Effect of different k values on model performance
k OA(%) 用多分辨率分支补偿后OA/% 提升/% 5 20.7 35.1 +14.4 10 85.4 88.3 +2.9 15 91.9 92.1 +0.2 20 92.5 93.4 +0.9 25 92.1 92.3 +0.2
Table 6. Ablation experiments of multi-resolution GCN module
View tableView in ArticleTable 6. Ablation experiments of multi-resolution GCN module
实验 GCN分支 M-R分支 融合 mAcc/% OA/% 1 √ × × 89.9 92.5 2 × √ × 84.0 89.1 3 √ √ × 89.9 92.6 4 √ √ √ 91.2 93.4
Table 7. The effect of different resolution point cloud on network performance
View tableView in ArticleTable 7. The effect of different resolution point cloud on network performance
不同分辨率的点云 mAcc/% OA/% [512,384,256,128] 90.4 92.7 [640,512,384,256] 90.6 92.8 [768,640,512,384] 90.9 93.0 [896,768,640,512] 91.2 93.4
Table 8. Comparison of the noise robustness of the several methods
View tableView in ArticleTable 8. Comparison of the noise robustness of the several methods
噪声水平 下降程度 3D-GCN AdaptConv DGCNN Ours 0.02 0.7 ↓1.8↓ 1.4↓ 0.9↓ 0.04 2.2↓ 2.2↓ 2.2↓ 1.8 ↓0.06 4.6↓ 3.3↓ 3.2↓ 3.1 ↓0.08 8.4↓ 6.5↓ 5.7 ↓6.4↓ 0.1 14.9↓ 10.8 ↓13.1↓ 11.7↓
Table 9. The impact of different number of feature extraction modules on network performance
View tableView in ArticleTable 9. The impact of different number of feature extraction modules on network performance
模块数量 mAcc/% OA/% 每轮训练时间/s 模型参数量/M 3 89.7 92.4 63 2.8 4 91.2 93.4 139 3.6 5 90.6 93.1 323 4.8
Tools
Get Citation
Copy Citation Text
Zhiyong Tao, Heng Li, Miaosen Dou, Sen Lin. Multi-resolution feature fusion for point cloud classification and segmentation network[J]. Opto-Electronic Engineering, 2023, 50(10): 230166-1
Paper Information
Category: Article
Received: Jul. 7, 2023
Accepted: Sep. 20, 2023
Published Online: Jan. 22, 2024
The Author Email: Li Heng (李衡)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20