Point Cloud Analysis Combining Gated Self-Calibration Mechanism and Graphical Convolutional Network

Jiali Xu; Zhijun Fang; Shiqian Wu

doi:10.3788/LOP202259.1210017

Laser & Optoelectronics Progress, Volume. 59, Issue 12, 1210017(2022)

Point Cloud Analysis Combining Gated Self-Calibration Mechanism and Graphical Convolutional Network

Jiali Xu1... Zhijun Fang1,* and Shiqian Wu2 |Show fewer author(s)

Author Affiliations

¹School of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, China

²School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, Hubei , China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(13)

Fig. 1. Structure of IE-Conv

Download full size

Fig. 2. Schematic diagrams of inner and outer point set module. (a) Internal point set module; (b) external point set module

Download full size

Fig. 3. Structure of internal point set module

Download full size

Fig. 4. Structure of external point set module

Download full size

Fig. 5. Architecture of interior-exterior point set shape feature convolutional network

Download full size

Table 1. Comparison of classification accuracy for ModelNet40 dataset

View table

Table 1. Comparison of classification accuracy for ModelNet40 dataset

Method	Input	Points /10³	Acc /%
Pointwise-CNN^［31］	pnt	1	86.1
ECC^［19］	pnt	1	87.4
PointNet^［8］	pnt	1	89.2
Point-CNN^［33］	pnt	1	91.7
DGCNN^［10］	pnt	1	92.2
SO-CNN^［15］	pnt	1	93.1
Dense-Point^［26］	pnt	1	93.2
RS-CNN^［14］	nor	1	92.8
PAT^［27］	pnt，nor	1	91.7
Spec-GCN^［30］	pnt，nor	1	91.8
PointConv^［1］	pnt，nor	1	92.5
A-CNN^［11］	pnt，nor	1	92.6
PointASNL^［13］	pnt，nor	1	93.2
ELM^［28］	pnt，nor	1	93.2
RS-CNN^［14］	pnt，nor	1	93.6
SO-Net^［29］	pnt，nor	2	90.9
PointNet++^［9］	pnt，nor	5	91.9
Spider-CNN^［32］	pnt，nor	5	92.4
SO-Net^［29］	pnt，nor	5	93.4
Proposed method	pnt，nor	1	93.9

Table 2. Comparison of classification complexity and time of the ModelNet40 dataset
View table
Table 2. Comparison of classification complexity and time of the ModelNet40 dataset
Method Number of parameters /MB Acc /% FLOPs /sample
PointNet 3.50 89.2 440
Spec-GCN 2.05 91.8 1112
PointNet++ 1.48 91.9 1684
DGCNN 1.84 92.2 2767
Proposed method 1.37 93.9 266

Table 3. Comparison of segmentation accuracy of ShapeNet dataset

View table

Table 3. Comparison of segmentation accuracy of ShapeNet dataset

Method	Air	Bag	Cap	Car	Chai	Ear.	Gui.	Knife	Lamp	Lap	Moto	Mug	Pistol	Rock	Skate	Table	Mean
PointNet^［8］	83.4	78.7	82.5	74.9	89.6	73.0	91.5	85.9	80.8	95.3	65.2	93.0	81.2	57.9	72.8	80.6	83.7
SONet^［29］	82.8	77.8	88.0	77.3	90.6	73.5	90.7	83.9	82.8	94.8	69.1	94.2	80.9	53.1	72.9	83.0	84.9
PointNet++^［9］	82.4	79.0	87.7	77.3	90.8	71.8	91.0	85.9	83.7	95.3	71.6	94.1	81.3	58.7	76.4	82.6	85.1
DGCNN^［10］	84.2	83.7	84.4	77.1	90.9	78.5	91.5	87.3	82.9	96.0	67.8	93.3	82.6	59.7	75.5	80.6	85.1
PCNN^［1］	82.4	80.1	85.5	79.5	90.8	73.2	91.3	86.0	85.0	95.7	73.2	94.8	83.3	51.0	75.0	81.8	85.1
ELM^［28］	84.0	80.4	88.0	80.2	90.7	77.5	91.2	86.4	82.6	95.5	70.0	93.9	84.1	55.6	75.6	82.1	85.3
SpiderCNN^［32］	83.5	81.0	87.2	77.5	90.7	76.8	91.1	87.3	83.3	95.8	70.2	93.5	82.7	59.7	75.8	82.8	85.3
SO-CNN	83.9	84.1	85.0	77.4	91.3	78.3	91.7	87.4	83.8	96.4	69.7	93.5	83.1	58.9	76.2	82.9	85.7
A-CNN^［11］	84.2	84.0	88.0	79.6	91.3	75.2	91.6	87.1	85.5	95.4	75.3	94.9	82.5	67.8	77.5	83.3	86.1
RS-CNN^［14］	83.5	84.8	88.8	79.6	91.2	81.1	91.6	88.4	86.0	96.0	73.7	94.1	83.4	60.5	77.7	83.6	86.2
Proposed method	84.0	86.2	88.1	79.5	91.6	77.5	91.3	88.0	86.3	96.1	72.8	95.0	83.6	62.2	75.9	83.9	86.4

Table 4. Visualization results of SR-Net) on ShapeNet dataset
View table
Table 4. Visualization results of SR-Net) on ShapeNet dataset
Object Visualization Object Visualization
Air Lamp
Bag Laptop
Cap Motor.
Car Mug
Chair Pistol
Ear. Rocket
Gui. Skate
Knife Table

Table 5. Ablation experiments with modules on ModelNet40 dataset
View table
Table 5. Ablation experiments with modules on ModelNet40 dataset
Model RS-CNN（*） Internal External Internal-external Acc /%
A 90.1
B √ 92.0
C √ 93.2
D √ √ 92.9
E √ 93.9

Table 6. Ablation experiments on ModelNet40 dataset for different prior expressions as gates

View table

Table 6. Ablation experiments on ModelNet40 dataset for different prior expressions as gates

Model	Priori expressions	Channel	Acc /%
A	${‖p_{i} - p_{i, j}‖}_{e d}$	1	92.4
A	${‖p_{i} - p_{i, j}‖}_{c o s d}$	1	92.4
B	$p_{i}^{c o o r d}$ 、 $p_{i, j}^{c o o r d}$	6	93.4
B	$p_{i}^{n o r}$ 、 $p_{i, j}^{n o r}$	6	93.4
C	$p_{i}^{c o o r d}$ 、 $p_{i, j}^{c o o r d}$ 、 ${‖p_{i} - p_{i, j}‖}_{e d}$	7	93.9
C	$p_{i}^{n o r}$ 、 $p_{i, j}^{n o r}$ 、 ${‖p_{i} - p_{i, j}‖}_{c o s d}$	7	93.9
D	$p_{i}^{c o o r d}$ 、 $p_{i, j}^{c o o r d}$ 、 ${‖p_{i} - p_{i, j}‖}_{e d}$	7	93.0
E	$p_{i}^{n o r}$ 、 $p_{i, j}^{n o r}$ 、 ${‖p_{i} - p_{i, j}‖}_{c o s d}$	7	92.5

Table 7. Robustness experiments on ModelNet40 dataset after adding translations or rotations to point clouds
View table
Table 7. Robustness experiments on ModelNet40 dataset after adding translations or rotations to point clouds
Method Self-calibrate Translation Rotate
-0.2 +0.2 90˚ 180˚
PointNet 70.8 70.6 42.5 38.6
PointNet++ 88.2 88.2 47.9 39.7
Proposed method 90.9 90.9 90.9 90.9
Proposed method √ 92.1 92.1 92.1 92.1

Table 8. Ablation experiments of different aggregation functions and self calibration functions on ModelNet40 dataset
View table
Table 8. Ablation experiments of different aggregation functions and self calibration functions on ModelNet40 dataset
Model Aggregation function Self-calibrate Acc /%
A Avg 92.7
B Max 93.2
C Max √ 93.5
D Sum 93.5
E Sum √ 93.9

Tools

Get Citation

Copy Citation Text

Jiali Xu, Zhijun Fang, Shiqian Wu. Point Cloud Analysis Combining Gated Self-Calibration Mechanism and Graphical Convolutional Network[J]. Laser & Optoelectronics Progress, 2022, 59(12): 1210017

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Jul. 29, 2021

Accepted: Sep. 23, 2021

Published Online: May. 23, 2022

The Author Email: Zhijun Fang (zjfang@sues.edu.cn)

DOI:10.3788/LOP202259.1210017

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Comparison of classification accuracy for ModelNet40 dataset

Table 1. Comparison of classification accuracy for ModelNet40 dataset

Table 2. Comparison of classification complexity and time of the ModelNet40 dataset

Table 2. Comparison of classification complexity and time of the ModelNet40 dataset

Table 3. Comparison of segmentation accuracy of ShapeNet dataset

Table 3. Comparison of segmentation accuracy of ShapeNet dataset

Table 4. Visualization results of SR-Net) on ShapeNet dataset

Table 4. Visualization results of SR-Net) on ShapeNet dataset

Table 5. Ablation experiments with modules on ModelNet40 dataset

Table 5. Ablation experiments with modules on ModelNet40 dataset

Table 6. Ablation experiments on ModelNet40 dataset for different prior expressions as gates

Table 6. Ablation experiments on ModelNet40 dataset for different prior expressions as gates

Table 7. Robustness experiments on ModelNet40 dataset after adding translations or rotations to point clouds

Table 7. Robustness experiments on ModelNet40 dataset after adding translations or rotations to point clouds

Table 8. Ablation experiments of different aggregation functions and self calibration functions on ModelNet40 dataset

Table 8. Ablation experiments of different aggregation functions and self calibration functions on ModelNet40 dataset

微信扫一扫：分享