Point Cloud Registration Method Based on Combination of Convolutional Neural Network and Improved Harris-SIFT

Changhua Li; Hao Shi; Zhijie Li

doi:10.3788/LOP57.201102

Laser & Optoelectronics Progress, Volume. 57, Issue 20, 201102(2020)

Point Cloud Registration Method Based on Combination of Convolutional Neural Network and Improved Harris-SIFT

Changhua Li, Hao Shi, and Zhijie Li^*

School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, Shaanxi 710055, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(12)

Fig. 1. Flow chart of point cloud registration method based on CNN combined with improved Harris-SIFT

Download full size

Fig. 2. Flow chart of improved Harris-SIFT algorithm to extract key points of point cloud

Download full size

Fig. 3. Extracted key points of different models by improved Harris-SIFT algorithm. (a) Bunny model; (b) Horse model

Download full size

Fig. 4. Structure of CNN model

Download full size

Fig. 10. Registration results of Jishi tower point cloud model. (a) Before registration; (b) after coarse registration; (c) after accurate registration

Download full size

Fig. 11. Comparison of registration effects of Jishi tower model. (a) ICP algorithm; (b) NV-TICP algorithm; (c) ISS-ICP algorithm

Download full size

Table 1. Dataset information of point cloud model
View table
Table 1. Dataset information of point cloud model
Dataset Amount of point data
Bunny 35947
Horse 48485
Dragon 437645

Table 2. Key points detected in Bunny point cloud model

View table

Table 2. Key points detected in Bunny point cloud model

Key point ofsource point cloud	Position coordinate	Key point oftarget point cloud	Positioncoordinate
1	(-0.0775, 0.0078, -0.0890)	1	(0.0785, 0.0487, -0.0762)
2	(0.0366, 0.3565, -0.3373)	2	(0.0010, 0.5621, -0.0154)
3	(-0.0394, 0.5782, 0.1947)	3	(-0.0864, 0.0509, 0.0643)
4	(0.0045, 0.0783, -0.0053)	4	(-0.0056, 0.0345, 0.7290)
5	(-0.0597, 0.1082, 0.0753)	5	(0.3648, 0.6439, -0.0542)
6	(-0.8963, 0.0091, 0.0802)	6	(-0.0040, 0.6909, 0.2003)
7	(-0.7205, 0.0004, 0.0507)
8	(0.0832, 0.0305, 0.2198)
9	(0.1002, 0.0405, 0.0077)

Table 3. Key points detected in Horse point cloud model

View table

Table 3. Key points detected in Horse point cloud model

Key point ofsource point cloud	Position coordinate	Key point oftarget point cloud	Positioncoordinate
1	(-0.0607, 0.0082, 0.2054)	1	(0.8734, -0.0880, 0.0007)
2	(0.4738, -0.0509, 0.0042)	2	(0.9867, 0.0092, -0.8460)
3	(0.0340, 0.0416, -0.0060)	3	(-0.0021, 0.0071, 0.0209)
4	(0.8192, 0.1417, -0.2090)	4	(0.0870, -0.0003, 0.9562)
5	(0.0900, -0.4203, 0.0404)	5	(-0.0065, 0.0535, 0.0030)
6	(0.8150, 0.1040, 0.1690)

Table 4. Comparison of four registration methods under different point cloud models

View table

Table 4. Comparison of four registration methods under different point cloud models

Model	Registration error
Model	Algorithm	E_R /(°)	E_M /mm	Running time /s
	ICP	12.46	7.71	5.297
Bunny	NV-ICP	10.89	5.51	21.895
	ISS-ICP	8.33	6.03	14.998
	CNN-ICP	3.77	1.12	5.470
	ICP	13.01	5.46	5.913
Horse	NV-ICP	11.72	4.74	20.785
	ISS-ICP	9.43	4.88	15.055
	CNN-ICP	3.57	1.03	6.438
	ICP	21.07	12.04	13.789
Dragon	NV-ICP	13.93	6.75	31.367
	ISS-ICP	9.52	5.35	21.352
	CNN-ICP	3.07	1.93	9.537

Table 5. Dataset information of Jishi-tower point cloud model
View table
Table 5. Dataset information of Jishi-tower point cloud model
Model Amount ofpoint data Percentage ofmissing point /%
Source point cloud 590560 17
Target point cloud 608260 14

Table 6. Comparison of registration effects of four registration methods in Jishi tower model
View table
Table 6. Comparison of registration effects of four registration methods in Jishi tower model
Registrationalgorithm Registration error Runningtime /s
E_R /(°) E_M /mm
ICP 104.06 (fail) 18.55 122.756
NV-TICP 34.58 8.47 81.567
ISS-ICP 43.55 6.76 45.257
CNN-ICP 5.52 1.80 15.880

Tools

Get Citation

Copy Citation Text

Changhua Li, Hao Shi, Zhijie Li. Point Cloud Registration Method Based on Combination of Convolutional Neural Network and Improved Harris-SIFT[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201102

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites