3D laser point cloud clustering method based on image information constraints

Table 1. Calibration results of internal parameters
View table
View in Article
Table 1. Calibration results of internal parameters
f_x f_y c_x c_y k₁ k₂ p₁ p₂
K 657.58 660.12 296.12 246.35 — — — —
D — — — — 0.238809 −0.643802 0.001786 −0.024125

Table 2. Calibration results of external parameters
View table
View in Article
Table 2. Calibration results of external parameters
x/mm y/mm z/mm Roll/rad Pitch/rad Yaw/rad
T 59.94 52.76 −14.46 −1.540 0.031 −1.581

Table 3. Affects of distribution spacing on the algorithm

View table

View in Article

Table 3. Affects of distribution spacing on the algorithm

Distribution spacing/cm	My-method		K-means		K-means++		Euclidean Clustering		DBSCAN
Distribution spacing/cm	My-method		K-means		K-means++		Euclidean Clustering		DBSCAN		$ω$	$η$	$ω$	$η$	$ω$	$η$	$ω$	$η$	$ω$	$η$
2	✓	—	✓	0.44	✓	0.72	✗	—	✗	—
5	✓	—	✓	0.46	✓	0.70	✗	—	✗	—
10	✓	—	✓	0.72	✓	0.88	✗	—	✓	—
15	✓	—	✓	0.62	✓	0.74	✓	—	✓	—
20	✓	—	✓	0.54	✓	0.70	✓	—	✓	—

Table 4. Performance comparison of multiple algorithms

View table

View in Article

Table 4. Performance comparison of multiple algorithms

Algorithm	Number of correctdivisions/number	Clusteringaccuracy/%	Average timespent/ms	Average number of iterations/number
Algorithm	Number of correctdivisions/number	Clusteringaccuracy/%	Average timespent/ms	Average number of iterations/number	DBSCAN	258	70.11	3.625	—
Euclidean Clustering	262	71.20	2.517	—
K-means	210	57.07	1.951	12
K-means++	222	60.33	3.373	10
My-method	320	86.96	1.106	6

Tools

Get Citation

Copy Citation Text

Jinze Xia, Haoming Sun, Shenghui Hu, Dongtai Liang. 3D laser point cloud clustering method based on image information constraints[J]. Opto-Electronic Engineering, 2023, 50(2): 220148

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites