Improved Lidar Obstacle Detection Method Based on Euclidean Clustering

Fig. 12. Global cluster comparison. (a) Original point cloud; (b) traditional Euclidean clustering algorithm; (c) improved Euclidean clustering algorithm

Download full size

Table 1. Comparison of ground segmentation
View table
Table 1. Comparison of ground segmentation
Algorithm Positive detection /times False detection /times Missed detection /times
Least square method 3 3 1
RANSAC algorithm 6 1 0

Table 2. Vehicles parked on roadside(165 vehicles)
View table
Table 2. Vehicles parked on roadside(165 vehicles)
Algorithm Positive detection /times False detection /times Positive detection rate /%
Traditional Euclidean clustering 103 62 62.42
Improved Euclidean clustering 147 18 89.09

Table 3. Pedestrian (113 pedestrians)
View table
Table 3. Pedestrian (113 pedestrians)
Algorithm Positivedetection /times Falsedetection /times Misseddetection /times Positive detectionrate /%
Traditional Euclidean clustering 103 62 19 66.37
Improved Euclidean clustering 147 18 22 76.10

Table 4. Mobile vehicles including non-motorized vehicles (33 vehicles)
View table
Table 4. Mobile vehicles including non-motorized vehicles (33 vehicles)
Algorithm Positive detection /times False detection /times Positive detection rate /%
Traditional Euclidean clustering 26 7 78.78
Improved Euclidean clustering 30 3 90.90

Tools

Get Citation

Copy Citation Text

Chang Liu, Jin Zhao, Zihao Liu, Xiqiao Wang, Kuncheng Lai. Improved Lidar Obstacle Detection Method Based on Euclidean Clustering[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201105

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites