TY - JOUR
T1 - Learning hierarchical features for automated extraction of road markings from 3-D mobile LiDAR point clouds
AU - Yu, Yongtao
AU - Li, Jonathan
AU - Guan, Haiyan
AU - Jia, Fukai
AU - Wang, Cheng
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2015/2/1
Y1 - 2015/2/1
N2 - This paper presents a novel method for automated extraction of road markings directly from three dimensional (3-D) point clouds acquired by a mobile light detection and ranging (LiDAR) system. First, road surface points are segmented from a raw point cloud using a curb-based approach. Then, road markings are directly extracted from road surface points through multisegment thresholding and spatial density filtering. Finally, seven specific types of road markings are further accurately delineated through a combination of Euclidean distance clustering, voxel-based normalized cut segmentation, large-size marking classification based on trajectory and curb-lines, and small-size marking classification based on deep learning, and principal component analysis (PCA). Quantitative evaluations indicate that the proposed method achieves an average completeness, correctness, and F-measure of 0.93, 0.92, and 0.93, respectively. Comparative studies also demonstrate that the proposed method achieves better performance and accuracy than those of the two existing methods.
AB - This paper presents a novel method for automated extraction of road markings directly from three dimensional (3-D) point clouds acquired by a mobile light detection and ranging (LiDAR) system. First, road surface points are segmented from a raw point cloud using a curb-based approach. Then, road markings are directly extracted from road surface points through multisegment thresholding and spatial density filtering. Finally, seven specific types of road markings are further accurately delineated through a combination of Euclidean distance clustering, voxel-based normalized cut segmentation, large-size marking classification based on trajectory and curb-lines, and small-size marking classification based on deep learning, and principal component analysis (PCA). Quantitative evaluations indicate that the proposed method achieves an average completeness, correctness, and F-measure of 0.93, 0.92, and 0.93, respectively. Comparative studies also demonstrate that the proposed method achieves better performance and accuracy than those of the two existing methods.
KW - Deep learning
KW - mobile light detection and ranging (LiDAR)
KW - point cloud
KW - road marking
KW - three dimensional (3-D) extraction
UR - https://www.scopus.com/pages/publications/85027949298
U2 - 10.1109/JSTARS.2014.2347276
DO - 10.1109/JSTARS.2014.2347276
M3 - 文章
AN - SCOPUS:85027949298
SN - 1939-1404
VL - 8
SP - 709
EP - 726
JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
IS - 2
M1 - 6891172
ER -