TY - JOUR
T1 - Road Manhole Cover Delineation Using Mobile Laser Scanning Point Cloud Data
AU - Yu, Yongtao
AU - Guan, Haiyan
AU - Li, Dilong
AU - Jin, Chunhua
AU - Wang, Cheng
AU - Li, Jonathan
N1 - Publisher Copyright:
© 2004-2012 IEEE.
PY - 2020/1
Y1 - 2020/1
N2 - Periodical road manhole cover measurement is extremely important to ensure road safety and reduce traffic disasters. This letter proposes an effective method for delineating road manhole covers from mobile laser scanning point cloud data. To improve processing efficiency, first, road surface points are segmented and rasterized into georeferenced intensity images. Then, object-oriented patches are generated through superpixel segmentation and further fed to a convolutional capsule network classifier for manhole cover detection. Finally, manhole covers are accurately delineated through a marked point process of disks. Quantitative evaluations on three data sets show that an average completeness, correctness, quality, and F1-measure of 0.965, 0.961, 0.929, and 0.963, respectively, are obtained. Comparative studies with three existing methods confirm that the proposed method performs superiorly in delineating manhole covers of varying conditions and on complex road surface environments.
AB - Periodical road manhole cover measurement is extremely important to ensure road safety and reduce traffic disasters. This letter proposes an effective method for delineating road manhole covers from mobile laser scanning point cloud data. To improve processing efficiency, first, road surface points are segmented and rasterized into georeferenced intensity images. Then, object-oriented patches are generated through superpixel segmentation and further fed to a convolutional capsule network classifier for manhole cover detection. Finally, manhole covers are accurately delineated through a marked point process of disks. Quantitative evaluations on three data sets show that an average completeness, correctness, quality, and F1-measure of 0.965, 0.961, 0.929, and 0.963, respectively, are obtained. Comparative studies with three existing methods confirm that the proposed method performs superiorly in delineating manhole covers of varying conditions and on complex road surface environments.
KW - Convolutional capsule network
KW - manhole cover
KW - marked point process
KW - mobile laser scanning
KW - point cloud
UR - https://www.scopus.com/pages/publications/85078696796
U2 - 10.1109/LGRS.2019.2916156
DO - 10.1109/LGRS.2019.2916156
M3 - 文章
AN - SCOPUS:85078696796
SN - 1545-598X
VL - 17
SP - 152
EP - 156
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
IS - 1
M1 - 8727503
ER -