A real-time road detection method based on reorganized lidar data.

Authors:
Fenglei Xu
Fenglei Xu
Qilu Hospital of Shandong University
China
Jing Lou
Jing Lou
National Institute for Communicable Disease Control and Prevention
China
Mingwu Ren
Mingwu Ren
Nanjing University of Science and Technology
Nanjing Shi | China

PLoS One 2019 16;14(4):e0215159. Epub 2019 Apr 16.

School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China.

Road Detection is a basic task in automated driving field, in which 3D lidar data is commonly used recently. In this paper, we propose to rearrange 3D lidar data into a new organized form to construct direct spatial relationship among point cloud, and put forward new features for real-time road detection tasks. Our model works based on two prerequisites: (1) Road regions are always flatter than non-road regions. (2) Light travels in straight lines in a uniform medium. Based on prerequisite 1, we put forward difference-between-lines feature, while ScanID density and obstacle radial map are generated based on prerequisite 2. According to our method, we construct an array of structures to store and reorganize 3D input firstly. Then, two novel features, difference-between-lines and ScanID density, are extracted, based on which we construct a consistency map and an obstacle map in Bird Eye View (BEV). Finally, the road region is extracted by fusing these two maps and refinement is used to polish up our outcome. We have carried out experiments on the public KITTI-Road benchmark, achieving one of the best performances among the lidar-based road detection methods. To further prove the efficiency of our method on unstructured road, the visual outcomes in rural areas are also proposed.

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0215159PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6467419PMC
April 2019
11 Reads

Publication Analysis

Top Keywords

road detection
16
lidar data
12
scanid density
8
based prerequisite
8
real-time road
8
road
6
based
5
bev finally
4
finally road
4
light travels
4
straight lines
4
travels straight
4
lines uniform
4
medium based
4
bird eye
4
uniform medium
4
eye view
4
road region
4
view bev
4
non-road regions
4

References

(Supplied by CrossRef)
Developing a Coordinated Signal Control System for Urban Ring Road Under the Vehicle-Infrastructure Connected Environment
C Ma et al.
IEEE Access 2018
Path optimization of taxi carpooling
M Changxi et al.
PLOS ONE 2018
Recent progress in road and lane detection: a survey
AB Hillel et al.
Machine Vision & Applications 2014
LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks
L Caltagirone et al.
CoRR 2018
Color-based road detection in urban traffic scenes
Y He et al.
IEEE Transactions on Intelligent Transportation Systems 2004
General Road Detection From a Single Image
H Kong et al.
IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society 2010
Vanishing point detection for road detection
H Kong et al.
Computer Vision and Pattern Recognition 2013

Similar Publications