Integrating Dense LiDAR-Camera Road Detection Maps by a Multi-Modal CRF Model

Road detection is an important task in autonomous navigation systems. In this paper, we propose a road detection method via a LiDAR-camera fusion strategy to exploit both the range and color information. The whole system consists of three parts. In the LiDAR based part, we transform the discrete 3D...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on vehicular technology 2019-12, Vol.68 (12), p.11635-11645
Main Authors: Gu, Shuo, Zhang, Yigong, Tang, Jinhui, Yang, Jian, Alvarez, Jose M., Kong, Hui
Format: Article
Language:English
Subjects:
Algorithms
Autonomous navigation
Cameras
Conditional random fields
Estimation
Image segmentation
KITTI
Laser radar
Lidar
LiDAR-camera fusion
Navigation systems
road detection
Roads
Task analysis
Three dimensional models
Three-dimensional displays
Weight reduction
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Road detection is an important task in autonomous navigation systems. In this paper, we propose a road detection method via a LiDAR-camera fusion strategy to exploit both the range and color information. The whole system consists of three parts. In the LiDAR based part, we transform the discrete 3D LiDAR point clouds to continuous 2D LiDAR range images and propose a distance-aware height-difference based scanning approach to get the road estimations quickly. In the camera based part, we apply a light-weight transfer learning based road segmentation network. In the LiDAR-camera fusion part, we transform the detection results from LiDAR and camera to dense and binary ones to solve the data imbalance problem and fuse them in a multi-modal conditional random field (MM-CRF) framework. Experiments show that the proposed MM-CRF fusion method can operate in real-time and achieve competitive performance compared with the state-of-the-art road detection algorithms on the KITTI-Road benchmark.
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2019.2946100