In this paper, we propose to fuse the LIDAR and monocular image in the framework of conditional random field to detect the road robustly in challenging scenarios. LIDAR points are aligned with pixels in image by cross calibration. Then boosted decision tree based classifiers are trained for image and point cloud respectively. The scores of the two kinds of classifiers are treated as the unary potentials of the corresponding pixel nodes of the random field. The fused conditional random field can be solved efficiently with graph cut. Extensive experiments tested on KITTI-Road benchmark show that our method reaches the state-of-the-art.
CRF based road detection with multi-sensor fusion
2015-06-01
587381 byte
Conference paper
Electronic Resource
English
Road surface condition detection with multi-scale fusion
European Patent Office | 2018
|ROAD SURFACE CONDITION DETECTION WITH MULTI-SCALE FUSION
European Patent Office | 2017
|Multi-sensor fusion method for road condition measurement
European Patent Office | 2021
|AEB control method based on multi-sensor road adhesion coefficient fusion
European Patent Office | 2024
|