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
01.06.2015
587381 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Road surface condition detection with multi-scale fusion
Europäisches Patentamt | 2018
|ROAD SURFACE CONDITION DETECTION WITH MULTI-SCALE FUSION
Europäisches Patentamt | 2017
|Multi-sensor fusion method for road condition measurement
Europäisches Patentamt | 2021
|AEB control method based on multi-sensor road adhesion coefficient fusion
Europäisches Patentamt | 2024
|