Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/IVS.2015.7225685 | 2015 IEEE Intelligent Vehicles Symposium (IV) |
Keywords | Field | DocType |
CRF based road detection,multisensor fusion,monocular image,LIDAR points,cross calibration,boosted decision tree based classifier,point cloud,unary potential,pixel node,fused conditional random field,graph cut,KITTI-road benchmark | Conditional random field,Cut,Computer vision,Random field,Pattern recognition,Computer science,Sensor fusion,Lidar,Pixel,Artificial intelligence,Point cloud,Gradient boosting | Conference |
ISSN | Citations | PageRank |
1931-0587 | 11 | 0.61 |
References | Authors | |
31 | 5 |