CRF based road detection with multi-sensor fusion

Liang Xiao; Bin Dai; Daxue Liu; Tingbo Hu; Tao Wu

doi:10.1109/ivs.2015.7225685

June 1, 2015

CRF based road detection with multi-sensor fusion

View at Publisher

Ask AI

Bookmark

Share

Key Points

To develop a robust road detection framework that fuses LIDAR point clouds and monocular camera images within a conditional random field model for challenging driving scenarios.
Aligned 3D LIDAR point clouds with 2D monocular camera pixels through cross-calibration.
Trained boosted decision tree classifiers separately on image and point cloud features to establish unary potentials.
Optimized the fused conditional random field using efficient graph-cut algorithms.
Achieved state-of-the-art performance for road detection on the standard KITTI-Road benchmark.
Demonstrated robust scene segmentation across challenging driving conditions through multi-modal sensor fusion.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Experimental evaluation demonstrates state-of-the-art road detection on the KITTI-Road benchmark using sensor fusion, highlighting enhanced perception for autonomous navigation.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Xiao et al. (2015) studied this question.

synapsesocial.com/papers/6a1687a74021539c0f656e40 https://doi.org/10.1109/ivs.2015.7225685

View at Publisher

Ask AI

Bookmark

Share

CRF based road detection with multi-sensor fusion

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

CRF based road detection with multi-sensor fusion

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading