Abstract | ||
---|---|---|
Road detection is a crucial problem for autonomous navigation system (ANS) and advance driver-assistance system (ADAS). In this paper, we propose a hierarchical road detection method for robust road detection in challenging scenarios. Given an on-board road image, we first train a Gaussian mixture model (GMM) to obtain road probability density map (RPDM), and next oversegment the image into superpixels. Based on RPDM and superpixels, initial seeds are selected in an unsupervised way, and the seed superpixels iteratively try to occupy their neighbors according to GrowCut framework, the road segment is obtained after convergency. Finally, we refine the road segment with a conditional random field (CRF), which enforces the shape prior on the road segmentation task. Experiments on two challenging databases demonstrate that the proposed method exhibits high robustness compared with the state-of-the-art. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICRA.2014.6906904 | ICRA |
Keywords | DocType | Volume |
robustness,advance driver-assistance system,road vehicles,GMM,GrowCut framework,traffic engineering computing,robust control,image segmentation,on-board road image,mixture models,seed superpixels,convergency,conditional random field,road probability density map,Gaussian processes,object detection,robust road detection,shape prior,hierarchical road detection method,ADAS,ANS,CRF,road traffic,RPDM,autonomous navigation system,Gaussian mixture model,probability,road segmentation task | Conference | 2014 |
Issue | ISSN | Citations |
1 | 1050-4729 | 3 |
PageRank | References | Authors |
0.39 | 7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Keyu Lu | 1 | 16 | 4.09 |
Jian Li | 2 | 49 | 6.61 |
Xiangjing An | 3 | 226 | 12.15 |
Hangen He | 4 | 307 | 23.86 |