Road Detection by PDF-Based Classification

Cheng Deng¹, Han Xie², Yunfan Chen³, Hyunchul Shin⁴

^1,2,3,4Department of Electronics and Communication Engineering, Hanyang University, Ansan, Republic of Korea

Abstract

Road detection is essential for road departure warning, autonomous driving, and supporting driver-assistance systems. The major challenge of vision-based road-detection techniques is to deal with illumination variations, especially extreme shadows and highlights. We propose an innovative method to obtain a road segmentation which is robust to extreme shadow and highlight conditions. The novelty of our approach is that we combine the shadow-invariant feature space with horizon estimation, tone mapping, and probability density function (PDF)-based classification, to achieve fast and accurate road region segmentation.

Keywords

Author's Profile

Author profile can be generated and linked through our partners World Book of Researchers. To include your profile online Click Here. After it is approved, please email to edlib @ asdf.res.in to create a link with all the papers.

• Cheng Deng : Profile
• Han Xie : Profile
• Yunfan Chen : Profile
• Hyunchul Shin : Profile

e-AID

Cite this Article as Follows

Cheng Deng, Han Xie, Yunfan Chen, Hyunchul Shin. Road Detection by PDF-Based Classification. International Conference on Artificial Intelligence and Application (2018): 05. Print.