Quality-guided lane detection by deeply modeling sophisticated traffic context

作者：

Highlights：

• This work proposes lane detection algorithm based on quality-related deep modeling.

• The proposed method can cope with variant number of lanes as well as lane changes.

• Our method is robust to different conditions and can be achieved in real time.

摘要

•This work proposes lane detection algorithm based on quality-related deep modeling.•The proposed method can cope with variant number of lanes as well as lane changes.•Our method is robust to different conditions and can be achieved in real time.

论文关键词：Lane detection,Image quality,Convolution neural network

论文评审过程：Received 26 May 2019, Revised 17 January 2020, Accepted 16 February 2020, Available online 19 February 2020, Version of Record 10 March 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115811