Lane estimation by particle-filtering combined with likelihood computation of line boundaries and motion compensation

作者：

Highlights：

• An efficient likelihood computation of line boundary pixels is combined with particle filtering.

• A newly introduced ROI weighting prohibits the fluctuation of lane boundary localization.

• Motion influence in estimating lane information is minimized by compensating the motion.

摘要

•An efficient likelihood computation of line boundary pixels is combined with particle filtering.•A newly introduced ROI weighting prohibits the fluctuation of lane boundary localization.•Motion influence in estimating lane information is minimized by compensating the motion.

论文关键词：Probabilistic lane estimation,Likelihood computation,Motion compensation,ROI weighting,Two-step particle filtering

论文评审过程：Received 26 September 2017, Accepted 27 April 2018, Available online 10 May 2018, Version of Record 16 September 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.04.003