A stereo matching approach based on particle filters and scattered control landmarks

作者：

Highlights：

• A stereo matching approach motivated by the particle filter framework in robot localization.

• Highly accurate GCPs, acquired by the computation of multiple cost efficient disparity maps.

• A Markov chain model has been introduced in the process to reduce the computational complexity of particle filtering.

• Application of RANSAC algorithm along with a histogram technique to refine any outliers.

摘要

•A stereo matching approach motivated by the particle filter framework in robot localization.•Highly accurate GCPs, acquired by the computation of multiple cost efficient disparity maps.•A Markov chain model has been introduced in the process to reduce the computational complexity of particle filtering.•Application of RANSAC algorithm along with a histogram technique to refine any outliers.

论文关键词：Stereo matching,Particle filters,Ground control points,Markov chains,Plane fitting

论文评审过程：Received 2 December 2013, Revised 20 October 2014, Accepted 1 April 2015, Available online 18 April 2015, Version of Record 15 May 2015.

论文官网地址：https://doi.org/10.1016/j.imavis.2015.04.001