Indoor corner recognition from crowdsourced trajectories using smartphone sensors

作者：

Highlights：

• Address the fake corner and pose diversity problem in indoor corner recognition.

• Propose a hierarchical architecture consisting of three classifiers.

• Propose to classify diverse poses into only two pose groups.

• Conduct field experiments to confirm the superiority of the proposed scheme.

摘要

•Address the fake corner and pose diversity problem in indoor corner recognition.•Propose a hierarchical architecture consisting of three classifiers.•Propose to classify diverse poses into only two pose groups.•Conduct field experiments to confirm the superiority of the proposed scheme.

论文关键词：Indoor corner recognition,Fake corner problem,Pose diversity problem,Indoor positioning system,Machine learning

论文评审过程：Received 9 September 2016, Revised 10 April 2017, Accepted 11 April 2017, Available online 12 April 2017, Version of Record 19 April 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.04.024