Creating navigation map in semi-open scenarios for intelligent vehicle localization using multi-sensor fusion

作者：

Highlights：

• A RSF map is proposed to collect the road features from multiple sensors.

• A new calibration method using plane-plane correspondences is developed.

• A new monocular 3D reconstruction method is introduced.

摘要

•A RSF map is proposed to collect the road features from multiple sensors.•A new calibration method using plane-plane correspondences is developed.•A new monocular 3D reconstruction method is introduced.

论文关键词：Intelligent vehicles,Road scenario fingerprint,Multi-view representation,Multi-sensor fusion,Map-based localization

论文评审过程：Received 21 November 2019, Revised 28 May 2021, Accepted 30 June 2021, Available online 6 July 2021, Version of Record 9 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115543