Regression of feature scale tracklets for decimeter visual localization

作者:

Highlights:

• A decimeter-level vehicle localization system using monocular vision is proposed.

• Regression of feature scale tracklets allows interpolation between database images.

• Visual estimates are combined with a motion model using a Kalman filter.

• Localization accuracy is within 1 m for 98% of a real-world dataset.

摘要

•A decimeter-level vehicle localization system using monocular vision is proposed.•Regression of feature scale tracklets allows interpolation between database images.•Visual estimates are combined with a motion model using a Kalman filter.•Localization accuracy is within 1 m for 98% of a real-world dataset.

论文关键词:Ego-localization,Monocular vision,Feature scale

论文评审过程:Received 5 April 2016, Revised 22 June 2017, Accepted 21 July 2017, Available online 5 August 2017, Version of Record 30 November 2017.

论文官网地址:https://doi.org/10.1016/j.imavis.2017.07.004