An Estimation Method of Visibility Level Based on Low Rank Matrix Completion Using Positional Relationship of GPV Data

Abstract

Listen

Translate article

This paper proposes a method for estimating visibility level based on low rank matrix completion using the positional relationship of GPV data. On a snowy day, the driving tasks can be hard because visibility is poor. By providing visibility level to drivers and road manager, safer traffic will be realized. To estimate visibility, weather data, which are significantly related to visibility, are used in the proposed method. In the proposed method, Grid Point Value (GPV) data and visibility data including missing values on unobserved points are generated to matrix corresponding to the actual location. The missing values are estimated based on low rank matrix completion. The effectiveness of our method are shown by utilizing actual data.