Road Safety Estimation Utilizing Big And Heterogeneous Vehicle Recorder Data

We present a method for estimating road safety using large-scale and heterogeneous vehicle recorder data. Our assamption in this study is that occurrences of traffic accidents on crossings could be estimated by their road shape, driving behaviors over them, and photos taken by dash cams. Utilizing 3 years dataset from 1,500 drivers in a fleet delivery company, we try to detect risky crossings based on supervised machine learning. Results show that our method provides good performance, and can extract potentially risky crossings.