Decision Tree Method to Analyze the Performance of Lane Support Systems

Road departure is one of the main causes single vehicle and frontal crashes. By implementing lateral support systems, a significant amount these accidents can be avoided. Typical are normally occurring due to unintentional lane where driver drifts towards across line identifying edge lane. The Lane Support Systems (LSS) uses cameras “read” lines on road alert if car approaching lines. Anyway, despite assumed technology readiness, there still much uncertainty regarding needs vision systems for “reading” limited results available from in field testing. In such framework paper presents an experimental test LSS performance carried out two rural roads with different geometric alignments marking conditions. faults, day light dry pavement conditions, were detected average 2% sections. A decision tree method was used analyze cause faults importance variable involved process. fault probability increased sections radius less than 200 m poor conditions marking.