Decision Tree Method to Analyze the Performance of Lane Support Systems

Abstract

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