摘要: |
Speeding continues to be a major factor in traffic crashes and fatalities. However, despite the importance of understanding it, studying speeding behavior poses many challenges. The Strategic Highway Research Program 2 (SHRP2) Naturalistic Driving Study has provided a unique dataset that has the potential to overcome some of these
challenges and greatly enhance our understanding of speeding behavior. The National Highway Traffic Safety Administration recently published the report "Analysis of SHRP2 Speeding Data" (DOT HS 812 858, March 2020). The current project further develops the SHRP2 Speeding Database created in our original SHRP2 Speeding project and conducting two new analyses to better understand drivers’ speeding behavior. To examine the first research question on the role of certain pre-crash driver and situational factors in
predicting speeding-related crashes, video data from drivers’ vehicles will be used to identify speeding-related
crashes and the presence of any pre-crash factors of interest. Once the data is narrowed and
classified, the information will be linked back to the SHRP2 Speeding Dataset so the pre-crash factors can
be examined as predictors of speeding-related crashes.
To examine the second research question regarding drivers’ speeding and aggressive driving behaviors in
the context of ambient traffic. radar data and lane positioning data will be used to identify drivers’
speeding and certain aggressive driving behaviors. Machine learning algorithms will then be developed
and applied to video data from this subset of drivers’ vehicles to classify speeding and aggressive driving
behaviors. Similar to the first analysis, this subset of information will then be linked back to the SHRP2
Speeding Dataset so drivers’ speeding and aggressive driving behaviors can be examined in the context of
ambient traffic. The substantive findings will provide useful information for traffic safety stakeholders,
particularly for planning countermeasures and for public information and education programs designed to
reduce speeding and speeding-related crashes. The methodological findings and enhanced dataset will
improve future use of the SHRP2 data by traffic safety researchers. |