Inference Method for Abnormal Traffic Events in Highway Monitoring Blind Spots

Abstract

Highway monitoring is critical for traffic safety and efficiency. However, monitoring blind spots—areas between surveillance points—poses significant challenges. This study proposes an inference method to detect abnormal traffic events in highway blind spots by analyzing vehicle counts from adjacent monitored regions. Utilizing Vissim and LumenRT for simulation, we create realistic highway scenarios to collect time series data. Cross-correlation is used to determine the time lag between vehicle counts, and Pearson's correlation coefficient evaluates the correlation between time-shifted data. The results show significant correlation under normal conditions, which decreases noticeably during abnormal events, confirming the method's effectiveness. This approach enhances the ability to monitor and respond to traffic anomalies in blind spots, improving overall highway safety and efficiency.