The Intersection Safety Challenge (ISC) is a USDOT initiative that seeks innovative solutions to reduce traffic-related fatalities and injuries at intersections. It supports advanced technologies that enhance safety for all road users and focus on mitigating risks in complex traffic environments. The STAR Lab team achieved 1st place in Stage 1A and the Tier 2 prize in Stage 1B and will advance to compete in Stage 2.
In Stage 1B, the team developed an innovative Cooperative Perception System (CPS) to generate a comprehensive understanding of intersection dynamics. This advanced system integrates multiple sensors, including eight visual cameras, five thermal cameras, and two 3D LiDARs, enabling 3D object detection, classification, and precise path and conflict prediction. The architecture of CPS, depicted in Figure 1, is structured into three primary modules: Object Detection and Classification, 2D-3D Camera Calibration, and Tracking and Prediction.
Figure 1. A Cooperative Perception System (CPS) integrating visual cameras, thermal cameras, and 3D LiDARs for real-time intersection monitoring, enabling object detection, classification, tracking, and conflict prediction to enhance traffic safety.