Multiple sensing technologies exist for Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS). One perception system that is particularly efficient in detecting Vulnerable Road Users, animals, and obstacles for Automatic Emergency Braking applications is thermal imaging. Thermal cameras can reliably operate in low-light and high-contrast luminosity conditions making them a suitable candidate to complement visible cameras and extend ADAS use cases to night conditions.

The scientific effort included a characterization of the thermal cameras’ capability to identify the pedestrian when coupled with an artificial intelligence image detection algorithm. It also included a simulation-based investigation of the potential safety benefits of thermal camera adoption. Additionally the analysis included a heuristic characterization of the detection capabilities for a car equipped with traditional cameras to provide a baseline for the comparison.