Vehicle occupancy monitoring with optical range-sensors

Abstract

New generations of "smart airbags" require information about a passenger's position, weight, size and posture to discriminate between adults, children, front- or rear-faced child seats, objects put on the seat or simply empty seats. The technical solution discussed here is based on a 3D-optical time-of-flight (TOF) sensor, with active modulated IR-illumination. Each individual pixel measures not only an intensity grey value but also the distance to a corresponding point in the scene under investigation. We present classification results for seat occupancy monitoring, obtained with statistical pattern recognition techniques. For head tracking we combine an ellipsoidal shape detector with an Extended Kalman Filter.