Automatic detection of vehicle occupants: the imaging problem and its solution

The automatic detection and counting of vehicle occupants is a challenging research problem that was given little attention until recently. An automat ed vehicle-occupant-counting system would greatly facilitate the operation of freeway lanes reserved for car pools (high occupancy vehicle lanes or HO V lanes). There are three major aspects of this problem: (a) the imaging as pect (sensor phenomenology), (b) the pattern recognition aspect, and (c) th e system architecture aspect. In this paper, we present a solution to the i maging aspect of the problem. We propose a novel system based on fusion of near-infrared imaging signals and we demonstrate its adequacy with theoreti cal and experimental arguments. We also compare our solution to other possi ble solutions across the electromagnetic spectrum, particularly in the ther mal infrared and visible regions.