A REAL-TIME ORIENTED SYSTEM FOR VEHICLE DETECTION

Starting from the analysis of the specific requirements of automotive on-board equipments, this work presents a system for vehicle detection in a monocular video sequence. The system is composed of a pipeline o f two different engines: PAPRICA, a massively parallel architecture fo r the efficient execution of low-level image processing tasks, improve d by the integration of a specific feature for direct data I/O; and a traditional serial architecture running medium-level tasks aimed to th e detection of the vehicles' position in the sequence. A preliminary v ersion of the system has been demonstrated on MOB-LAB land vehicle, wh ile a fully optimized one is currently under tuning in laboratory.