Designing a Driver Vigilance Monitoring Device

Portable medical devices processing images or executing complex artificial intelligence algorithms are posing a challenge for microprocessor manufacturers. Since these devices require a processing platform that is able to satisfy their application real-time requirements. Single processor platforms are unable to provide a satisfactory performance at a reasonable cost. In this book the alternative of using a multi-processor platform is explored. A design methodology that utilizes the flexibility and short design cycle of FPGAs in order to achieve this target is proposed. The method allows optimizing the multi-processor platform and the software code targeting each processing core to meet real-time constraints. The effectiveness of the design methodology is practically demonstrated by building a real life driver vigilance monitoring system based on visual cues extraction and evaluation. The application drives the whole design process to prove its efficiency. Moreover the book covers the practical steps of building the video processing algorithm.