Vehicle drivers face Monitoring System Research and Implementation
|School||University of Electronic Science and Technology|
|Keywords||Driving status FPGA Hardware and software co-design Multi-core NIOSII|
With the development of society , the the car increasing number of traffic accidents tended to increase . The study showed that a large part is due to driver fatigue . Driver fatigue affect the driver's alertness and ability to drive safely . Therefore, how to avoid and prevent fatigue driving , is of great significance to reduce the accident rate . This article has designed a driver monitoring alert system based on visual clues . The system uses a new algorithm to detect the state of the driver 's eyes in the successive frames in the calculation of the duration of the driver 's eyes closed , to assess the degree of alertness of the driver . This paper presents a short design cycle , high flexibility of the FPGA design , the use of parallel processing to meet real-time requirements of complex calculations . Hardware and software co-design and dynamic segmentation method to optimize the design parameters and each core software coding of multi-core platform . Consecutive frames process in the multi-core FPGA processing platform to meet the requirements of real-time processing and chip area constraints . System after verification of Grimace face database and achieved good results . Practice, the pseudo- closed eyes must be twice in a row to trigger an alert , reducing the probability of false positives . Timing analysis, parallel processing to enhance the system performance , but also proved a powerful multi-core system design FPGA prototype design tool . The flexible FPGA technology with hardware and software co-design , providing people with the method to explore the design space , time , minimum funding requirements in the system design .