Abstract
A new high-speed infrared video-based fatigue detection system was developed using a system on a programmable chip (SoPC) in this study. Based on the limitations of PERCLOS, we merged the eyes and mouth fatigue related characteristics to improve detection accuracy, used a Difference of Gaussian (DoG) filter and Ada-boosting algorithm to implement driver fatigue detection based on multi-feature fusion. The detection system was produced using FPGA with a parallel processing structure and pipeline technology. This system is innovative and it can detect fatigued states efficiently and rapidly.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have