Research on Fatigue Driving Assessment Based on Multi-Source Information Fusion

Abstract

Fatigue driving has become one of the main causes of traffic accidents. At present, many driving fatigue detection methods are based on the image processing technology, while these methods are easy to be affected by the driving environment, which limits the accuracy and reliability and accuracy of the detection. For this limitation, this paper introduces the multi-source information detection and fusion technology, using sensors to get kinds of information, including PERCLOS value, attitude feature, facial expressions and body temperature, then uses the neural network learning method to identify the driver's state based on the fused information, which could improve the improve the accuracy and reliability of driving fatigue detection. Experiments have been carried out to prove that the proposed method is considerably effective.