The invention discloses a driving fatigue monitoring method based on
human body multi-class characteristics. The driving fatigue monitoring method comprises driver electroencephalogram
signal monitoring and driver
head posture monitoring. The driver electroencephalogram
signal monitoring comprises the steps that an entropy value is calculated through electroencephalogram signals, and electroencephalogram
signal driving fatigue monitoring indexes are formed through
dimensionality reduction; according to driver
head posture information monitoring, a miniature
infrared temperature sensor is usedfor recording driver
head posture information, and head posture driving fatigue monitoring indexes are generated; and finally, the correlation between the electroencephalogram
signal monitoring indexes and the head posture
information monitoring indexes are analyzed by using Pearson
correlation analysis, and the influence of various interferences on the monitoring indexes is lowered, thereby forming comprehensive driving fatigue monitoring of various characteristics of the driver. The method is high in recognition degree, the
system is easy to establish, the method is easy to implement, the purpose of more accurately monitoring the fatigue state of the driver is achieved, and traffic hidden dangers caused by driving fatigue are reduced. The method has the advantages of being scientific, reasonable, high in applicability and good in effect.