Driver Fatigue State Detection Method and System Based on Attitude Features

Abstract

The invention discloses a driver fatigue state detection method based on attitude features, comprising: judging the driver's driving state by a first fatigue detection algorithm; if the first fatigue detection algorithm judges that the driving state is a fatigue state, triggering a second fatigue detection Algorithm, otherwise, it is judged that the driving state is a sober state; the processing of the second fatigue detection algorithm includes: extracting the posture features of the collected images, the posture characteristics including head posture characteristics and skeleton posture characteristics; judging head posture characteristics according to the head posture characteristics. Head state, if the head state is in motion state, judge the driving state as awake state; otherwise, judge the body state according to the skeleton posture characteristics, if the body state is in motion state, judge the driving state as awake state, otherwise judge the driving state as fatigue state. Multiple identifications are performed on the driver's fatigue state, and secondary screening is performed based on the driver's posture characteristics, which greatly reduces the false detection rate and improves the accuracy of driver fatigue state judgment.

Description

technical field

[0001] The invention relates to the technical fields of image processing and safe driving, in particular to a driver fatigue state detection method and system based on attitude features. Background technique

[0002] At present, there are many research methods for the detection of driver fatigue state, which can be roughly divided into detection based on driver’s physiological signal, detection based on driver’s operation behavior, detection based on vehicle state information and detection based on driver’s physiological response. feature detection methods. Among them, the detection method based on the driver's physiological response characteristics is non-contact detection, which will not interfere with the driver's normal driving behavior during the detection process, and will not be interfered by the driver's personal driving habits. It has become a research topic at home and abroad. hotspot. The current fatigue detection is mainly based on facial expres...

Images