Driver state monitoring system based on Kinect

Abstract

The invention discloses a driver state monitoring system based on Kinect. The system comprises a face feature information collection module, an information processing module, a multi-feature information fusion module, an alarm module and a database storage module. Face feature information is obtained through utilization of an infrared camera and a color camera provided by the Kinect; driver face expressions and mouth, eye and head features are monitored; the data obtained by the Kinect is preprocessed through combination of an image processing technology; a state of the driver is comprehensively judged by fusing various feature information; when it is monitored that the state of the driver is abnormal, the alarm module alarms in real time, and the state information of the driver is stored in a local database for search of history data; moreover, a driving habit of the driver is summarized through the history data; and pre-warning is carried out. The accuracy of monitoring the state of the driver in the daytime particular in the night can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a driver state monitoring system based on Kinect. Background technique [0002] With the improvement of transportation infrastructure, the rapid growth of the number of motor vehicles in my country has been stimulated. The problem of traffic safety has become a major problem to be solved urgently in today's society. According to investigations and studies, it is shown that 85% of the cause of traffic accidents is caused by the driver himself. Therefore, in order to reduce traffic accidents and ensure driving safety, it is necessary to intelligently monitor the state of the driver during the driving process of the vehicle, and provide real-time early warning of the driving state of the driver due to fatigue driving and inattention during driving. [0003] At present, the monitoring technology for driver status is mainly manifested in the following aspects: ...

AI Technical Summary

Problems solved by technology

[0004] The first category, the detection method based on the driver's physiological signal, mainly uses EEG signal detection and ECG signal detection to obtain the driver's state. Interference caused by driver operation is difficult to promote

[0005] The second category is based on the monitoring of driver fatigue state. Its shortcoming is that the monitoring method is single. This single detection is difficult to reflect the complexity of the driver's driving state. It lacks the fusion processing of various characteristic information and the accuracy of monitoring. not tall

Images