Dangerous driving detection method, device and equipment and readable storage medium

Abstract

The invention relates to a dangerous driving detection method, device and equipment and a readable storage medium, and relates to the technical field of safe driving, and the method comprises the steps: collecting real-time hand motion data and real-time chest motion data of a driver based on a millimeter wave radar; performing FFT (Fast Fourier Transform) on the real-time hand action data to obtain an action spectrogram; importing the action spectrogram into an XGBoost classifier to detect whether the action corresponding to the action spectrogram is a handheld call action; if yes, performing FFT (Fast Fourier Transform) on the real-time chest movement data to obtain a respiration spectrogram; importing the respiratory spectrogram into a support vector machine to detect whether an action corresponding to the respiratory spectrogram is a speaking action or not; if yes, judging that the driver is in a dangerous driving state. According to the method and the device, the dangerous behavior of the driver can be effectively detected, the privacy protection of the user is realized while the accuracy is ensured, and the method and the device can adapt to a complex environment.

Description

technical field [0001] The present application relates to the technical field of safe driving, in particular to a dangerous driving detection method, device, equipment and readable storage medium. Background technique [0002] The driver's driving concentration determines the safety of the car driving process. in. In the process of driving, the behavior of the driver talking on the mobile phone often distracts the driver's attention, so that the probability of road safety accidents increases several times. Therefore, how to detect in real time whether the driver is holding a mobile phone call, and prevent this dangerous driving behavior in time is a problem worth thinking about. [0003] In related technologies, the driver's call detection is often implemented based on image or sound features. For example, a camera is used to capture the driver's behavior in real time, and then process the captured image, and finally judge whether the driver has dangerous driving behavior...

AI Technical Summary

Problems solved by technology

[0004] The present application provides a dangerous driving detection method, device, equipment and readable storage medium to solve the problem of insufficient privacy protection for the driver and limited accuracy rate caused by realizing the driver's call detection based on image or sound features in the related art. Environmental factors have a big impact on the problem

Images