Drowsy driving detection method and system thereof, and computer device

Patent metadata

Field	Value
Publication number	US-12488601-B2
Application number	US-202117924555-A
Country	US
Kind code	B2
Filing date	Jun 1, 2021
Priority date	Jun 12, 2020
Publication date	Dec 2, 2025
Grant date	Dec 2, 2025

Abstract

A drowsy driving detection method comprises: acquiring a side face image of a currently seated driver collected by a camera module; performing face recognition on the side face image to obtain side face feature parameters, and determining, according to the side face feature parameters, whether an ID file corresponding to the currently seated driver exists in a driver ID library; and if yes, periodically acquiring a side face image of the driver in the current period collected by the camera module, obtaining eye movement feature parameters of the driver in the current period according to the side face image of the current period, and determining whether the driver is driving while drowsy according to a comparison result between the eye movement feature parameters of the current period and the normal eye movement feature parameters of the driver.

First claim

What is claimed is:

1 . A drowsy driving detection method, comprising:
acquiring a side face image of a driver currently seated captured by a camera module, wherein the side face image is a left side face image or a right side face image of the driver, wherein the left or right side face image is captured by the camera module from a left or a right side of a head of the driver; performing a face recognition on the side face image to obtain a side face feature parameter, and determining whether there is an ID file corresponding to the driver currently seated in a driver ID library according to the side face feature parameter, wherein the ID file comprises a side face feature parameter of the driver and a normal eye movement feature parameter of the driver in an awake state; and periodically acquiring side face images of the driver in a current period captured by the camera module during a driving process, obtaining an eye movement feature parameter of the driver in the current period according to the side face images of the driver in the current period, and determining whether the driver is drowsily driving according to a comparison result between the eye movement feature parameter in the current period and the normal eye movement feature parameter of the driver, if there is an ID file corresponding to the driver currently seated in the driver ID library; wherein the eye movement feature parameter in the current period comprises at least one of a distance parameter between upper and lower eyelids in the current period, a blink time parameter in the current period, and a parameter of percentage of eyelid closure over the pupil over time in the current period, and the normal eye movement feature parameter of the driver comprises at least one of a distance parameter between normal upper and lower eyelids, a normal blink time parameter, and a parameter of percentage of normal eyelid closure over the pupil over time.

2 . The drowsy driving detection method of claim 1 , further comprising:
acquiring multiple frames of side face images of the driver captured by the camera module in a period of normal awake state while the driver is driving, performing an image recognition on the multiple frames of side face images to obtain a plurality of eye movement feature parameters, obtaining a normal eye movement feature parameter of the driver currently seated according to the plurality of eye movement feature parameters, and establishing an ID file corresponding to the driver currently seated according to the side face feature parameter and the normal eye movement feature parameter of the driver currently seated, if there is no ID file corresponding to the driver currently seated in the driver ID library; and after establishing the ID file corresponding to the driver currently seated, periodically acquiring the side face images of the driver in current period captured by the camera module during the driving process, and obtaining the eye movement feature parameter of the driver in the current period according to the side face images of the driver in the current period, and determining whether the driver is drowsily driving according to the comparison result between the eye movement feature parameter of the driver in the current period and the normal eye movement feature parameter of the driver.

3 . The drowsy driving detection method of claim 1 , further comprising:
acquiring an intensity parameter of current in-vehicle ambient light sampled by an ambient light recognition sensor; determining whether to perform a soft light supplementation on a side face of the driver according to a comparison result between the intensity parameter of the current in-vehicle ambient light and a preset intensity threshold; and generating a light supplementation control instruction, and sending the light supplementation control instruction to a light supplementation actuator, to control the light supplementation actuator to execute the light supplementation control instruction, if it is determined to perform the soft light supplementation on the side face of the driver.

4 . The drowsy driving detection method of claim 1 , further comprising:
acquiring an intensity parameter of a current in-vehicle ambient light captured by an ambient light recognition sensor; determining whether to use a CMOS camera component or an infrared CCD camera component to capture the side face image of the driver according to a comparison result between the intensity parameter of the current in-vehicle ambient light and a preset intensity threshold, wherein the camera module comprises the CMOS camera component and the infrared CCD camera component; generating a first wake-up instruction and a first dormancy instruction, sending the first wake-up instruction to the CMOS camera component to control the CMOS camera component to execute the first wake-up instruction, and sending the first dormancy instruction to the infrared CCD camera component to control the infrared CCD camera component to execute the first dormancy instruction, if it is determined that the CMOS camera component is used to capture the side face image of the driver; and generating a second wake-up instruction and a second dormancy instruction, sending the second wake-up instruction to the infrared CCD camera component to control the infrared CCD camera component to execute the first wake-up instruction, and sending the second dormancy instruction to the CMOS camera component to control the CMOS camera component to execute the second dormancy instruction, if it is determined that the infrared CCD camera component is used to capture the side face image of the driver.

5 . The drowsy driving detection method of claim 1 , further comprising:
acquiring a parameter information of a first plane where a camera optical axis of the camera module is located; performing an image recognition on the side face image to obtain a parameter information of a second plane where a side face of the driver is located; and determining whether the first plane is perpendicular to the second plane according to the parameter information of the first plane and the parameter information of the second plane; and generating a lens adjustment control instruction, and sending the lens adjustment control instruction to a lens adjustment drive mechanism, to control the lens adjustment drive mechanism to drive the camera module to move, if the first plane is not perpendicular to the second plane, so that the first plane where the camera optical axis of the camera module is located is perpendicular to the second plane where the side face of the driver is located.

6 . A drowsy driving detection system, comprising:
a processor; and a memory for storing computer-readable instructions executable by the processor; wherein the processor is configured to perform a drowsy driving detection method, the method comprising: acquiring a side face image of a driver currently seated captured by a camera module, wherein the side face image is a left side face image or a right side face image of the driver, wherein the left or right side face image is captured by the camera module from a left or a right side of a head of the driver; performing a face recognition on the side face image to obtain a side face feature parameter, and determining whether there is an ID file corresponding to the driver currently seated in a driver ID library according to the side face feature parameter, wherein the ID file comprises a side face feature parameter of the driver and a normal eye movement feature parameter of the driver in an awake state; and periodically acquiring side face images of the driver in a current period captured by the camera module during a driving process, obtaining an eye movement feature parameter of the driver in

Assignees

• Guangzhou Automobile Group Co

Inventors

• Zhang Ying
• Wu Tianlai
• Cai Jichen
• He Dongjian
• Sha Jinzhou
• Chen Chao

Classifications

• B60W40/09

  Driving style or behaviour · CPC title

• H04N23/56 Primary

  provided with illuminating means · CPC title

• G06V40/18

  Eye characteristics, e.g. of the iris · CPC title

• G06V40/168

  Feature extraction; Face representation · CPC title

• B60W2540/229

  Attention level, e.g. attentive to driving, reading or sleeping · CPC title