阅读说明：本技术 一种驾驶状态检测的方法、系统、设备及可读存储介质 (Method, system and equipment for detecting driving state and readable storage medium ) 是由 仲崇亮 于 2019-09-25 设计创作，主要内容包括：本申请公开了一种驾驶状态检测的方法,包括：获取指定区域内的三维面部图像信息,并利用三维面部图像信息建立3D面部模型；利用3D面部模型确定驾驶员的视线的凝视位置；判断凝视位置是否在预设范围内；若否,则判断凝视时间是否超过第一阈值；其中,凝视时间为驾驶员视线停留在凝视位置的时间；若凝视时间超过第一阈值,则确定驾驶员处于疲劳驾驶状态。本申请利用基于3D的图像采集技术获取三维面部图像信息,并利用建立好的3D面部模型来检测驾驶员是否处于疲劳驾驶状态,提高了驾驶状态检测的精度,减少了疲劳驾驶误判情况的发生。本申请同时还提供了一种驾驶状态检测的系统、设备及计算机可读存储介质,具有上述有益效果。(The application discloses a method for detecting a driving state, which comprises the following steps: acquiring three-dimensional face image information in a designated area, and establishing a 3D face model by using the three-dimensional face image information; determining a gaze location of a driver's gaze using a 3D face model; judging whether the gaze position is within a preset range; if not, judging whether the staring time exceeds a first threshold value; wherein the gaze time is the time when the driver's sight line stays at the gaze position; if the gaze time exceeds a first threshold, it is determined that the driver is in a fatigue driving state. According to the method and the device, the three-dimensional facial image information is acquired by using the 3D-based image acquisition technology, and whether the driver is in the fatigue driving state is detected by using the established 3D facial model, so that the driving state detection precision is improved, and the occurrence of the fatigue driving misjudgment condition is reduced. The application also provides a system and equipment for detecting the driving state and a computer readable storage medium, and the system and the equipment have the beneficial effects.)

1. A method of driving state detection, comprising:

acquiring three-dimensional face image information in a designated area, and establishing a 3D face model by using the three-dimensional face image information;

determining a gaze location of a driver's gaze using the 3D face model;

judging whether the gaze position is within a preset range;

if not, judging whether the staring time exceeds a first threshold value; wherein the gaze time is a time the driver's gaze stays at the gaze location;

determining that the driver is in a fatigue driving state if the gaze time exceeds the first threshold.

2. The method according to claim 1, further comprising, after acquiring three-dimensional face image information within a specified area;

determining position information of each preset feature point in the three-dimensional face image information;

determining facial motion data from the location information;

detecting whether the driver is in the fatigue driving state according to the facial motion data.

3. The method of claim 1, further comprising, when the gaze location is within the preset range:

acquiring running information of a current vehicle and vehicle distance information between the current vehicle and surrounding vehicles;

detecting whether the driver is in a fatigue driving state according to the driving information;

if not, judging whether the vehicle distance information is smaller than a second threshold value;

if the vehicle distance information is smaller than the second threshold value, determining that the driver is in the fatigue driving state;

the driving information comprises a time interval of lane departure of the current vehicle, a speed change value of the current vehicle in a preset time interval and a vehicle speed when the current vehicle turns.

4. The method of claim 3, further comprising:

recording driving behavior data of the driver;

establishing an exclusive driving state detection model of the driver according to the driving behavior data, the driving information and the vehicle distance information;

and detecting whether the driver is in the fatigue driving state or not by using the exclusive driving state detection model.

5. The method of claim 4, further comprising:

uploading the driving behavior data, the driving information and the vehicle distance information to a cloud platform so that the cloud platform records the driving behavior data, the driving information and the vehicle distance information of the driver.

6. The method of claim 1, after determining that the driver is in a fatigue driving state, further comprising:

and sending out an alarm signal.

7. The method of claim 6, wherein said issuing an alarm signal comprises:

acquiring running information and vehicle distance information, and calculating the danger level of the current vehicle according to the running information and the vehicle distance information;

and sending out an alarm signal corresponding to the danger level.

8. A system for driving condition detection, comprising:

the system comprises a first model establishing module, a second model establishing module and a third model establishing module, wherein the first model establishing module is used for acquiring three-dimensional face image information in a designated area and establishing a 3D face model by using the three-dimensional face image information;

the sight line simulation module is used for simulating the gaze position of the sight line of the driver by utilizing the 3D face model;

the first judgment module is used for judging whether the gaze position is within a preset range;

the second judging module is used for judging whether the gaze time exceeds a first threshold value or not when the gaze position is judged not to be in the preset range;

a first determination module to determine that the driver is in a fatigue driving state if the gaze time exceeds the first threshold.

9. A driving state detection apparatus characterized by comprising:

a memory for storing a computer program;

a processor for implementing the steps of the method of driving state detection according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method of driving state detection according to any one of claims 1 to 7.