CN111243236A - Fatigue driving early warning method and system based on deep learning - Google Patents
Fatigue driving early warning method and system based on deep learning Download PDFInfo
- Publication number
- CN111243236A CN111243236A CN202010053964.8A CN202010053964A CN111243236A CN 111243236 A CN111243236 A CN 111243236A CN 202010053964 A CN202010053964 A CN 202010053964A CN 111243236 A CN111243236 A CN 111243236A
- Authority
- CN
- China
- Prior art keywords
- module
- categories
- deep learning
- fatigue driving
- alarm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
Abstract
The invention discloses a fatigue driving early warning method and system based on deep learning, which comprises the following steps: the system comprises a parameter analyzing module, a video collecting module, an image processing module, an identification module, a picture frame module and an alarm module; the parameter analysis module is used for reading various parameter settings of a program when the program is started, the video acquisition module acquires videos and transmits effective videos to the image processing module, the image processing module reads and records the length and the width of the images and generates a zero matrix with the same size, the images are transmitted to the identification module, the identification module generates block diagram coordinates of detection results and confidence degrees of the detection results, the frame module traverses all categories by identifying the block diagram coordinates and the confidence degrees of the detection results, frames and labels the categories of the categories with the confidence degrees larger than a threshold value according to the block diagram coordinates, frames with different colors are drawn according to different categories and distinguished, and the alarm module sends alarm signals.
Description
Technical Field
The invention relates to the technical field of fatigue driving early warning, in particular to a fatigue driving early warning system based on deep learning.
Background
At present, with the continuous improvement of the living standard of people and the continuous development of the automobile industry and the social economy, the driving becomes an important part of the daily life of people. However, the multiple traffic accidents threaten the safety of people when going out, and cause economic loss when going out, and endanger the lives of people when going out.
In recent years, fatigue driving by drivers has become one of the main causes of motor vehicle accidents. Fatigue driving often occurs when the driver continues to drive the vehicle or cannot ensure wakefulness. At this time, the physiological and psychological functions of the driver are unbalanced, which objectively results in a reduction in driving skill. The driver's thinking, attention, perception, reaction, judgment, will, motor nerves and the like are affected by the cause of fatigue driving. In long-time fatigue driving, a driver is sleepy and tired, the attention is hard to concentrate, the visual field is gradually narrowed, and the thinking ability is reduced. Even absentmindedness or short-time memory loss can occur, unsafe factors such as slow response, misoperation or untimely correction time and the like occur, and the probability of road traffic accidents is easily caused. The judgment ability of the driver is reduced and the response is slow when the driver is tired, and the misoperation rate is increased at the moment. When a driver is slightly tired, the gearbox can be operated untimely and inaccurate; when a driver is in moderate fatigue, the operation action is not consistent, and the phenomenon of forgetting the operation sometimes occurs; when a driver is in severe fatigue, the driver often operates mechanically or dozes off midway, and when the driver is in severe fatigue, the vehicle loses control.
Currently, many techniques are used to detect the fatigue state of the driver, and these techniques can be roughly classified into three categories: driving mode of the vehicle, physiological state of the driver, and computer vision techniques. However, the main drawback of vehicle-based driving pattern detection methods is that their accuracy depends on the personal characteristics of the vehicle and its driver; the detection based on the physiological characteristics is the highest accuracy in all the existing fatigue detection methods, but because a plurality of sensors are added on the body to interfere with the invasiveness of the driver, the acquisition of signals can bring discomfort to the driver; non-invasive methods of bio-signal exist, but the accuracy is not high; visual feature-based methods detect drowsiness by using non-invasive visual information such as yawning, facial expressions, head movements and eye states. Due to non-contact, methods based on visual features have become a promising area of research for drowsiness detection. Methods based on yawning and head movements cannot reliably detect the onset of drowsiness because these methods do not directly indicate drowsiness.
Therefore, it is an urgent need to solve the above-mentioned problems by those skilled in the art to determine fatigue state of a driver due to eye closure and blinking frequency.
Disclosure of Invention
In view of the above, the invention provides a fatigue driving early warning method and system based on deep learning.
In order to achieve the purpose, the invention adopts the following technical scheme:
a fatigue driving early warning method based on deep learning comprises the following steps:
s1, acquiring an eye image of the driver;
s2, establishing a Faster R-CNN human eye opening and closing detection model;
s3, detecting the eye image of the driver by using Faster R-CNN, and acquiring the coordinates of the block diagram and the confidence of the detection result;
s4, traversing all categories, drawing frames and labeling the categories of which the confidence degrees are greater than the threshold according to the coordinates of the block diagram, and drawing frames with different colors for distinguishing according to different categories;
and S5, outputting the detection type.
Preferably, the specific process of step S2 is as follows:
s21, selecting RPN as a network structure, and performing simulation training through a CEW data set;
s22, labeling the anchor points, wherein the anchor points with the highest intersection ratio overlapping with the Box of the real label or the anchor points with the intersection ratio reaching 0.7 are positive labels, and the anchor points with the intersection ratio lower than 0.3 are negative labels;
s22, training the shared convolutional layer, and finely adjusting parameters of the specific layer;
preferably, the categories are open eye or closed eye.
Preferably, the specific process of detecting in step S3 is as follows: the im _ detect function is used to detect the driver's eye image.
A system using a deep learning based driver fatigue warning method, comprising: the system comprises a parameter analyzing module, a video collecting module, an image processing module, an identification module, a picture frame module and an alarm module;
the parameter analysis module is used for reading various parameter settings of the program when the program is started, the video acquisition module is used for acquiring video, and transmitting the effective video to the image processing module, wherein the image processing module is used for reading and recording the length and the width of the image and generating a zero matrix with the same size, then, the image is transmitted to the recognition module, the recognition module uses the trained Fast R-CNN detection network to generate the frame coordinate of the detection result and the confidence coefficient of the detection result, the frame module is used for recognizing the frame coordinate and the confidence coefficient of the detection result, traversing all categories, drawing frames for all categories with confidence degrees larger than a threshold value according to the coordinates of the block diagram and labeling the categories, and drawing frames with different colors for distinguishing according to different categories, wherein the alarm module is used for sending alarm signals.
Preferably, the categories are open eye and closed eye.
Preferably, the alarm module is connected with a buzzer, the buzzer alarms when the alarm module outputs a high level, and the buzzer stops alarming when the alarm module outputs a low level.
According to the technical scheme, compared with the prior art, the invention discloses a fatigue driving early warning system based on deep learning, which is characterized in that the eye image information of a driver is collected through a video collection module, the length and the width of an image are recorded through an image processing module, a zero matrix with the same size is generated, the coordinates and the confidence coefficient of a block diagram of a detection result generated by a recognition module are more accurate through training of a Faster R-CNN network, the category is divided through a picture frame module, and when the eye closing times reach a threshold value, the warning is carried out.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart provided by the present invention.
Fig. 2 is a schematic structural diagram provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A fatigue driving early warning method based on deep learning comprises the following steps:
s1, acquiring an eye image of the driver;
s2, establishing a Faster R-CNN human eye opening and closing detection model;
s3, detecting the eye image of the driver by using Faster R-CNN, and acquiring the coordinates of the block diagram and the confidence of the detection result;
s4, traversing all categories, drawing frames and labeling the categories of which the confidence degrees are greater than the threshold according to the coordinates of the block diagram, and drawing frames with different colors for distinguishing according to different categories;
and S5, outputting the detection type.
In order to further optimize the above technical solution, the specific process of step S2 is:
s21, selecting RPN as a network structure, and performing simulation training through a CEW data set;
s22, labeling the anchor points, wherein the anchor points with the highest intersection ratio overlapping with the Box of the real label or the anchor points with the intersection ratio reaching 0.7 are positive labels, and the anchor points with the intersection ratio lower than 0.3 are negative labels;
s22, training the shared convolutional layer, and finely adjusting parameters of the specific layer;
to further optimize the above technical solution, the categories are open eye or closed eye.
In order to further optimize the above technical solution, the specific process of detecting in step S3 is as follows: the im _ detect function is used to detect the driver's eye image.
A fatigue driving early warning system of a deep learning network model training method comprises the following steps: the system comprises a parameter analyzing module 1, a video collecting module 2, an image processing module 3, an identification module 4, a picture frame module 5 and an alarm module 6;
the parameter analysis module 1 is responsible for reading various parameter settings of the program when the program is started, such as whether to use an RPN network, names of networks and models used by codes, whether to use a CPU, a number of GPU equipment and the like; the video acquisition module 2 captures a video by using a VideoCapture function of OpenCV, when a camera is started, a frame of image is automatically read in, and if the read image is effective, the read image is transmitted to the image processing module 3; after receiving the sent frame of image, the image processing module 3 reads and records the length and width of the image through a numpy packet, generates a zero matrix with the same size, prepares for outputting a future image, and then transmits the image to the identification module 4; the identification module 4 calls a fast _ rcnn own im _ detect function to detect, the im _ detect function receives two parameters, namely a net object and an image to be identified, and returns two parameters: box and scores, wherein the box is a coordinate of a block diagram used for storing the detection result, and the scores is the confidence coefficient of the detection result; the frame module 5 traverses all categories through the frame coordinate and the confidence coefficient of the detection result obtained by the recognition module 4, frames all categories with confidence coefficient larger than the threshold according to the frame coordinate, marks the categories, and draws and distinguishes the frames with different colors according to the different categories, namely open eyes and closed eyes; the alarm module 6 is used for sending an alarm signal.
In order to further optimize the technical scheme, the alarm module 6 is connected with a buzzer 7, the buzzer 7 gives an alarm when the alarm module 6 outputs a high level, and the buzzer 7 stops giving an alarm when the alarm module 6 outputs a low level.
Examples
Fig. one shows an implementation process of the present invention, after the system is started, the parameter analysis module 1 will read the used network model and related configuration files, complete the preloading of the model, the video acquisition module 2 starts monitoring, the image processing module 3 records the specification information (length, width) of the image, and then transmits it to the identification module 4. The recognition module 4 will return a confidence array and a block coordinates array for the recognized class. After a series of treatments: obtaining confidence score and block coordinates (x) from the confidence array and block coordinates arraymin，ymin，xmax，ymax) And stacking the images according to columns, storing the images into a dets array together, performing non-maximum suppression on the dets array, namely removing all small areas to obtain an identification result, and calling the picture frame module 5 to perform picture frame. Adding 1 to the eye closing frequency statistic every time the eye closing frequency is identified, subtracting 1 from the eye closing frequency statistic every time the eye opening frequency is identified, and not performing the operation of subtracting 1 when the eye closing frequency statistic is 0; when the statistics of the eye closing times is larger than the threshold value, the alarm module 6 sends a high level to the buzzer 7, the buzzer 7 starts to give an alarm, until the statistics of the eye closing times is 0, the alarm module 6 sends a low level to the buzzer 7, and the buzzer 7 stops giving an alarm.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A fatigue driving early warning method based on deep learning is characterized by comprising the following steps:
s1, acquiring an eye image of the driver;
s2, establishing a Faster R-CNN human eye opening and closing detection model;
s3, detecting the eye image of the driver by using Faster R-CNN, and acquiring the coordinates of the block diagram and the confidence of the detection result;
s4, traversing all categories, drawing frames and labeling the categories of which the confidence degrees are greater than the threshold according to the coordinates of the block diagram, and drawing frames with different colors for distinguishing according to different categories;
and S5, outputting the detection type.
2. The fatigue driving early warning method based on deep learning is characterized in that the specific process of the step S2 is as follows:
s21, selecting RPN as a network structure, and performing simulation training through a CEW data set;
s22, labeling the anchor points, wherein the anchor points with the highest intersection ratio overlapping with the Box of the real label or the anchor points with the intersection ratio reaching 0.7 are positive labels, and the anchor points with the intersection ratio lower than 0.3 are negative labels;
s22, training the shared convolution layer and fine-tuning the parameters of the special layer.
3. The fatigue driving early warning method based on deep learning is characterized in that the category is eye opening or eye closing.
4. The fatigue driving early warning method based on deep learning is characterized in that the specific process of detection in the step S3 is as follows: the im _ detect function is used to detect the driver's eye image.
5. A system using the deep learning based fatigue driving warning method according to any one of claims 1 to 4, comprising: the system comprises a parameter analyzing module (1), a video collecting module (2), an image processing module (3), an identification module (4), a picture frame module (5) and an alarm module (6);
the parameter analysis module (1) is used for reading various parameter settings of a program when the program is started, the video acquisition module (2) is used for acquiring videos and transmitting effective videos to the image processing module (3), the image processing module (3) is used for reading and recording the length and the width of an image and generating a zero matrix with the same size, then the image is transmitted to the identification module (4), the identification module (4) uses a trained Fast R-CNN detection network to generate block diagram coordinates of a detection result and confidence degrees of the detection result, the frame module (5) is used for traversing all categories by identifying the block diagram coordinates and the confidence degrees of the detection result, frames and categories of which all the confidence degrees are greater than a threshold are drawn according to the block diagram coordinates and labeled, and frames with different colors are drawn according to different categories to be distinguished, the alarm module (6) is used for sending an alarm signal.
6. The deep learning-based fatigue driving warning system of claim 5, wherein the categories are open eyes and closed eyes.
7. The fatigue driving warning system based on deep learning as claimed in claim 5, wherein a buzzer (7) is connected to the alarm module (6), the buzzer (7) gives an alarm when the alarm module (6) outputs a high level, and the buzzer (7) stops giving an alarm when the alarm module (6) outputs a low level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010053964.8A CN111243236A (en) | 2020-01-17 | 2020-01-17 | Fatigue driving early warning method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010053964.8A CN111243236A (en) | 2020-01-17 | 2020-01-17 | Fatigue driving early warning method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111243236A true CN111243236A (en) | 2020-06-05 |
Family
ID=70879509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010053964.8A Pending CN111243236A (en) | 2020-01-17 | 2020-01-17 | Fatigue driving early warning method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111243236A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198617A (en) * | 2013-03-26 | 2013-07-10 | 无锡商业职业技术学院 | Fatigue driving warning system |
| CN104257392A (en) * | 2014-09-26 | 2015-01-07 | 马天驰 | Fatigue driving detection prompt method and detection prompt device |
| JP2017505733A (en) * | 2014-01-15 | 2017-02-23 | 国防科学技術大学 | Method and apparatus for detecting safe driving state of driver |
| CN107657236A (en) * | 2017-09-29 | 2018-02-02 | 厦门知晓物联技术服务有限公司 | Vehicle security drive method for early warning and vehicle-mounted early warning system |
| CN107766835A (en) * | 2017-11-06 | 2018-03-06 | 贵阳宏益房地产开发有限公司 | traffic safety detection method and device |
| CN109523652A (en) * | 2018-09-29 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | Processing method, device, equipment and the storage medium of insurance based on driving behavior |
| CN109886241A (en) * | 2019-03-05 | 2019-06-14 | 天津工业大学 | Driver fatigue detection based on shot and long term memory network |
| CN110147738A (en) * | 2019-04-29 | 2019-08-20 | 中国人民解放军海军特色医学中心 | A kind of driver fatigue monitoring and pre-alarming method and system |
| TWI669664B (en) * | 2018-09-14 | 2019-08-21 | 大陸商虹軟科技股份有限公司 | Eye state detection system and method for operating an eye state detection system |
| CN110245574A (en) * | 2019-05-21 | 2019-09-17 | 平安科技（深圳）有限公司 | A kind of human fatigue state identification method, device and terminal device |
| CN110428908A (en) * | 2019-07-31 | 2019-11-08 | 广西壮族自治区人民医院 | A kind of eyelid movement functional assessment system based on artificial intelligence |
| CN209719572U (en) * | 2019-03-22 | 2019-12-03 | 中国科学院重庆绿色智能技术研究院 | A kind of fatigue driving control system for identifying |
| JP2019536673A (en) * | 2017-08-10 | 2019-12-19 | ペキン センスタイム テクノロジー ディベロップメント カンパニー リミテッド | Driving state monitoring method and device, driver monitoring system, and vehicle |
-
2020
- 2020-01-17 CN CN202010053964.8A patent/CN111243236A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198617A (en) * | 2013-03-26 | 2013-07-10 | 无锡商业职业技术学院 | Fatigue driving warning system |
| JP2017505733A (en) * | 2014-01-15 | 2017-02-23 | 国防科学技術大学 | Method and apparatus for detecting safe driving state of driver |
| CN104257392A (en) * | 2014-09-26 | 2015-01-07 | 马天驰 | Fatigue driving detection prompt method and detection prompt device |
| JP2019536673A (en) * | 2017-08-10 | 2019-12-19 | ペキン センスタイム テクノロジー ディベロップメント カンパニー リミテッド | Driving state monitoring method and device, driver monitoring system, and vehicle |
| CN107657236A (en) * | 2017-09-29 | 2018-02-02 | 厦门知晓物联技术服务有限公司 | Vehicle security drive method for early warning and vehicle-mounted early warning system |
| CN107766835A (en) * | 2017-11-06 | 2018-03-06 | 贵阳宏益房地产开发有限公司 | traffic safety detection method and device |
| TWI669664B (en) * | 2018-09-14 | 2019-08-21 | 大陸商虹軟科技股份有限公司 | Eye state detection system and method for operating an eye state detection system |
| CN109523652A (en) * | 2018-09-29 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | Processing method, device, equipment and the storage medium of insurance based on driving behavior |
| CN109886241A (en) * | 2019-03-05 | 2019-06-14 | 天津工业大学 | Driver fatigue detection based on shot and long term memory network |
| CN209719572U (en) * | 2019-03-22 | 2019-12-03 | 中国科学院重庆绿色智能技术研究院 | A kind of fatigue driving control system for identifying |
| CN110147738A (en) * | 2019-04-29 | 2019-08-20 | 中国人民解放军海军特色医学中心 | A kind of driver fatigue monitoring and pre-alarming method and system |
| CN110245574A (en) * | 2019-05-21 | 2019-09-17 | 平安科技（深圳）有限公司 | A kind of human fatigue state identification method, device and terminal device |
| CN110428908A (en) * | 2019-07-31 | 2019-11-08 | 广西壮族自治区人民医院 | A kind of eyelid movement functional assessment system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101593425B (en) | Machine vision based fatigue driving monitoring method and system | |
| US11783601B2 (en) | Driver fatigue detection method and system based on combining a pseudo-3D convolutional neural network and an attention mechanism | |
| CN101639894B (en) | Method for detecting train driver behavior and fatigue state on line and detection system thereof | |
| Hossain et al. | IOT based real-time drowsy driving detection system for the prevention of road accidents | |
| WO2020078465A1 (en) | Method and device for driving state analysis, driver monitoring system and vehicle | |
| CN102263937B (en) | Driver's driving behavior monitoring device and monitoring method based on video detection | |
| Gupta et al. | Implementation of motorist weariness detection system using a conventional object recognition technique | |
| CN105788176A (en) | Fatigue driving monitoring and prompting method and system | |
| CN107563346A (en) | One kind realizes that driver fatigue sentences method for distinguishing based on eye image processing | |
| CN110588512A (en) | Dangerous driving identification and early warning device, method and system | |
| CN103247150A (en) | Fatigue driving preventing system | |
| Mašanović et al. | Driver monitoring using the in-vehicle camera | |
| Kannan et al. | Driver drowsiness detection and alert system | |
| CN112401857A (en) | Driver drunk driving detection method | |
| CN111243236A (en) | Fatigue driving early warning method and system based on deep learning | |
| Su et al. | A simple approach to implementing a system for monitoring driver inattention | |
| CN113901866A (en) | Fatigue driving early warning method based on machine vision | |
| Apoorva et al. | Review on Drowsiness Detection | |
| Kawtikwar et al. | Eyes on the road: a machine learning-based fatigue detection system for safer driving | |
| CN202177912U (en) | Driver driving behavior monitoring device based on video detection | |
| Vinoth et al. | A drowsiness detection using smart sensors during driving and smart message alert system to avoid accidents | |
| CN114998874A (en) | Driver abnormal behavior detection method based on deep learning | |
| Priya et al. | Machine Learning-Based System for Detecting and Tracking Driver Drowsiness | |
| CN114529887A (en) | Driving behavior analysis method and device | |
| Tejashwini et al. | Drowsy Driving Detection System–IoT Perspective |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |
|
| RJ01 | Rejection of invention patent application after publication |