CN111784973B - MDVR equipment integration fatigue detection method of fleet management platform - Google Patents
MDVR equipment integration fatigue detection method of fleet management platform Download PDFInfo
- Publication number
- CN111784973B CN111784973B CN202010749726.0A CN202010749726A CN111784973B CN 111784973 B CN111784973 B CN 111784973B CN 202010749726 A CN202010749726 A CN 202010749726A CN 111784973 B CN111784973 B CN 111784973B
- Authority
- CN
- China
- Prior art keywords
- eye
- time
- threshold
- accumulated time
- closing
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 28
- 230000010354 integration Effects 0.000 title claims abstract description 6
- 230000001186 cumulative effect Effects 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000009825 accumulation Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 7
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004399 eye closure Effects 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 208000013433 lightheadedness Diseases 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 235000015096 spirit Nutrition 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- 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
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Life Sciences & Earth Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
- Time Recorders, Dirve Recorders, Access Control (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses an MDVR equipment integration fatigue detection method of a fleet management platform, when the real-time movement speed of a vehicle exceeds a movement speed threshold, eye opening detection is carried out, temporary eye closing accumulated time is counted according to the fact that the eye opening of two continuous frames of eyes is smaller than an eye opening threshold, and when the temporary eye closing accumulated time exceeds a certain threshold, the temporary eye closing accumulated time is counted, and continuous intermittent misjudgment caused by a bad optical environment is reduced; detecting that the cumulative eye opening time of the human eyes exceeds an eye opening time threshold, the human face recognition human face rotation angle and the shaking amplitude are too large, and clearing the cumulative eye closing time, wherein the cumulative eye opening time needs to be accumulated in a continuous time period, and otherwise, the cumulative eye opening time is cleared, so that the probability of clearing the cumulative eye closing time by mistake is extremely low; the target driver is judged to be in a fatigue state only when the eye closing accumulated time exceeds the eye closing accumulated time threshold, so that the number of wrong alarms is greatly reduced.
Description
Technical Field
The invention relates to the field of driving safety, in particular to a detection method for detecting driver fatigue by using MDVR (vehicle-mounted hard disk video recorder) equipment of a fleet management platform in driving.
Background
Traffic accidents have always been one of the most serious threats to the security of lives and properties faced by mankind, and most of them occur due to human factors of drivers. In the driving process of a vehicle, fatigue of a driver is one of important reasons for causing a malignant traffic accident, and the traffic safety is seriously damaged. The long-distance automobile driver has the phenomena of frequent beating, deep eyelid, inattention, vague nerves, light-headedness, slow response and the like when driving under a single road condition for a long time due to overlong continuous driving time.
In order to reduce the mental stress of drivers and prompt and early warn fatigue in time, the fatigue detection is carried out on the drivers, and meanwhile, the drivers are reminded, so that traffic accidents can be prevented and reduced to a great extent, and the traveling of citizens is safer. On the market, vehicle-mounted auxiliary equipment for fatigue driving detection mainly detects whether two eyes of a driver are closed or not by means of camera optics, so that whether the driver is in transition fatigue or not is detected. When the eyes of the driver are closed or the driver dozes off, the alarm reminds the driver of getting spirits and paying attention to danger. However, the device is used as a driving auxiliary device, and in order to remind a driver to avoid risks, the principle that more reports are preferred and the reports cannot be missed is adopted for the driving state judgment mode of the driver, so that a large amount of error alarm information can be generated.
Meanwhile, based on similar functions, in order to supervise the behavior of the driver, the fatigue state of the driver of the whole fleet is comprehensively analyzed and managed, the driver is prevented from driving the vehicle in the fatigue state, and the function can be loaded by the vehicle-mounted hard disk video recording equipment based on the Internet of vehicles. Through the camera, the fatigue state of inspection driver, under the tired condition of driver, video section is taken out, as the evidence, uploads to the high in the clouds, makes things convenient for motorcade management layer to know driver's fatigue state to implement the management. In such a working mode, if a strategy like "rather misreporting and unreported" is still adopted, a large amount of invalid videos may be uploaded, which brings great troubles to fleet management based on the function and related managers, and in fact, secondary screening of the uploaded videos is required manually. The excessive trouble and the ineffective video can lead to the management layer being careless, the long-term fright to the driver and the fatigue driving behavior is lacked, and finally the whole system is completely ineffective.
Disclosure of Invention
The invention provides a detection method for detecting driver fatigue by MDVR equipment of a fleet management platform, which judges the driving state of a driver on the basis of detecting the eye opening degree of human eyes through deep learning and reduces false alarm triggering of the fatigue state of the driver, so that the usability of related functions of the MDVR after being accessed to the fleet management platform is improved.
The invention relates to an MDVR equipment integration fatigue detection method of a fleet management platform, which comprises the following steps:
s1, presetting a motion speed threshold of the vehicle, obtaining the real-time motion speed of the vehicle through GPS positioning of the vehicle, and detecting the opening degree of human eyes after the real-time motion speed of the vehicle reaches the motion speed threshold;
s2, acquiring a face video of the target driver, carrying out eye opening detection on each frame of picture in a continuous section of video, and calculating an eye opening threshold value of human eyes;
s3, comparing the eye opening of each frame of picture with an open eye threshold, if the eye opening of two continuous frames of pictures is smaller than the open eye threshold, counting the time interval of the two frames of pictures into temporary closed eye accumulated time, and if the eye opening of the picture is larger than the open eye threshold, resetting the temporary closed eye accumulated time;
s4, if the temporary eye-closing accumulated time exceeds a certain threshold value, the temporary eye-closing accumulated time in the period of time is counted into the eye-closing accumulated time, and meanwhile, the temporary eye-closing accumulated time is cleared;
s5, if the change of the center position of the face is detected to be too large or the change of the rotation angle of the face is detected to be too large within a period of time, no time accumulation is carried out, and the eye closing accumulated time and the temporary eye closing accumulated time are cleared;
s6, presetting an eye opening time threshold, detecting the eye opening time of the human eyes in real time, calculating the eye opening accumulated time, clearing the eye opening accumulated time if the eyes are closed in the eye opening process, and clearing the eye closing accumulated time and the temporary eye closing accumulated time if the eye opening accumulated time exceeds the eye opening time threshold;
and S7, presetting an eye closing accumulated time threshold, and if the eye closing accumulated time is not cleared for a long time and is greater than the eye closing accumulated time threshold, judging that the target driver is in a fatigue state.
According to the MDVR equipment integration fatigue detection method of the fleet management platform, the eye opening degree is detected only when the real-time movement speed of the vehicle exceeds the movement speed threshold value, and the uploaded ineffective videos can be greatly reduced; the temporary eye closing accumulated time is counted according to the condition that the eye opening of the human eyes of two continuous frames is smaller than an open eye threshold value, and the eye closing accumulated time is counted only when the temporary eye closing accumulated time exceeds a certain threshold value, so that the continuous intermittent misjudgment accumulated eye closing accumulated time caused by a poor optical environment is reduced; if the situation that the accumulated eye-opening time of the human eyes exceeds the eye-opening time threshold value, the human face recognition human face rotation angle and the shaking amplitude are too large is detected, all time accumulation is stopped, and the eye-closing accumulated time is cleared, the eye-opening accumulated time needs to be cleared, the eye-closing situation cannot occur in a continuous time period, otherwise, the eye-opening accumulated time is cleared, and the possibility of mistakenly clearing the eye-closing accumulated time is extremely low; the target driver is judged to be in a fatigue state only when the eye closing accumulated time exceeds the eye closing accumulated time threshold; the accumulated eye closing time is accumulated once only when the accumulated temporary eye closing time exceeds a certain value (for example, one second), and if the eye opening is detected before the accumulated temporary eye closing time, the accumulated temporary eye closing time is cleared; therefore, the probability of false alarm is extremely low, the accuracy of the fatigue detection result is improved, the number of false alarms is greatly reduced, and the invalid video clips uploaded to the cloud server are reduced. The function of intercepting fatigue-related videos and uploading the videos to a management department does not need to inform a driver, and the function of connecting with a driving assistance-related function is also not needed, so that the missed report of fatigue events with a small probability to a certain extent can be accepted.
Drawings
Fig. 1 is a block diagram of steps of an MDVR device integrated fatigue detection method for a fleet management platform.
Detailed Description
As shown in fig. 1, a method for detecting integrated fatigue of MDVR devices of a fleet management platform includes the following steps:
s1, presetting a motion speed threshold of the vehicle, obtaining the real-time motion speed of the vehicle through GPS positioning of the vehicle, and detecting the opening degree of human eyes after the real-time motion speed of the vehicle reaches the motion speed threshold; if the speed target threshold value is not reached, or no GPS satellite signal exists, or the positioning accuracy is not enough, zero clearing is not carried out, and all time carried out before zero clearing is accumulated;
s2, acquiring a face video of the target driver, carrying out eye opening detection on each frame of picture in a continuous section of video, and calculating an eye opening threshold value of human eyes;
s3, comparing the eye opening of each frame of picture with an open eye threshold, if the eye opening of two continuous frames of pictures is smaller than the open eye threshold, counting the time interval of the two frames of pictures into temporary closed eye accumulated time, and if the eye opening of the picture is larger than the open eye threshold, resetting the temporary closed eye accumulated time;
s4, if the temporary eye-closing accumulated time exceeds a certain threshold value, the temporary eye-closing accumulated time in the period of time is counted into the eye-closing accumulated time, and meanwhile, the temporary eye-closing accumulated time is cleared;
s5, if the change of the center position of the face is detected to be too large or the change of the rotation angle of the face is detected to be too large within a period of time, no time accumulation is carried out, and the eye closing accumulated time and the temporary eye closing accumulated time are cleared;
s6, presetting an eye opening time threshold, detecting the eye opening time of the human eyes in real time, calculating the eye opening accumulated time, clearing the eye opening accumulated time if the eyes are closed in the eye opening process, and clearing the eye closing accumulated time and the temporary eye closing accumulated time if the eye opening accumulated time exceeds the eye opening time threshold;
and S7, presetting an eye closing accumulated time threshold, and if the eye closing accumulated time is not cleared for a long time and is greater than the eye closing accumulated time threshold, judging that the target driver is in a fatigue state.
The MDVR equipment integrated fatigue detection method of the fleet management platform can use vehicle-mounted MDVR equipment as terminal equipment of a vehicle networking fleet management system, is used for being installed on various operation vehicles and capturing and recording face related information of various images, and when the MDVR equipment detects that an abnormal event occurs, the MDVR equipment reports warning information to a server and uploads related videos as evidences. When the precision and the coordinates of the current positioning information fed back by the GPS and the real-time moving speed of the vehicle exist and are accurate, and when the vehicle moves to a certain speed, it is necessary to judge whether the target driver is tired to drive.
The degree of openness of human eyes can be obtained by a human eye characteristic point picking technology. Specifically, the human face feature point positioning based on the cascaded convolutional neural network can be used for acquiring the height and the length of the human eyes through the feature points, and the opening threshold value is equal to the eye height divided by the eye length, namely, the ratio of the height to the width is used as the opening of the human eyes.
In step S1, the eye opening detection is performed only when the real-time moving speed of the vehicle exceeds the moving speed threshold, and if the GPS signal is lost or the speed is less than the threshold (e.g., 5 km/h), the accumulation is not performed, and the original accumulated data is cleared. The phenomenon that the normal rest behavior of a driver is intercepted and uploaded by mistake can be greatly prevented when the vehicle is in a parking state. This feature can substantially reduce uploading of ineffective video.
In the steps S3 and S4, the temporary eye-closing accumulated time is counted according to the fact that the eye opening size of the eyes of two consecutive frames is smaller than the opening threshold, and the temporary eye-closing accumulated time is counted only when the temporary eye-closing accumulated time exceeds a certain threshold, if the eyes are opened halfway (that is, the opening size is larger than the threshold), the related temporary eye-closing time count is cleared, so that the continuous intermittent false judgment caused by the poor optical environment is greatly reduced.
The threshold for opening mentioned in step S3 may be preset, or may be dynamically adjusted according to the size of the driver' S eyes and the installation situation. The concrete mode is as follows:
if the driver does not actively move to a large extent within a period of time (the method is described in s 5), and the driving speeds of the cars fed back by the GPS are all higher than a certain threshold (for example, 5 km/h), and the detected value of the effective degree of openness exceeds a certain proportion (for example, 80%), the effective degree of openness is averaged and multiplied by a certain proportion (for example, 40%) to serve as the threshold of the degree of openness.
In order to exclude some abnormal detection results of the detection algorithm, we set the aspect ratio of the eye corresponding to the effective opening degree value, and must satisfy a certain condition (for example, the aspect ratio must be greater than 10%, below this threshold, it can be basically considered that the human eye is closed, and such a value cannot be added into the cumulative averaging).
If the preset open degree threshold value is not used, the subsequent calculation is carried out after the dynamic open degree threshold value is solved, otherwise, no threshold value is used for comparison.
The main objective of the features proposed in the steps S5 and S6 is to confirm that the driver is in a non-fatigue state with a high probability, and further reduce the triggering of false alarm of fatigue detection.
The step S5 requires that the face of the target driver must be in a stable state when performing the fatigue triggering. The large-amplitude movement and the large-amplitude rotation do not occur, and the loss can not occur. And if the face is not detected by the detection equipment, clearing the eye closing accumulated time.
In the concrete implementation, if the face of the driver is in the condition of large-amplitude movement and large-amplitude rotation, the driver is shown to actively act, and the visitor shows that the driver is not fatigued. On the other hand, if the driver moves in the picture, an error may occur in the detection of the size of the eyes due to motion blur.
More specifically, when the size of the target human eye is detected, the coordinates of the human face region are obtained at the same time, and the movement condition of the human face region is checked by taking the center of the region coordinates as the center. And checking the change condition of the human face size according to the size of the human face area. In practical use, the distance between two farthest central points in the whole time range of detection (for example, within one second) can be used as the movement displacement of the central points. The maximum face width and length in the whole time range can be used as the threshold. In other words, if the relative displacement of the center point is greater than the length of the largest face in the Y-axis direction, or greater than the length of the smallest face in the X-axis direction, the driver is considered to be actively moving greatly.
More specifically, we can also use an analysis method based on deep learning to calculate the angle of the face relative to the camera, and if the angle change is too large in a certain time range (for example, within one second), and exceeds a certain preset threshold, for example, 30 degrees, it is considered that the face is rotating violently, and it is considered that the driver is actively moving greatly.
According to the two condition analyses, if the driver is detected to actively move to a large extent, the detection of the face of the driver or the driver is considered to be in an unstable state.
In specific work, if a driver is in an unstable state, all original time counts related to eye closure are cleared. And we start the relevant detection only if the driver's face is stable for more than a period of time (say one second).
In step S6, the accumulation of the eye-open time requires that the eye-closing cannot occur in a continuous time period, and otherwise, the eye-open time is cleared, so that the possibility of erroneously clearing the eye-closing time is extremely low.
In the step S7, since the eye-closing accumulated time exceeds the eye-closing accumulated time threshold, it is determined that the target driver is in a fatigue state, and since the time accumulated value is very easy to be cleared in a non-fatigue state due to the multiple time clearing manners included in the steps S5 and S6, the probability of false alarm is very low, the accuracy of the fatigue detection result is improved, the number of false alarms is greatly reduced, and the number of invalid video clips uploaded to the cloud server is reduced.
Claims (4)
1. An MDVR equipment integration fatigue detection method of a fleet management platform is characterized by comprising the following steps:
s1, presetting a motion speed threshold of the vehicle, obtaining the real-time motion speed of the vehicle through GPS positioning of the vehicle, and detecting the opening degree of human eyes after the real-time motion speed of the vehicle reaches the motion speed threshold;
s2, acquiring a face video of the target driver, carrying out eye opening detection on each frame of picture in a continuous section of video, and calculating an eye opening threshold value of human eyes;
s3, comparing the eye opening of each frame of picture with an open eye threshold, if the eye opening of two continuous frames of pictures is smaller than the open eye threshold, counting the time interval of the two frames of pictures into temporary closed eye accumulated time, and if the eye opening of the picture is larger than the open eye threshold, resetting the temporary closed eye accumulated time;
s4, if the temporary eye-closing accumulated time exceeds a certain threshold value, the temporary eye-closing accumulated time in the period of time is counted into the eye-closing accumulated time, and meanwhile, the temporary eye-closing accumulated time is cleared;
s5, if the change of the center position of the face is detected to be too large or the change of the rotation angle of the face is detected to be too large within a period of time, no time accumulation is carried out, and the eye closing accumulated time and the temporary eye closing accumulated time are cleared;
s6, presetting an eye opening time threshold, detecting the eye opening time of the human eyes in real time, calculating the eye opening accumulated time, clearing the eye opening accumulated time if the eyes are closed in the eye opening process, and clearing the eye closing accumulated time and the temporary eye closing accumulated time if the eye opening accumulated time exceeds the eye opening time threshold;
and S7, presetting an eye closing accumulated time threshold, and if the eye closing accumulated time is not cleared for a long time and is greater than the eye closing accumulated time threshold, judging that the target driver is in a fatigue state.
2. The method of claim 1, wherein if the detection device does not detect a human face, clearing the cumulative closed-eye time and clearing the cumulative temporary closed-eye time.
3. The method of claim 1, wherein the eye opening threshold of the human eye is updated in real time, and the average value of the eye opening of the human eye in each period of time multiplied by a certain percentage is counted as the eye opening threshold.
4. The method of claim 3, wherein the calculation of the open eye threshold is performed only when the real-time speed of the vehicle exceeds the motion speed threshold and a human face is detected, the open eye threshold fails if the open eye threshold is not updated for a long time, and no accumulated time is performed during the period of the open eye threshold failure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010749726.0A CN111784973B (en) | 2020-07-30 | 2020-07-30 | MDVR equipment integration fatigue detection method of fleet management platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010749726.0A CN111784973B (en) | 2020-07-30 | 2020-07-30 | MDVR equipment integration fatigue detection method of fleet management platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111784973A CN111784973A (en) | 2020-10-16 |
| CN111784973B true CN111784973B (en) | 2021-12-14 |
Family
ID=72766973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010749726.0A Active CN111784973B (en) | 2020-07-30 | 2020-07-30 | MDVR equipment integration fatigue detection method of fleet management platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111784973B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112842861A (en) * | 2020-12-23 | 2021-05-28 | 复旦大学 | Brain-computer interface rehabilitation training method based on multi-sensory stimulation motion feedback |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1458006A (en) * | 2003-07-02 | 2003-11-26 | 北京交通大学 | Method for detecting fatigue driving based on multiple characteristic fusion |
| CN102149326A (en) * | 2008-09-16 | 2011-08-10 | 爱信精机株式会社 | Drowsiness determining device and program |
| CN103020594A (en) * | 2012-12-03 | 2013-04-03 | 清华大学苏州汽车研究院（吴江） | Fatigue state detecting method for eliminating driver individual difference by utilizing online learning |
| CN107292251A (en) * | 2017-06-09 | 2017-10-24 | 湖北天业云商网络科技有限公司 | A kind of Driver Fatigue Detection and system based on human eye state |
| CN107303907A (en) * | 2016-04-21 | 2017-10-31 | 现代自动车株式会社 | For the apparatus and method for the sleepiness for determining driver |
| CN109522820A (en) * | 2018-10-29 | 2019-03-26 | 江西科技学院 | A kind of fatigue monitoring method, system, readable storage medium storing program for executing and mobile terminal |
| CN110059599A (en) * | 2019-04-08 | 2019-07-26 | 盐城工学院 | Driving fatigue method for early warning |
| CN110309760A (en) * | 2019-06-26 | 2019-10-08 | 深圳市微纳集成电路与***应用研究院 | The method that the driving behavior of driver is detected |
| CN110901385A (en) * | 2019-12-31 | 2020-03-24 | 南斗六星***集成有限公司 | Active speed limiting method based on fatigue state of driver |
| CN111191573A (en) * | 2019-12-27 | 2020-05-22 | 中国电子科技集团公司第十五研究所 | Driver fatigue detection method based on blink rule recognition |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101692980B (en) * | 2009-10-30 | 2011-06-08 | 深圳市汉华安道科技有限责任公司 | Method and device for detecting fatigue driving |
-
2020
- 2020-07-30 CN CN202010749726.0A patent/CN111784973B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1458006A (en) * | 2003-07-02 | 2003-11-26 | 北京交通大学 | Method for detecting fatigue driving based on multiple characteristic fusion |
| CN102149326A (en) * | 2008-09-16 | 2011-08-10 | 爱信精机株式会社 | Drowsiness determining device and program |
| CN103020594A (en) * | 2012-12-03 | 2013-04-03 | 清华大学苏州汽车研究院（吴江） | Fatigue state detecting method for eliminating driver individual difference by utilizing online learning |
| CN107303907A (en) * | 2016-04-21 | 2017-10-31 | 现代自动车株式会社 | For the apparatus and method for the sleepiness for determining driver |
| CN107292251A (en) * | 2017-06-09 | 2017-10-24 | 湖北天业云商网络科技有限公司 | A kind of Driver Fatigue Detection and system based on human eye state |
| CN109522820A (en) * | 2018-10-29 | 2019-03-26 | 江西科技学院 | A kind of fatigue monitoring method, system, readable storage medium storing program for executing and mobile terminal |
| CN110059599A (en) * | 2019-04-08 | 2019-07-26 | 盐城工学院 | Driving fatigue method for early warning |
| CN110309760A (en) * | 2019-06-26 | 2019-10-08 | 深圳市微纳集成电路与***应用研究院 | The method that the driving behavior of driver is detected |
| CN111191573A (en) * | 2019-12-27 | 2020-05-22 | 中国电子科技集团公司第十五研究所 | Driver fatigue detection method based on blink rule recognition |
| CN110901385A (en) * | 2019-12-31 | 2020-03-24 | 南斗六星***集成有限公司 | Active speed limiting method based on fatigue state of driver |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111784973A (en) | 2020-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101867041B1 (en) | Method and device for detecting safe driving state of driver | |
| US11661075B2 (en) | Inward/outward vehicle monitoring for remote reporting and in-cab warning enhancements | |
| CN112389448B (en) | Abnormal driving behavior identification method based on vehicle state and driver state | |
| CN110997387B (en) | Risk handling for vehicles with autonomous driving capability | |
| KR101095528B1 (en) | An outomatic sensing system for traffic accident and method thereof | |
| CA2925843C (en) | System for traffic behaviour surveillance | |
| CN113256924A (en) | Monitoring system, monitoring method and monitoring device for rail train | |
| CN113676702B (en) | Video stream-based target tracking and monitoring method, system, device and storage medium | |
| CN111046797A (en) | Oil pipeline warning method based on personnel and vehicle behavior analysis | |
| CN110796862B (en) | Highway traffic condition detection system and method based on artificial intelligence | |
| CN104318769A (en) | Violation vehicle monitoring and alarming system and method | |
| CN114360210A (en) | Vehicle fatigue driving early warning system | |
| CN111784973B (en) | MDVR equipment integration fatigue detection method of fleet management platform | |
| CN111564020A (en) | Driving safety prevention and control system, storage medium and computer equipment | |
| CN111241918B (en) | Vehicle tracking prevention method and system based on face recognition | |
| CN116913099A (en) | Intelligent traffic real-time monitoring system | |
| EP3269608B1 (en) | Detection of tailgating situations | |
| CN108921969A (en) | Information storage system and its application | |
| CN104636723B (en) | Driving method for early warning based on certain objects image analysing computer in video image | |
| CN111216699A (en) | Visual automobile intelligent automatic emergency braking control method and system | |
| Tsai et al. | A safety driving assistance system by integrating in-vehicle dynamics and real-time traffic information | |
| CN110287838A (en) | A kind of monitoring method and system for driving to play mobile phone behavior | |
| CN112863189B (en) | Behavior identification method and device for preventing overtaking and electronic equipment | |
| CN117995021B (en) | Vehicle safety early warning method and system based on multi-source data fusion algorithm | |
| US20240005783A1 (en) | Driver assistance system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An Integrated Fatigue Detection Method for MDVR Devices on a Fleet Management Platform Effective date of registration: 20230314 Granted publication date: 20211214 Pledgee: Bank of China Limited by Share Ltd. Guangzhou Tianhe branch Pledgor: SHARPVISION CO.,LTD. Registration number: Y2023980034821 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 101, Building 6, No.1 Ruihua Road, Tianhe District, Guangzhou, Guangdong 510660 Patentee after: SHARPVISION CO.,LTD. Address before: 510660 the fifth floor of No.3 in Huangzhou Industrial Park, chebei Road, Tianhe District, Guangzhou City, Guangdong Province Patentee before: SHARPVISION CO.,LTD. |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Granted publication date: 20211214 Pledgee: Bank of China Limited by Share Ltd. Guangzhou Tianhe branch Pledgor: SHARPVISION CO.,LTD. Registration number: Y2023980034821 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A fatigue detection method for MDVR equipment integration in a fleet management platform Granted publication date: 20211214 Pledgee: Bank of China Limited by Share Ltd. Guangzhou Tianhe branch Pledgor: SHARPVISION CO.,LTD. Registration number: Y2024980012293 |