CN109190600A - A kind of driver's monitoring system of view-based access control model sensor - Google Patents
A kind of driver's monitoring system of view-based access control model sensor Download PDFInfo
- Publication number
- CN109190600A CN109190600A CN201811215095.3A CN201811215095A CN109190600A CN 109190600 A CN109190600 A CN 109190600A CN 201811215095 A CN201811215095 A CN 201811215095A CN 109190600 A CN109190600 A CN 109190600A
- Authority
- CN
- China
- Prior art keywords
- image
- driver
- module
- head module
- alert levels
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 68
- 230000000712 assembly Effects 0.000 claims abstract description 4
- 238000000429 assembly Methods 0.000 claims abstract description 4
- 210000003128 head Anatomy 0.000 claims description 58
- 238000001514 detection method Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 5
- 206010048232 Yawning Diseases 0.000 claims description 4
- 239000000779 smoke Substances 0.000 claims description 2
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 210000000744 eyelid Anatomy 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 210000001747 pupil Anatomy 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- 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
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
This application involves a kind of driver's monitoring systems of view-based access control model sensor, belong to field of computer technology, which includes: the first image that infrared photography head module is used to acquire driver；Visible image capturing head module is used to acquire the second image of driver；Monitoring controller is used to determine PERCLOS according to the first image；Second image is pre-processed；Pretreated second image input disaggregated model is obtained into classification results, which is used to indicate whether driver in a state of fatigue and/or state of diverting attention；Alert levels are determined according to PERCLOS and classification results；Alarm module is used to control corresponding alarm assemblies according to alert levels and alarm；It can solve the problem of existing driver's monitoring system can not detect the state of diverting attention of driver；The comprehensive of driver's monitoring system monitoring driver's driving condition can be improved, to improve drive safety.
Description
Technical field
The present invention relates to a kind of driver's monitoring systems of view-based access control model sensor, belong to field of computer technology.
Background technique
With the fast development of China's economic society and the continuous improvement of living standards of the people, the car ownership in China is in
The situation of existing rapid growth.With increasing for car ownership, traffic accident amount is consequently increased.
The reason of causing traffic accident is varied, excludes the immutable factor such as weather and condition of road surface, most of former
Because all related with driver itself.Two most important the reason is that diverting attention and fatigue driving, and therefore, it is necessary to the behaviors to driver
It is monitored with state, alerting drivers even drive function adapter tube with auxiliary when necessary, to effectively prevent traffic accident
Occur.
Driver's monitoring system of mainstream generally uses visual sensor at present, is concentrated mainly on driver fatigue detection side
Face.One infrared camera of installation acquires driver's Front facial image generally in vehicle drive room, then gives fatigue detection device
Processing.
However, driver's monitoring system only concentrates on driver fatigue context of detection, and system for distraction of driver is also to cause to hand over
Therefore the major reason of interpreter's event realizes that it is urgently to be resolved for carrying out detection to system for distraction of driver by driver's monitoring system
Problem.
Summary of the invention
The purpose of the present invention is to provide a kind of technical solutions of driver's monitoring system of view-based access control model sensor.For up to
To above-mentioned purpose, the invention provides the following technical scheme: the system comprises: infrared photography head module, visible image capturing head mould
Block, monitoring controller and alarm module, the infrared photography head module, the visible image capturing head module and the alarm module
It is communicated to connect between the monitoring controller respectively；
The infrared photography head module, for acquiring the first image of driver；The first image is sent to described
Monitoring controller；
The visible image capturing head module, for acquiring the second image of the driver；Second image is sent
To the monitoring controller；
The monitoring controller, for obtaining the first image and second image；It is true according to the first image
Time PERCLOS shared by eyes closed certain proportion in fixed driver's unit time；Second image is carried out pre-
Processing；Pretreated second image input disaggregated model is obtained into classification results, the classification results are used to indicate described drive
Whether the person of sailing in a state of fatigue and/or state of diverting attention；Alert levels are determined according to the PERCLOS and the classification results；
The alarm module, for obtaining the alert levels；Corresponding alarm assemblies are controlled according to the alert levels
It alarms.
Optionally, the fatigue state includes: at least one of to yawn and nod.
The state of diverting attention includes: at least one of to make a phone call, see the mobile phone, smoke and glance right and left.
Optionally, it includes advanced simplifying finger that the monitoring controller, which uses multi-core heterogeneous system grade chip SoC, the SoC,
Enable collection machine ARM core, the first digital signal processor DSP core and the second DSP core；
First DSP core, tracks for the sight to the driver, and executes described according to first figure
As the step of determining the PERCLOS；
Second DSP core described pre-processes second image for executing；By pretreated second figure
The step of obtaining classification results as input disaggregated model, the disaggregated model are convolutional neural networks CNN model；
The ARM core, for executing the step for determining alert levels according to the PERCLOS and the classification results
Suddenly.
Optionally, the alert levels include slight, moderate and severe；The alarm module respectively with instrument board, loudspeaking
Device is connected with seat vibration device；The alarm module, is used for:
When the alert levels are slight, it is bright and trigger loudspeaker output first to trigger the instrument board indicator light
The sound of duration warns；
When the alert levels are moderate, the sound for triggering the second duration of the loudspeaker output is warned and is triggered described
Seat vibration device carries out the seat vibration of third duration, and second duration is greater than first duration；
When the alert levels are severe, trigger the loudspeaker output sound and warn and trigger the seat vibration device
Seat vibration is carried out, until stopping when the monitoring trigger subsequent detection goes out alert levels reduction.
Optionally, the infrared photography head module and the visible image capturing head module are adopted with identical Image Acquisition frame per second
Collect image, described image acquisition frame rate is determined according to the image-capable of the monitoring controller.
Optionally, the infrared photography head module is connected with near-infrared luminous diode (LED) module, the near-infrared LED
Module is used for:
Receive the synchronous switch control signal of the infrared photography head module；
Signal is controlled according to the synchronous switch to control described in LED light transmitting near infrared light by LED drive circuit
Driver；Alternatively, controlling LED light by LED drive circuit stops transmitting near infrared light.
Optionally, the infrared photography head module and the near-infrared LED module are installed on instrument board in the vehicle
Top.
Optionally, the visible image capturing head module is installed on the left side A column or position of rear view mirror of the vehicle.
Optionally, the monitoring controller is installed on the cockpit front of the vehicle.
Optionally, the infrared photography head module and the visible image capturing head module pass through cable and the monitoring respectively
Controller is connected.
The beneficial effects of the present invention are: by the way that two image capture modules, i.e. infrared photography head module and visible are arranged
Light video camera head module acquires the image of driver respectively；Two images are analyzed respectively by monitoring controller, determination is driven
Whether the person of sailing in a state of fatigue and/or state of diverting attention；Can solve existing driver's monitoring system can not be to driver's
The problem of state of diverting attention is detected；The comprehensive of driver's monitoring system monitoring driver's driving condition can be improved, thus
Improve drive safety.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention and the accompanying drawings.
Detailed description of the invention
Fig. 1 is that a kind of structure of the driver's monitoring system for view-based access control model sensor that the application one embodiment provides is shown
It is intended to.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Fig. 1 is that a kind of structure of the driver's monitoring system for view-based access control model sensor that the application one embodiment provides is shown
It is intended to, as shown in Figure 1, the system is in vehicle, which to be included at least: infrared photography head module 110, visible image capturing head
Module 120, monitoring controller 130 and alarm module 140.
Wherein, infrared photography head module 110, visible image capturing head module 120 and alarm module 140 are controlled with monitoring respectively
It is communicated to connect between device 130.Optionally, infrared photography head module 110 and visible image capturing head module 120 respectively by cable with
Monitoring controller 130 is connected.Alarm module 140 can be connected by cable with monitoring controller 130；Alternatively, can also pass through
Interface is connected with monitoring controller 130；Alternatively, can also wirelessly be connected with monitoring controller 130, the application is not right
Infrared photography head module 110, visible image capturing head module 120 and alarm module 140 communicate between monitoring controller 130 respectively
The mode of connection limits.
Infrared photography head module 110, for acquiring the first image of driver；First image is sent to monitoring control
Device.Optionally, the first image can be the front head image of driver.
Optionally, infrared photography head module 110 is also connected with near-infrared luminous diode (Light Emitting
Diode, LED) module 150.Pass through wired or wireless side between infrared photography head module 110 and near-infrared LED module 150
Formula is connected, and the present embodiment does not limit the connection type between infrared photography head module 110 and near-infrared LED module 150.
Optionally, near-infrared LED module 150, is used for: the synchronous switch for receiving infrared photography head module 110 controls signal；
Signal is controlled according to synchronous switch, and LED light transmitting near infrared light driver is controlled by LED drive circuit；Alternatively, passing through
LED drive circuit controls LED light and stops transmitting near infrared light.
Optionally, infrared photography head module 110 and near-infrared LED module are installed on the top of instrument board in vehicle.
Visible image capturing head module 120, for acquiring the second image of driver；Second image is sent to monitoring control
Device.Second image is different from the first image, and the second image can be driver front upper part of the body image.
Optionally, infrared photography head module 110 and visible image capturing head module 120 are acquired with identical Image Acquisition frame per second
Image.Image Acquisition frame per second is determined according to the image-capable of monitoring controller.Such as: Image Acquisition frame per second is per second 10
Frame.Visible image capturing head module 120 is installed on the left side A column or position of rear view mirror of vehicle.Wherein, A column in left side refers to front
Pillar between wind glass and left front car door.
Monitoring controller 130, for obtaining the first image and the second image；When determining driver's unit according to the first image
Time shared by interior eyes closed certain proportion (Percentage of Eyelid Closure over the Pupil,
Over Time, PERCLOS)；Second image is pre-processed；Pretreated second image input disaggregated model is obtained
Classification results；Alert levels are determined according to PERCLOS and classification results.Wherein, classification results are used to indicate whether driver locates
In fatigue state and/or state of diverting attention.
The calculation of PERCLOS refers to following formula:
PERCLOS=eyes closed frame number/detection time section totalframes * 100%
Optionally, monitoring controller 130 detects eyelid by image recognition algorithm and covers whether the area of pupil is more than pre-
If threshold value；If being more than the eyes closed that preset threshold is driver.Preset threshold can be 70%, 80%, 90% etc., this reality
Example is applied not limit the value of preset threshold.
Optionally, pretreatment includes but is not limited to: at least one of color space conversion and image scaling.
Optionally, fatigue state includes: at least one of to yawn and nod.State of diverting attention includes: to make a phone call, see hand
Machine at least one of smokes and glances right and left.
Optionally, monitoring controller 130 uses multi-core heterogeneous system grade chip (System on Chip, SoC), SoC packet
Include advanced reduced instruction set machine ARM core 131, the first digital signal processor (Digital Signal Processing,
DSP) core 132 and the second DSP core 133.
First DSP core 131, tracks for the sight to driver, and executes and determine PERCLOS according to the first image
The step of.
Second DSP core 132 pre-processes the second image for executing；By the input point of pretreated second image
Class model obtains the step of classification results.
Optionally, disaggregated model is convolutional neural networks CNN model；Certainly, disaggregated model may be other types of
Model for classifying, the present embodiment do not limit the type of disaggregated model.
ARM core 133, for executing the step of determining alert levels according to PERCLOS and classification results.
Optionally, monitoring controller 130 is installed on the cockpit front of vehicle.
Alarm module 140, for obtaining alert levels；Corresponding alarm assemblies are controlled according to alert levels to alarm.
Optionally, alert levels include slight, moderate and severe；Alarm module respectively with instrument board, loudspeaker and seat
Vibrator is connected；Alarm module 140, is used for:
When alert levels are slight, triggering instrument board indicator light is bright and triggers the sound police that loudspeaker exports the first duration
Show；
Alert levels be moderate when, triggering loudspeaker export the second duration sound warn and trigger seat vibration device into
The seat of row third duration shakes, and the second duration is greater than the first duration；
When alert levels are severe, triggering loudspeaker output sound, which warns and triggers seat vibration device, carries out seat shake
It is dynamic, until stopping when monitoring trigger subsequent detection goes out alert levels reduction.
A kind of workflow of driver's monitoring system of view-based access control model sensor provided in this embodiment is as follows:
Step 1, after driver actuation, monitoring controller 130 powers on start-up operation.
Step 2, monitoring controller 130 starts to supply electricity to other components in driver's monitoring system after powering on；It is infrared to take the photograph
As head module 110 is powered to near-infrared LED module 150；Near-infrared LED module 150, which starts to work normally, issues near infrared light, shines
Penetrate driver's face.
Step 3, infrared photography head module 110 starts to acquire driver front head image, it is seen that light video camera head module 120
Start to acquire driver front upper part of the body image, the Image Acquisition frame per second of the two is consistent.
Step 4, the first DSP core 131 in monitoring controller 130SoC receives the driving that infrared photography head module 110 acquires
Member's front head image (i.e. the first image), does PERCLOS measurement and eye tracking, and the second DSP core 132 receives visible image capturing
The driver front upper part of the body image (i.e. the second image) that head module 120 acquires, does CNN classification after image preprocessing.
Step 5, the result that the ARM core 133 in monitoring controller 130SoC merges two DSP core algorithm process carries out logic
What judge to need to trigger the alarm of rank to determine what state is current driver's be in.
Step 6, alarm module 140 triggers alarm according to the result of fusion logic judgment, and alert levels are divided into slight, moderate
With severe three-level, instrument board indicator light, sound and seat vibration can be triggered with alerting drivers.
In conclusion driver's monitoring system of view-based access control model sensor provided in this embodiment, passes through two figures of setting
The image that picture acquisition module, i.e. infrared photography head module and visible image capturing head module acquire driver respectively；It is controlled by monitoring
Device processed analyzes two images respectively, determines whether driver in a state of fatigue and/or state of diverting attention；It can solve
The problem of some driver's monitoring systems can not detect the state of diverting attention of driver；Driver's monitoring system can be improved
The comprehensive of driver's driving condition is monitored, to improve drive safety.
In addition, by the way that the first DSP core and the second DSP core are arranged in monitoring controller, so that monitoring controller 130 can be with
Image is opened in parallel processing two simultaneously, is improved monitoring controller 130 and is obtained the real-time of classification results.
In addition, be based on driver's monitoring system provided by the present application, monitoring controller can also monitor except yawn, point
Head makes a phone call, sees the mobile phone, smoking, other states except glance right and left this six kinds of driver fatigues and state of diverting attention；In addition also
It can further support the functional modules such as recognition of face, iris recognition, there is scalability.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of driver's monitoring system of view-based access control model sensor, which is characterized in that be installed in vehicle, the system packet
It includes: infrared photography head module, visible image capturing head module, monitoring controller and alarm module, the infrared photography head module, institute
It states visible image capturing head module and the alarm module communicates to connect between the monitoring controller respectively；
The infrared photography head module, for acquiring the first image of driver；The first image is sent to the monitoring
Controller；
The visible image capturing head module, for acquiring the second image of the driver；Second image is sent to institute
State monitoring controller；
The monitoring controller, for obtaining the first image and second image；Institute is determined according to the first image
State time PERCLOS shared by eyes closed certain proportion in driver's unit time；Second image is pre-processed；
Pretreated second image input disaggregated model is obtained into classification results, the classification results, which are used to indicate the driver, is
No in a state of fatigue and/or state of diverting attention；Alert levels are determined according to the PERCLOS and the classification results；
The alarm module, for obtaining the alert levels；Corresponding alarm assemblies are controlled according to the alert levels to carry out
Alarm.
2. system according to claim 1, which is characterized in that
The fatigue state includes: at least one of to yawn and nod.
The state of diverting attention includes: at least one of to make a phone call, see the mobile phone, smoke and glance right and left.
3. system according to claim 1, which is characterized in that the monitoring controller uses multi-core heterogeneous system grade chip
SoC, the SoC include advanced reduced instruction set machine ARM core, the first digital signal processor DSP core and the second DSP core；
First DSP core, tracks for the sight to the driver, and executes described true according to the first image
The step of fixed PERCLOS；
Second DSP core described pre-processes second image for executing；Pretreated second image is defeated
Enter the step of disaggregated model obtains classification results, the disaggregated model is convolutional neural networks CNN model；
The ARM core, for executing described the step of determining alert levels according to the PERCLOS and the classification results.
4. system according to claim 1, which is characterized in that the alert levels include slight, moderate and severe；The report
Alert module is connected with instrument board, loudspeaker and seat vibration device respectively；The alarm module, is used for:
When the alert levels are slight, it is bright and trigger the loudspeaker and export the first duration to trigger the instrument board indicator light
Sound warning；
When the alert levels are moderate, the sound for triggering the second duration of the loudspeaker output warns and triggers the seat
Vibrator carries out the seat vibration of third duration, and second duration is greater than first duration；
When the alert levels are severe, trigger the loudspeaker output sound and warn and trigger the seat vibration device progress
Seat vibration, until stopping when the monitoring trigger subsequent detection goes out alert levels reduction.
5. system according to claim 1, which is characterized in that the infrared photography head module and the visible image capturing head mould
Block acquires image with identical Image Acquisition frame per second, and described image acquisition frame rate is according to the image procossing energy of the monitoring controller
Power determines.
6. system according to claim 1, which is characterized in that the infrared photography head module is connected with near-infrared luminous two pole
Pipe LED module, the near-infrared LED module, is used for:
Receive the synchronous switch control signal of the infrared photography head module；
Signal is controlled according to the synchronous switch, and driving described in LED light transmitting near infrared light is controlled by LED drive circuit
Member；Alternatively, controlling LED light by LED drive circuit stops transmitting near infrared light.
7. system according to claim 6, which is characterized in that the infrared photography head module and the near-infrared LED module
It is installed on the top of instrument board in the vehicle.
8. system according to claim 1, which is characterized in that the visible image capturing head module is installed on a left side for the vehicle
Side A column or position of rear view mirror.
9. system according to claim 1, which is characterized in that before the monitoring controller is installed on the cockpit of the vehicle
Portion.
10. according to claim 1 to 9 any systems, which is characterized in that the infrared photography head module and the visible light
Camera module passes through cable respectively and is connected with the monitoring controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811215095.3A CN109190600A (en) | 2018-10-18 | 2018-10-18 | A kind of driver's monitoring system of view-based access control model sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811215095.3A CN109190600A (en) | 2018-10-18 | 2018-10-18 | A kind of driver's monitoring system of view-based access control model sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109190600A true CN109190600A (en) | 2019-01-11 |
Family
ID=64945946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811215095.3A Pending CN109190600A (en) | 2018-10-18 | 2018-10-18 | A kind of driver's monitoring system of view-based access control model sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190600A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119714A (en) * | 2019-05-14 | 2019-08-13 | 济南浪潮高新科技投资发展有限公司 | A kind of Driver Fatigue Detection and device based on convolutional neural networks |
| CN111645695A (en) * | 2020-06-28 | 2020-09-11 | 北京百度网讯科技有限公司 | Fatigue driving detection method and device, computer equipment and storage medium |
| CN111753741A (en) * | 2020-06-28 | 2020-10-09 | 北京小眼探索科技有限公司 | Special vehicle auxiliary driving method and device based on deep learning and storage medium |
| CN112201008A (en) * | 2020-08-21 | 2021-01-08 | 深圳市豪恩汽车电子装备股份有限公司 | Fatigue driving monitoring system and method |
| CN112584058A (en) * | 2019-09-30 | 2021-03-30 | 杭州海康汽车技术有限公司 | Image acquisition system, method and device |
| CN114155592A (en) * | 2021-12-21 | 2022-03-08 | 清华大学苏州汽车研究院（吴江） | Multi-source fusion visual perception cabin system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830389A (en) * | 2006-04-21 | 2006-09-13 | 太原理工大学 | Device for monitoring fatigue driving state and its method |
| US20060261931A1 (en) * | 2003-08-15 | 2006-11-23 | Ziyi Cheng | Automobile security defence alarm system with face identification and wireless communication function |
| CN104637246A (en) * | 2015-02-02 | 2015-05-20 | 合肥工业大学 | Driver multi-behavior early warning system and danger evaluation method |
| CN108269383A (en) * | 2016-12-30 | 2018-07-10 | 河南辉煌信通软件有限公司 | Driver fatigue monitor system based on PERCLOS algorithms |
-
2018
- 2018-10-18 CN CN201811215095.3A patent/CN109190600A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060261931A1 (en) * | 2003-08-15 | 2006-11-23 | Ziyi Cheng | Automobile security defence alarm system with face identification and wireless communication function |
| CN1830389A (en) * | 2006-04-21 | 2006-09-13 | 太原理工大学 | Device for monitoring fatigue driving state and its method |
| CN104637246A (en) * | 2015-02-02 | 2015-05-20 | 合肥工业大学 | Driver multi-behavior early warning system and danger evaluation method |
| CN108269383A (en) * | 2016-12-30 | 2018-07-10 | 河南辉煌信通软件有限公司 | Driver fatigue monitor system based on PERCLOS algorithms |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119714A (en) * | 2019-05-14 | 2019-08-13 | 济南浪潮高新科技投资发展有限公司 | A kind of Driver Fatigue Detection and device based on convolutional neural networks |
| CN110119714B (en) * | 2019-05-14 | 2022-02-25 | 山东浪潮科学研究院有限公司 | Driver fatigue detection method and device based on convolutional neural network |
| CN112584058A (en) * | 2019-09-30 | 2021-03-30 | 杭州海康汽车技术有限公司 | Image acquisition system, method and device |
| CN112584058B (en) * | 2019-09-30 | 2023-02-07 | 杭州海康汽车技术有限公司 | Image acquisition system, method and device |
| CN111645695A (en) * | 2020-06-28 | 2020-09-11 | 北京百度网讯科技有限公司 | Fatigue driving detection method and device, computer equipment and storage medium |
| CN111753741A (en) * | 2020-06-28 | 2020-10-09 | 北京小眼探索科技有限公司 | Special vehicle auxiliary driving method and device based on deep learning and storage medium |
| CN111753741B (en) * | 2020-06-28 | 2024-03-15 | 北京小眼探索科技有限公司 | Special vehicle driving assisting method and device based on deep learning and storage medium |
| CN112201008A (en) * | 2020-08-21 | 2021-01-08 | 深圳市豪恩汽车电子装备股份有限公司 | Fatigue driving monitoring system and method |
| CN114155592A (en) * | 2021-12-21 | 2022-03-08 | 清华大学苏州汽车研究院（吴江） | Multi-source fusion visual perception cabin system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190600A (en) | A kind of driver's monitoring system of view-based access control model sensor | |
| CN105336105B (en) | A kind of method of preventing fatigue driving, smart machine and system | |
| CN106709420B (en) | Method for monitoring driving behavior of commercial vehicle driver | |
| CN104183091B (en) | System for adjusting sensitivity of fatigue driving early warning system in self-adaptive mode | |
| US20160272217A1 (en) | Two-step sleepy driving prevention apparatus through recognizing operation, front face, eye, and mouth shape | |
| CN205158585U (en) | Prevention driver fatigue's smart machine and system | |
| CN106778618A (en) | A kind of fatigue driving monitoring early warning system | |
| Anjali et al. | Real-time nonintrusive monitoring and detection of eye blinking in view of accident prevention due to drowsiness | |
| CN112220480B (en) | Driver state detection system based on millimeter wave radar and camera fusion and vehicle | |
| CN103198618A (en) | Mobile phone capable of preventing fatigue driving and warning method | |
| Charniya et al. | Drunk driving and drowsiness detection | |
| CN106600894A (en) | Fatigue driving and drunk driving monitoring and warning system | |
| CN105701971B (en) | It is a kind of that fatigue driving system, device and method are prevented based on iris recognition | |
| CN106467057A (en) | The method of lane departure warning, apparatus and system | |
| CN104376684A (en) | Monitoring system capable of preventing fatigue driving | |
| CN208324889U (en) | Traffic safety alarm system and vehicle | |
| CN109801475A (en) | Method for detecting fatigue driving, device and computer readable storage medium | |
| CN107585026A (en) | A kind of anti-fatigue-driving system | |
| CN108670278A (en) | A kind of driver fatigue detection and alarm system and method based on smart mobile phone | |
| CN105599607B (en) | A kind of vehicle starting device and method based on driver status | |
| CN103824421B (en) | Active safety fatigue driving detection caution system | |
| CN209962386U (en) | Driver fatigue monitoring system | |
| CN104376685A (en) | Fatigue driving preventing vehicle control method | |
| CN205722310U (en) | A kind of train driver Activity recognition system based on video sequence | |
| CN110239555A (en) | A kind of device and method of auxiliary vehicle safety operation |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 301, Building 5, No. 17, Dongwang Road, Suzhou Industrial Park, Jiangsu Province, 215123 Applicant after: Zhixing Automotive Technology (Suzhou) Co.,Ltd. Address before: Room 301, Building 5, No. 17, Dongwang Road, Suzhou Industrial Park, Jiangsu Province, 215123 Applicant before: IMOTION AUTOMOTIVE TECHNOLOGY (SUZHOU) Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |
|
| RJ01 | Rejection of invention patent application after publication |