WO2008020458A2 - Procédé et système pour détecter l'état de somnolence d'un conducteur - Google Patents

Procédé et système pour détecter l'état de somnolence d'un conducteur Download PDF

Info

Publication number
WO2008020458A2
WO2008020458A2 PCT/IN2007/000346 IN2007000346W WO2008020458A2 WO 2008020458 A2 WO2008020458 A2 WO 2008020458A2 IN 2007000346 W IN2007000346 W IN 2007000346W WO 2008020458 A2 WO2008020458 A2 WO 2008020458A2
Authority
WO
WIPO (PCT)
Prior art keywords
driver
image
camera
images
capture
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.)
Ceased
Application number
PCT/IN2007/000346
Other languages
English (en)
Other versions
WO2008020458A3 (fr
Inventor
R. Krishnamurthy
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ANANYA INNOVATIONS Ltd
Original Assignee
ANANYA INNOVATIONS Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ANANYA INNOVATIONS Ltd filed Critical ANANYA INNOVATIONS Ltd
Publication of WO2008020458A2 publication Critical patent/WO2008020458A2/fr
Anticipated expiration legal-status Critical
Publication of WO2008020458A3 publication Critical patent/WO2008020458A3/fr
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING SYSTEMS, e.g. PERSONAL 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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
    • B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
    • B60K28/02—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver
    • B60K28/06—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver responsive to incapacity of driver
    • B60K28/066—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver responsive to incapacity of driver actuating a signalling device
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W40/09—Driving style or behaviour
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V40/193—Preprocessing; Feature extraction
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W2040/0818—Inactivity or incapacity of driver
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20004—Adaptive image processing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30268—Vehicle interior

Definitions

  • the present invention relates to a driver Drowsy Detection System which is a real time and non-intrusive method of driver drowsy detection.
  • This system monitors, detects and tracks the driver's eyelid closure and analyses the drivers fatigue or distraction. This information is used to warn the driver and prevents the drivers from falling asleep or being distracted and thus enhances or increases the road safety.
  • a moving vehicle presents challenges like variable lighting and changing backgrounds that is not easily solvable.
  • Several techniques have been proposed for improving the monitoring and vigilance of drivers to prevent falling asleep while at the wheel which generally results in catastrophic highway wrecks.
  • Work on driver alertness has not yet led to an effective system as the known proposals appear to inadequately deal with additional complications like mouth opening and closing, full occlusion, or blinking of a driver.
  • Prior art solutions for drowsy detection systems can be classified into intrusion and non-intrusion methods. A number of prior art approaches will now be described.
  • Intrusive techniques detect drowsiness by using sensors, which are used to actuate an alarm system. Such systems involve anatomically invasive instrumentation devices or use of thermal sensing electrodes. Such devices are considered to be physiologically and psychologically discomforting to drivers. Certain others intrusive methods that have been contemplated by means of sensing physiological characteristics by monitoring changes in physiological signals, such as brain waves, heart rate, and eye blinking; and measures physical changes such as sagging posture, leaning of the driver's head and the Open/closed states of the eyes. While this is most accurate but is not realistic, since sensing electrodes would have to be attached directly onto the driver's body, and hence be annoying and distracting to the driver. In addition, long time driving would result in perspiration on the sensors, diminishing their ability to monitor accurately.
  • Prior art proposes non-intrusive systems such as sensing of arterial blood supply in the portions of the driver's body to perform intrusion-free physiological condition monitoring of drivers. While this is a non-invasive technique, this requires customized headgear or face gear which incorporates contact sensors which only monitors the cranial blood flow, which asserts to be a generalized indicator of well-being.
  • the Percentage of time eyelids are closed (PERCLOS) system for analysis of eyelid closure percentage is considered the most reliable non-contact indicator of fatigue.
  • PERCLOS Percentage of time eyelids are closed
  • This system developed for measuring the percentage of time the eyelids of a human being is closed. This is a semi automatic system that grabs the frame and stores it in a location and processes it.
  • PERCLOS use two NIR sources of different wavelength of 850nm &950nm.
  • the iris is detected as a round shaped object on subtracting one image with the other. This is monitored for a period of time and percentage is calculated for the non-occurrence of the iris.
  • This technique has several limitations, including its reliance on carefully positioned illuminators to produce reflections from the eyes to locate the eye positions relative to the camera. These limitations are especially troubling when ambient lighting conditions vary, making it difficult to detect eyelid status.
  • Some non-intrusive methods sense driver's response by periodically requesting the driver to send a response to the system to indicate alertness. The problem with this technique is that it will eventually become tiresome and annoying to the driver.
  • the primary object of the present invention is to overcome one or more problems of the conventional prior art by various embodiments of the present invention.
  • Yet another object of the present invention is to provide a Driver Drowsy Detection System that over comes many of the disadvantages described by the prior art devices.
  • Still another object of the present invention is to provide a Driver Drowsy Detection
  • Still another object of the present invention is to provide for increased efficiency by avoiding frame loss.
  • Still another object of the present invention is to provide for a Driver Drowsy Detection System that uses customized image processing algorithm to concentrate on the face detection and eye detection based on illumination pattern provided by IR LED.
  • Still another object of the present invention is to provide neural network method to authenticate the eyes movement detected using the image-processing algorithm to reduce the chance of misdetection or wrong alarm.
  • Still another object of the present invention to keep the number of LED array used well below the hazardous level of IRLED illumination thus making the system a very safe product.
  • Still another object of the present invention is to provide high-end low cost Digital processor for porting the algorithm and giving warning.
  • Still another object of the present invention is to provide for a Driver Drowsy Detection System that is not biased on skin colour.
  • the present invention provides for a method to detect drowsy state of driver, said method comprising steps of capturing images of the driver to monitor the status of the driver; preprocessing the captured images to make the image suitable for effective processing; finding out average value of all pixels available in the preprocessed image using adaptive binarization; performing face segmentation on the preprocessed images to eliminate background features and to segregate the face alone from the image and localizing the eyes based on eyeball pattern matching and thereafter determining absence of the eyeballs for predetermined consecutive images to detect drowsy state of the driver and thereby alerting the driver, and also
  • a system to detect drowsy state of driver said system comprises camera with IR illuminator to capture images of the driver; processor for processing the images captured; external memory to store the images captured from the camera; and counter to count absence of eyeballs in consecutive frames and alarm to wake the driver from his drowsy state.
  • Figure 1 shows the flow chart which explains working of the invention.
  • FIG. 1 shows the working of the hardware.
  • Figure 3 shows side view of CCD camera located and the monitoring system ECU with warning system.
  • Figure 4 shows top view of camera and ECU with warning system.
  • FIG. 5 shows block diagram of the system used in present invention.
  • the primary embodiment of the present invention is a method to detect drowsy state of driver, said method comprising steps of; capturing images of the driver to monitor the status of the driver; preprocessing the captured images to make the image suitable for effective processing; finding out average value of all pixels available in the preprocessed image using adaptive binarization; performing face segmentation on the preprocessed images to eliminate background features and to segregate the face alone from the image; and localizing the eyes based on eyeball pattern matching and thereafter determining absence of the eyeballs for predetermined consecutive images to detect drowsy state of the driver and thereby alerting the driver.
  • camera with image sensor which is sensitive to capture IR lit images is used to capture the images.
  • IR LEDs are used to brighten the face of the driver without disrupting the driver to capture the image.
  • the camera is Phase Alternating
  • the preprocessing is performed to eliminate noises due to external adverse lighting condition and/or vibration of the vehicle occurred during image capture.
  • median filter is used to eliminate the noises.
  • the median filter considers each pixel in the image and looks at its nearby neighbors to decide whether or not it is representative of its surroundings.
  • filtering is carried out by replacing the pixel value with the median of neighborhoods pixel value.
  • the median is calculated by first sorting all the pixel values from surrounding neighborhood into numerical order and then replacing the pixel being considered with the middle pixel value.
  • the face segmentation involves
  • the face segmentation is performed irrespective of all lighting and day and night conditions.
  • the segmentation is performed based on the intensity variation of light.
  • the average value is fixed as threshold for binarization.
  • the vertical projection function is calculated by considering pixels along each column of the frame. In still another embodiment of the present invention, the pixel values along the column are suppressed if the value found equal to zero.
  • the method identifies the eye opening and closure, and also non-eye region due to external factors.
  • the multi layered neural network is used to authenticate detected object is either eye or not.
  • the method provides audio warning in form of alarm to wake the driver from his drowsy state.
  • Still another embodiment of the present invention is a system to detect drowsy state of driver, said system comprises; camera with TR illuminator to capture images of the driver; processor for processing the images captured; external memory to store the images captured from the camera; and counter to count absence of eyeballs in consecutive frames and alarm to wake the driver from his drowsy state.
  • the processor is DSP processor.
  • camera with image sensor which is sensitive to capture IR lit images is used to capture the images.
  • IR LEDs are used to brighten the face of the driver without disrupting the driver to capture the image.
  • the camera is Phase Alternating
  • PAL Charged coupled Device
  • the external memory is SDRAM used to store the image data through the DSP processor.
  • the SDRAM consists of four buffers where first two buffers are used to store the input data and last two are used to store processed output data and the data are handled on the FIFO basis.
  • the processed output data optionally sent to display unit for testing.
  • the image data stored in the external SDRAM are taken to the DSP processor using Direct Memory Access
  • IR pass filter is used at the camera end to block visible light and to capture only IR reflected images by the camera.
  • system is a real time and non- intrusive method of driver drowsy detection.
  • the processor counts the absence of eyeballs in 12 consecutive frames and gives alarm to wake the driver from his drowsy state.
  • the system as shown in figure 2 designed in the present invention detects the drowsy condition of driver. This is achieved by capturing image of driver and processing the same .
  • the image is processed in a DSP processor.
  • Image processing algorithms and neural network are used for processing the image and eye detection. Furtheron based on the eye closure time the processor concludes the drowsy state of driver and warns driver as shown in figure 1.
  • the system captures the images of the driver and processes the images in a processor.
  • the processor monitors for closed eye (absence of eye ball) in consequent frames and in case the frames show a closed eye in twelve consequent frames it triggers a alarm.
  • the camera with IR illuminators marked as 1 is placed behind the steering wheel and the ECU (i.e. the processing unit -hvarning system) marked as 2 is placed in the dashboard.
  • the camera focuses on the driver and it captures the video image, which is transferred to ECU, which has the IP algorithm and neural network for image processing .
  • FIG 5 it gives details about the hardware setup.
  • the images are captured with the camera, using which the status of Driver is monitored.
  • IR LEDs used brighten the face of driver without disrupting the driver (as IR is in non visible region of light spectrum) and the camera is selected in such a way that its Image sensor is sensitive to capture IR lit Images.
  • the Camera output is in YUV analog format.
  • a PAL Camera with 1/3 inch CCD Sensor is used.
  • the Analog output of camera is fed to Video Decoder and the Digital Image output is connected to the DSP processor.
  • the DSP processor has very limited memory and hence it cannot store large chunk of Image data. So, external SDRAM is used to store the data'via DSP processor as shown in figure 5.
  • the SDRAM consists of four buffers and data are handled on the FIFO basis. First two buffers are used to store the input data and the last two buffers are used to store processed output data. The processed output frames can be sent to Display unit if required (for testing).
  • the Image data stored in the external SDRAM are taken to the DSP processor using DMAs. These data are processed by image processing algorithms
  • the Images captured by the camera may have noises and hence it is difficult to process the Images as such.
  • the sources of the noise could be due to external adverse lighting condition, vibration of the vehicle, etc.
  • the Images are preprocessed. Preprocessing algorithms eliminate the noises to a maximum level and aids to yield good results in further Image Processing.
  • Median filter is used to eliminate the noises.
  • the median filter considers each pixel in the image in turn and looks at its nearby neighboring pixels to decide whether or not it is representative of its surroundings. Filtering is done by replacing the pixel value with the median of neighborhood pixel values. The median is calculated by first sorting all the pixel values from the surrounding neighborhood into numerical order and then replacing the pixel being considered with the middle pixel value.
  • the captured image contains driver's face and unwanted background features.
  • Driver's face we need to eliminate background features and segregate the face alone.
  • the face segmentation involves Vertical projection function to suppress almost all the unwanted background features.
  • the purpose of face segmentation is to enhance the speed of processing and reduction in search area of the eye, as the algorithm runs only on the area of Interest.
  • the face segmentation is done irrespective of all lighting & day and night conditions.
  • the face segmentation is performed based on the intensity variation of light.
  • IR pass filter is used at the camera end to block the visible light and hence only the IR reflected images are captured by the camera.
  • Adaptive binarization is a technique, which involves finding out the average value of all the pixels available in that particular frame. This average value is fixed as the threshold for binarization.
  • the eyes are localized based on the Eyeball pattern matching. If the pattern is found in the frame it is considered as Eye. This method identifies the Eye opening and closure, but in some cases, due to external factors, it also detects non-eye region. To confirm the detected object as Eye or not, Neural Network is used.
  • Multilayered Neural Network is designed and it is trained with the Eye and Non-Eye patterns extracted from the Eye detection of Image processing.
  • the Trained Multilayered Neural is interfaced with the previous stage. Each of the doubtful eye locations in the previous stage are fed as input to this trained neural network for conforming the presence of the eye.
  • the warning system is used to wake the driver from his drowjsy state. This is done by giving an audio warning in form of alarm.
  • the alarm gives beep sound for a few seconds ensuring the driver wakes up from drowsy state.
  • CCD Charged coupled device
  • IR LED Infra Red LED

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Transportation (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Mechanical Engineering (AREA)
  • Ophthalmology & Optometry (AREA)
  • Combustion & Propulsion (AREA)
  • Chemical & Material Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)
  • Emergency Alarm Devices (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un procédé et un système pour détecter l'état de somnolence d'un conducteur. Ce procédé consiste à capturer l'image du conducteur et à la traitant. L'image est traitée dans un processeur DSP. Des procédés de traitement d'image et un réseau neuronal sont utilisés pour le traitement de l'image et la détection des yeux. Ensuite, compte tenu du temps de fermeture des yeux, le processeur détermine l'état de somnolence du conducteur et avertit celui-ci.
PCT/IN2007/000346 2006-08-18 2007-08-16 Procédé et système pour détecter l'état de somnolence d'un conducteur Ceased WO2008020458A2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IN1457CH2006 2006-08-18
IN01457/CHE/2006 2006-08-18

Publications (2)

Publication Number Publication Date
WO2008020458A2 true WO2008020458A2 (fr) 2008-02-21
WO2008020458A3 WO2008020458A3 (fr) 2009-09-24

Family

ID=39082455

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IN2007/000346 Ceased WO2008020458A2 (fr) 2006-08-18 2007-08-16 Procédé et système pour détecter l'état de somnolence d'un conducteur

Country Status (1)

Country Link
WO (1) WO2008020458A2 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2497670A1 (fr) * 2011-03-11 2012-09-12 Johnson Controls Automotive Electronics GmbH Procédé et appareil de surveillance de la promptitude mentale du conducteur d'un véhicule
US20160378079A1 (en) * 2015-06-24 2016-12-29 Hon Hai Precision Industry Co., Ltd. Computing device and electrical device controlling method
KR20190089776A (ko) * 2018-01-23 2019-07-31 폭스바겐 악티엔 게젤샤프트 복수의 제어 장치에서 센서 데이터를 처리하기 위한 방법, 대응되게 설계된 전처리 유닛 및 차량
CN110276273A (zh) * 2019-05-30 2019-09-24 福建工程学院 融合面部特征与图像脉搏心率估计的驾驶员疲劳检测方法
WO2019200434A1 (fr) * 2018-04-19 2019-10-24 Seeing Machines Limited Système de protection de source de lumière infrarouge
KR20220155499A (ko) * 2021-05-14 2022-11-23 호남대학교 산학협력단 자율 주행 실시간(real-time) 데이터 획득 및 분석을 위한 엣지디바이스

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7202792B2 (en) * 2002-11-11 2007-04-10 Delphi Technologies, Inc. Drowsiness detection system and method

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012123330A1 (fr) * 2011-03-11 2012-09-20 Johnson Controls Automotive Electronics Gmbh Procédé et appareil pour surveiller et contrôler la vigilance d'un conducteur
CN103476622A (zh) * 2011-03-11 2013-12-25 约翰逊控制器汽车电子有限责任公司 用于监测和控制驾驶员警觉性的方法和设备
US20140167968A1 (en) * 2011-03-11 2014-06-19 Johnson Controls Automotive Electronics Gmbh Method and apparatus for monitoring and control alertness of a driver
US9139087B2 (en) 2011-03-11 2015-09-22 Johnson Controls Automotive Electronics Gmbh Method and apparatus for monitoring and control alertness of a driver
EP2497670A1 (fr) * 2011-03-11 2012-09-12 Johnson Controls Automotive Electronics GmbH Procédé et appareil de surveillance de la promptitude mentale du conducteur d'un véhicule
US20160378079A1 (en) * 2015-06-24 2016-12-29 Hon Hai Precision Industry Co., Ltd. Computing device and electrical device controlling method
KR102179933B1 (ko) * 2018-01-23 2020-11-17 폭스바겐 악티엔게젤샤프트 복수의 제어 장치에서 센서 데이터를 처리하기 위한 방법, 대응되게 설계된 전처리 유닛 및 차량
KR20190089776A (ko) * 2018-01-23 2019-07-31 폭스바겐 악티엔 게젤샤프트 복수의 제어 장치에서 센서 데이터를 처리하기 위한 방법, 대응되게 설계된 전처리 유닛 및 차량
US10922557B2 (en) 2018-01-23 2021-02-16 Volkswagen Aktiengesellschaft Method for processing sensor data in multiple control units, preprocessing unit, and transportation vehicle
WO2019200434A1 (fr) * 2018-04-19 2019-10-24 Seeing Machines Limited Système de protection de source de lumière infrarouge
US11941894B2 (en) 2018-04-19 2024-03-26 Seeing Machines Limited Infrared light source protective system
US12444208B2 (en) 2018-04-19 2025-10-14 Seeing Machines Limited Infrared light source protective system
CN110276273A (zh) * 2019-05-30 2019-09-24 福建工程学院 融合面部特征与图像脉搏心率估计的驾驶员疲劳检测方法
CN110276273B (zh) * 2019-05-30 2024-01-02 福建工程学院 融合面部特征与图像脉搏心率估计的驾驶员疲劳检测方法
KR20220155499A (ko) * 2021-05-14 2022-11-23 호남대학교 산학협력단 자율 주행 실시간(real-time) 데이터 획득 및 분석을 위한 엣지디바이스
KR102585254B1 (ko) * 2021-05-14 2023-10-05 호남대학교 산학협력단 자율 주행 실시간(real-time) 데이터 획득 및 분석을 위한 엣지디바이스

Also Published As

Publication number Publication date
WO2008020458A3 (fr) 2009-09-24

Similar Documents

Publication Publication Date Title
US9392956B2 (en) Dry sensor EEG/EMG and motion sensing system for seizure detection and monitoring
US9955903B2 (en) Eye closure detection using structured illumination
US8063786B2 (en) Method of detecting drowsiness of a vehicle operator
CN102047304B (zh) 驾驶注意力程度判定装置、方法
US20150379362A1 (en) Imaging device based occupant monitoring system supporting multiple functions
JPH11316884A (ja) 覚醒状態を求める装置
CN101426418B (zh) 用于无能力监视的系统和方法
Anjali et al. Real-time nonintrusive monitoring and detection of eye blinking in view of accident prevention due to drowsiness
WO2008020458A2 (fr) Procédé et système pour détecter l'état de somnolence d'un conducteur
Vitabile et al. Bright pupil detection in an embedded, real-time drowsiness monitoring system
Chatterjee et al. Driving fitness detection: A holistic approach for prevention of drowsy and drunk driving using computer vision techniques
Coetzer et al. Driver fatigue detection: A survey
Liu et al. Driver fatigue detection through pupil detection and yawing analysis
Khan et al. Efficient Car Alarming System for Fatigue Detectionduring Driving
KR20180131045A (ko) 다 센서 기반의 감지ㆍ경보수단과 중앙처리수단이 일체로 구성된 졸음운전 방지장치 및 제어방법
Bhaskar EyeAwake: A cost effective drowsy driver alert and vehicle correction system
JPH08290726A (ja) 居眠り警報装置
PS et al. Development of artificial intelligence system for driver drowsiness detection
JPH0596971A (ja) 居眠り運転防止装置
Chiou et al. Abnormal driving behavior detection using sparse representation
Sinha et al. Driver alert system for accident avoidance
Chopra et al. A comprehensive analysis of driver drowsiness detection techniques
Hammoud et al. On driver eye closure recognition for commercial vehicles
Malathy et al. Extraction of eye features of driver for detecting fatigue using OpenCV
Deng et al. Fatigue detection based on infrared video pupillography

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07827532

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase

Ref country code: DE

NENP Non-entry into the national phase

Ref country code: RU

122 Ep: pct application non-entry in european phase

Ref document number: 07827532

Country of ref document: EP

Kind code of ref document: A2