EP3895142A1 - Procédé de détermination d'un niveau de somnolence d'un conducteur de véhicule - Google Patents
Procédé de détermination d'un niveau de somnolence d'un conducteur de véhiculeInfo
- Publication number
- EP3895142A1 EP3895142A1 EP19829064.5A EP19829064A EP3895142A1 EP 3895142 A1 EP3895142 A1 EP 3895142A1 EP 19829064 A EP19829064 A EP 19829064A EP 3895142 A1 EP3895142 A1 EP 3895142A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- driver
- predetermined
- parameter
- computer
- images
- 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
- 206010041349 Somnolence Diseases 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012544 monitoring process Methods 0.000 claims description 21
- 230000004397 blinking Effects 0.000 claims description 19
- 210000000744 eyelid Anatomy 0.000 claims description 15
- 230000004886 head movement Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000010191 image analysis Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 210000003128 head Anatomy 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 210000001747 pupil Anatomy 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 208000004350 Strabismus Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 235000019580 granularity Nutrition 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000005236 sound signal 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
- A61B5/1128—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using image analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
- A61B5/6893—Cars
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
- G08B29/188—Data fusion; cooperative systems, e.g. voting among different detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/20—Calibration, including self-calibrating arrangements
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
-
- 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
- B60W2040/0827—Inactivity or incapacity of driver due to sleepiness
-
- 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
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/403—Image sensing, e.g. optical camera
-
- 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/221—Physiology, e.g. weight, heartbeat, health or special needs
-
- 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/223—Posture, e.g. hand, foot, or seat position, turned or inclined
-
- 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/229—Attention level, e.g. attentive to driving, reading or sleeping
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- 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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/005—Handover processes
- B60W60/0051—Handover processes from occupants to vehicle
-
- 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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/005—Handover processes
- B60W60/0059—Estimation of the risk associated with autonomous or manual driving, e.g. situation too complex, sensor failure or driver incapacity
Definitions
- TITLE Method for determining a drowsiness level of a vehicle driver
- the invention relates to the field of assistance with driving a motor vehicle, manual or autonomous driving, and relates, more particularly, to a device and a method for monitoring a vehicle driver in particular trigger an alert or activate an automatic driving mode in the event of drowsiness or distraction.
- This type of monitoring device includes a camera and a computer, which processes the images generated by the camera and alerts the driver in case of drowsiness or distraction.
- the calculator analyzes, for example, the movement of the driver's eyes, head or upper body, facial expressions, head orientation or a combination of some or all of these parameters.
- the computer analyzes these parameters for a given period of time. For example, when the computer analyzes the driver's eyes, it can in particular determine the frequency of blinking of the eyelids, the amplitude of the blinking of the eyelid, the duration of the blinking of the eyelids, etc. It then compares these values to a threshold or a range of predetermined values characterizing an awake state in order to deduce therefrom whether the driver is awake, distracted or drowsy and to alert him if necessary.
- the computer deduces that the driver is in the awake state but if the duration of the blinking of the eyelids is greater than 350 ms, the calculator deduces that the driver drowsiness increases.
- the thresholds or ranges of values characterizing an awake state are predetermined in the factory and stored in a memory area of the computer so as to be used for all conductors.
- the device can trigger alerts, which has a significant drawback, or on the contrary does not trigger an alert while the driver is in a distracted or drowsy state, which then has a major drawback.
- the present invention aims to provide a simple, reliable and effective solution for detecting a level of drowsiness in a vehicle driver.
- the invention firstly relates to a method for determining a level of drowsiness of a driver of a vehicle, in particular a motor vehicle, from a predetermined image analysis algorithm.
- said vehicle comprising a camera and a computer
- said computer implementing said predetermined algorithm from a set comprising at least one parameter relating to the attitude of the driver, the method implemented by the computer, comprising:
- a learning phase carried out for a predetermined period, preferably after each start of the vehicle engine, comprising the steps of:
- a phase for monitoring the state of the driver comprising the steps of:
- the method according to the invention advantageously makes it possible to determine the level of drowsiness of a vehicle driver (inversely proportional to his level of attention), as a function of parameters and parameter values specific to said driver.
- the method comprises a step of alerting the driver when the determined level of drowsiness is greater than a predetermined threshold.
- the process thus makes it possible to alert the driver in the event of a level of drowsiness or low attention).
- the method comprises an alert step, after the detection of a high level of drowsiness of the driver.
- Such an alert may consist of one or a combination of the following alert means: light signal, sound signal (for example the vehicle alarm), alert message broadcast on a vehicle screen or sent to an external device, for example a smartphone, a seat vibration or actuators (steering wheel or pedals).
- alert means light signal, sound signal (for example the vehicle alarm), alert message broadcast on a vehicle screen or sent to an external device, for example a smartphone, a seat vibration or actuators (steering wheel or pedals).
- the predetermined duration of the learning phase of the process is between 5 and 20 minutes.
- Such a duration makes it possible to generate by the camera, a sequence of images sufficiently supplied in images to be analyzed in order to extract reliable information concerning the behavior of the driver, and to determine sets of parameters or parameter values. characteristics of said conductor.
- the predetermined duration of the learning phase of the process is less than 20 minutes. Such a duration is sufficient to obtain the desired information concerning the driver, in other words to determine sets of parameters or parameter values characteristic of said driver, and to start the monitoring phase, to determine the level of drowsiness of the driver in real time.
- the at least one parameter of each set used in the method is one of the driver's blinking frequency, the driver's blinking time, the blinking amplitude of the driver's eyelids, driver's face activity, size of driver's face contour, height of opening between eyelids of each driver's eye, head movements with amplitude and duration as indicators main.
- These parameters are simple parameters for detecting driver drowsiness levels.
- the execution of the predetermined algorithm carried out in the monitoring phase is carried out according to a plurality of implementations in parallel.
- Each implementation of the algorithm provides different indicators and analyzes that complete the majority of possible states among drivers.
- a single implementation of the algorithm cannot solve all the possibilities for detecting the level of driver drowsiness.
- the need to have a parallel implementation of the algorithm with different thresholds and parameters covers the majority of events and can provide the best real-time alert for the driver.
- the monitoring phase may include a step of updating the degree of relevance for each implementation of the algorithm performed, the degrees of relevance remaining different from each other, the degree of relevance the most high being attributed to the set of predetermined parameters and / or predetermined intervals of parameter values used for which the determined values of the parameters vary the least, in order to identify the reactions and attitude of the driver in question, in particular with regard to drowsiness and fatigue.
- the invention also relates to a vehicle computer, in particular automobile, allowing the determination of a level of drowsiness of a driver of said vehicle from a predetermined image analysis algorithm, the vehicle comprising a camera.
- said computer implementing said predetermined algorithm from a set comprising at least one parameter relating to the attitude of the driver, the computer being configured to: during a learning phase carried out for a predetermined period, preferably after each start of the vehicle engine:
- o receive a sequence of images of the driver generated by the camera, for example 10, 15, 20, 25, 30, 45, 60 ... up to 200 images per second, o execute the predetermined algorithm on said sequence d images generated in a plurality of implementations carried out in parallel, each implementation using a different set of predetermined parameters and / or predetermined intervals of parameter values, so as to determine a plurality of values for each parameter of said set ,
- o receive a sequence of images of the driver generated by the camera, o execute the predetermined algorithm on said sequence of images generated in at least one implementation from at least the set of parameters and / or values parameters having the highest degree of relevance, so as to determine a plurality of values for each parameter of said set,
- o determine a level of drowsiness of the driver from at least one value determined for each parameter of said set and from at least a predetermined threshold relating to said at least one parameter.
- the computer according to the invention advantageously makes it possible to determine the level of drowsiness of a vehicle driver, as a function of parameters and parameter values specific to said driver.
- the computer thus makes it possible to alert the driver in the event of a high level of drowsiness of said driver.
- the predetermined duration of the learning phase is between 5 and 20 minutes.
- the at least one parameter from each set used by the computer is one of the driver's blinking frequency, the driver's blinking time, the blinking amplitude of the driver, the activity of the driver's face, the size of the outline of the driver's face, the height of the opening between the eyelids of each driver's eye, head movements with amplitude and duration as the main indicators .
- the execution of the predetermined algorithm performed by the computer in the step of executing the monitoring phase is carried out according to a plurality of implementations in parallel.
- Each implementation provides different indicators and analyzes that complete the majority of possible states among drivers.
- a single implementation cannot resolve all possibilities for detecting the level of drowsiness or driver attention.
- the need to have a parallel implementation of the algorithm with different thresholds and parameters covers the majority of events and can provide the best real-time alert for the driver.
- the invention also relates to a vehicle, in particular a motor vehicle, comprising a camera configured to generate a sequence of images and a computer, as described above, connected to said camera in order to receive said sequence of images.
- FIG. 1 schematically illustrates an embodiment of the vehicle according to the invention.
- FIG. 2 represents an embodiment of the method according to the invention.
- the computer according to the invention is intended to be mounted in a vehicle, in particular motor vehicle, with manual or autonomous driving, in order to determine a level of drowsiness of the driver of said vehicle and to alert or activate automatic driving if necessary.
- the level of drowsiness can correspond to a state (asleep, poorly concentrated, alert ...) or a quantified level, for example alphanumerically, in order to define levels reflecting granularities of drowsiness (for example, level 1 for an alert driver, level 2 for a poorly concentrated driver, level 3 for a driver while falling asleep, level 4 for a sleeping driver ).
- the device comprises a camera 11 installed in the vehicle 1, which films the driver and a computer 12, also on board the vehicle 1, which processes the images generated by the camera 11.
- the camera 11 is, for example, placed behind the driver's steering wheel and makes it possible to generate a sequence of images periodically, for example 10, 15, 20, 25, 30, 45, 60 ... up to at 200 frames per second, representing the driver, preferably his face.
- the sequence of images is sent in real time to the computer 12 so that said computer 12 analyzes said images.
- the computer 12 is configured to implement a predetermined algorithm, on said sequence of images generated, in particular on one or more characteristic points (for example, the corner of the eyes, the position of the pupil, etc.) of the images of the sequence of images received, which he determined in the images, in order to determine the level of drowsiness of the driver, that is to say, to determine if the driver is drowsy while driving vehicle 1 and / or if he is drowsy or distracted.
- characteristic points for example, the corner of the eyes, the position of the pupil, etc.
- the predetermined algorithm is implemented from a set comprising at least one parameter relating to the attitude of the driver behind the wheel.
- This or these parameters can be, for example, the frequency of the driver's blinking eyelids, the duration of the driver's blinking eyelids, the height of the driver's eyelid opening, the position of certain facial features (such as the ears , the mouth, the nose, etc.), the shape or the size of the outline of the driver's face (in the case where the size of the outline of the face is small, this means that the driver is facing, and important, that driver is in profile), activity of the driver's face, head movements with amplitude and duration as main indicators, etc.
- the value of each parameter can also be modified.
- Each implementation of the algorithm is executed in real time with a configuration of different values for the decision thresholds.
- each threshold will be modified and personalized for the driver in question according to his behavior.
- the opening of the eyes, the duration of its blinks, the speed of closing and opening of the eyes, the amplitude and the speed of the head movements are some parameters that can be used and adjusted during the learning phase.
- the duration of the analysis time window is preferably fixed at the start for each implementation of the algorithm and different configurations are tested during the learning phase.
- the decision-making model is preferably based on the confidence indicators for each of the implementations and gives rise to a more robust alert than the conventional algorithms oriented on a single analysis.
- the computer 12 is configured to, during a learning phase carried out for a predetermined period, preferably after each start of the engine of the vehicle 1, receive a sequence of images of the driver generated by the camera 11, execute the predetermined algorithm on said sequence of images generated in a plurality of implementations carried out in parallel, each implementation using a different set of predetermined parameters and / or predetermined intervals of parameter values, so as to determine a plurality of values for each parameter of said set, and determining a different degree of relevance for each set used, the highest degree of relevance being assigned to the set of predetermined parameters and / or predetermined intervals of parameter values used for which the determined values of the parameters vary the least.
- the computer 12 is configured to, once the learning phase is completed, during a phase of monitoring the state of the driver, receive a sequence of images of the driver generated by the camera 11, execute the predetermined algorithm on said sequence of images generated in at least one implementation from at least the set of parameters and / or parameter values having the highest degree of relevance, so as to determine a plurality of values for each parameter of said set, and determining a level of drowsiness of the driver from the at least one value determined for each parameter of said set and from at least a predetermined attention threshold relating to said at least one parameter.
- the vehicle 1 further comprises an interface 13, for example at the level of the dashboard of the vehicle 1, making it possible in particular to display or broadcast an alert message for the attention of the driver when his level drowsiness is greater than a predetermined alert threshold.
- an interface 13 for example at the level of the dashboard of the vehicle 1, making it possible in particular to display or broadcast an alert message for the attention of the driver when his level drowsiness is greater than a predetermined alert threshold.
- the method comprises a phase, called "learning" PH1.
- This learning phase PH1 is preferably carried out each time that the engine of the vehicle 1 is started.
- the learning phase PH1 comprises a step E0 of generating a sequence of images by the camera 11. Said generated sequence of images, representing the driver, is then sent to the computer 12.
- the computer 12 determines one or more characteristic points of the images of the sequence of images generated, for example the corner of the eye, the position of the pupil, etc.
- the learning phase PH1 comprises a step E2 of execution by the computer 12 of the predetermined algorithm on said sequence of images generated by the camera 11.
- the algorithm is performed a plurality of times in parallel and each implementation of said algorithm uses a different set of predetermined parameters and / or predetermined intervals of parameter values, so as to determine at least one value for each parameter of said set.
- each implementation is unique because it is carried out from a predetermined set of parameters and / or values of different parameters.
- the PH1 learning phase includes a step E3 of determining a degree of relevance for each set used.
- this step makes it possible to classify the set or sets, from the implementations carried out during the previous step, from the most relevant to the least relevant with respect to the attitude of the driver, that is to say from prioritize the set or sets which best describe the level of drowsiness or attention of the driver behind the wheel of vehicle 1 at that time.
- this determination step E3 also optionally comprises the selection of the set or sets, from among the plurality of sets, the one or the most relevant. This selection makes it possible either to know the relevant set or sets to be considered by the method, or to not use the least relevant set or sets, in other words the set or sets which, after their respective implementation by the algorithm, represent the driver’s drowsiness level is inaccurate or too rough.
- the determination method makes it possible to determine the set or sets, by their parameters or their respective parameter values, the / most able to describe the behavior of a particular driver.
- each driver has one or more specific sets which allow him to describe his driving behavior. This or these sets will therefore be used subsequently to determine the level of drowsiness of the driver.
- the method comprises a phase called "monitoring" PH2, after the learning phase PH1, allowing the use of the predefined algorithm combined with the most relevant set (s) and / or the set (s) previously selected.
- the monitoring phase PH2 can last as long as the engine of vehicle 1 is started.
- Said monitoring phase PH2 comprises a step E4 of generating a sequence of images of the driver by the camera 11. Said generated sequence of images, representing the driver, is then sent to the computer 12.
- the PH2 monitoring phase comprises a step of continuous execution E5 of the predetermined algorithm from said sequence of images generated in the PH2 monitoring phase and of the most relevant set or sets or of the sets selected in the PH1 learning phase.
- the computer 12 executes the predefined algorithm, thus making it possible to categorize the behavior of the driver as a function of different levels of drowsiness, from an alert level to a non-alert level and finally a drowsy level .
- Having more than one set of parameters and / or parameter value adapted to the behavior of a driver behind the wheel allows, in the event of uncertainty, to use several sets to characterize the attitude of said driver, and thus accurately determine his level of drowsiness. For example, if when the driver drives vehicle 1 and there is a lot of sun, this will force said driver to squint, the opening of the eyes is therefore smaller than when there is no sun , but that does not indicate a state of drowsiness. On the other hand, an illness could force the driver to blink more frequently than usual, or even when the driver is at a red light and wants to close his eyes for a few seconds to rest his eyes or stretch. , this also does not indicate a low level of drowsiness or attention. There is therefore a need to use the predefined algorithm with several sets, comprising different parameters used, in order to confirm or deny the level of drowsiness of the driver.
- said predetermined algorithm also makes it possible to update the characteristic set or sets of each driver. Indeed, for example, in the case where the driver falls asleep for a few seconds at the wheel, then wakes up following external stimuli (such as the sound of the horn of another road user) the parameters or the values characteristic parameters of the relevant set or sets, and therefore adapted to the driver's behavior, will be different before and after falling asleep.
- the execution step E5 therefore makes it possible to update the most relevant sets, in particular by modifying the order of relevance of the sets and also by updating parameters.
- said predetermined algorithm from the selected and updated sets, determines whether the driver is in a level of high drowsiness (ie of low attention).
- the PH2 monitoring phase comprises a step E6 of determining a level of driver drowsiness, making it possible to categorize said level of driver drowsiness. Thanks to the plurality of sets adapted to each driver and to the fact that the set or sets are updated during the use of the vehicle 1, it is easier to obtain a driver-specific diagnosis with a better level of precision.
- an alert signal is generated for the attention of the driver in an alert step E7, which is outside of the PH2 monitoring phase.
- the computer 12 sends a warning message to the interface 13, in order to warn the driver.
- This alert can be in the form of an audible signal or a light signal, for example an icon which lights up on the interface 13, a vibration of the seat or of the actuators (steering wheel, pedals).
- This step allows you to categorize the driver's attitude according to whether the driver is attentive to driving, if he is not attentive / distracted or if he is drowsy. There can be multiple levels in each category.
- the computer 12 could control the change to autonomous driving mode when the driver is distracted or dark in a drowsy state.
- the driver's condition plays an important role and the system can decide to make an emergency stop maneuver if the driver is not in a state to regain control.
- this example comprises a predetermined algorithm executed, according to the learning phase PH1, five times by the computer 12, from a sequence of images generated by the camera 11 and from five predetermined sets of parameters and / or different parameter values.
- the first set includes a parameter concerning the frequency of blinking of the eyes with a threshold at 200 ms, above which the risk that the driver is in a drowsy state is high.
- the second set includes a parameter concerning the frequency of blinking of the eyes with a threshold of 300 ms.
- the third set concerns the frequency of blinking of the eyes, the threshold of which is 350 ms.
- the fourth set concerns a parameter relating to the frequency of blinking of the eyes whose threshold is 400 ms and a parameter concerning the opening of the eyes, whose computer 1 1 varies the value to determine the most adequate and that which will correspond best to the driver of the vehicle 1.
- the fifth set concerns a parameter relating to the size of the head, since from the front the size of the head is less than when the person is in profile.
- the five sets obtained are prioritized according to their degree of relevance during the step of determining E3 the degree of relevance of the learning phase PH1.
- the order of relevance determined in this step is as follows: second set, fifth set, third set, fourth set, first set.
- the selection of certain sets can be carried out in order to use during the process only the most relevant sets, making inactive the non-selected sets. In the present case, it is considered that the second, fifth and third sets are selected.
- the computer 12 determines the driver's level of drowsiness. As said before, it allows you to determine if the driver is attentive to driving, if he is not attentive / distracted or if he is drowsy.
- an alert message is sent by the computer 12 to the interface 13 which alerts the driver drowsiness level, for example thanks to a light icon, an audible alert or a prevention message.
- This alert stimulates the driver if he is asleep, and / or advises him to make a stop.
- an autonomous driving mode of the vehicle 1 could be activated.
- the invention therefore makes it possible to precisely determine a level of drowsiness of the driver so as to alert him or take over from driving automatically.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Multimedia (AREA)
- Computer Security & Cryptography (AREA)
- Data Mining & Analysis (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Child & Adolescent Psychology (AREA)
- Social Psychology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Bioinformatics & Computational Biology (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1872824A FR3090171B1 (fr) | 2018-12-13 | 2018-12-13 | Procédé de détermination d’un niveau de somnolence d’un conducteur de véhicule |
PCT/EP2019/085147 WO2020120760A1 (fr) | 2018-12-13 | 2019-12-13 | Procédé de détermination d'un niveau de somnolence d'un conducteur de véhicule |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3895142A1 true EP3895142A1 (fr) | 2021-10-20 |
Family
ID=66166248
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP19829064.5A Pending EP3895142A1 (fr) | 2018-12-13 | 2019-12-13 | Procédé de détermination d'un niveau de somnolence d'un conducteur de véhicule |
Country Status (5)
Country | Link |
---|---|
US (1) | US20220027646A1 (fr) |
EP (1) | EP3895142A1 (fr) |
CN (1) | CN113168758B (fr) |
FR (1) | FR3090171B1 (fr) |
WO (1) | WO2020120760A1 (fr) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11983921B2 (en) * | 2021-07-26 | 2024-05-14 | Ubkang (Qingdao) Technology Co., Ltd. | Human abnormal behavior response method and mobility aid robot using the same |
FR3141404A1 (fr) * | 2022-10-31 | 2024-05-03 | Alstom Holdings | Dispositif de veille pour conducteur de véhicule ferroviaire, à confort amélioré |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5813993A (en) * | 1996-04-05 | 1998-09-29 | Consolidated Research Of Richmond, Inc. | Alertness and drowsiness detection and tracking system |
AUPQ896000A0 (en) * | 2000-07-24 | 2000-08-17 | Seeing Machines Pty Ltd | Facial image processing system |
CN101030316B (zh) * | 2007-04-17 | 2010-04-21 | 北京中星微电子有限公司 | 一种汽车安全驾驶监控系统和方法 |
CN101593352A (zh) * | 2009-06-12 | 2009-12-02 | 浙江大学 | 基于面部朝向和视觉焦点的驾驶安全监测系统 |
KR101327007B1 (ko) * | 2011-10-17 | 2013-11-13 | 현대자동차주식회사 | 차량 운행상태 정보 기반 운전 집중도 판단 방법 및 그 시스템 |
US9471881B2 (en) * | 2013-01-21 | 2016-10-18 | International Business Machines Corporation | Transductive feature selection with maximum-relevancy and minimum-redundancy criteria |
CN105354988B (zh) * | 2015-12-11 | 2018-02-27 | 东北大学 | 一种基于机器视觉的驾驶员疲劳驾驶检测系统及检测方法 |
FR3048542A1 (fr) * | 2016-03-01 | 2017-09-08 | Valeo Comfort & Driving Assistance | Dispositif et methode de surveillance personnalises d'un conducteur d'un vehicule automobile |
CN110291478B (zh) * | 2016-12-22 | 2023-09-29 | 斯坦福国际研究院 | 驾驶员监视和响应系统 |
US11341756B2 (en) * | 2017-10-02 | 2022-05-24 | Fotonation Limited | Human monitoring system incorporating calibration methodology |
-
2018
- 2018-12-13 FR FR1872824A patent/FR3090171B1/fr active Active
-
2019
- 2019-12-13 EP EP19829064.5A patent/EP3895142A1/fr active Pending
- 2019-12-13 WO PCT/EP2019/085147 patent/WO2020120760A1/fr unknown
- 2019-12-13 CN CN201980082525.5A patent/CN113168758B/zh active Active
- 2019-12-13 US US17/296,783 patent/US20220027646A1/en active Pending
Also Published As
Publication number | Publication date |
---|---|
US20220027646A1 (en) | 2022-01-27 |
FR3090171A1 (fr) | 2020-06-19 |
FR3090171B1 (fr) | 2021-01-29 |
CN113168758A (zh) | 2021-07-23 |
WO2020120760A1 (fr) | 2020-06-18 |
CN113168758B (zh) | 2023-01-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6627811B2 (ja) | 集中度判定装置、集中度判定方法及び集中度判定のためのプログラム | |
WO2017149047A1 (fr) | Dispositif et méthode de surveillance d'un conducteur d'un véhicule automobile | |
US11587461B2 (en) | Context-sensitive adjustment of off-road glance time | |
WO2020120760A1 (fr) | Procédé de détermination d'un niveau de somnolence d'un conducteur de véhicule | |
WO2017149046A1 (fr) | Dispositif et méthode de surveillance d'un conducteur d'un véhicule de transport | |
US11148673B2 (en) | Vehicle operator awareness detection | |
FR2977851A1 (fr) | Commande de regulation de vitesse d'un vehicule | |
WO2017137612A1 (fr) | Dispositif et méthode anti-collision pour un véhicule automobile | |
WO2016135391A1 (fr) | Dispositif d'aide à la conduite d'un véhicule en fonction d'une estimation d'au moins un niveau de vigilance globale du conducteur | |
FR3012029A1 (fr) | Procede de detection de la baisse de vigilance du conducteur d'un vehicule automobile | |
FR3057517A1 (fr) | Dispositif de prevention des situations dangereuses pour un conducteur d'un vehicule de transport et procede associe | |
JP6357939B2 (ja) | 車両用制御装置 | |
WO2020120751A1 (fr) | Procédé de détermination d'un niveau de vigilance d'un conducteur | |
EP3867126B1 (fr) | Procédé et dispositif d'aide à la conduite d'un véhicule automobile en phase de recul | |
US20230356736A1 (en) | Systems and methods for driver state conditioned visual signals | |
EP4296136A1 (fr) | Procédé d'alerte d'un conducteur d'un véhicule automobile après détermination de zones non surveillées par le conducteur | |
FR3129123A1 (fr) | Activation automatique de clignotants d’un véhicule automobile | |
FR3057516A1 (fr) | Dispositif de prevention des situations dangereuses pour un conducteur d'un vehicule de transport et procede associe | |
FR3118444A1 (fr) | Dispositif d’analyse de la perception d’un danger par un conducteur de véhicule et procédé associé | |
WO2021065002A1 (fr) | Système de prévention de la somnolence d'un conducteur, ordinateur, terminal, procédé de prévention de la somnolence d'un conducteur et programme | |
FR3113881A1 (fr) | Procédé d’affichage sécurisé d’informations dans un véhicule. | |
CN116088790A (zh) | 车辆的多媒体音量的控制方法、装置、车辆及存储介质 | |
CN114212093A (zh) | 一种安全驾驶监控方法、系统及可存储介质 | |
FR3130732A1 (fr) | Procédé pour déterminer l’attention d’un conducteur dans un véhicule circulant de manière partiellement autonome | |
WO2022157026A1 (fr) | Procédé de détermination d'un niveau de distraction d'un conducteur de véhicule |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20210713 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: CONTINENTAL AUTOMOTIVE TECHNOLOGIES GMBH |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20231123 |
|
RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: CONTINENTAL AUTOMOTIVE TECHNOLOGIES GMBH |