EP4120892A1 - Verarbeitungseinheit, system, und computerimplementiertes verfahren für einen fahrzeuginnenraum zur wahrnehmung und reaktion auf gerüche eines fahrzeuginsassen - Google Patents
Verarbeitungseinheit, system, und computerimplementiertes verfahren für einen fahrzeuginnenraum zur wahrnehmung und reaktion auf gerüche eines fahrzeuginsassenInfo
- Publication number
- EP4120892A1 EP4120892A1 EP21712061.7A EP21712061A EP4120892A1 EP 4120892 A1 EP4120892 A1 EP 4120892A1 EP 21712061 A EP21712061 A EP 21712061A EP 4120892 A1 EP4120892 A1 EP 4120892A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- vehicle
- sensor
- vehicle occupant
- processing unit
- odors
- 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.)
- Withdrawn
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/20—Means to switch the anti-theft system on or off
- B60R25/25—Means to switch the anti-theft system on or off using biometry
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0015—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system
- A61B5/0022—Monitoring a patient using a global network, e.g. telephone networks, internet
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0062—Arrangements for scanning
- A61B5/0064—Body surface scanning
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0075—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/117—Identification of persons
- A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
- A61B5/1176—Recognition of faces
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue
- A61B5/1468—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using chemical or electrochemical methods, e.g. by polarographic means
- A61B5/1477—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using chemical or electrochemical methods, e.g. by polarographic means non-invasive
-
- 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
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- 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
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4005—Detecting, measuring or recording for evaluating the nervous system for evaluating the sensory system
- A61B5/4011—Evaluating olfaction, i.e. sense of smell
-
- 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
- A61B5/4845—Toxicology, e.g. by detection of alcohol, drug or toxic products
-
- 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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/01—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles operating on vehicle systems or fittings, e.g. on doors, seats or windscreens
- B60R25/04—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles operating on vehicle systems or fittings, e.g. on doors, seats or windscreens operating on the propulsion system, e.g. engine or drive motor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
- B60R25/30—Detection related to theft or to other events relevant to anti-theft systems
- B60R25/305—Detection related to theft or to other events relevant to anti-theft systems using a camera
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- 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
- G06V40/172—Classification, e.g. identification
Definitions
- Vehicle interior for the perception and reaction to odors of a vehicle occupant
- the invention relates to a processing unit, a system and a computer-implemented method for a vehicle interior for the perception and reaction to odors of a vehicle occupant.
- Odor sensors are known from the prior art, see for example US 2019/0227042 A1.
- the known odor sensors are based on light absorption spectroscopy, surface adsorption processes or chemical reactions.
- Alcolocks also called alcohol ignition locks, that is, immobilizers in a vehicle that block the vehicle driver from starting the vehicle above a certain level of breath alcohol, see, for example, press releases from the European Parliament.
- the well-known alcolocks include a hand-held device within reach of the driver's seat that measures the alcohol concentration in the breath.
- Handge devices and attached devices are uncomfortable.
- the object of the invention was to improve the perception of odors in a vehicle by vehicle occupants, in particular vehicle drivers, and since improved immobilizers for vehicles can be provided with them.
- the invention provides a processing unit for a vehicle interior for sensing and responding to odors of a vehicle occupant.
- the processing unit comprises a first interface to a first sensor that detects odor molecules in the air and / or body odor of the vehicle occupant in a vehicle interior and converts them into first signals in order to receive the first signals.
- the first signals result from a Licht Cartwir effect or include frequencies and / or amplitudes of vibrations.
- the processing unit comprises a second interface to a second sensor which identifies the vehicle occupant in order to obtain an identification of the vehicle occupant.
- the processing unit executes commands that cause the processing unit, depending on a position of the vehicle occupant in the vehicle interior, to assign odors of the vehicle occupant that indicate drugs and / or diseases to the identification of the vehicle occupant and, in the case of a positive allocation, a second Signal generated, the commands include a first machine learning algorithm that is trained, depending on the first signals alcohol, cocaine, amphetamines, cigarette smoke, cannabis, tetrahydrocannabinol, morphine, methadone, ammonia, acetone or a combination of these substances in the Identify smells of the vehicle occupant.
- the processing unit comprises a third interface to at least one vehicle unit in order to provide the vehicle occupant and / or a vehicle controller with the second signal.
- the first machine learning algorithm is trained on semantic image segmentation to identify the vehicle occupant.
- the commands include a second machine learning algorithm that is trained on semantic image segmentation to identify the vehicle occupant.
- the processing unit is a computing unit that processes input signals and provides output signals, for example as regulating and / or control signals.
- the processing unit comprises an electronic circuit, for example integrated circuits.
- the processing unit comprises programmable logic modules, for example field programmable gateway arrays, in which circuit structures can be programmed by means of hardware commands.
- the processing unit comprises at least one central processor unit that executes software program commands, and / or at least one graphics processor unit for executing processes in parallel or at least one multi-core processor.
- the processing unit comprises at least one memory module, for example RAM, DRAM, SDRAM or SRAM, for a signal and / or data exchange with processors.
- the processing unit is a system-on-chip. That means all or at least a big one Some of the functions are integrated on a chip and can be expanded modularly.
- the processing unit or the chip is integrated into an electronic control device, for example an electronic control device for vehicle control.
- the processing unit executes an artificial neural network that models the mitral cells, apical and lateral dendrites of the Mitralzel cells, the respective soma of the mitral cells and granule cells of the olfactory bulb. That is, the artificial neural network is programmed or is executed on the processing unit in such a way that the olfactory system of mammals is modeled by the execution. For example, the odor molecules from the exhaled breath are made available to the apical dendrites of each mitral cell.
- the mitral cells are neurons of the artificial neural network.
- the apical dendrites correspond to weighted connections of the mitral cell neurons.
- the mitral cell neurons are activated, for example, via activation functions of the artificial neural network and activate further neurons in a further layer of the artificial neural network.
- the other neurons in the other layer correspond to the body cells of the olfactory bulb.
- the processing unit comprises a neural circuit which simulates the olfactory system of mammals.
- the neural circuit is a neuromorphic circuit.
- the olfactory system of mammals is mapped in hardware through the neuromorphic circuit.
- the neuromorphic circuit is manufactured using CMOS technology, for example, which means it is based on complementary metal-oxide semiconductors.
- the neuromorphic circuit includes neuristors, which are components that include models of neurons and synapses.
- the elements of the neuromorphic circuit model, for example, mitral cells, apical and lateral dendrites of the mitral cells, the respective soma of the mitral cells and granule cells of the olfactory bulb.
- the elements of the neuromorphic circuit are connected in an artificial neural network.
- the artificial neural network which modeled the olfactory system of mammals, executed on the neuromorphic circuit.
- the processing unit executes an artificial neural network which models the mitral cells, apical and lateral dendrites of the mitral cells, the respective soma of the mitral cells and granule cells of the olfactory bulb. That is, the artificial neural network is programmed or executed on the neuromorphic circuit in such a way that the execution models the olfactory system of mammals. For example, the odor molecules from the exhaled breath are made available to the apical dendrites of each mitral cell.
- the mitral cells are neurons of the artificial neural network.
- the apical dendrites correspond to weighted connections of the mitral cell neurons.
- the mitral cell neurons are activated, for example, via activation functions of the artificial neural network and activate further neurons in a further layer of the artificial neural network.
- the other neurons in the other layer correspond to the granule cells of the olfactory bulb.
- Vehicles include passenger vehicles, for example cars, minibuses, buses, light and heavy commercial vehicles, agricultural machinery, for example tractors or excavators, rail-bound vehicles, for example trains, ships and passenger drones.
- the invention is therefore not restricted to cars, for example, but represents an advantageous application for several types of vehicles that are driven by a vehicle driver in terms of perception and reaction to odors on perception and reaction to odors is an advantageous application.
- vehicles of fleet operators are equipped with the subject matter of the invention. In this way, fleet operators receive, for example, information about their drivers with regard to their ability to drive as a function of alcohol consumption or an illness recognized by the subject matter of the invention.
- the recordings according to the invention are transmitted to the fleet operator, for example via electronic logbook entries and / or via radio communication.
- Odors include breath odor and other odors from other body orifices of living beings, that is to say body odors, for example body vapors through the skin. If there are animals, for example dogs, in the vehicle interior, the first sensor also detects smells from the animals. Based on the functionalities of the first sensor, it is initially not possible to distinguish from which living beings, for example humans or animals, odors are detected. The living beings are differentiated by the functionality of the second sensor. That is, through the combination of the functionalities of the first sensor and the second sensor, odors can be assigned to the respective living beings.
- Vehicle occupants include vehicle drivers, vehicle occupants who do not perform the task of driving a vehicle, for example co-drivers or passengers, and animals.
- the functionalities of the first sensor detect odors from the driver, front passenger and animals in the vehicle interior.
- odors are evaluated by vehicle drivers.
- Light interaction includes light scattering, backscattering, reflection, transmission, diffraction and refraction.
- the first signals result from light scattering.
- Odor molecules are recorded, for example, by means of the signatures of the odor molecules.
- the signatures include absorption lines in an absorption spectrum, scattered light specific for the respective molecules, for example Raman or Ra yleigh scattering, specific oscillation patterns based on molecular masses or characteristics in impedance spectroscopy.
- the vibration patterns are recorded, for example, with acceleration sensors, for example micro-electro-mechanical systems.
- the signatures for the respective molecule are specific scattered light, for example scattered light from backscattering.
- An odor molecule is a molecule with a distinctive odor.
- the odor molecule (R) - (+) - limonene characterizes the main odorous substance of the lemon.
- the signals are, for example, electrical signals.
- the electrical signals include oscillation frequencies.
- the vehicle occupant is identified via face recognition, for example via three-dimensional face recognition, the second sensor being a 3D sensor or 2D sensor or comprising several 2D sensors.
- three-dimensional face recognition comprises recognition, classification and / or localization of individual points on the face, for example cheekbones or distances between eyes.
- the vehicle occupant is identified via skin texture analysis.
- skin texture analysis includes arrangement of lines and pores.
- the instructions that the processing unit executes are program instructions or hardware instructions.
- the commands are available as software code or machine code, for example.
- Machine learning is a technology that teaches computers and other data processing devices to perform tasks by learning from data, rather than being programmed to perform the tasks.
- the machine learning algorithm learns the smells and / or the identification of the vehicle occupant from the data.
- One advantage of determining odors that indicate drugs and / or diseases in the breath and / or from the body odor of the vehicle occupant using the first machine learning algorithm is that no chemical methods are used to determine the alcohol content in breath, for example on a blowpipe are required and are therefore uncomfortable, or surface contact processes, for example adsorption processes, or invasive processes, for example Blood alcohol determination, are to be used. Breathing air and other body odors are released continuously and are evaluated by the processing unit.
- the first machine learning algorithm comprises a graph neural network, in the input layer of which a graph is entered, the nodes of which model atoms and the edges of which model molecular connections.
- the odor molecules are modeled as graphs and the smells are determined with a graph neural network.
- the graphene neural network has learned, for example, to determine the odors associated with the odor molecules from the structure of odor molecules. This type of odor determination is known as a quantitative structure odor relationship, see for example B. Sanchez-Lengeling et al., “Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules”, arXiv: 1910.10685v2 [stat.ML]
- Drugs and / or diseases have characteristic smells that can be detected in the air we breathe. Drugs that can be detected in the air or that are consumed include alcohol, cocaine, amphetamines, cigarette smoke, cannabis, tetrahydrocannabinol, morphine and methadone. For example, a smell of ammonia suggests kidney disease. A smell of acetone suggests diabetes.
- the second signal comprises an electrical signal for a display device, for example a display in the form of an infotainment system or a head -Up displays or an acoustic device, for example a loudspeaker system in the vehicle interior, to inform the vehicle occupant visually or acoustically that they are not fit to drive because of their alcohol content.
- the second signal also includes a regulating and / or control signal for the vehicle control in order to prevent the vehicle from moving off in this case.
- a control unit for vehicle communication is another example of a vehicle unit.
- Vehicle communication includes vehicle to everything and vehicle to vehicle communication.
- a fleet operator for example, is operated via vehicle communication Company that owns the vehicle or a government agency informs that a driver of one of their vehicles is unfit to drive because of alcohol content.
- the processing unit compares or matches the odors with the driver of the vehicle.
- the dependency of a position of the vehicle occupant also evaluates whether the vehicle occupant to whom the smells were assigned is located in a vehicle driver's area, for example on the vehicle driver's seat, and in the detection area of the first and / or second sensor.
- the driver's ability to drive is impaired by alcohol consumption.
- a co-driver is fit to drive.
- the front passenger could move into the area of the vehicle driver when starting the journey.
- the processing unit would evaluate the passenger's smells, not detect any drugs, and provide a second signal to drive off via the third interface of the vehicle control system.
- the impaired driver would then drive the vehicle.
- the processing unit recognizes in this case that the detected smells are assigned to the passenger and not to the driver.
- the invention provides a system for a vehicle interior for the perception and reaction to odors of a vehicle occupant be ready.
- the system comprises at least one first sensor which detects odor molecules in the air and / or body odor of the vehicle occupant in the vehicle interior and converts them into first signals.
- the system further comprises at least one second sensor that identifies the vehicle occupant.
- the system comprises a processing unit according to the invention, which is connected to transmit signals to the first and second sensor via a first and second interface.
- the system provides a second signal to the processing unit of an optical, acoustic and / or tactile information unit or a vehicle control unit via a third interface.
- the invention provides a computer-implemented method for sensing and responding to odors of a vehicle occupant.
- the method comprises the steps
- the invention provides a computer program for perceiving and responding to odors of a vehicle occupant.
- the computer program includes commands that cause an inventive Processing unit executes a method according to the invention when the computer program is executed on the processing unit.
- the machine learning algorithm trained on semantic image segmentation first classifies the living being, that is, whether a person or an animal, for example a dog, has been recorded. Then a body of the living being is recognized and body parts are classified. A body model is thus obtained. Body parts that are classified include the face and limbs, such as hands. Features of the face or limbs, such as the hands, are then determined.
- Semantic image segmentation enables face recognition, limb, for example hand recognition, and identification via face recognition and / or limb, for example hand recognition.
- the first or second machine learning algorithm segments a face of a vehicle occupant from three-dimensional recordings of a vehicle interior and assigns the meaning of the face to this recording area, analogously for limbs, for example hands.
- further elements are segmented and assigned their respective meanings, for example mouth, eyes, nose, ears, forehead, chin and / or facial muscles and their arrangement with one another.
- the number of fingers, length and / or width of individual fingers, fingernail structure, palm size, vein pattern of the palm of the hand, the back of the hand or the finger veins are biometric features that identify the vehicle occupant.
- the machine learning algorithm comprises an artificial neural network that is trained on semantic image segmentation.
- the artificial neural network is, for example, a convolution network, for example a VGG Net, see K. Simonyan et al., “Very Deep Convolutional Networks For Large-Scale Image Recognition”, arXiv: 1409.1556v6 [cs.CV].
- the artificial one is trained by means of monitored learning. This makes the learning process easier to understand than with unsupervised learning, which is advantageous for the validation and safeguarding of the processing unit.
- the machine learning algorithm comprises a random forest classifier comprising uncorrelated decision trees which grow after a certain randomization during a learning process. For a classification, each tree in this forest can make a decision and the class with the most votes decides the final classification.
- Advantages of the Random Forest are, in particular, that it trains relatively quickly due to the short training and / or construction times of a single decision tree, that evaluations can be parallelized due to several trees and that important classes, such as for face recognition or limb recognition, for example hand recognition, can be recognized.
- the machine learning algorithm comprises a support vector machine classifier which subdivides a set of objects into classes in such a way that as broad an area as possible remains free of objects around class boundaries.
- the Maschineniemalgorithmus for example the artificial neural network on the computer according to the invention, is trained on semantic image segmentation.
- the computer includes a microarchitecture for the parallelized execution of processes in order to be able to train the artificial neural network with a large number of data in a time-efficient manner.
- Graphics processors include such a microarchitecture.
- the trained network is executed on the computer.
- the processing unit is integrated in a vehicle or in an on-board network of a vehicle.
- the first and the second sensor are integrated into the vehicle electrical system. This will make the Communication between the sensors, the processing unit and the vehicle control system is facilitated.
- the vehicle electrical system is, for example, a CAN bus.
- At least part of the communication between the sensors, the processing unit and the vehicle control takes place wirelessly according to one aspect of the invention, for example by means of Bluetooth Low Energy, ANT or ANT +, or another radio network standard, for example for the 868 MHz band for which it was recognized , which can transmit relatively high energy densities.
- communication between the sensors and between the sensors and the processing unit takes place wirelessly.
- the communication between the processing unit and the vehicle control is wired in order to increase operational safety and to be able to better ward off cyberattacks.
- the first sensor is a vehicle lidar sensor.
- the vehicle lidar sensor is designed to detect odor molecules as a function of light scattered back from the vehicle interior.
- a vehicle lidar sensor is a lidar sensor that is suitable for use in the vehicle environment, for example in the vehicle interior.
- vehicle lidar sensors emit laser pulses with wavelengths in the infrared range that are not harmful to humans.
- the vehicle lidar sensor comprises a CCD or CMOS chip with integrated evaluation electronics for spectroscopy, for example Raman spectroscopy.
- spectroscopy for example Raman spectroscopy.
- light wavelengths of the backscattered light, including elastic backscattering by the odor molecules are determined from the signals of the pixels of the CCD or CMOS chip, on the basis of which the odor molecules are detected.
- the vehicle lidar sensor is designed to emit several light pulses of different wavelengths and to detect the odor molecules from the backscattered light for each of the wavelengths.
- the vehicle lidar sensor comprises control electronics in order to emit different wavelengths.
- the vehicle lidar sensor is designed to emit two light pulses of different wavelengths.
- a first wavelength is selected in such a way that it is absorbed by the substance whose concentration is to be determined.
- the second wavelength is chosen such that it is not absorbed or absorbed as little as possible.
- a concentration profile of the substance is thus calculated from the stepwise comparison of the backscatter signals at the first and the second wavelength using differential absorption. In this way, for example, a concentration of alcohol molecules in the breath or the body odor of the vehicle occupant is then advantageously determined in the vehicle interior.
- the vehicle lidar sensor comprises a quality switch.
- the Q-switch With the Q-switch, the light pulses become shorter. This enables high peak performances to be achieved even with comparatively low energies.
- the low energies mean that the vehicle lidar sensor is harmless to the vehicle driver. High peak performance makes odor molecules dissolvable.
- the Q-switch is, for example, an electro-optical modulator.
- the vehicle lidar sensor is housed.
- the second sensor is a 2D or 3D camera sensor, radar sensor or lidar sensor.
- the system is designed to obtain the identification of the vehicle occupant from facial recognition of the vehicle occupant.
- the 3D camera sensor is, for example, a time-of-flight sensor.
- a three-dimensional geometry of the face is determined using a time-of-flight method based on which the second sensor works.
- the three-dimensional geometry of the face is determined by means of structured light.
- Structured Lightning is implemented, for example, with a 3D camera sensor or a lid sensor.
- the system comprises a sensor that combines the functionalities of the first and second sensor, the sensor being a light transit time sensor, the first signals result from light from the sensor scattered back from the vehicle interior and the identification of the Vehicle occupants sen from light transit times of light pulses from the sensor to a body surface, for example the face surface of the vehicle occupant.
- the sensor is, for example, a time-of-flight camera or a vehicle lidar sensor.
- vehicle systems comprising an interior monitoring system for monitoring a state of alertness of a vehicle driver and for monitoring safety systems, for example fastened seat belts.
- interior monitoring systems include a time-of-flight camera or a vehicle lidar sensor.
- the invention proposes to configure these systems in such a way that smells that indicate drugs and / or diseases are perceived in the breath and / or body vapors of vehicle occupants by means of these systems in order to prevent the vehicle from moving off if necessary. This means that no additional systems are required, for example to provide an alcohol-sensitive immobilizer.
- the second sensor detects individual limbs.
- the system is designed to identify the vehicle occupant as a function of the detected limbs. For example, hands are recorded by a camera. The system then differentiates between the hands of the vehicle driver and the hands of a passenger. This further prevents misuse.
- the first sensor is a finger alcohol measuring device on which a finger of a hand is placed, is illuminated and the blood alcohol concentration is determined based on reflections or other light interactions.
- the first sensor when used in the vehicle interior, is on a vehicle steering wheel or in an area of a dashboard and the second sensor or the sensor is on the vehicle steering wheel, in an area of the dashboard, in an area of a windshield of the vehicle or arranged in an area of a vehicle headliner.
- the first sensor is a vehicle lid sensor designed to detect odor molecules as a function of light scattered back from the vehicle interior
- the second sensor is a CCD or CMOS sensor for spectroscopy of the backscattered light.
- the second sensor is a time-of-flight sensor of an interior monitoring system.
- the second signal is a control signal for an immobilizer of the vehicle and the third interface provides the second signal of the immobilizer or the second signal is a control signal and forwards a fail-safe or fail-operational state the vehicle.
- the invention thus provides an alcohol-sensitive immobilizer or an improved alcolock.
- Fail-safe means that, for example, the vehicle does not start up if the driver has detected odors that indicate drugs and / or illness.
- Fail-operational means that, for example, the vehicle remains operational and continues to drive until it is safe to stop if the driver of the vehicle detects smells that indicate drugs and / or illness while driving.
- the system comprises a memory and / or communication means to store identified odors of drugs and / or diseases and / or to provide information about the identified odors to a company that owns the vehicle or to a government agency. This allows the company or government agency to remotely stop one of their vehicles or switch them to a fail-operational state. It is also used to monitor vehicle drivers employed by the company or by government agencies with regard to their ability to drive.
- Fig. 2 shows an embodiment of a system according to the invention in a vehicle interior
- FIG. 3 shows an embodiment of a processing unit according to the invention
- Fig. 6 is a schematic representation of an embodiment of a fiction, contemporary method.
- the system 20 is inte grated in Fig. 2 in a vehicle interior. 4 shows the system 20 schematically.
- the system 20 comprises, for example, a first sensor 21.
- the first sensor 21 is integrated into a vehicle steering wheel and designed to detect odor molecules in the breathed air and / or from the body odor of the vehicle occupant F.
- the system 20 further comprises second sensors 22 which identify a face of the vehicle driver by means of software-based face recognition.
- One of the second sensors 22 is arranged, for example, in the area of a rearview mirror in the vehicle interior and is, for example, a time-of-flight camera.
- the other of the second sensors 22 is integrated in the dashboard and includes, for example, a camera, lidar or radar sensor.
- the system 20 comprises a processing unit 10 as shown in FIG. 3.
- the processing unit 10 receives signals from the first sensor 21 via a first interface 11.
- the processing unit 10 receives signals from the second sensor (s) 22 via a second interface 12.
- the processing unit determines the breathing air and / or body odors of the vehicle occupant , which emits breathing air in the direction of the vehicle steering wheel, smells that, for example, indicate alcohol consumption.
- the odors or the substances relevant to the odors are determined by means of machine learning processes.
- the processing unit links the smells with the identity of the vehicle occupant in order to prevent fraud or misuse of the system 20. If it is recognized, for example, that the alcohol concentration in the driver's breath exceeds a legal limit value, the processing unit 10 generates a second signal.
- the second signal is provided, for example, via a third interface 13 of the processing unit 10 to a vehicle control ECU.
- the second signal causes the vehicle control system to prevent the vehicle from starting the engine and / or starting the transmission.
- the vehicle control ECU is, for example, an electronic control unit.
- Fig. 5 shows the system in the embodiment with only one sensor, for example a time-of-flight sensor or a lidar sensor.
- One sensor takes over the functionalities of the first sensor 21 and the second sensor 22.
- the method according to the invention is shown in FIG. 6.
- first signals that describe odor molecules are obtained.
- a procedural step V2 an identification of the vehicle occupant is obtained.
- odors are identified that indicate drugs and / or diseases as a function of the first signals by means of a first machine learning algorithm that is trained, as a function of the first signals, odors including odors of alcohol, cocaine, amphetamines, cigarette smoke, cannabis To identify tetrahydro- cannabinol, morphine, methadone, ammonia, acetone or a combination of these substances.
- the odors are assigned to the identification of the vehicle occupant as a function of a position of the vehicle occupant F in the vehicle interior.
- a second signal is generated in the event of a positive assignment.
- the second signal is provided to at least one vehicle unit.
- the method is carried out with the processing unit 10 or the system 20.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Psychiatry (AREA)
- Mechanical Engineering (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physiology (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Optics & Photonics (AREA)
- Child & Adolescent Psychology (AREA)
- Electromagnetism (AREA)
- Neurosurgery (AREA)
- Neurology (AREA)
- Remote Sensing (AREA)
- Computational Linguistics (AREA)
- Radar, Positioning & Navigation (AREA)
- Evolutionary Computation (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102020203584.9A DE102020203584B4 (de) | 2020-03-20 | 2020-03-20 | Verarbeitungseinheit, System, und computerimplementiertes Verfahren für einen Fahrzeuginnenraum zur Wahrnehmung und Reaktion auf Gerüche eines Fahrzeuginsassen |
| PCT/EP2021/055990 WO2021185645A1 (de) | 2020-03-20 | 2021-03-10 | Verarbeitungseinheit, system, und computerimplementiertes verfahren für einen fahrzeuginnenraum zur wahrnehmung und reaktion auf gerüche eines fahrzeuginsassen |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4120892A1 true EP4120892A1 (de) | 2023-01-25 |
Family
ID=74874810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21712061.7A Withdrawn EP4120892A1 (de) | 2020-03-20 | 2021-03-10 | Verarbeitungseinheit, system, und computerimplementiertes verfahren für einen fahrzeuginnenraum zur wahrnehmung und reaktion auf gerüche eines fahrzeuginsassen |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20230127231A1 (de) |
| EP (1) | EP4120892A1 (de) |
| DE (1) | DE102020203584B4 (de) |
| WO (1) | WO2021185645A1 (de) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102022201704B4 (de) | 2022-02-18 | 2025-12-18 | Zf Friedrichshafen Ag | Gasanalyse-System für Fahrzeuge und Anordnung mehrerer derartiger Gasanalyse-Systemen |
| DE102022201701A1 (de) * | 2022-02-18 | 2023-08-24 | Zf Friedrichshafen Ag | Fahrzeugbedienelement zum Messen von Konzentrationen von Substanzen in Ausatemluft und/oder Körpergeruch von Fahrzeuginsassen |
| DE102022201915A1 (de) | 2022-02-24 | 2023-08-24 | Zf Friedrichshafen Ag | Steuergerät, Bausatz, Verfahren und Computerprogramm für ein Transportsystem zum gezielten Regeln und/oder Steuern einer Zu- und/oder Abluft und Transportsystem |
| DE102022203044A1 (de) | 2022-03-29 | 2023-10-05 | Zf Friedrichshafen Ag | Gasanalyse-System anordbar in einem Fahrzeuginnenraum und ausgelegt zum Bestimmen von Substanzen in Ausatemluft und/oder Körpergeruch von Fahrzeuginsassen |
| DE102022204281A1 (de) | 2022-05-02 | 2023-11-02 | Zf Friedrichshafen Ag | Verfahren zur Analyse einer Menge eines innerhalb eines Fahrzeugs vorliegenden Gases, Verwendung von analytischen Daten und Verwendung einer Analyseeinrichtung sowie Analyseeinrichtung, Analysesystem und Fahrzeug |
| DE102022212997B3 (de) | 2022-12-02 | 2024-06-06 | Zf Friedrichshafen Ag | Anordnung wenigstens eines Systems in einem Innenraum eines Fahrzeuges zum Überwachen eines Zustandes wenigstens eines Fahrzeuginsassen |
| DE102022212999B3 (de) | 2022-12-02 | 2024-06-06 | Zf Friedrichshafen Ag | Lenkstockschalter zum Überwachen wenigstens eines Fahrzeuginsassen und Fahrzeug umfassend einen derartigen Lenkstockschalter |
| WO2024115622A1 (de) | 2022-12-02 | 2024-06-06 | Zf Friedrichshafen Ag | Lenkstockschalter zum überwachen wenigstens eines fahrzeuginsassen und fahrzeug umfassend einen derartigen lenkstockschalter |
| DE102022212996A1 (de) | 2022-12-02 | 2024-06-13 | Zf Friedrichshafen Ag | Fahrzeuginsassen- Überwachungssystem und Fahrzeug umfassend ein Fahrzeuginsassen-Überwachungssystem |
| MX2024005447A (es) * | 2023-05-04 | 2024-12-06 | Chancelor Winston HEMPHILL | Sistema integrado de prevención de la conducción bajo los efectos del alcohol u otras drogas y métodos relacionados con este |
| USD1121517S1 (en) * | 2023-06-19 | 2026-04-07 | Aston Martin Lagonda Limited | Air vent for automobile or replica thereof |
| USD1121522S1 (en) * | 2023-06-19 | 2026-04-07 | Aston Martin Lagonda Limited | Dashboard for automobile or replica thereof |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7823681B2 (en) | 2007-10-10 | 2010-11-02 | B.E.S.T. Labs, Inc. | Breath alcohol ignition interlock device with biometric facial recognition with real-time verification of the user |
| US8686864B2 (en) | 2011-01-18 | 2014-04-01 | Marwan Hannon | Apparatus, system, and method for detecting the presence of an intoxicated driver and controlling the operation of a vehicle |
| US20150379362A1 (en) | 2013-02-21 | 2015-12-31 | Iee International Electronics & Engineering S.A. | Imaging device based occupant monitoring system supporting multiple functions |
| KR101637773B1 (ko) | 2014-12-11 | 2016-07-07 | 현대자동차주식회사 | 냄새 감성 판정 장치 및 방법 |
| US9988055B1 (en) | 2015-09-02 | 2018-06-05 | State Farm Mutual Automobile Insurance Company | Vehicle occupant monitoring using infrared imaging |
| US9797881B2 (en) | 2015-11-05 | 2017-10-24 | GM Global Technology Operations LLC | Method and system for controlling a passive driver impairment detection system in a vehicle |
| US10095229B2 (en) | 2016-09-13 | 2018-10-09 | Ford Global Technologies, Llc | Passenger tracking systems and methods |
| CN109313112A (zh) | 2016-09-27 | 2019-02-05 | 株式会社而摩比特 | 气味测量装置及气味数据管理装置 |
| US20190197430A1 (en) * | 2017-12-21 | 2019-06-27 | Lyft, Inc. | Personalized ride experience based on real-time signals |
-
2020
- 2020-03-20 DE DE102020203584.9A patent/DE102020203584B4/de active Active
-
2021
- 2021-03-10 WO PCT/EP2021/055990 patent/WO2021185645A1/de not_active Ceased
- 2021-03-10 EP EP21712061.7A patent/EP4120892A1/de not_active Withdrawn
- 2021-03-10 US US17/913,121 patent/US20230127231A1/en not_active Abandoned
Also Published As
| Publication number | Publication date |
|---|---|
| DE102020203584B4 (de) | 2024-12-12 |
| DE102020203584A1 (de) | 2021-09-23 |
| US20230127231A1 (en) | 2023-04-27 |
| WO2021185645A1 (de) | 2021-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102020203584B4 (de) | Verarbeitungseinheit, System, und computerimplementiertes Verfahren für einen Fahrzeuginnenraum zur Wahrnehmung und Reaktion auf Gerüche eines Fahrzeuginsassen | |
| DE102018207069B4 (de) | Verfahren und Steuereinheit zum Betreiben eines autonomen Fahrzeugs | |
| DE112019001601T5 (de) | Sicherheitsverbessertes computergestütztes-fahren-verfahren und -vorrichtung | |
| Yang et al. | Comparison among driving state prediction models for car-following condition based on EEG and driving features | |
| EP3947086B1 (de) | Verfahren und einrichtung zur überwachung eines fahrbetriebsbedingten gesundheitszustandes von insassen eines insbesondere autonomen fahrzeugs | |
| DE102007046037B3 (de) | Vorrichtung zur Erhöhung der Sicherheit im Straßenverkehr | |
| EP2751788B1 (de) | Vorrichtung zur einstellung wenigstens eines betriebsparameters wenigstens eines fahrzeugsystems eines kraftfahrzeugs | |
| DE10321750A1 (de) | Fahrzeugpersonalisierung durch biometrische Identifizierung | |
| DE102019210929B4 (de) | Computerimplementiertes Verfahren zum maschinellen Lernen von Husten- und/oder Niesgeräuschen von ein Beförderungsmittel nutzenden Fahrgästen, um bei erkannten Husten- und/oder Niesgeräuschen Maßnahmen zur Reinigung des Beförderungsmittels einzuleiten, und Steuergerät, Verfahren, Vorrichtung, Beförderungsmittel und Computerprogramm zum Einleiten der Maßnahmen | |
| DE112018007454T5 (de) | Insassenzustand-Bestimmungsvorrichtung, Warnausgabe-Steuervorrichtung und Insassenzustand-Bestimmungsverfahren | |
| DE102024117270B4 (de) | System und Verfahren zum Vorhersagen von Verletzungen von Fahrzeuginsassen nach einem Ereignis | |
| DE102021128908A1 (de) | Automatisiertes triageschwestersystem in einem fahrzeug | |
| Tariq et al. | Motor imagery based EEG features visualization for BCI applications | |
| DE102008038855B4 (de) | System zur Erkennung einer Gefahrensituation | |
| DE112022001065T5 (de) | Informationsverarbeitungseinrichtung, informationsverarbeitungsverfahren und informationsverarbeitungsprogramm | |
| EP3968850B1 (de) | System zum erfassen von biosignalen einer person, fortbewegungsmittel mit einem solchen system | |
| DE102018132868A1 (de) | Warnsystem und Warnverfahren für ein Fahrzeug | |
| DE102019203080A1 (de) | Verfahren und System zum Bestimmen eines Kinetosezustandes einer Person, wobei die Person ein Fahrzeuginsasse ist | |
| DSouza et al. | Brain-based indicators of passenger trust during open-road driving | |
| Fu et al. | Decoding passenger's EEG signals from encountering emergency road events | |
| DE102019208979A1 (de) | Steuergerät zum Einsatz in einem Kraftfahrzeug | |
| DE102019208992A1 (de) | Steuergerät zum Einsatz in einem Kraftfahrzeug | |
| DE102019208970A1 (de) | Steuergerät zum Einsatz in einem Kraftfahrzeug | |
| Kolachalama et al. | A Deep Learning Framework for Time Series Prediction of Passenger Motion Sickness Based on Vehicle Dynamics Data | |
| DE102022204113A1 (de) | Verfahren, System und Computerprogramm zur sicheren Erprobung eines automatisierten Fahrzeuges durch Erhöhen der Aufmerksamkeit eines Sicherheitsfahrers |
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: 20220906 |
|
| 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) | ||
| GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
| INTG | Intention to grant announced |
Effective date: 20250212 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20250613 |