WO2024251503A1 - Procédé de détection d'un être vivant - Google Patents
Procédé de détection d'un être vivant Download PDFInfo
- Publication number
- WO2024251503A1 WO2024251503A1 PCT/EP2024/063765 EP2024063765W WO2024251503A1 WO 2024251503 A1 WO2024251503 A1 WO 2024251503A1 EP 2024063765 W EP2024063765 W EP 2024063765W WO 2024251503 A1 WO2024251503 A1 WO 2024251503A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- database
- detection method
- living
- 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.)
- Ceased
Links
Classifications
-
- 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
- G06V20/593—Recognising seat occupancy
-
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/886—Radar or analogous systems specially adapted for specific applications for alarm systems
-
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
-
- 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
- G06V40/15—Biometric patterns based on physiological signals, e.g. heartbeat, blood flow
Definitions
- the present invention relates to a method for detecting a living being. It finds a particular but non-limiting application in motor vehicles.
- a method for detecting a living being inside a vehicle comprises analyzing the respiratory rate from the variation of a power or phase signal over time and comparing it with a respiratory model of a living being. This makes it possible in particular to trigger an alarm system when an occupant, in particular a child, is forgotten in the vehicle.
- a disadvantage of this state of the art is that the reliance on a clear respiratory signal pattern can be masked by any movement of the living being's body. Furthermore, the body movement patterns of living beings are difficult to model due to their variability and the detection algorithms used are generally based on a simple signal-to-noise ratio check to detect movements of living beings with high energy (i.e. with a high signal-to-noise ratio). However, this type of detection can be confused with external effects (vehicle vibrations, vehicle jolts, etc.) that generate energy comparable to a movement of a living being and can easily lead to false alarms, called true negative cases.
- the present invention aims to propose a method for detecting a living being which makes it possible to resolve the aforementioned drawback.
- the invention proposes a method for detecting a living being, characterized in that said detection method comprises: - acquiring a plurality of images in a time window, each image comprising a series of data with which a position, a power and a speed are associated, - constructing a first database of instantaneous data from the plurality of images, said instantaneous data being based on said position, said power and said speed of each data of each image acquired in said time window, - constructing a second database of temporal data from said plurality of images, said temporal data being calculated from a periodic signal of each image taken over a moving time window, - applying said first database and said second database as input to a machine learning model, - the execution of said machine learning model, - the establishment of a classification by said machine learning model as to the presence/absence of a living being, - based on said classification, the transmission of corresponding information to a management unit.
- the detection method is based on the introduction of a temporal characteristic.
- This temporal characteristic takes into account the changes of the radar images over time.
- the objective is to have a characteristic that reflects any periodic or oscillatory pattern of a signal (e.g. respiratory) and to use it to improve the accuracy of the detection.
- a signal e.g. respiratory
- One of the advantages over conventional detection methods is that this characteristic is not used alone but combined with other characteristics based on a single radar image and, therefore, the final decision does not depend solely on a single characteristic as in the case of conventional detection methods.
- said detection method may further comprise one or more additional characteristics taken alone or in all technically possible combinations, among the following.
- the instantaneous data are: - average values of said position and/or said power and/or said speed of said data of each image, or - variances of said data of each image.
- said machine learning model is a supervised model.
- said supervised model is a support vector machine or a random forest.
- said periodic signal is a breath or a heartbeat.
- said living being is of the adult, child, or animal type.
- said time window is approximately five seconds.
- the time data is a maximum power or a phase variation of said periodic signal.
- the construction of said second database comprises: - buffering the time data to obtain a plurality of time values, - the removal of the continuous component of said time values, - applying a Fourier Transform to said time values to obtain frequency values, - from said frequency values, the extraction of a maximum value in a given frequency range.
- said given frequency range is a breathing frequency range or a heartbeat frequency range.
- the construction of said second database further comprises the normalization of said frequency values before said extraction of said maximum value.
- said plurality of images is obtained from waves received by a wave emission/reception entity of a sensor.
- said moving time window is three images per second.
- said detection method is a method of detecting a living being inside a vehicle.
- the data series is a series of points.
- the images are images acquired inside a vehicle.
- said periodic signal is representative of a type of living being.
- the senor is a radar sensor.
- the images are radar images.
- the moving time window has the same duration as the time window.
- a system for detecting a living being characterized in that said detection system comprises: - (a) a sensor configured to acquire a plurality of images in a time window, each image comprising a series of data with which a position, a power and a speed are associated, - (b) a processing unit configured to: - constructing a first database of instantaneous data from the plurality of images, said instantaneous data being based on said position, said power and said speed of each data of each image acquired in said time window, - constructing a second database of temporal data from said plurality of images, said temporal data being calculated from a periodic signal of each image taken over a moving time window, - applying said first database and said database as input to a machine learning model, - run said machine learning model, - (c) said machine learning model configured to be executed and establish a classification as to the presence/absence of a living being, - said processing unit being further configured to, depending on said classification, transmit corresponding information to a management
- FIG. 1 illustrates a non-limiting example of a radar image acquired by a radar image acquisition step of the radar detection method. , said radar image comprising a plurality of points,
- FIG. 1 illustrates a first graph which illustrates a phase variation of a periodic signal corresponding to the breathing or heartbeat of a living being and a second graph which illustrates noise in the absence of a living being, according to a non-limiting embodiment
- FIG. 1 illustrates a first graph that illustrates a power level of a periodic signal corresponding to a child's breathing, and a second graph that illustrates a power level of a water bottle, according to a non-limiting embodiment
- FIG. 1 illustrates a system for detecting a living being configured to implement the method of detecting the , according to a non-limiting embodiment.
- the method 1 for detecting a living being o is described with reference to FIGS. 1 to 7.
- the living being o is located in a passenger compartment 20 of a vehicle 2, namely inside the vehicle 2.
- This non-limiting embodiment is taken in the remainder of the description.
- the living being o is located on a back seat in a non-limiting example.
- the detection method 1 makes it possible in particular to detect a living being o in a vehicle 2.
- the vehicle 2 is a motor vehicle.
- motor vehicle we mean any type of motorized vehicle.
- This embodiment is taken as a non-limiting example in the remainder of the description. In the remainder of the description, the vehicle 2 is thus otherwise called motor vehicle 2.
- the detection method 1 comprises the following steps.
- a plurality of images I are acquired by a sensor 21 in a time window w.
- the sensor 21 is a radar sensor.
- the images I are therefore in this case radar images I.
- the time window w is approximately five seconds. It is less than 10 seconds according to the EuroNCAP specification for the automotive application.
- each radar image I comprises a series of data p with which a position Po, a power Pu and a speed v are associated.
- the position Po is defined by the Cartesian parameters x, y and z or by the parameters of radius (or distance), azimuth and elevation.
- the data p are points. This non-limiting embodiment is taken as a non-limiting example in the remainder of the description. It will be noted that the acquisition (in milliseconds) of a single radar image is done in an acquisition window called a "frame" in English.
- the plurality of radar images I are obtained from radar waves r' received by a radar wave transmitting/receiving entity 210 of the radar sensor 21 configured to transmit radar waves r (which are millimeter waves) and receive in return radar waves r' (which are millimeter waves) which have reflected on a target object, such as a living being o.
- a Fourier Transform FFT is applied by a processing unit (not shown) of the radar sensor 21 to calculate the reflection distances on the target object, for example according to a time of flight algorithm known to those skilled in the art (“Time Of Flight” in English). This process known to those skilled in the art is called “Range Processing” in English. It is not shown in the figures.
- the processing unit of the radar sensor 21 calculates peaks of the reflection distances by removing the peaks that have not moved over the time window w. This process known to those skilled in the art is called “Clutter Removal” in English. It is not illustrated in the figures.
- the radar images I are images acquired inside the motor vehicle 2, namely in its passenger compartment 20.
- a first database DS of instantaneous data Fi is constructed by a processing unit 4 from the plurality of radar images I.
- the instantaneous data Fi (otherwise called instantaneous characteristics Fi) are based on the position Po, the power Pu and/or the speed v of each point p of each radar image I acquired in said time window w.
- the instantaneous data Fi are: - the average values of the position data Po, power Pu and speed v of the points p of each radar image I, - the variances Va of the position data Po, power Pu and speed v of the points p of each radar image I.
- temporal data Ft are used as described below. The idea of using temporal data Ft (otherwise called temporal characteristics Ft) comes from the fact that a radar image I of a target object, here a living being o, can show periodic patterns, in particular in the case of respiration or heart rate. The temporal data Ft are thus calculated from a periodic signal S. In non-limiting embodiments, the periodic signal S is thus a respiration or a heart rate (corresponding to heartbeats).
- the periodic signal S illustrated in drawing (a) of the illustrates a periodic diagram of the Ph phase of a living being, here an adult, over a moving time window w'.
- the signal emitted in an emission window called "Chirp” in English, the emission being done periodically and on the ordinate is represented the phase Ph in degrees (°).
- the emission "Chirps" (in microseconds) are used to construct the radar image I of each acquisition window. In an acquisition window, there are several emission "Chirps”.
- a similar periodic pattern can be extracted from the variation of power over time that is due to the periodic movement of breathing or heart rate of a living being o. Indeed, the power changes periodically due to the back and forth movement of breathing or heart rate of the living being o that moves closer to and away from the radar wave transmitting/receiving entity 210 of the radar sensor 21.
- Drawing (a) of the illustrates a non-limiting example of a child in different positions inside the motor vehicle 2, the different positions pos1, pos2, pos3, pos4, pos5, pos6 being illustrated by different gray colors.
- the diagram is compared to a true negative diagram (drawing (b)) which uses a water bottle which is shaken in the motor vehicle 2, these different positions pos1', pos2', pos3', pos4', pos5', pos6' also being illustrated by different gray colors.
- the maximum power Pk of the radar image I On the abscissa is shown the maximum power Pk of the radar image I .
- the number of radar images I is represented on the ordinate.
- the drawing (a) illustrates the variation in power of a periodic signal S on a moving window w' corresponding to the breathing or a heartbeat of a living being o which is here a child, at different positions here in the passenger compartment 20 of the motor vehicle 2.
- the drawing (b) thus illustrates the variation in power of an inert object, here a bottle of water, at different positions here in the passenger compartment 20 of the motor vehicle 2.
- the power levels are similar in both cases, but the variation is different in time, namely the periodic pattern.
- a second database DS’ of temporal data Ft is constructed by the processing unit 4 from the plurality of radar images I.
- the temporal data Ft are calculated from a periodic signal S of each radar image I recorded on the moving time window w’.
- a moving time window w’ there will thus be a periodic signal S of several radar images I.
- the moving time window w’ has the same duration as the time window w.
- the moving time window w’ is three radar images I per second. This makes it possible to have a variation of the temporal data Ft over time sufficient to be able to differentiate cases of true positives (living being o) from cases of true negatives (inert object in motion).
- step E3 can be performed in parallel with step E2 or before step E2.
- the time data Ft are a maximum power Pmax or a phase variation ⁇ of said periodic signal S.
- the construction of the second database DS' comprises: - in a sub-step E30, placing the time data Ft in a buffer memory B to obtain a plurality of time values Vt, - in a sub-step E31, the removal of the continuous component DC of said time values Vt, - in a sub-step E32, the application of a Fourier Transform FFT on said time values Vt to obtain frequency values Vf, - in a sub-step E34, from said frequency values Vf, the extraction of a maximum value Max in a given frequency range I_Bth.
- the maximum power information Pmax or phase variation ⁇ is calculated according to a history using the moving time window w’.
- the buffer B has a size for ten radar images I, which corresponds to approximately three seconds if the moving time window w’ is three radar images I per second.
- the application of the Fourier Transform FFT allows to move from the time domain to the frequency domain.
- the given frequency range I_Bth is a breathing frequency range or a heartbeat frequency range.
- the maximum value Max is a power.
- the frequency of the maximum value Max represents the frequency and therefore the periodicity of the maximum power Pmax or of the phase variation ⁇ seen previously.
- the construction of said second database DS' further comprises: - in a sub-step E33, the normalization Norm of said frequency values Vf before said extraction of said maximum value Max. This makes the calculations simpler.
- the normalization process being known to those skilled in the art, it is not described here.
- a normalized frequency value equal to 0.5. This value makes it possible to start on a neutral value which does not indicate whether we have a living or inert object. It should be noted that a normalized frequency value equal to 0 corresponds to an inert object (something which therefore does not breathe).
- a step E4 the first database DS and the second database DS’ are applied by the processing unit 4 as input to a machine learning model ML.
- ML machine learning model
- the ML machine learning model is a supervised model.
- the supervised model is a support vector machine or a random forest. Since the operation of these supervised models is known to those skilled in the art, they are not described here.
- a step E5 the ML machine learning model is executed.
- the machine learning model ML establishes a classification Cl as to the presence/absence of a living being o.
- the periodic signal S is in particular representative of a type of living being o.
- the type of living being o comprises that of a child, that of an adult, or that of an animal. Consequently, the temporal data Ft which are calculated from the periodic signal S and which are used as input to the machine learning model ML are also representative of the type of living being o.
- the machine learning model ML in a non-limiting embodiment, there will be a classification Cl associated with the radar images I taken inside the motor vehicle 2 which will indicate whether they correspond to a living being o or not and if so, to what type (adult, child, animal).
- the ML machine learning model will have been previously trained with at least one instantaneous database Fi (different from the first database DS) of true positive cases and true negative cases and labels associated with the associated true positive cases and true negative cases, and a temporal database Ft (different from the second database DS’) of true positive cases and true negative cases and labels associated with the associated true positive cases and true negative cases.
- the temporal data Ft make it possible to differentiate a living being o from an inert object but also the type of living being o (adult, child, animal) because the periodic patterns (breathing or heart rate) represented by the periodic signals S are different for these different types of living being o.
- the processing unit 4 transmits corresponding information D (absence/presence of a living being o) to a management unit ECU.
- the management unit ECU is an electronic control unit 2 of the motor vehicle 2.
- the ECU management unit can trigger an alarm to warn that there is a living being o in the motor vehicle 2.
- the method of detecting 1 a living being o is implemented by a detection system Sys of a living being o illustrated in the .
- the detection system Sys comprises a radar sensor 21 configured to acquire a plurality of radar images I in a time window w, each radar image I comprising a series of points p with which are associated a position Po, a power Pu and a speed v (illustrated function f21(21, I, (p(Po, Pu, v), w)).
- the radar sensor 21 comprises a radar wave transmitting/receiving entity 210.
- the radar wave transmitting/receiving entity 210 comprises as illustrated in the : - two 2100 transmitting antennas configured to transmit radar waves r, - three receiving antennas 2110 configured to receive in return radar waves r' which have been reflected on a target object, such as a living being o.
- the detection system Sys further comprises a processing unit 4 configured to: - constructing a first database DS of instantaneous data Fi from the plurality of radar images I, said instantaneous data Fi being based on said position Po, said power Pu and said speed v of each point p of each radar image I acquired in said time window w (illustrated function f41(4, DS, Fi(I)), - constructing a second database DS' of temporal data Ft from the plurality of radar images I, the temporal data Ft being calculated from a periodic signal S of each radar image I taken over a moving time window w' (illustrated function f42(4, DS', Ft(S)), - apply this first DS database and this second DS' database as input to a ML machine learning model (illustrated function f43(4, DS, DS', ML)), - run said ML machine learning model (illustrated function f44(4, ML)).
- a processing unit 4 configured to:
- the processing unit 4 is further configured to, depending on said classification Cl, transmit corresponding information D to a management unit ECU (illustrated function f45(4, ECU, D(Cl))).
- a management unit ECU illustrated function f45(4, ECU, D(Cl)
- the Sys detection system further comprises said ML machine learning model which is configured to: - receive as input the data Fi, Ft respectively from the first database DS and the second database (illustrated function f51(ML, DS, DS')), - be executed (illustrated function f52(ML)), - establish a classification Cl as to the presence/absence of a living being o (illustrated function f53(ML, Cl, S(o)).
- the description of the invention is not limited to the embodiments described above and to the field described above.
- the detection method 1 can be applied for monitoring the breathing or heart rate of elderly people in hospitals.
- the management unit ECU is an electronic control unit of a medical monitoring device.
- the management unit ECU can trigger an alarm to warn that the living being o is no longer breathing or that its heart is no longer beating.
- the radar image I is a thermal map.
- the sensor 21 is an ultrasonic sensor.
- the invention described presents in particular the following advantages: - it allows for more reliable and more precise detection of living beings, - it allows to identify the type of living being o, - the combination of instantaneous data Fi with temporal data Ft makes it possible to improve the detection of true positive cases and to reduce the cases of true negatives and thus to have a differentiation between a living being o and an inert object more robust; the detection method 1 is thus more robust. Thus, the detection rate and the robustness with respect to false alarms are improved.
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
- l’acquisition d’une pluralité d’images dans une fenêtre temporelle, chaque image comprenant une série de données auxquelles sont associées une position, une puissance et une vitesse,
- la construction d’une première base de données de données instantanées à partir de la pluralité d’images, lesdites données instantanées étant basées sur ladite position, ladite puissance et ladite vitesse de chaque donnée de chaque image acquise dans ladite fenêtre temporelle,
- la construction d’une deuxième base de données de données temporelles à partir de ladite pluralité d’images, lesdites données temporelles étant calculées à partir d’un signal périodique de chaque image relevé sur une fenêtre de temps mouvante,
- l’application de ladite première base de données et de ladite deuxième base de données en entrée d’un modèle d’apprentissage automatique,
- l’exécution dudit modèle d’apprentissage automatique,
- l’établissement d’une classification par ledit modèle d’apprentissage automatique quant à la présence/absence d’un être vivant,
- en fonction de ladite classification, la transmission d’une information correspondante à une unité de gestion.
- des valeurs moyennes de ladite position et/ou de ladite puissance et/ou de ladite vitesse desdites données de chaque image, ou
- des variances desdites données de chaque image.
- la mise dans une mémoire tampon des données temporelles pour obtenir une pluralité de valeurs temporelles,
- la suppression de la composante continue desdites valeurs temporelles,
- l’application d’une Transformée de Fourier sur lesdites valeurs temporelles pour obtenir des valeurs fréquentielles,
- à partir desdites valeurs fréquentielles, l’extraction d’une valeur maximum dans une plage de fréquences donnée.
- (a) un capteur configuré pour acquérir une pluralité d’images dans une fenêtre temporelle, chaque image comprenant une série de données auxquelles sont associées une position, une puissance et une vitesse,
- (b) une unité de traitement configurée pour :
- construire une première base de données de données instantanées à partir de la pluralité d’images, lesdites données instantanées étant basées sur ladite position, ladite puissance et ladite vitesse de chaque donnée de chaque image acquise dans ladite fenêtre temporelle,
- construire une deuxième base de données de données temporelles à partir de ladite pluralité d’images, lesdites données temporelles étant calculées à partir d’un signal périodique de chaque image relevé sur une fenêtre de temps mouvante,
- appliquer ladite première base de données et ladite base de données en entrée d’un modèle d’apprentissage automatique,
- exécuter ledit modèle d’apprentissage automatique,
- (c) ledit modèle d’apprentissage automatique configuré pour être exécuté et établir une classification quant à la présence/absence d’un être vivant,
- ladite unité de traitement étant en outre configurée pour en fonction de ladite classification, transmettre une information correspondante à une unité de gestion.
- les valeurs moyennes des données position Po, puissance Pu et vitesse v des points p de chaque image radar I,
- les variances Va des données position Po, puissance Pu et vitesse v des points p de chaque image radar I.
Outre des données instantanées Fi, des données temporelles Ft sont utilisées comme décrit ci-après. L’idée d’utiliser des données temporelles Ft (autrement appelées caractéristiques temporelles Ft) vient du fait qu’une image radar I d’un objet cible, ici un être vivant o, peut montrer des schémas périodiques, en particulier dans le cas de la respiration ou du rythme cardiaque. Les données temporelles Ft sont calculées ainsi à partir d’un signal périodique S. Dans des modes de réalisation non limitatifs, le signal périodique S est ainsi une respiration ou un rythme cardiaque (correspondant à des battements du cœur).
- dans une sous-étape E30, la mise dans une mémoire tampon B des données temporelles Ft pour obtenir une pluralité de valeurs temporelles Vt,
- dans une sous-étape E31, la suppression de la composante continue DC desdites valeurs temporelles Vt,
- dans une sous-étape E32, l’application d’une Transformée de Fourier FFT sur lesdites valeurs temporelles Vt pour obtenir des valeurs fréquentielles Vf,
- dans une sous-étape E34, à partir desdites valeurs fréquentielles Vf, l’extraction d’une valeur maximum Max dans une plage de fréquences donnée I_Bth.
- dans une sous-étape E33, la normalisation Norm desdites valeurs fréquentielles Vf avant ladite extraction de ladite valeur maximum Max. Cela permet de rendre les calculs plus simples. Le processus de normalisation étant connu de l’homme du métier, il n’est pas décrit ici.
- deux antennes émettrices 2100 configurées pour émettre des ondes radar r,
- trois antennes réceptrices 2110 configurées pour recevoir en retour des ondes radar r’ qui se sont réfléchies sur un objet cible, tel qu’un être vivant o.
- construire une première base de données DS de données instantanées Fi à partir de la pluralité d’images radar I, lesdites données instantanées Fi étant basées sur ladite position Po, ladite puissance Pu et ladite vitesse v de chaque point p de chaque image radar I acquise dans ladite fenêtre temporelle w (fonction illustrée f41(4, DS, Fi(I)),
- construire une deuxième base de données DS’ de données temporelles Ft à partir de la pluralité d’images radar I, les données temporelles Ft étant calculées à partir d’un signal périodique S de chaque image radar I relevé sur une fenêtre de temps mouvante w’ (fonction illustrée f42(4, DS’, Ft(S)),
- appliquer cette première base de données DS et cette deuxième base de données DS’ en entrée d’un modèle d’apprentissage automatique ML (fonction illustrée f43(4, DS, DS’, ML)),
- exécuter ledit modèle d’apprentissage automatique ML (fonction illustrée f44(4, ML)).
- recevoir en entrée les données Fi, Ft respectivement de la première base de données DS et de la deuxième base de données (fonction illustrée f51(ML, DS, DS’)),
- être exécuté (fonction illustrée f52(ML)),
- établir une classification Cl quant à la présence/absence d’un être vivant o (fonction illustrée f53(ML, Cl, S(o)).
- elle permet d’avoir une détection d’êtres vivants o plus fiable et plus précise,
- elle permet d’identifier le type d’être vivants o,
- la combinaison des données instantanées Fi avec les données temporelles Ft permet d’améliorer la détection des cas de vrais positifs et de réduire les cas de vrais négatifs et ainsi d’avoir une différenciation entre un être vivant o et un objet inerte plus robuste ; le procédé de détection 1 est ainsi plus robuste. Ainsi, on améliore le taux de détection et la robustesse vis-à-vis des fausses alarmes.
Claims (15)
- Procédé de détection (1) d’un être vivant (o), caractérisé en ce que ledit procédé de détection (1) comprend :
- l’acquisition d’une pluralité d’images (I) dans une fenêtre temporelle (w), chaque image (I) comprenant une série de données (p) auxquelles sont associées une position (Po), une puissance (Pu) et une vitesse (v),
- la construction d’une première base de données (DS) de données instantanées (Fi) à partir de la pluralité d’images (I), lesdites données instantanées (Fi) étant basées sur ladite position (Po), ladite puissance (Pu) et ladite vitesse (v) de chaque donnée (p) de chaque image (I) acquise dans ladite fenêtre temporelle (w),
- la construction d’une deuxième base de données (DS’) de données temporelles (Ft) à partir de ladite pluralité d’images (1), lesdites données temporelles (Ft) étant calculées à partir d’un signal périodique (S) de chaque image (I) relevé sur une fenêtre de temps mouvante (w’),
- l’application de ladite première base de données (DS) et de ladite deuxième base de données (DS’) en entrée d’un modèle d’apprentissage automatique (ML),
- l’exécution dudit modèle d’apprentissage automatique (ML),
- l’établissement d’une classification (Cl) par ledit modèle d’apprentissage automatique (ML) quant à la présence/absence d’un être vivant (o),
- en fonction de ladite classification (Cl), la transmission d’une information correspondante (D) à une unité de gestion (ECU). - Procédé de détection (1) selon la revendication 1, selon lequel les données instantanées (Fi) sont :
- des valeurs moyennes de ladite position (Po) et/ou de ladite puissance (Pu) et/ou de ladite vitesse (v0) desdites données (p) de chaque image (I), ou
- des variances desdites données (p) de chaque image (I). - Procédé de détection (1) selon la revendication 1 ou la revendication 2, selon lequel ledit modèle d’apprentissage automatique (ML) est un modèle supervisé.
- Procédé de détection (1) selon la revendication précédente, selon lequel ledit modèle supervisé est une machine à vecteurs de support ou une forêt aléatoire.
- Procédé de détection (1) selon l’une quelconque des revendications précédentes, selon lequel ledit signal périodique (S) est une respiration ou un battement de cœur.
- Procédé de détection (1) selon l’une quelconque des revendications précédentes, selon lequel ledit être vivant (o) est de type adulte, enfant, ou animal.
- Procédé de détection (1) selon l’une quelconque des revendications précédentes, selon lequel ladite fenêtre temporelle (w) est d’environ cinq secondes.
- Procédé de détection (1) selon l’une quelconque des revendications précédentes, selon lequel les données temporelles (Ft) sont une puissance maximum (Pmax) ou une variation de phase (Δ) dudit signal périodique (S).
- Procédé de détection (1) selon l’une quelconque des revendications précédentes, selon lequel la construction de ladite deuxième base de données (DS’) comprend :
- la mise dans une mémoire tampon (B) des données temporelles (Ft) pour obtenir une pluralité de valeurs temporelles (Vt),
- la suppression de la composante continue (DC) desdites valeurs temporelles (Vt),
- l’application d’une Transformée de Fourier (FFT) sur lesdites valeurs temporelles (Vt) pour obtenir des valeurs fréquentielles (Vf),
- à partir desdites valeurs fréquentielles (Vf), l’extraction d’une valeur maximum (Max) dans une plage de fréquences donnée (I_Bth). - Procédé de détection (1) selon la revendication précédente, selon lequel ladite plage de fréquences donnée (I_Bth) est une plage de fréquences de respiration ou une plage de fréquences de battements de cœur.
- Procédé de détection (1) selon la revendication 9 ou la revendication 10, selon lequel la construction de ladite deuxième base de données (DS’) comprend en outre :
- la normalisation desdites valeurs fréquentielles (Vf) avant ladite extraction de ladite valeur maximum (Max). - Procédé de détection (1) selon l’une quelconque des revendications précédentes, selon lequel ladite pluralité d’images (I) est obtenue à partir d’ondes reçues (r) par une entité d’émission/réception d’ondes (210) d’un capteur (21).
- Procédé de détection (1) selon l’une quelconque des revendications précédentes, selon lequel ladite fenêtre de temps mouvante (w’) est de trois images (I) par seconde.
- Procédé de détection (1) selon l’une quelconque des revendications précédentes, selon lequel ledit procédé de détection (1) est un procédé de détection d’un être vivant (o) à l’intérieur d’un véhicule (2).
- Système de détection (Sys) d’un être vivant (o), caractérisé en ce que ledit système de détection (Sys) comprend :
- (a) un capteur (21) configuré pour acquérir une pluralité d’images (I) dans une fenêtre temporelle (w), chaque image (I) comprenant une série de données (p) auxquelles sont associées une position (Po), une puissance (Pu) et une vitesse (v),
- (b) une unité de traitement (4) configurée pour :
- construire une première base de données (DS) de données instantanées (Fi) à partir de la pluralité d’images (I), lesdites données instantanées (Fi) étant basées sur ladite position (Po), ladite puissance (Pu) et ladite vitesse (v) de chaque donnée (p) de chaque image (I) acquise dans ladite fenêtre temporelle (w),
- construire une deuxième base de données (DS’) de données temporelles (Ft) à partir de ladite pluralité d’images (I), lesdites données temporelles (Ft) étant calculées à partir d’un signal périodique (S) de chaque image (I) relevé sur une fenêtre de temps mouvante (w’),
- appliquer ladite première base de données (DS) et ladite base de données (DS’) en entrée d’un modèle d’apprentissage automatique (ML),
- exécuter ledit modèle d’apprentissage automatique (ML),
- (c) ledit modèle d’apprentissage automatique (ML) configuré pour être exécuté et établir une classification (Cl) quant à la présence/absence d’un être vivant (o),
- ladite unité de traitement (4) étant en outre configurée pour en fonction de ladite classification (Cl), transmettre une information correspondante (D) à une unité de gestion (ECU).
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP24726282.7A EP4725001A1 (fr) | 2023-06-08 | 2024-05-17 | Procédé de détection d'un être vivant |
| CN202480043309.0A CN121420337A (zh) | 2023-06-08 | 2024-05-17 | 用于检测生物体的方法 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FRFR2305778 | 2023-06-08 | ||
| FR2305778A FR3149714A1 (fr) | 2023-06-08 | 2023-06-08 | Procédé de détection d’un être vivant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024251503A1 true WO2024251503A1 (fr) | 2024-12-12 |
Family
ID=87974354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/EP2024/063765 Ceased WO2024251503A1 (fr) | 2023-06-08 | 2024-05-17 | Procédé de détection d'un être vivant |
Country Status (4)
| Country | Link |
|---|---|
| EP (1) | EP4725001A1 (fr) |
| CN (1) | CN121420337A (fr) |
| FR (1) | FR3149714A1 (fr) |
| WO (1) | WO2024251503A1 (fr) |
-
2023
- 2023-06-08 FR FR2305778A patent/FR3149714A1/fr active Pending
-
2024
- 2024-05-17 CN CN202480043309.0A patent/CN121420337A/zh active Pending
- 2024-05-17 WO PCT/EP2024/063765 patent/WO2024251503A1/fr not_active Ceased
- 2024-05-17 EP EP24726282.7A patent/EP4725001A1/fr active Pending
Non-Patent Citations (3)
| Title |
|---|
| HYUN EUGIN ET AL: "Machine Learning-Based Human Recognition Scheme Using a Doppler Radar Sensor for In-Vehicle Applications", SENSORS, vol. 20, no. 21, 1 November 2020 (2020-11-01), CH, pages 6202, XP093089376, ISSN: 1424-8220, DOI: 10.3390/s20216202 * |
| KIM JU-YEON ET AL: "Peak Detection Algorithm for Vital Sign Detection Using Doppler Radar Sensors", SENSORS, vol. 19, no. 7, 1 January 2019 (2019-01-01), CH, pages 1575, XP093089612, ISSN: 1424-8220, DOI: 10.3390/s19071575 * |
| YANG XIUZHU ET AL: "Spatial-Temporal-Circulated GLCM and Physiological Features for In-Vehicle People Sensing Based on IR-UWB Radar", IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, vol. 71, 1 January 2022 (2022-01-01), USA, pages 1 - 13, XP093089370, ISSN: 0018-9456, DOI: 10.1109/TIM.2022.3165808 * |
Also Published As
| Publication number | Publication date |
|---|---|
| EP4725001A1 (fr) | 2026-04-15 |
| CN121420337A (zh) | 2026-01-27 |
| FR3149714A1 (fr) | 2024-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP0791839B1 (fr) | Procédé et dispositif de détection de présence d'une être vivant d'espèce particulière dans un espace surveillé par un capteur Doppler | |
| FR2809186A1 (fr) | Procede et dispositif pour mesurer la vitesse d'un mobile | |
| WO2009081018A1 (fr) | Installation de detection de personnes dans un espace delimite | |
| WO1995007473A1 (fr) | Procede et dispositif pour la detection et la localisation d'obstacles dans l'environnement d'un vehicule | |
| EP4083659B1 (fr) | Dispositif et procédé de traitement du signal issus d'un ensemble de transducteurs ultrasonores | |
| EP4349257A1 (fr) | Dispositif radar pour toilettes | |
| JP2021171271A (ja) | 信号処理システム、及びセンサシステム | |
| EP2544020A1 (fr) | Procédé et dispositif de détection d'une cible masquée par des réflecteurs de forte énergie | |
| WO2024251503A1 (fr) | Procédé de détection d'un être vivant | |
| FR3117966A1 (fr) | Système de détection d’intrusion pour un véhicule et véhicule et procédé associés | |
| WO2023110357A1 (fr) | Procede de detection de presence a l'interieur d'un vehicule verrouille et dispositif de detection associe | |
| FR2873210A1 (fr) | Procede de tfac par segmentation statistique et normalisation | |
| FR2953939A1 (fr) | Systeme radar uhf pour mettre en oeuvre un procede d'elimination d'un fouillis de vegetation | |
| FR3047713A1 (fr) | Dispositif et methode anti-collision pour un vehicule automobile | |
| FR3133252A1 (fr) | Procédé de détection et discrimination de gestes | |
| WO2009086928A1 (fr) | Procede, systeme et installation de detection pour garantir l'unicite de passage d'un objet | |
| WO2023110451A1 (fr) | Procédé de réduction de bruit de signaux radar et calculateur | |
| EP3470871A1 (fr) | Procédé de détection de signaux radar | |
| FR2835082A1 (fr) | Procede de traitement probabiliste des points detectes par un systeme de supervision de l'environnement | |
| EP4188753A1 (fr) | Dispositif d'analyse d'un habitacle de vehicule | |
| WO2026022014A1 (fr) | Système de détection de présence de vie au sein d'un véhicule automobile | |
| FR3153055A1 (fr) | Procede d’activation d’une fonction vehicule et dispositif d’activation associe | |
| WO2024200048A1 (fr) | Procede de detection de presence a l'interieur d'un vehicule verrouille, dispositif de detection associe | |
| WO2025228720A1 (fr) | Système de détection de présence de vie au sein d'un véhicule automobile | |
| EP0874250A1 (fr) | Procédé de traitement des trajets multiples et dispositif pour sa mise en oeuvre |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24726282 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024726282 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2024726282 Country of ref document: EP Effective date: 20260108 |
|
| ENP | Entry into the national phase |
Ref document number: 2024726282 Country of ref document: EP Effective date: 20260108 |
|
| ENP | Entry into the national phase |
Ref document number: 2024726282 Country of ref document: EP Effective date: 20260108 |
|
| ENP | Entry into the national phase |
Ref document number: 2024726282 Country of ref document: EP Effective date: 20260108 |
|
| ENP | Entry into the national phase |
Ref document number: 2024726282 Country of ref document: EP Effective date: 20260108 |
|
| WWP | Wipo information: published in national office |
Ref document number: 2024726282 Country of ref document: EP |