Method and device for deriving a plantar pressure line

Description

Technical field

[0001] The invention relates to the field of podometry. In particular, it relates to a method for determining a plantar pressure line of an individual. The invention further relates to a device or system for determining a plantar pressure line of an individual. Prior art

[0002] Below we describe the known prior art from which the invention was developed.

[0003] The foot, comprising 26 bones, 107 ligaments and nearly 19 muscles, is a particularly complex part of the human body. It also plays an important role since it is the keystone allowing a human being to move. The slightest deterioration of the latter can quickly become disabling. Although this is particularly true in the context of practicing a sport involving contact of the foot with the ground, a poor gait during daily activities can also have a significant impact on health. The study of the forces applied to the foot during walking is therefore constantly evolving and new systems or new indicators to facilitate these studies are regularly emerging.

[0004] Thus, it has already been proposed to monitor an individual's gait using pressure sensors or inertial units located in particular at the foot. Recent publications show in particular the interest of using inertial units positioned at the foot to access gait data in real time (WO2019077266) or even data on gait disorders (WO2019193301) or advanced gait parameters (WO2020217037). Correlation between the kinematics and kinetics of a person's gait has also been shown using wearable sensors such as inertial units on the limbs and plantar pressure sensors (Michaela Anne A. Dela Cruz et al. Joint Gait Kinematic and Kinetic Analysis using Inertial Measurement Units and Plantar Pressure Sensor System. Conference 2019 IEEE. 10.1109 / HNICEM48295.2019.9072701).Furthermore, a method for predicting plantar force and gait state has been proposed to avoid the delay in controlling a walking aid exoskeleton (MAHDAVIAN MOHAMMAD ET AL: "Motion Generation of a Wearable Hip Exoskeleton Robot Using Machine Learning-Based Estimation of Ground Reaction Forces and Moments", 2019 IEEE / ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM), 10.1109 / AIM.2019.8868759). However, none of these documents focus on determining a plantar pressure line.

[0005] Among the many indicators concerning gait, the plantar pressure line ("gaitline" in English terminology) is an essential indicator for the analysis of an individual's support. In particular, an abnormal plantar pressure line could originate from morphological alterations such as fractures or bone microlesions, a difference in the length of a metatarsal or even hallux valgus, but also from neurological alterations such as hemiplegia or neurodegenerative diseases such as Parkinson's.

[0006] The plantar pressure line has been studied for years using force or pressure sensors. Indeed, the plantar pressure line is a line that illustrates how an average pressure, a center of pressure, of a foot changes during the time the foot is in contact with the ground. Many other documents propose methods and apparatus, involving the calculation of a plantar pressure line, to diagnose problems of posture or body movement, in particular defects or problems of position and gait (US20090163834) such as those related to a rupture of the anterior cruciate ligament based (CN108209924) or those associated with a risk of falling of an elderly person (CN111631719).

[0007] However, this analysis is often carried out by healthcare professionals since it requires a very specific measurement system and the expertise of the healthcare professional to analyze the results generated by the measurement system.

[0008] Traditionally, the analysis of the plantar pressure line, as practiced by health professionals, is based mainly on the study of plantar pressures in static and dynamic conditions, more commonly through pedometric or baropodometric studies. By triggering receptors (pressure sensors), placed in a mat connected to a computer, under the effect of the support of a patient's foot, an instantaneous map of these supports is obtained. The signal produced by the activation of the receptors is collected and processed, then reproduced in the form of an image where each pressure value is converted into color. The health professional can thus visualize at what levels the plantar pressures are located, in order to deduce a plantar pressure line possibly revealing an altered gait.Such analyses are essential for the healthcare professional since it is from these that he will be able, for example, to offer the patient suitable foot orthoses to correct the patient's gait.

[0009] Other solutions have been proposed, mainly through the integration of pressure sensors into soles. Indeed, the use of accelerometers has been considered detrimental to the accuracy of a model and requiring additional sensors of another type to derive parameters that require information on the plantar pressure line (WO2012026818). For example, the study carried out by Janin M. "Athletic walking: modification of plantar pressures by orthotic elements"; Kinesiology; 2002:203:13-4 details a gait analysis system based on pressure variations during the gait. The equipment required for the analysis of ground pressures is a device comprising a support with vertical unidirectional piezoelectric sensors, identical in shape to a sole and capable of being inserted into the sports shoe in order to record pressure variations during the gait.This analysis system is connected to a computer for acquisition, and is composed of a recording box and conductive cables, a remote-controlled recording card allowing the dynamic recording of plantar supports and their distributions. Thus, despite the absence of a specific mat for pressure analysis, the equipment cannot provide continuous monitoring of the pressure line or the calculation of a pressure line from outdoor activity.

[0010] Recently, shoes have been proposed that include pressure sensors and are capable of generating data that can be further processed to provide a plantar pressure line of an individual. In particular, the spatially averaged output signal of the sensors can enable the generation of a plantar pressure line in a two-dimensional space. More particularly, patent application No. WO2013022344 relates to a system for analyzing the dynamics of the foot and in particular its viscoelastic behavior to evaluate the efficiency of a run, the risk of injury or the comfort of a user. Such a system takes the form of a sole comprising a pressure-sensitive surface equipped with a plurality of pressure sensors to generate an electronic signal as a function of an exerted pressure.Furthermore, an electronic device is arranged in the sole and makes it possible to carry out measurements, as a function of time, of a moving pressure center exerted by the user's foot on the pressure-sensitive surface, thereby forming a plantar pressure line along a front axis of a walking direction.

[0011] However, existing solutions are not optimal. They require the deployment of expensive equipment or take the form of a system integrating numerous devices whose implementation This work must be carried out under specific conditions to obtain relevant measurements. In addition, pressure-sensitive systems integrated into the soles are still too fragile and expensive. Under these conditions, they do not allow abnormal gait to be easily and accurately determined.

[0012] There is therefore a need for a new solution integrated into a shoe allowing dynamic analysis of the plantar pressure line in order to enable the easy and robust identification of abnormal gait.

[0013] The invention aims to overcome the drawbacks of the prior art. In particular, the invention aims to propose a method for quickly determining, and preferably in real time, a plantar pressure line, without the need to use expensive or fragile equipment. The invention also aims to propose a device and a system for determining a pressure line in many situations. Summary of the invention

[0014] The invention aims to overcome these drawbacks.

[0015] The invention relates in particular to a method for inferring a plantar pressure line, said plantar pressure line corresponding to the temporal evolution of the position of the barycenter of the plantar pressures during the movement of an individual and comprising a plurality of successive positions of said barycenter of the plantar pressures for a foot of said individual, said method being implemented by one or more microprocessors from movement data generated by at least one inertial unit coupled to the foot of said individual, for example coupled to a shoe worn by said individual or to the foot of said individual, said at least one inertial unit being configured to generate movement data for a plurality of instants of a support phase of a foot of said individual, said method comprising the following steps: Loading a correlation model, said correlation model defining a relationship between a plurality of data obtained from plantar pressure sensors and a plurality of foot angle values ​​relative to a predetermined reference frame, said relationship making it possible to determine the position of the barycenter of the plantar pressures at each instant of a support phase; Calculating foot angle values ​​relative to the predetermined reference frame, from the movement data generated by the at least one inertial unit, over at least two instants of the support phase of the foot of said individual; and Inferring a plurality of successive positions of the barycenter of the plantar pressures to form the plantar pressure line of the foot of said individual, from the angle values ​​calculated over the at least two instants of the support phase of the foot and from the correlation model.

[0016] The applicant has developed a method capable of determining a plantar pressure line from movement data generated by an inertial unit. While the plantar pressure line was previously only accessible from data from pressure sensors, such an innovation makes it possible to considerably expand the use cases and monitoring of the plantar pressure line.

[0017] The applicant has developed in particular a method for determining an inferred plantar pressure line for an individual wearing shoes to which inertial units are coupled. Such a system is much more affordable than conventional pedometer mats and less fragile than soles incorporating on-board pressure sensors.

[0018] According to other optional features of the method, the latter may optionally include one or more of the following features, alone or in combination: the inference step is repeated so as to establish the plantar pressure line inferred from several support phases. Thus, the determined pressure line is a dynamic pressure line providing more information than a static pressure line. the inertial unit(s) are six-axis or nine-axis inertial units. The calculation step is therefore carried out from movement data generated on six axes or nine axes. In particular, by six-axis or nine-axis inertial units. The use of inertial units comprising a gyroscope and an accelerometer is particularly advantageous in the context of the invention. the inertial unit(s) are positioned in a removable or non-removable sole. The calculation step is therefore carried out from movement data generated by inertial units while they are positioned in a removable or non-removable sole.The position of the inertial unit(s) in a removable sole makes it possible in particular to adapt to different shoes worn by the user. The inertial unit(s) are positioned in an electronic box arranged to be fixed to the shoe worn by said individual. The calculation step is therefore carried out from movement data generated by inertial units while they are positioned in an electronic box arranged to be fixed to the shoe worn by said individual. Indeed, the inertial unit can be positioned on the top of the shoe, for example at the tongue, the upper or the counter. The inertial unit(s) are integrated into an electronic device comprising the one or more microprocessors configured to implement the method.The calculation step is therefore carried out from movement data generated by inertial units while they are positioned in an electronic box, said electronic box also comprising the one or more microprocessors configured to calculate the foot angle values ​​relative to the predetermined reference frame. Preferably, the inference is also implemented by the one or more microprocessors arranged in the electronic box. Thus, the calculation is carried out directly at the level of a device integrating the units without requiring access to dedicated computer servers. the electronic device is integrated into a sole. Thus, the calculation of foot angle values ​​and inference of a plurality of pressure centers are implemented by the one or more microprocessors positioned in an electronic box integrated into a sole.The calculation of foot angle values ​​is performed for at least five moments of foot strike. This increases the accuracy of the determined plantar pressure line. The calculation of foot angle values ​​involves the calculation of values ​​of at least two foot angles. This increases the accuracy of the determined plantar pressure line. It involves a calculation of a plantar pressure line without taking into account data from a pressure sensor coupled to the individual's shoe. Thus, it is no longer necessary to integrate fragile and expensive pressure sensors. It involves a calculation of a plantar pressure line for each of the individual's feet. The calculation of the plantar pressure line is therefore done for each of the individual's feet. It involves a comparison of the plantar pressure lines of each of the individual's feet. This allows asymmetries to be identified.It comprises a comparison of the plantar pressure lines obtained for the same foot for two different time intervals. This makes it possible to identify a change in the pressure lines over time. The correlation model corresponds to a machine learning model. The machine learning model is selected from a supervised, unsupervised or reinforcement learning model. This makes it possible to increase the accuracy of the determined plantar pressure line. It comprises a step of preprocessing the movement data generated by the at least one inertial unit, the preprocessing step comprising frequency filtering, gravity suppression, and / or drift suppression.the calculated foot angle values, relative to the predetermined reference frame, comprise angle values ​​selected from: an angle of the anteroposterior axis of the foot relative to its line of progression, an angle of the anteroposterior axis of the foot relative to the ground, an angle of the transverse axis of the foot relative to its line of progression or an angle of the transverse axis of the foot relative to the ground. This makes it possible to increase the accuracy of the determined plantar pressure line. it further comprises a step of transmitting the inferred plantar pressure line to an external terminal.

[0019] According to a second object, the invention relates to a device for inferring a plantar pressure line, said plantar pressure line corresponding to the temporal evolution of the position of the barycenter of the plantar pressures during the movement of an individual and comprising a plurality of successive positions of said barycenter of the plantar pressures for a foot of said individual, said inference device comprising one or more microprocessors, said one or more microprocessors being configured to: Loading a correlation model, said correlation model defining a relationship between a plurality of data obtained from plantar pressure sensors and a plurality of foot angle values ​​relative to a predetermined reference frame, said relationship making it possible to determine the position of the barycenter of the plantar pressures at each instant of a support phase; Calculating foot angle values ​​relative to the predetermined reference frame, from movement data generated by at least one inertial unit, over at least two instants of the support phase of the foot of said individual; and Inferring a plurality of successive positions of the barycenter of the plantar pressures to form the plantar pressure line of the foot of said individual, from the angle values ​​calculated over the at least two instants of the support phase of the foot and from the correlation model.

[0020] According to other optional characteristics of the device, the latter may further comprise at least one inertial unit capable of being coupled to a shoe worn by said individual or to the foot of said individual, said at least one inertial unit being configured to generate movement data for a plurality of instants of a support phase of a foot of said individual. Brief description of the drawings

[0021] Other characteristics and advantages of the invention will be better understood upon reading the description which follows and with reference to the appended drawings, given for illustrative purposes and in no way limiting. There Figure 1 represents a diagram of a method according to an embodiment of the invention. The Figure 2 represents a diagram of a method according to another embodiment of the invention. The dotted steps are optional. The Figure 3depicts an illustration of four steps of an individual, highlighting a line of gait and foot angles. The Figure 4 illustrates different positions of the inertial unit coupled to a shoe or a foot. The Figure 5 represents the illustration of two plantar pressure lines inferred by a method according to the invention. The Figure 6 represents a system comprising a device for inferring a plantar pressure line according to the invention.

[0022] The figures do not necessarily respect the scales, particularly in thickness, and this is for illustration purposes.

[0023] Aspects of the present invention are described with reference to flowcharts and / or functional diagrams of methods, apparatuses (systems) and computer program products according to embodiments of the invention.

[0024] In the figures, flowcharts and block diagrams illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a system, device, module, or code, which includes one or more executable instructions for implementing the specified logical function(s). In some implementations, the functions associated with the blocks may appear in a different order than shown in the figures. For example, two blocks shown in succession may, in fact, be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order, depending on the functionality involved.Each block of the block diagrams and / or flowchart, and combinations of blocks in the block diagrams and / or flowchart, may be implemented by special hardware systems that perform the specified functions or acts or carry out combinations of special hardware and computer instructions. Description of the embodiments

[0025] Below, we describe a summary of the invention and the associated vocabulary, before presenting the disadvantages of the prior art, and finally showing in more detail how the invention overcomes them.

[0026] In the remainder of the description, the expression “plantar pressure line” within the meaning of the invention corresponds to the evolution of the position of the center of plantar pressure (e.g. barycenter) during the movement of an individual (e.g. walking or running), preferably from the heel landing until the toes lift off.

[0027] The expression "inferred plantar pressure line" or "inference of a plantar pressure line" within the meaning of the invention corresponds to a prediction of the evolution of the position of the center of plantar pressures (e.g. barycenter) during the movement of an individual as generated from movement data of the individual's foot. Preferably, the inferred plantar pressure line corresponds to a dynamic plantar pressure line. That is to say, it is generated through an analysis over time of the distribution of plantar pressure and in particular of the center of plantar pressures.

[0028] The expression "motion data" may correspond, within the meaning of the invention, to data comprising values ​​of acceleration, angular velocity, magnetic fields or even fusion data obtained from one or more of these values. The motion data may be raw data or pre-processed data.

[0029] The expression "support phase" within the meaning of the invention may correspond, in the context of an analysis of the walking or running cycle, to the moment when the foot is at least partly in contact with the ground. It may in particular include the attack of the step, the front step, the back step, and the propulsion which ends with the lifting off of the foot.

[0030] The expression “instant of the support phase” within the meaning of the invention corresponds to a time interval occurring during the placement of the foot, also called the support phase of the foot.

[0031] The expression “walking cycle” within the meaning of the invention corresponds to the time interval between two heel presses of the same leg on the ground, or more generally two identical repeated events.

[0032] For the purposes of the invention, the term "correlation model" means a finite sequence of operations or instructions for calculating a value from one or more input values. The implementation of this finite sequence of operations makes it possible, for example, to assign a value Y, such as a label Y, to an observation described by a set of characteristics or parameters X, for example by implementing a function f, capable of reproducing Y by having observed X. Y = f X + e where e symbolizes the noise or measurement error.

[0033] For the purposes of the invention, the term "supervised machine learning model" means a correlation model automatically generated from data, called observations, which have been labeled.

[0034] For the purposes of the invention, the term "unsupervised machine learning model" means a correlation model automatically generated from data, called observations, which have not been labeled.

[0035] The expression "foot angle values" within the meaning of the invention may correspond to angle values ​​making it possible to represent the position of an individual's foot in its environment, that is to say, for example, relative to a predetermined reference frame. This position may be relative to the individual's limbs, for example, with the angle formed by the axis of the tibia and the anteroposterior axis of the foot. This position may also be relative to elements external to the individual, for example, with the angle formed by the anteroposterior axis of the foot and the ground. Finally, this position may also be relative to an angle formed by the anteroposterior axis of the foot and a calculated walking line or a calculated trajectory of the foot.

[0036] The expression “predetermined reference frame” within the meaning of the invention may correspond to an inertial reference frame such as a terrestrial reference frame or a non-inertial reference frame such as one or more limbs of the individual or even a reference frame generated from movement data of the individual.

[0037] A "sole" is an object that separates the individual's foot from the ground. A shoe may have an upper sole layer in direct contact with the individual's foot and a lower sole layer in direct contact with the ground or, more generally, the external environment. A shoe may also have a removable insole.

[0038] "Removable" means the ability to be easily detached, removed or dismantled without having to destroy the fastening means, either because there are no fastening means or because the fastening means are easily and quickly removable (e.g. notch, screw, tab, lug, clips). For example, removable means that the object is not fixed by welding or by another means not intended to allow the object to be detached.

[0039] “Process”, “calculate”, “determine”, “display”, “transform”, “extract”, “compare” or more broadly “executable operation”, within the meaning of the invention, means an action performed by a device or processor unless the context indicates otherwise. In this regard, operations refer to actions and / or processes of a data processing system, for example a computer system or an electronic computing device, which manipulates and transforms data represented as physical (electronic) quantities in the memories of the computer system or other devices for storing, transmitting or displaying information. These operations may be based on applications or software.

[0040] The terms or phrases "application", "software", "program code", and "executable code" mean any expression, code or notation, of a set of instructions intended to cause data processing to perform a particular function directly or indirectly (e.g. after a conversion operation to other code). Examples of program code may include, but are not limited to, a subroutine, a function, an executable application, source code, object code, a library and / or any other sequence of instructions designed for execution on a computer system.

[0041] For the purposes of the invention, the term "processor" means at least one hardware circuit configured to execute operations according to instructions contained in a code. The hardware circuit may be an integrated circuit. Examples of a processor include, but are not limited to, a central processing unit, a graphics processor, an application-specific integrated circuit (ASIC), and a programmable logic circuit.

[0042] The term "electronic device" means any device comprising a processing unit or a processor, for example in the form of a microcontroller cooperating with a data memory, possibly a program memory, said memories being able to be dissociated. The processing unit cooperates with said memories by means of an internal communication bus.

[0043] For the purposes of the invention, the term "coupled" means connected, directly or indirectly, with one or more intermediate elements. Two elements may be coupled mechanically, electrically, or linked by a communication channel.

[0044] The study of individual gait is expanding rapidly, and monitoring and characterization processes are multiplying. However, some analyses that have been used for decades, such as the study of the center of plantar pressure, still require fragile and expensive equipment, limiting the widespread adoption of these studies.

[0045] While plantar pressure sensors were, until the present invention, considered an essential step for determining a plantar pressure line, the applicant has developed a solution making it possible to determine this plantar pressure line from data coming from an inertial unit.

[0046] Thus, according to a first aspect, the invention relates to a method 1 for inferring a plantar pressure line 30.

[0047] There Figure 1 illustrates an embodiment of this inference method 1.

[0048] As illustrated, a method of determining a plantar pressure line 30 (illustrated in Figure 5 ) inferred according to the invention will comprise a loading 200 of a correlation model, a calculation 400 of angle values ​​of a foot over at least two instants of the support phase of the foot of an individual; and an inference 500 of the plantar pressure line of the foot of the individual from the calculated angle values ​​and the correlation model.

[0049] As will be detailed later and illustrated in the Figure 2, an inference method 1 according to the invention may also comprise a learning step 100, a step 300 of generating data by the inertial unit, a pre-processing 350 of the data generated by the movement sensors, a step 600 of comparing inferred plantar pressure lines 30, a transmission 700 of the inferred plantar pressure line, or even a storage 800 of the data, in particular data linked to the inferred plantar pressure line.

[0050] The method 1 for inferring a plantar pressure line 30 according to the invention is preferably implemented by one or more microprocessors 22. As will be detailed later, the method is implemented from data comprising movement data, or calculated from movement data, generated by at least one inertial unit 21 coupled to a shoe worn by said individual.

[0051] The microprocessor(s) 22 implementing the method according to the invention may be integrated into an electronic device also integrating the inertial unit(s) or may be integrated into a computer device, such as a computer or a computer server, configured to receive data generated by the inertial unit(s). An inference device 2 according to the invention will be detailed further in the remainder of this description.

[0052] As shown in the Figure 2 , a method according to the invention may comprise a learning step 100. This learning step is preferably a step carried out prior to the implementation of the method on the movement data of an individual. Furthermore, it may be repeated and be enriched with data generated within the framework of the present invention.

[0053] A learning step 100 may include a collection of training data then an aggregation and storage of this target data in a database.

[0054] The training data will include data from pressure sensors. Indeed, the plantar pressure line is usually calculated from plantar pressure data. This plantar pressure data may have been generated by any device known to a person skilled in the art and capable of generating plantar pressure data for an individual. For example, the plantar pressure data may have been generated from a treadmill, or even from insoles incorporating pressure sensors. In addition, the training data will include foot movement data during the stance phase, preferably generated from one or more inertial measurement units.

[0055] The learning step 100 enables the generation of a correlation model based on pressure sensor data acquired during walking. In particular, the correlation model defines, through one or more instructions, a relationship between a plurality of data obtained from plantar pressure sensors and a plurality of foot angle values.

[0056] Such a model is advantageously configured so as to be able to infer position data of the plantar center of pressure, and preferably its displacement, from movement data of a foot.

[0057] Preferably, the learning step 100 may comprise the generation of multiple machine learning models and a selection of the machine learning model providing the best prediction performance.

[0058] A method according to the invention comprises a step 200 of loading a correlation model. As can be understood by a person skilled in the art, loading 200 may correspond to storing the correlation model for use.

[0059] This step implies that the correlation model has already been generated previously, for example during a learning step 100 and that it is its inference capacity which is used within the framework of the method according to the invention.

[0060] Preferably, the correlation model corresponds to a machine learning model. For example, the machine learning model may be selected from a supervised, unsupervised or reinforcement machine learning model.

[0061] Alternatively, it has been shown that a correlation model, not equipped with machine learning capabilities but still generated from pressure sensor data acquired during the stance phase and the corresponding foot movement data, could allow the inference of a plantar pressure line.

[0062] As shown in the Figure 2 , a method according to the invention may comprise a step 300 of generating data by at least one inertial unit. The inertial unit 21 may for example be a six-axis or nine-axis inertial unit.

[0063] In the context of the generation 300 of the movement data, the inertial unit(s) 21 are coupled to a shoe. For example, a method according to the invention may use movement data from several inertial units 21 coupled to one or two shoes.

[0064] As will be detailed later, the inertial unit 21 generating the movement data is preferably positioned in an electronic box 20 arranged to be integrated into a sole. Nevertheless, the invention can be implemented from data generated by one or more inertial units positioned on a shoe or at the level of an ankle. In particular, during the step 300 of generation of the data by the inertial unit 21, the inertial unit 21 can be positioned in an electronic box 20 fixed to the shoe worn by an individual.

[0065] The data generated by the inertial unit 21 may preferably be generated during an individual's walk, a run or any other exercise likely to generate movement data that can be used in the context of an analysis of the kinetics of movement of the foot in space. This data is called movement data. The inertial unit is preferably coupled to a shoe but more generally it is coupled to an individual's foot. The coupling may be direct or via a shoe.

[0066] In the context of the method according to the invention, the movement data are generated for a plurality of instants of the foot placement.

[0067] In particular, during the step 300 of generating movement data by the inertial unit(s), the movement data is generated for at least ten instants of the foot being placed, preferably at least twenty and more preferably at least fifty.

[0068] Preferably, the movement data will comprise movement data generated between the instant of heel strike and the instant of toe strike. The movement data may also comprise movement data generated between the instant of heel lift-off and the instant of toe lift-off. Indeed, the applicant has determined that these data are of particular importance for improving the prediction performance of the method according to the invention.

[0069] Furthermore, the method 1 for inferring a plantar pressure line 30 inferred according to the invention may include a preprocessing step 350 of the movement data generated by the inertial unit(s).

[0070] In particular, this step of preprocessing 350 of the movement data may correspond to the preprocessing of the acceleration, angular velocity, and / or magnetic field values. For example, it may comprise in particular at least one processing selected from: frequency filtering, gravity suppression on the acceleration values, gravity suppression, noise suppression on the acceleration values ​​and drift suppression on the measured angular velocity values.

[0071] Thus, the motion data may correspond to data generated by an inertial unit 21 that has been normalized, filtered, supplemented, or to data that has been merged, for example, by Kalman filtering. Preferably, the motion data includes variable values ​​in the form of time series. These variable values ​​may preferably correspond to acceleration and angular velocity values. They may optionally include magnetic field data or a merging of these data.

[0072] As illustrated in figures 1 And 2 , a method according to the invention comprises a step 400 of calculating foot angle values. In particular, this calculation 400 of foot angle values ​​is made with respect to the predetermined reference frame.

[0073] The step 400 of calculating foot angle values ​​preferably corresponds to a step of calculating angle values ​​for the individual's two feet so as to generate an inferred plantar pressure line 30 for each of the individual's feet.

[0074] These foot angle values ​​are in particular calculated from the movement data generated by the at least one inertial unit 21. Furthermore, preferably, they are calculated over at least two instants of the individual's foot position, or support phase.

[0075] Preferably, the step 400 of calculating foot angle values ​​comprises calculating angle values ​​for at least five times of the foot being placed, preferably at least ten and more preferably at least twenty.

[0076] There are many methods for calculating foot angle values ​​depending on the reference frames used. Indeed, foot angle values ​​generally correspond to angle values ​​of a foot relative to its environment. Examples of foot angle values ​​that can be calculated are illustrated in Figure 3 .

[0077] These angle values ​​42, 44 may for example be calculated as a function of the individual's walking line 40. They may also be calculated relative to the ground or relative to the anteroposterior axis 41, 43 of the individual's foot 11a, 12a. The walking line may be calculated conventionally by methods known to those skilled in the art and then used as a reference for calculating the foot angle values ​​within the framework of the present invention.

[0078] Preferably, the calculated foot angle values ​​comprise angle values ​​selected from: an angle of the anteroposterior axis of the foot relative to its line of progression, an angle of the anteroposterior axis of the foot relative to a plane formed by the ground, an angle of the transverse axis of the foot relative to its line of progression or an angle of the transverse axis of the foot relative to a plane formed by the ground.

[0079] In addition to using foot angle values ​​calculated at several times during the foot's landing, the present invention derives a particular advantage from using values ​​of several foot angles. Thus, preferably, the step 400 of calculating foot angle values ​​comprises calculating values ​​of at least two foot angles, preferably at least three foot angles and more preferably at least four foot angles.

[0080] For example, the Figure 4illustrates an individual's foot coupled with inertial units positioned in three different locations: at the level of the counter 20a; in the outer or inner sole 20b; or on the front of the foot 20c, for example at the level of the laces or the tongue.

[0081] There Figure 4 also shows that the invention can be implemented from a 20d inertial unit directly coupled to the individual's foot. This coupling can be done using an adhesive material to temporarily stick the inertial unit to the foot or using an accessory capable of holding the inertial unit against the individual's foot. The accessory could, for example, be elastic and take the form of an ankle brace or a strap.

[0082] Among the angles that can be used in the context of the invention, we can for example cite the striking angle corresponding to a measurement of the angle between the base of the foot and the ground at initial contact. This angle can continue to be measured during the attack phase of the step until the anterior step phase. As illustrated, the angle 46 between the base of the foot 45 and the ground can also be measured during the propulsion phase.

[0083] As illustrated in figures 1 And 2 , a method according to the invention comprises a step 500 of inference of the plantar pressure line 30 of the individual. As illustrated in Figure 5 , the plantar pressure line 30 can be considered as corresponding to a plurality of inferred plantar pressure centers.

[0084] The inference step 500 may include the determination of a plantar pressure line 30 for each of the individual's feet 11a, 12a.

[0085] This inference step 500 is preferably carried out from the angle values ​​calculated on the at least two instants and from the correlation model.

[0086] Preferably, the inference step 500 comprises the use of angle values ​​calculated for at least five instants of the foot landing, preferably at least ten and more preferably at least twenty.

[0087] Advantageously, the calculated angle values ​​used during the inference 500 of the plantar pressure line 30 comprise a majority of angle values ​​calculated from movement data generated between the instant of heel strike and the instant of toe strike and between the instant of heel lift-off and the instant of toe lift-off.

[0088] Preferably, the calculated angle values ​​used during the inference 500 of the plantar pressure line 30 comprise at least 60% of angle values ​​calculated from movement data generated between the instant of heel strike and the instant of toe strike and between the instant of heel lift-off and the instant of toe lift-off.

[0089] More preferably, the calculated angle values ​​used during the inference 500 of the plantar pressure line 30 comprise at least 70% of angle values ​​calculated from movement data generated between the instant of heel strike and the instant of toe strike and between the instant of heel lift-off and the instant of toe lift-off.

[0090] Even more preferably, the calculated angle values ​​used during the inference 500 of the plantar pressure line 30 comprise at least 80% of angle values ​​calculated from movement data generated between the instant of heel strike and the instant of toe strike and between the instant of heel lift-off and the instant of toe lift-off.

[0091] This inference step 500 is preferably carried out from values ​​of several angles. Preferably, the inference step 500 is preferably carried out from the values ​​of at least two angles of the foot, preferably at least three angles of the foot and more preferably at least four angles of the foot.

[0092] In the context of the invention, the inference step 500 may be repeated so as to establish a plantar pressure line 30 inferred from several support phases, for example obtained during walking or running cycles. This pressure line may for example be composed from a calculation taking into account several repetitions such as a mean or median calculation.

[0093] As discussed, one of the advantages of the present invention is to be able to predict a plantar pressure line without having to use a pressure sensor, whereas before the present invention this was a necessary step in podometry when establishing a plantar pressure line. Thus, advantageously, the determination of the inferred plantar pressure line 30 does not take into account data coming from a pressure sensor coupled to the individual's shoe. More broadly, the inference of the plantar pressure line 30 according to the invention does not take into account data coming from a pressure sensor having generated pressure data associated with said individual.

[0094] As shown in the Figure 2 , a method according to the invention may comprise a step 600 of comparing inferred plantar pressure lines 30.

[0095] In particular, the method according to the invention may include a comparison of the plantar pressure lines 30 inferred from each of the individual's feet.

[0096] It may also include a comparison of the plantar pressure lines 30 inferred for the same foot for two different time intervals.

[0097] As shown in the Figure 2 , a method according to the invention may comprise a step 700 of transmitting the plantar pressure line 30 to a remote electronic device 50, 60, also called external terminal 50, 60.

[0098] Preferably, the method may also comprise a step 800 of storing data. This storing is preferably done continuously. In particular, this may correspond to the storing of all the data generated and / or calculated within the framework of a method according to the invention. The stored data may for example be raw data as generated by the motion sensors, preprocessed data, transformed data or even inferred plantar pressure line data. Preferably, the stored data correspond to inferred plantar pressure line data.

[0099] Advantageously, the calculation of an inferred plantar pressure line 30 is done in real time, that is to say less than 1 hour after the generation of the data by one or more of the movement sensors of a sole, preferably less than 10 minutes, more preferably less than one minute, even more preferably less than 10 seconds.

[0100] According to another aspect, the invention relates to an inference device 2 of a plantar pressure line 30. As described, the plantar pressure line 30 comprises a plurality of inferred pressure centers for a foot of an individual.

[0101] An inference device 2 according to the invention is detailed in the Figure 6. Such an inference device 2 can in particular be used to infer a plantar pressure line 30 from movement data generated by one or more inertial units 21. It applies when the movement sensors 21 are coupled to the foot of an individual, for example coupled to the shoe of an individual.

[0102] Preferably, an inference device 2 comprises one or more microprocessors 22 configured to execute a method according to the invention, preferably the inference method 1, and its various embodiments, preferred, advantageous or not.

[0103] In particular, the one or more microprocessors 22 are configured to load a correlation model. Preferably, the correlation model defines a relationship between a plurality of data obtained from plantar pressure sensors and a plurality of foot angle values ​​relative to a predetermined reference frame.

[0104] The one or more microprocessors 22 can also be configured to calculate values ​​of angles of the foot relative to the predetermined reference frame, from movement data generated by at least one inertial unit 21, over at least two instants of the support phase of the foot of said individual.

[0105] Further, the one or more microprocessors 22 may also be configured to infer a plurality of pressure centers to form the plantar pressure line 30 of the individual's foot, from the angle values ​​calculated over the at least two instants of the foot's stance phase and the correlation model.

[0106] The inference device 2 of a plantar pressure line 30 may also include the inertial unit(s) 21. In this case, it will preferably be of reduced size and may be fixed to the foot of an individual by any means. It may, for example, be directly fixed to the foot in a removable manner using an adhesive device. It may also be coupled to the foot of the individual via a shoe worn by the individual. In this case, it may be fixed to the shoe or integrated into the sole. Preferably, the inference device 2 is integrated into a sole, for example in a removable manner.

[0107] Advantageously, the inference device 2 weighs less than 10 grams and is arranged so that it can be housed in an inner and / or outer sole. A small volume, for example less than 10 cm 3< , limits the impact on the comfort of the individual and has the advantage of optimizing production costs by making the integration of this technology into the sole during the industrial process less expensive and simpler.

[0108] In particular, such an inference device 2 according to the invention comprises a motion sensor such as an inertial unit 21 configured to generate motion data of a foot of the individual. During the use of the inference device 2 by an individual, the inertial unit 21 acquires signals representative of a motion parameter (acceleration and / or speed, for example angular speed) of the user's foot, along the X, Y, Z axes.

[0109] The inertial unit 21 is for example made up of at least one accelerometer and one gyroscope. Preferably, it comprises several accelerometers and gyroscopes. The inference device 2 may also comprise one or more magnetometers so as to acquire three additional raw signals corresponding to the magnetic field values ​​in three dimensions. Thus, the movement data can be processed to generate movement data resulting from a fusion between inertial and magnetic data.

[0110] Each inference device 2 may further include other sensors, including an inclinometer, a barometer, a temperature sensor and an altimeter to benefit from increased precision.

[0111] The inference device 2 according to the invention also comprises a data memory 23, configured to store at least part of the generated movement data and / or inferred plantar pressure lines. The data memory 23 is also configured to store the correlation model.

[0112] The various components of the inference device 2 are preferably arranged on an electronic card 24 (or printed circuit), but the invention can provide various types of arrangement such as for example a single module combining all the functions described here. Similarly, these means can be divided into several electronic cards or else gathered on a single electronic card. Furthermore, when an action is attributed to a device, a means or a module, this is in fact generally carried out by a microprocessor of the device or module controlled by instruction codes recorded in a memory. Similarly, if an action is attributed to an application, this is in fact carried out by a microprocessor of the device in a memory of which the instruction codes corresponding to the application are recorded. When a device or module transmits or receives a message, this message is transmitted or received by a communication interface.

[0113] The inference device 2 according to the invention advantageously comprises one or more communication means 25. The one or more communication means 25 are capable of receiving and transmitting the data on at least one communication network R1. Preferably, the communication is carried out via a wireless protocol such as Wi-Fi, 3G, 4G, 5G and / or Bluetooth. Preferably, the communication protocol is a BLE or ANT+ protocol. These communication protocols allow low energy consumption.

[0114] Preferably, the inference device 2 according to the invention comprises a first communication means 25 configured so that the inference device 2 is capable of transmitting at least one inferred plantar pressure line 30 to an external terminal 50, 60. This data can be transmitted in real time or delayed to an external terminal 50, 60. The external terminal or the remote electronic device 50, 60 can for example be a remote system such as a tablet, a mobile phone (“smartphone” in English terminology), a computer or a server.

[0115] Advantageously, an inference device 2 according to the invention further comprises a second communication means 25 configured so that a first inference device 2 is able to communicate with a second inference device 2.

[0116] In particular, the inference devices 2 may be configured to communicate with each other and to initiate the collection of movement data and the inference of an individual's plantar pressure line only after receiving a message from the other inference device 2. This contributes to the synchronization of the inference devices 2.

[0117] Advantageously, if an inference device 2 were to disconnect or lose synchronization over time with respect to the other inference device 2, a method according to the invention could comprise a step of synchronizing the inference devices 2. Thus, a search signal is sent by the connected inference device 2, the disconnected inference device 2 receives the search signal and synchronizes with the connected inference device 2.

[0118] Furthermore, the inference device 2 according to the invention may comprise a wired connection port 26, preferably protected by a removable tab. This wired connection port may be, for example, a USB or Firewire port. Advantageously, the USB port is also resistant to water or humidity. Furthermore, the USB port is advantageously surmounted by a polymer beam to give it greater resistance in use conditions. This wired connection port 26 may be used as mentioned above to recharge the battery but also to exchange data and, for example, to update the firmware of the electronic card carrying the various components of the inference device 2.

[0119] Preferably, the removable tab or USB cover protects the USB port from foreign objects. For example, the removable tab protects the USB port from water or dust. Such a tab can preferably be made of an elastomer or polyurethane polymer.

[0120] Furthermore, the inference device 2 according to the invention may comprise an energy source 27. The energy source is preferably of the battery type, rechargeable or not. Preferably the energy source is a rechargeable battery. Furthermore, it may be associated with a system for recharging by movement or by external energy. The system for recharging by external energy may in particular be a system for recharging by wired connection, an induction or even photovoltaic recharging system.

[0121] The energy source 27 is preferably of the battery type, rechargeable or not. Preferably the energy source is a rechargeable battery. Recharging can be carried out using different technologies such as: by charger, with a connector flush with the sole; with a mechanical recharging device integrated into the sole, such as for example a piezoelectric device capable of providing electrical energy from walking; with a contactless device, for example by induction; and / or with a photovoltaic device.

[0122] Furthermore, according to another aspect, the present invention relates to a system 3 for inferring a plantar pressure line 30 of an individual.

[0123] Such an inference system 3 of a plantar pressure line 30 of an individual, described in connection with the Figure 6, will advantageously comprise one or more inference devices 2 according to the present invention. In particular, the inference system 3 according to the invention comprises two inference devices 2 according to the present invention.

[0124] In particular, each of the inference devices 2 is designed so as to be able to communicate independently with the other and / or directly with an external terminal 50, 60 in order to be able to exchange its own information on the inferred plantar pressure line 30.

[0125] In particular, the inference system 3 according to the invention may comprise a pair of soles 11, 12 each comprising an inference device 2 according to the invention. The soles 11, 12 usable in the context of the inference system 3 according to the invention may, for example, correspond to outer soles or inner soles of shoes. These soles may be removable or be permanently integrated into the sole assembly of the shoes. Conventionally, the soles 11, 12 making up said pair of soles each comprise an inference device 2 according to the invention. As shown in the Figure 6 , the inference device 2 is preferably positioned at a middle portion of the sole.

[0126] As mentioned, the inference system 3 according to the invention may comprise an external terminal 50, 60 configured to receive data from the inference device(s) 2.

[0127] Advantageously, a dedicated application is installed on this external terminal 50, 60 in order to process the information transmitted by the inference device(s) 2 and allow the user to interact with the invention. It is then, for example, possible to access the external terminal 50, 60 via a web interface. All communications with the external terminal 50, 60 can be secured, for example, by HTTPS protocols (for “HyperText Transfer Protocol Secure” according to English terminology) and AES encryption (for “Advanced Encryption Standard” according to English terminology) 512. Thus, this can allow, via a client, access to the data by medical personnel responsible for monitoring the user.

[0128] The external terminal 50,60 is generally a tablet, a mobile phone ("smartphone" in English terminology), a gateway, a router, a computer or a server. It may be able to transfer this data to a remote server. It is then, for example, possible to access this remote server via a web interface.

[0129] Thus, the user can access data related to the inferred plantar pressure line(s) 30.

[0130] The invention may be the subject of numerous variations and applications other than those described above. In particular, unless otherwise indicated, the different structural and functional features of each of the implementations described above should not be considered as combined and / or closely and / or inextricably linked to each other, but on the contrary as simple juxtapositions. Furthermore, the structural and / or functional features of the different embodiments described above may be the subject in whole or in part of any different juxtaposition or any different combination.

Claims

1. A method (1) for inferring a plantar pressure line (30), said plantar pressure line (30) corresponding to the time evolution of the position of the barycenter of plantar pressures during the movement of an individual and including a plurality of successive positions of said barycenter of plantar pressures for a foot of said individual, said method being implemented by one or several microprocessors (22) from movement data generated by at least one inertial unit (21) coupled to a shoe worn by said individual or said individual's foot, said at least one inertial unit (21) being configured to generate movement data for a plurality of instants of a stance phase of a foot of said individual, said method including the following steps: - loading (200) a correlation model, said correlation model defining a relationship between a plurality of data obtained from plantar pressure sensors and a plurality of foot angle values relative to a predetermined reference frame, said relationship enabling the determination of the position of the barycenter of plantar pressures at each instant of a stance phase; - calculating (400) foot angle values relative to the predetermined reference frame, from the movement data generated by the at least one inertial unit (21), over at least two instants of the stance phase of the foot of said individual; and - inferring (500) a plurality of successive positions of the barycenter of plantar pressures to form the plantar pressure line (30) of the said individual's foot, from the angle values calculated over the at least two instants of the stance phase of the foot and from the correlation model.

2. The method (1) for inferring a plantar pressure line (30) according to claim 1, characterized in that the inference step (500) is repeated so as to establish the plantar pressure line (30) inferred from several stance phases.

3. The method (1) for inferring a plantar pressure line (30) according to any one of claims 1 or 2, characterized in that the calculation step (400) is carried out from movement data generated by the inertial units (21) while they are positioned in a removable or non-removable sole.

4. The method (1) for inferring a plantar pressure line (30) according to any one of claims 1 to 3, characterized in that the calculation step (400) is carried out from movement data generated by the inertial units (21) while they are positioned in an electronic casing arranged to be fixed on the shoe worn by said individual.

5. The method (1) for inferring a plantar pressure line (30) according to any one of claims 1 to 3, characterized in that the calculation step (400) is carried out from movement data generated by the inertial units (21) while they are positioned in an electronic casing, said electronic casing also including the one or several microprocessors (22) configured to calculate the foot angle values relative to the predetermined reference frame.

6. The method (1) for inferring a plantar pressure line (30) according to the preceding claim, characterized in that the calculation (400) of foot angle values and the inference (500) of a plurality of pressure centers are implemented by one or several microprocessors (22) positioned in an electronic casing integrated into a sole.

7. The method (1) for inferring a plantar pressure line (30) according to any one of claims 1 or 2, characterized in that the calculation step (400) is performed from movement data generated by the inertial units (21) while they are positioned at three different locations on the foot of said individual.

8. The method (1) for inferring a plantar pressure line (30) according to any one of the preceding claims, characterized in that the calculation (400) of foot angle values includes the calculation of values of at least two angles of the foot.

9. The method (1) for inferring a plantar pressure line (30) according to any one of the preceding claims, characterized in that said predetermined reference frame is external to the human body and is selected from: the ground, a calculated gait line, or a calculated trajectory of said foot of said individual.

10. The method (1) for inferring a plantar pressure line (30) according to the preceding claim, characterized in that the calculated foot angle values, relative to the predetermined reference frame, include angle values selected from: an angle of the antero-posterior axis of the foot relative to its progression line, an angle of the antero-posterior axis of the foot relative to the ground, an angle of the transverse axis of the foot relative to its progression line or an angle of the transverse axis of the foot relative to the ground or the strike angle between the base of the foot and the ground at initial contact..

11. The method (1) for inferring a plantar pressure line (30) according to the preceding claim, characterized in that it includes a comparison of the plantar pressure lines (30) of each of the feet of the individual.

12. The method (1) for inferring a plantar pressure line (30) according to any one of the preceding claims, characterized in that it includes a comparison of the plantar pressure lines (30) obtained for the same foot for two different time intervals.

13. The method (1) for inferring a plantar pressure line (30) according to any one of the preceding claims, characterized in that it includes a step of preprocessing the movement data generated by the at least one inertial unit (21), the preprocessing step including frequency filtering, gravity suppression, and / or drift suppression.

14. A device for inferring (2) a plantar pressure line (30), said plantar pressure line (30) corresponding to the time evolution of the position of the barycenter of plantar pressures during the movement of an individual and including a plurality of successive positions of said barycenter of plantar pressures for a foot of said individual, said inference device (2) including one or several microprocessors (22), said one or several microprocessors (22) being configured to: - load a correlation model, said correlation model defining a relationship between a plurality of data obtained from plantar pressure sensors and a plurality of foot angle values relative to a predetermined reference frame, said relationship enabling the determination of the position of the barycenter of plantar pressures at each instant of a stance phase; - calculate foot angle values relative to the predetermined reference frame, from movement data generated by at least one inertial unit (21), over at least two instants of the stance phase of the foot of said individual; and - infer a plurality of successive positions of the barycenter of the plantar pressures to form the plantar pressure line (30) of said individual's foot, from the angle values calculated over the at least two instants of the stance phase of the foot and from the model correlation.

15. The device for inferring (2) a plantar pressure line (30) according to the preceding claim, characterized in that it further includes, the at least one inertial unit (21) coupled to a shoe worn by said individual or to said individual's foot, said at least one inertial unit (21) being configured to generate movement data for a plurality of instants of a stance phase of a foot of said individual.