Gait analysis system

Abstract

The application is suitable for the technical field of medical equipment, and provides a gait analysis system, which comprises a first pressure sensor module, a second pressure sensor module, an FPGA processor module and an upper computer module, wherein the first pressure sensor module is used for collecting first pressure data generated by a user walking on a first sensor array, the second pressure sensor module is used for collecting second pressure data generated by the user wearing a second sensor array walking, the FPGA processor module is used for simultaneously receiving the first pressure data and the second pressure data, converting the first pressure data and the second pressure data into target data according to a target protocol, and transmitting the target data to the upper computer module, and the upper computer module is used for processing the target data to obtain gait analysis data. The application can reduce the use conditions of gait analysis and improve the accuracy of gait analysis.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical equipment, and particularly relates to a gait analysis system. BACKGROUND

[0002] Gait analysis refers to analyzing the behavior characteristics of walking, so as to check the walking state. Since the control of walking is very complex, including central command, body balance and coordination control, etc., gait analysis can assist clinical diagnosis, efficacy evaluation, etc. For example, peripheral nerve injury, central nerve injury, etc. can cause gait abnormalities, and gait analysis can help gait abnormality patients to improve and restore walking ability.

[0003] At present, gait analysis is mainly divided into qualitative analysis (visual inspection) and quantitative analysis. The qualitative analysis is mainly analyzed by medical personnel through visual observation, which is affected by subjective factors and is not accurate. The quantitative analysis needs to arrange auxiliary equipment (such as digital detection instrument or high-speed camera, etc.) in the test site, and the test personnel wear multiple types of wearable devices to perform gait analysis. The auxiliary equipment is expensive and the test preparation is complicated. SUMMARY

[0004] The embodiment of the application provides a gait analysis system, which can reduce the use conditions of gait analysis and improve the accuracy of gait analysis.

[0005] The embodiment of the application provides a gait analysis system, which comprises a first pressure sensor module, a second pressure sensor module, an FPGA processor module and an upper computer module.

[0006] The first pressure sensor module is used for collecting first pressure data generated by a user walking on a first sensor array.

[0007] The second pressure sensor module is used for collecting second pressure data generated by the user wearing a second sensor array walking.

[0008] The FPGA processor module is used for simultaneously receiving the first pressure data and the second pressure data, converting the first pressure data and the second pressure data into target data according to a target protocol, and transmitting the target data to the upper computer module.

[0009] The upper computer module is used for processing the target data to obtain gait analysis data.

[0010] Optionally, the first pressure sensor module further comprises a first analog-to-digital conversion module and a first analog switch module.

[0011] The first analog switch module is configured to receive a first data acquisition instruction sent by the FPGA processor module, and switch a sensor array element in the first sensor array according to the first data acquisition instruction.

[0012] The first analog-to-digital conversion module is configured to acquire first pressure data generated by a user wearing the first sensor array and walking according to the first data acquisition instruction.

[0013] Optionally, the first sensor array is composed of m rows and n columns of sensor array elements, where m and n are integers greater than 1, sensor array elements in the same row of the first sensor array share a row lead-out wire, and sensor array elements in the same column of the first sensor array share a column lead-out wire.

[0014] Optionally, the first pressure sensor module is specifically configured to:

[0015] The first analog switch module receives a first data acquisition instruction sent by the FPGA processor module, where the first data acquisition instruction includes a set sampling frequency.

[0016] The first analog switch module switches the column lead-out wire in the first sensor array according to the sampling frequency.

[0017] The first analog-to-digital conversion module performs parallel data acquisition on all row lead-out wires in the first sensor array when the column lead-out wire is switched.

[0018] The first analog-to-digital conversion module aggregates all acquired data to obtain the first pressure data when the column lead-out wire in the first sensor array is traversed.

[0019] Optionally, the sensor array element density of the first sensor array is less than the sensor array element density of the second sensor array.

[0020] Optionally, the FPGA processor module includes a data alignment module and a protocol conversion module, where:

[0021] The data alignment module is configured to perform data alignment according to the sending time of the first pressure data and the second pressure data.

[0022] The protocol conversion module is configured to convert the aligned first pressure data and second pressure data into the target data according to the target protocol.

[0023] Optionally, the protocol conversion module is specifically configured to:

[0024] convert the aligned first pressure data and the second pressure data into target data according to data type configuration information and data storage configuration information in the target protocol, wherein the target data comprises a pressure data frame or a pressure data array.

[0025] Optionally, the host computer module comprises a data preprocessing module, a first data feature extraction module, a second data feature extraction module, and a multi-feature fusion analysis module, wherein:

[0026] The data preprocessing module is configured to filter out environmental noise in the target data.

[0027] The first data feature extraction module is configured to extract gait cycle features from the pressure data frame or the pressure data array.

[0028] The second data feature extraction module is configured to extract gait space-time features from the pressure data frame or the pressure data array.

[0029] The multi-feature fusion analysis module is configured to perform feature fusion analysis on the gait cycle features and the gait space-time features according to a trained multi-feature fusion classification model to obtain the gait analysis data.

[0030] Optionally, the first data feature extraction module is specifically configured to:

[0031] determine time points of state changes of different parts of the foot sole according to distribution positions of pressure in the pressure data frame or the pressure data array, wherein the state changes of different parts of the foot sole include heel landing, heel leaving, toe landing, and toe leaving.

[0032] calculate the gait cycle features according to the time points, wherein the gait cycle features include at least one of features corresponding to a support phase and a swing phase.

[0033] Optionally, the second data feature extraction module is specifically configured to:

[0034] determine position coordinates of different parts of the foot sole according to distribution positions of pressure in the pressure data frame or the pressure data array.

[0035] determine time lengths of the state changes of different parts of the foot sole according to the time points of the state changes of different parts of the foot sole.

[0036] calculate the gait space-time features according to the position coordinates of different parts of the foot sole and the time lengths of the state changes of different parts of the foot sole, wherein the gait space-time features include at least one of features corresponding to a step length, a step width, a step stride, a step speed, and a step frequency.

[0037] The beneficial effects of the embodiments of the present application compared with the prior art are:

[0038] The present application can realize simple and accurate gait analysis by collecting pressure data of the user through the first pressure sensor module and the second pressure sensor module. Specifically, the first pressure sensor module collects the first pressure data generated by the user walking on the first sensor array, and the second pressure sensor module collects the second pressure data generated by the user wearing the second sensor array walking, so that more abundant plantar pressure information can be obtained, thereby improving the accuracy of gait analysis. At the same time, collecting plantar pressure information through the first pressure sensor module and the second pressure sensor module means that multiple types of wearable devices do not need to be worn, thereby reducing the use conditions of gait analysis and improving the applicability of gait analysis. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0040] Figure 1 is a functional architecture diagram of a gait analysis system provided by an embodiment of the present application;

[0041] Figure 2 is a structural schematic diagram of an insole provided by an embodiment of the present application;

[0042] Figure 3 is a structural schematic diagram of the insole from the side provided by an embodiment of the present application;

[0043] Figure 4 is a functional architecture diagram of a first pressure sensor module provided by an embodiment of the present application;

[0044] Figure 5 is a functional architecture diagram of an FPGA processor module provided by an embodiment of the present application;

[0045] Figure 6 is a functional architecture diagram of an upper computer module provided by an embodiment of the present application;

[0046] Figure 7 is a system structure diagram of a gait analysis system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0047] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0048] It will be understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0049] It will be understood that the term "and / or," when used in the specification and in the following claims, is intended to mean one or more of the associated listed items can be present, and, if desired, all possible combinations of the associated listed items can be present.

[0050] As used in the specification and the appended claims, the term "if' can be construed to mean "when" or "upon" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be construed to mean "upon determining" or "in response to determining" or "upon detecting [the described condition or event]" or "in response to detecting [the described condition or event]" depending on the context.

[0051] In addition, the terms "first," "second," "third," etc. are used herein only to distinguish one element from another, and do not imply a relative importance or a given order.

[0052] Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "in a various embodiment" or "in some embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment, unless otherwise specified. Furthermore, the terms "comprise," "comprises," "comprising," and other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0053] Currently, when using quantitative analysis methods to analyze the gait of patients with gait abnormalities, in order to improve the accuracy of gait analysis, different types of wearable devices, detection devices, etc. are often used to cooperate with each other to complete the examination. For example, when analyzing the gait of Parkinson's patients, the patient needs to wear different types of wearable devices such as acceleration sensors, gyroscope sensors, and range sensors to collect gait data, and cooperate with auxiliary equipment (such as digital detection instruments or high-speed cameras, etc.) to perform gait analysis. Due to the high cost of such auxiliary equipment and the overly complicated test preparation (such as usage conditions and steps), the applicability of gait analysis is poor.

[0054] In order to improve the applicability of gait analysis, the present application provides a gait analysis system based on a pressure sensor.

[0055] Figure 1 The functional architecture diagram of a gait analysis system provided by an embodiment of the present application is shown. In this embodiment, the gait analysis system 1 includes a first pressure sensor module 101, a second pressure sensor module 102, an FPGA processor module 103, and an upper computer module 104, which are described in detail as follows:

[0056] The first pressure sensor module 101 is configured to collect first pressure data generated by a user walking on a first sensor array.

[0057] In some embodiments, the first sensor array described above can be a pressure sensor array arranged in a floor mat. The first pressure sensor module described above can be installed in the floor mat and used to collect first pressure data generated by the first sensor array when the user walks on the floor mat. Since the first pressure sensor module 101 collects first pressure data generated by the first sensor array, it means that the user does not need to wear it, and the first sensor array is arranged in the floor mat, which is convenient to roll up and carry, has better mobility, and can be used in more places.

[0058] The second pressure sensor module 102 is configured to collect second pressure data generated by the user walking while wearing a second sensor array.

[0059] In some embodiments, the second sensor array described above can be a pressure sensor array arranged in an insole. The second pressure sensor module described above can be installed in the insole and used to collect second pressure data generated by the second sensor array when the user wears the insole and walks.

[0060] It should be noted that the insole described above can be a split external insole, that is, the insole described above can be fixed outside the shoes of the tester, thereby adapting to different testers. Referring to Figure 2 the structure of the insole is shown, wherein the insole described above can be divided into a forefoot part and a heel part, and is fixed to the sole of the tester by a fixing clamp. Referring toFigure 3 As shown in the structure diagram of the insole side view, the forefoot part and the heel part both contain a circuit layer and a sponge, the circuit layer is provided with a pressure sensor (i.e., a second sensor array) at a pressure sensing area of the toe and the heel, and the rest of the circuit layer contains a battery slot, a microprocessor, a memory, a wireless signal transmitting part, etc. Since the split external insole has the characteristics of simple wearing and convenient disassembly, it can better adapt to different testers and better sense the stress conditions of different parts (toe, heel, etc.).

[0061] The FPGA processor module 103 is configured to receive the first pressure data and the second pressure data simultaneously, convert the first pressure data and the second pressure data into target data according to a target protocol, and transmit the target data to the host computer module.

[0062] In some embodiments, the FPGA processor module can be installed in a Field Programmable Gate Array (FPGA) chip, and is configured to convert the first pressure data and the second pressure data into target data according to a target protocol. The target protocol refers to a specific protocol used to convert data from different sources into the same format standard.

[0063] The host computer module 104 is configured to process the target data to obtain gait analysis data.

[0064] In some embodiments, the host computer module 104 can be installed in a host computer. The host computer is a computer or other digital device used to control or monitor another device or devices (such as sensors, actuators, controllers, etc.), for example, a computer, a mobile phone, etc.

[0065] The present application can achieve simple and accurate gait analysis by collecting pressure data from the first pressure sensor module and the second pressure sensor module for gait analysis of a user. Specifically, the first pressure sensor module collects first pressure data generated by the user walking on the first sensor array, and the second pressure sensor module collects second pressure data generated by the user wearing the second sensor array walking, so that more abundant plantar pressure information can be obtained, thereby improving the accuracy of gait analysis. At the same time, collecting plantar pressure information through the first pressure sensor module and the second pressure sensor module means that multiple types of wearable devices do not need to be worn, thereby reducing the use conditions of gait analysis and improving the applicability of gait analysis.

[0066] In the embodiments of the present application, with reference to Figure 4 The first pressure sensor module 101 further includes a first analog switch module 1011 and a first analog-to-digital conversion module 1012.

[0067] The first analog switch module 1011 is configured to receive a first data acquisition instruction sent by the FPGA processor module 103, and switch a sensor array element in the first sensor array according to the first data acquisition instruction.

[0068] The first analog-to-digital conversion module 1012 is configured to acquire first pressure data generated by a user wearing the first sensor array walking according to the first data acquisition instruction.

[0069] In some embodiments, the first analog switch module 1011 described above can be installed in a multiplexer (MUX) chip, and is configured to switch a sensor array element in the first sensor array according to a first data acquisition instruction sent by the FPGA processor module 103. The first analog-to-digital conversion module 1012 described above can be installed in an analog-to-digital converter (ADC), and is configured to convert an analog voltage signal collected by the sensor array into a digital signal and transmit the digital signal to the FPGA processor module 103.

[0070] In an optional embodiment of the present application, the first sensor array described above is composed of m rows and n columns of sensor array elements, where m and n are both integers greater than 1, sensor array elements in the same row of the first sensor array share a row lead-out wire, and sensor array elements in the same column of the first sensor array share a column lead-out wire.

[0071] It should be noted that, since the first sensor array described above is arranged in a floor mat, the number of sensor array elements in the first sensor array will change according to the number of floor mats spliced. For example, assuming that each floor mat has a size of 1m*1m and contains one layer of pressure sensor array (100*100), if 10 floor mats are spliced into a size of 1m*10m, the corresponding first pressure sensor array is 1000*100. Meanwhile, sensor array elements in each row or column are connected through the same wire to facilitate data acquisition of the sensor array elements in the whole row or column.

[0072] Further, the first pressure sensor module 101 is specifically configured to:

[0073] The first analog switch module 1011 receives a first data acquisition instruction sent by the FPGA processor module 103, where the first data acquisition instruction includes a set sampling frequency;

[0074] The first analog switch module 1011 switches the column lead-out wire in the first sensor array according to the sampling frequency;

[0075] The first analog-to-digital conversion module 1012 performs parallel data acquisition on all row lead-out wires in the first sensor array when the column lead-out wires are switched;

[0076] The first analog-to-digital conversion module 1012 collects all the acquired data to obtain the first pressure data when all column lead-out wires in the first sensor array are traversed.

[0077] In some embodiments, since different numbers of floor mats are spliced in the column direction according to actual measurement sites or other requirements when gait analysis is performed using the floor mat, in order to improve the efficiency of data acquisition, column scanning can be used for data acquisition. For example, the FPGA processor module 103 controls the first analog switch module 1011 to switch different column lead-out wires through a first data acquisition instruction. The first analog-to-digital conversion module 1012 performs parallel data acquisition on all row lead-out wires every time a column lead-out wire is switched. When all column lead-out wires are traversed, the signals of all sensor elements of the sensor array are acquired. Assuming that the sampling frequency set by the host computer module is 100 Hz, the first analog switch module needs to be switched 100 times per second.

[0078] In the embodiments of the present application, the density of the sensor elements of the first sensor array is less than the density of the sensor elements of the second sensor array.

[0079] In some embodiments, in order to improve the efficiency of data acquisition and avoid excessive data acquisition, the density of the sensor elements of the sensor array in the insole can be greater than the density of the sensor elements of the sensor array in the floor mat. Since the floor mat has a large area, the smaller density of the sensor elements in the floor mat can avoid excessive data acquisition and improve the efficiency of data acquisition. Since the insole has a small area, the larger density of the sensor elements in the insole can improve the accuracy of data acquisition without excessively affecting the efficiency of data acquisition.

[0080] It should be noted that the composition structure and data acquisition method of the second sensor array in the insole are similar to those of the floor mat, which will not be described here.

[0081] In an optional embodiment of the present application, referring to Figure 5 The FPGA processor module 103 includes a data alignment module 1031 and a protocol conversion module 1032, wherein:

[0082] The data alignment module 1031 is configured to perform data alignment according to the sending time of the first pressure data and the second pressure data.

[0083] The protocol conversion module 1032 is configured to convert the aligned first pressure data and second pressure data into the target data according to a target protocol.

[0084] In some embodiments, due to the separability of the insole and the splicing of the ground mat, the first pressure data and the second pressure data are derived from different sensor arrays. In order to avoid large errors in data processing, the data alignment module 1031 is used to unify the first pressure data and the second pressure data to the same time node by using the sending time of the first pressure data and the second pressure data, or to make the difference between the time nodes of the first pressure data and the second pressure data less than a preset time threshold.

[0085] In the embodiments of the present application, the protocol conversion module 1032 is specifically configured to:

[0086] The protocol conversion module 1032 is configured to convert the aligned first pressure data and second pressure data into the target data according to a target protocol.

[0087] In some embodiments, the data type configuration information is used to configure different data types for different data. The data storage configuration information is used to configure the format of data storage. Assuming that in the case of 10 ground mat splicing (i.e. 10 array splicing), first, the timestamp is stored in int32 data type, then the data of 1000 rows of the first column of lead-out wires is stored in int16 data type, and then the data of 1000 rows of the second column of lead-out wires, and so on, until the data of 1000 rows of the 100th column. These data constitute a complete data frame or pressure data array (i.e. target data). If the sampling rate is 100 Hz, it means that the data per second contains 100 such data frames.

[0088] In the embodiments of the present application, referring to Figure 6 The host computer module 104 includes a data preprocessing module 1041, a first data feature extraction module 1042, a second data feature extraction module 1043, and a multi-feature fusion analysis module 1044.

[0089] The data preprocessing module 1041 is configured to filter out environmental noise in the target data.

[0090] The first data feature extraction module 1042 is configured to extract gait cycle features from the pressure data frame or the pressure data array.

[0091] The second data feature extraction module 1043 is configured to extract gait space-time features according to the pressure data frame or the pressure data array.

[0092] The multi-feature fusion analysis module 1044 is configured to perform feature fusion analysis on the gait cycle features and the gait space-time features according to a trained multi-feature fusion classification model, to obtain the gait analysis data.

[0093] In some embodiments, the data preprocessing module 1041 can filter out environmental noise in the target data by using a preset signal filtering method, which can be one of a median filtering method, a moving average filtering method, a Kalman filtering method, etc. The gait cycle features are features reflecting the walking process of a user, in which the same foot moves from the heel off the ground to the heel on the ground again. The gait space-time features are features related to the moving time and the moving distance during the user's walking. The trained multi-feature fusion classification model can be a trained multi-layer perceptron (MLP) or a convolutional neural network (CNN). For example, the training steps of the multi-feature fusion classification model can include: collecting gait feature data with labels in a public database, calculating the gait features of the data, and labeling the data by experts; inputting the two types of data into an initial model (MLP or CNN); constructing a cost function of the model using model parameters, and adjusting the model parameters step by step using a softmax regression method to reduce the cost function; when the cost function reaches a minimum value, the model parameters at this time are the optimal model parameters, and the multi-feature fusion classification model is obtained. The gait analysis data can be directly obtained by using the multi-feature fusion classification model. When evaluating the user's movement disorder, the gait analysis data can include a movement disorder evaluation result, which can include one of normal movement disorder, mild movement disorder, moderate movement disorder, and severe movement disorder.

[0094] In the embodiments of the present application, the first data feature extraction module 1042 is specifically configured to:

[0095] determine a time point of a state change of different parts of the foot sole according to the distribution position of the pressure in the pressure data frame or the pressure data array, wherein the state change of different parts of the foot sole includes the heel landing, the heel off the ground, the toe landing, and the toe off the ground;

[0096] calculate the gait cycle features according to the time point, wherein the gait cycle features include at least one feature corresponding to the support phase and the swing phase.

[0097] In some embodiments, since the sensor data is transmitted to the host computer in the form of data frames (or matrices), the time points of state changes of different parts of the foot sole, including foot heel landing, foot heel lifting, toe lifting, etc., can be determined according to the distribution position of the pressure in the above-mentioned data frames (or matrices). For example, assuming that the 99th frame of data shows that the pressure data of all sensor elements is 0, and the 100th frame of pressure data shows that the pressure of the foot heel sensor element is 1 and the pressure of other elements is 0, it means that at the first second, the foot heel starts to touch the ground, and the time point at this time is recorded as the time point of the foot heel landing.

[0098] In an optional embodiment of the present application, taking the gait cycle characteristics of the right foot as an example, the early stage of the support phase represents the time from the first touch of the right foot to the toe lifting of the left foot; the middle stage of the support phase represents the time from the instant of the toe lifting of the left foot to the lifting of the right heel; the late stage of the support phase represents the time from the lifting of the right heel to the touch of the left foot; the early stage of the swing phase represents the time from the first touch of the left foot to the toe lifting of the right foot; and the late stage of the swing phase represents the time from the toe lifting of the right foot to the first touch of the right foot.

[0099] In an embodiment of the present application, the second data feature extraction module 1043 is specifically configured to:

[0100] determine the position coordinates of different parts of the foot sole according to the distribution position of the pressure in the pressure data frame or the pressure data array;

[0101] determine the time length of the state change of different parts of the foot sole according to the time point of the state change of different parts of the foot sole;

[0102] calculate the spatiotemporal features of the gait according to the position coordinates of different parts of the foot sole and the time length of the state change of different parts of the foot sole; wherein the spatiotemporal features of the gait include at least one feature corresponding to the step length, the step width, the step stride, the step speed, and the step frequency.

[0103] The step length can be determined according to the longitudinal straight-line distance from the heel landing point of one foot to the heel landing point of the other foot; the step stride can be determined according to the longitudinal straight-line distance between the front and rear heel landing points of the same foot; the step width can be determined according to the horizontal distance between the midpoints of the heels of the left and right feet; the step speed can be determined by the straight-line distance of walking and the walking time; and the step frequency can be determined by 60 / average time of the step length.

[0104] In some embodiments, the position of the state change of different parts of the foot sole and the length of each step can be determined according to the distribution position of the pressure in the above-mentioned data frame (or matrix). For example, in the case of a sampling rate of 100 Hz, the first frame of data is that the sensor elements with coordinates of (0, 10) and (10, 10) respectively detect the left heel and the right heel, and the 101st frame of data is that the sensor element with coordinates of (10, 110) again detects the right heel, which indicates that the right foot has moved a length of 100 sensor elements in 1 second. If the distance between the sensor elements is 5 mm and the size of the sensor element itself is also 5 mm, the corresponding step length is 10 mm*100 = 100 cm. Other gait space-time features can be calculated by a similar method, which will not be described here.

[0105] In an optional embodiment of the present application, the system structure diagram of the above-mentioned gait analysis system can refer to Figure 7 The column lead-out wires of the ground mat array are connected with a multiplexer (MUX) chip set, and the FPGA controls the MUX to switch different column lead-out wires to be connected to a power supply voltage (Volt Current Condenser, VCC). The row lead-out wires are connected with a voltage dividing resistor and then grounded. One end of the voltage dividing resistor connected with the row lead-out wires is connected with an ADC chip set. The ADC chip set converts the analog voltage signal into a digital signal and transmits it to the FPGA. After the FPGA integrates the data, the data is uploaded to the PC host computer. The composition structure of the insole array is similar to that of the ground mat. The data of the insole is transmitted to the FPGA in real time through Bluetooth, and then transmitted to the PC host computer after the FPGA integrates the data.

[0106] It should be understood that the size of the serial number of each step in the above-mentioned embodiments does not mean the order of execution. The execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0107] Those skilled in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0108] In the embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. For example, the embodiments of the modules described above are merely schematic and can be divided into other ways. For example, the division of the modules or units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0109] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0110] The above-described embodiments are merely used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A gait analysis system, characterized by, The first pressure sensor module, the second pressure sensor module, the FPGA processor module and the host computer module are included, and wherein: The first pressure sensor module is configured to collect first pressure data generated by a user walking on a first sensor array, the first sensor array being a pressure sensor array arranged in a floor mat; The second pressure sensor module is configured to collect second pressure data generated by the user walking while wearing a second sensor array, the second sensor array being a pressure sensor array arranged in a shoe pad, and a sensor element density of the first sensor array being less than a sensor element density of the second sensor array; The FPGA processor module is configured to simultaneously receive the first pressure data and the second pressure data, and convert the first pressure data and the second pressure data into target data according to a target protocol, and transmit the target data to the host computer module; The host computer module is configured to process the target data to obtain gait analysis data.

2. The gait analysis system of claim 1, wherein, The first pressure sensor module further includes a first analog-to-digital conversion module and a first analog switch module, and wherein: The first analog switch module is configured to receive a first data acquisition instruction sent by the FPGA processor module, and switch sensor elements in the first sensor array according to the first data acquisition instruction; The first analog-to-digital conversion module is configured to collect first pressure data generated by the user walking while wearing the first sensor array according to the first data acquisition instruction.

3. The gait analysis system of claim 2, wherein, The first sensor array is composed of m rows and n columns of sensor elements, wherein m and n are both integers greater than 1, sensor elements in the same row of the first sensor array share a row lead-out wire, and sensor elements in the same column of the first sensor array share a column lead-out wire.

4. The gait analysis system of claim 3, wherein, The first pressure sensor module is specifically configured to: The first analog switch module receives a first data acquisition instruction sent by the FPGA processor module, wherein the first data acquisition instruction includes a set sampling frequency; The first analog switch module switches the column lead-out wire in the first sensor array according to the sampling frequency; The first analog-to-digital conversion module performs parallel data collection on all row lead-out wires in the first sensor array when the column lead-out wire is switched; The first analog-to-digital conversion module collects all data under the condition that the column lead-out wire in the first sensor array is traversed, and obtains the first pressure data.

5. The gait analysis system of any one of claims 1-4, wherein, The FPGA processor module includes a data alignment module and a protocol conversion module, and wherein: The data alignment module is configured to perform data alignment according to a sending time of the first pressure data and the second pressure data; The protocol conversion module is configured to convert the aligned first pressure data and second pressure data into the target data according to the target protocol.

6. The gait analysis system of claim 5, wherein, The protocol conversion module is specifically configured to: The first pressure data and the second pressure data after alignment are converted into target data according to data type configuration information and data storage configuration information in the target protocol, wherein the target data includes a pressure data frame or a pressure data array.

7. The gait analysis system of claim 6, wherein, The host computer module includes a data preprocessing module, a first data feature extraction module, a second data feature extraction module, and a multi-feature fusion analysis module, wherein: The data preprocessing module is configured to filter out environmental noise in the target data. The first data feature extraction module is configured to extract gait cycle features from the pressure data frame or the pressure data array. The second data feature extraction module is configured to extract gait space-time features from the pressure data frame or the pressure data array. The multi-feature fusion analysis module is configured to perform feature fusion analysis on the gait cycle features and the gait space-time features according to a trained multi-feature fusion classification model to obtain the gait analysis data.

8. The gait analysis system of claim 7, wherein, The first data feature extraction module is specifically configured to: determine time points of state changes of different parts of the foot sole according to distribution positions of pressure in the pressure data frame or the pressure data array, wherein the state changes of different parts of the foot sole include heel landing, heel leaving, toe landing, and toe leaving; calculate the gait cycle features according to the time points, wherein the gait cycle features include at least one feature corresponding to a support phase or a swing phase.

9. The gait analysis system of claim 8, wherein, The second data feature extraction module is specifically configured to: determine position coordinates of different parts of the foot sole according to distribution positions of pressure in the pressure data frame or the pressure data array; determine time lengths of the state changes of different parts of the foot sole according to the time points of the state changes of different parts of the foot sole; calculate the gait space-time features according to the position coordinates of different parts of the foot sole and the time lengths of the state changes of different parts of the foot sole, wherein the gait space-time features include at least one feature corresponding to a step length, a step width, a step amplitude, a step speed, or a step frequency.

Images