A real-time detection method and system for double-foot take-off time in race walking based on plantar pressure signals, a terminal and a storage medium

Abstract

The application relates to the technical field of data processing, and discloses a real-time detection method, system, terminal and storage medium for the double-foot take-off time of a race-walk based on a plantar pressure signal, which comprises the following steps: sampling a multi-channel plantar pressure signal of a race-walker, fusing and calculating the total pressure of each sampling point to form a pressure time sequence curve; adopting a sliding window to detect the local maximum value in the pressure time sequence curve in real time, obtaining a support peak sequence, and determining a gait conversion window limit range according to the support peak sequence; calculating the touch-down time and the take-off time within the gait conversion window limit range; obtaining an effective emptying time sample set according to the touch-down time and the take-off time, eliminating abnormal values, and obtaining a final effective emptying time sample set. The application can effectively solve the interference of the plantar pressure signal in the race-walk, such as the adhesion and sliding offset of insoles, realizes real-time monitoring and accurate identification of the double-foot emptying state of the race-walk, and provides support for intelligent detection and scientific training of the race-walk project.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, system, terminal, and computer-readable storage medium for real-time detection of the time the feet leave the ground in race walking based on plantar pressure signals. Background Technology

[0002] Currently, smart insoles with built-in pressure sensors are common in the industry. They collect foot pressure signals to determine the time when the foot touches the ground and leaves the ground during walking. Usually, by comparing the ground contact and leave time parameters of the left and right feet, the duration of the human body's feet in the air can be calculated.

[0003] However, existing detection methods still have significant technical shortcomings: First, there is a lack of unified technical specifications for selecting plantar pressure signals. In actual testing, there is no clear definition of the criteria for value selection. Typically, pressure data from the heel is used for the moment the foot touches the ground, while pressure data from the toe area is used for the time the foot leaves the ground. Some studies also use multi-region pressure fusion data as a judgment benchmark. However, different signal locations and methods of measurement directly change the judgment results at different time points, greatly affecting the accuracy of detecting the time of foot flight. The selection of pressure values ​​obtained from sensor data at different locations is also affected by individual differences.

[0004] Secondly, numerous interference factors exist in actual race walking scenarios. For example, the insole adheres tightly to the foot during the swing phase of the gait (airborne phase). Slippage and displacement between the foot and the insole during the support phase can cause distortion of pressure signals and abnormal data fluctuations. Existing conventional algorithms do not have corresponding anti-interference processing logic designed for these practical usage conditions, making it difficult to eliminate data deviations caused by external interference. This further reduces the reliability of motion time parameter detection and fails to meet the requirements for high-precision motion posture and gait parameter monitoring.

[0005] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0006] The main objective of this invention is to provide a real-time detection method, system, terminal, and computer-readable storage medium for the time of two feet off the ground in race walking based on plantar pressure signals. This aims to solve the problems of low detection accuracy and easy misjudgment in traditional pressure sensor-based detection of the time of two feet off the ground, which are caused by interference from factors such as selective analysis of plantar pressure signals, local adhesion between the insole and the sole, and rebound sliding between the foot and the insole material.

[0007] To achieve the above objectives, the present invention provides a real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals. The real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals includes the following steps: Multi-channel plantar pressure signals of race walkers are sampled by a pressure sensor array, and the total pressure of a single foot at each sampling point is calculated based on the multi-channel plantar pressure signals to form a pressure time series curve. The local maximum value in the pressure time series curve is detected by the sliding window method to obtain the support peak sequence, and the gait transition window is determined based on the support peak sequence. Within the gait transition window, calculate the first-order difference value of the current foot pressure signal. Based on the first-order difference value of the current foot pressure signal, obtain the first initial sampling point. Starting from the first initial sampling point, search backward to obtain the first target sampling point. Calculate the time of takeoff based on the first target sampling point. Within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated. Based on the first-order difference value of the contralateral foot pressure signal, the second initial sampling point is obtained. The last low-level sampling point before the pressure rises at the second initial sampling point is taken as the second target sampling point. The ground contact time is calculated based on the second target sampling point. Based on the takeoff time and the ground contact time, a valid takeoff time sample set is obtained. Outliers are removed from the valid takeoff time sample set to obtain the final valid takeoff time sample set, in order to detect whether the race walker's movements are standardized.

[0008] Optionally, the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals, wherein the step of sampling multi-channel plantar pressure signals of race walkers through a pressure sensor array, and calculating the total pressure of a single foot at each sampling point based on the multi-channel plantar pressure signals to form a pressure time-series curve, specifically includes: By using a multi-channel thin-film pressure sensor array mounted on the foot pressure insole, the multi-channel plantar pressure signals of race walkers are sampled at various sampling points. Based on the multi-channel plantar pressure signals at each sampling point, the total pressure of a single foot at each sampling point is calculated. ; in, Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the index of the sampling point. Indicates the current foot The pressure sensor channel is in the first Pressure signal at each sampling point This indicates the number of pressure sensor channels in a single shoe insole. The index indicates the number of pressure sensor channels in a single shoe insole. The current foot indicates either the left or right foot. The total pressure of each foot at each sampling point is summarized to form the pressure time series curve of the sampling point.

[0009] Optionally, the real-time detection method for race walking foot-off-ground time based on plantar pressure signals, wherein the step of using a sliding window method to detect local maxima in the pressure time-series curve to obtain a support peak sequence specifically includes: Using the sliding window method, sampling points that meet the preset candidate support peak conditions are selected from the pressure time series curve as candidate support peaks, and a candidate support peak sequence is formed. The candidate support peak sequence is screened, and the maximum value existing in the local region where each support peak alternates is retained. The maximum value is taken as the support peak, and a support peak sequence is formed based on a preset adjustment rule. The preset candidate support peak conditions are as follows: ; in, Indicates the half width of the sliding window. This represents the support peak threshold coefficient. This represents the historical average pressure value of the current foot throughout the entire testing process. This indicates taking the maximum value. Indicates the current foot is at the sampling point The former Pressure values ​​at each point Indicates the current foot is at the sampling point The former Pressure values ​​at each point Indicates the current foot is at the sampling point The pressure value at that location, Indicates the current foot is at the sampling point After Pressure values ​​at each point; The preset adjustment rule is as follows: ; in, To achieve the minimum gait period in race walking, This indicates the first support peak in the support peak sequence. This indicates the second support peak in the support peak sequence. This indicates the last support peak in the support peak sequence. This indicates the number of support peaks in the support peak sequence. Indicates the first peak in the support peak sequence The time for each support peak Indicates the first peak in the support peak sequence The time of each support peak.

[0010] Optionally, in the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals, the gait transition window includes: a gait transition window of left foot leaving the ground - right foot touching the ground and a gait transition window of right foot leaving the ground - left foot touching the ground; The step of determining the gait transition window based on the support peak sequence specifically includes: Based on the order of the left and right foot support peaks in the support peak sequence, the first right foot support peak that appears after any left foot support peak is taken as the paired right foot support peak. Add a preset starting window offset to the position of the left foot support peak as the left boundary of the window, and subtract a preset ending window offset from the position of the paired right foot support peak as the right boundary of the window to construct a gait transition window from left foot off the ground to right foot touching the ground. The position of the right foot support peak plus the starting window offset is used as the left boundary of the window, and the position of the left foot support peak that first appears after the right foot support peak is subtracted from the ending window offset as the right boundary of the window, thus constructing a gait transition window from right foot off the ground to left foot touching the ground. The starting window offset and the ending window offset are preset sampling points used to eliminate pressure fluctuation interference near the support peak.

[0011] Optionally, the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals, wherein the step of calculating the first-order difference value of the current foot pressure signal within the gait transition window, obtaining a first initial sampling point based on the first-order difference value of the current foot pressure signal, searching backward from the first initial sampling point to obtain a first target sampling point, and calculating the time of departure based on the first target sampling point specifically includes: Within the gait transition window, calculate the first-order difference value of the current foot pressure signal: ; in, This represents the first-order difference value of the current foot pressure signal. Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the index of the sampling point. Represents the gait transition window; Based on the first-order difference value of the current foot pressure signal, the condition is first satisfied within the gait transition window. The first initial sampling point, where, Indicates the threshold of the rate of pressure drop. Indicates the first peak in the support peak sequence The total pressure of a single foot supporting a peak, This indicates the number of consecutively decreasing verification points. Indicates the first initial sampling point; Starting from the first initial sampling point, search backwards to find the first point that satisfies... The first target sampling point, where, This represents the low-level pressure threshold coefficient. Indicates the number of stable verification points. Indicates the first target sampling point; Calculate the time of departure from the ground based on the first target sampling point: ; in, Indicates the time of liftoff. Indicates the sampling time interval.

[0012] Optionally, the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals includes: calculating the first-order difference value of the pressure signal of the contralateral foot within the gait transition window; obtaining a second initial sampling point based on the first-order difference value of the pressure signal of the contralateral foot; taking the last low-level sampling point before the pressure of the second initial sampling point rises at a rate greater than a preset rate threshold as the second target sampling point; and calculating the ground contact time based on the second target sampling point. Specifically, this includes: Within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated: ; in, This represents the first-order difference value of the side foot pressure signal. Indicates the opposite foot. Indicates the opposite foot in the 1st position Total pressure per foot at each sampling point Indicates the opposite foot in the 1st position Total pressure per foot at each sampling point Indicates the index of the sampling point. Represents the gait transition window; Based on the first-order difference value of the lateral foot pressure signal, the condition is obtained that the condition is first satisfied within the gait transition window. The second initial sampling point, where, This indicates the preset pressure rise rate threshold. This indicates the number of continuously increasing verification points. Indicates the first peak in the support peak sequence The total pressure of a single foot supporting a peak, Indicates the second initial sampling point; The last low-order sampling point before the pressure of the second initial sampling point increases at a rate greater than the preset rate threshold is taken as the second target sampling point: ; in, Indicates the second target sampling point; Calculate the ground contact time based on the second target sampling point: ; in, Indicates the moment of contact with the ground. Indicates the sampling time interval.

[0013] Optionally, the real-time detection method for race walking foot takeoff time based on plantar pressure signals, wherein obtaining a valid takeoff time sample set based on the takeoff time and the ground contact time, and removing outliers from the valid takeoff time sample set to obtain the final valid takeoff time sample set, specifically includes: Based on the takeoff time and the ground contact time, a single valid takeoff time sample is obtained: ; in, This represents a single valid takeoff time sample. Indicates the moment of contact with the ground. Indicates the time of liftoff; By aggregating all individual valid takeoff time samples, a set of valid takeoff time samples under the same pace condition is obtained. ,in, This represents the first sample in the set of valid vacancy time samples. This represents the second sample in the set of valid vacancy time samples. This represents the first and last sample in the set of valid vacancy time samples. This indicates the number of valid vacancy time samples; Calculate the mean and standard deviation of the effective takeoff time sample set, and based on the mean and standard deviation, use 3... The principle is to construct a final effective range, and outliers in the effective takeoff time sample set are removed based on the final effective range to obtain the final effective takeoff time sample set.

[0014] Furthermore, to achieve the above objectives, the present invention also provides a real-time detection system for the time of two feet leaving the ground in race walking based on plantar pressure signals, wherein the real-time detection system for the time of two feet leaving the ground in race walking based on plantar pressure signals includes: The single-foot total pressure calculation module is used to sample multi-channel plantar pressure signals of race walkers through a pressure sensor array, calculate the single-foot total pressure at each sampling point based on the multi-channel plantar pressure signals, and form a pressure time series curve. The support peak identification module is used to detect local maxima in the pressure time series curve using the sliding window method, obtain the support peak sequence, and determine the gait transition window based on the support peak sequence. The takeoff time determination module is used to calculate the first-order difference value of the current foot pressure signal within the gait transition window, obtain the first initial sampling point based on the first-order difference value of the current foot pressure signal, search backward from the first initial sampling point to obtain the first target sampling point, and calculate the takeoff time based on the first target sampling point. The ground contact time determination module is used to calculate the first-order difference value of the contralateral foot pressure signal within the gait transition window, obtain the second initial sampling point based on the first-order difference value of the contralateral foot pressure signal, take the last low-level sampling point before the pressure rises at the second initial sampling point as the second target sampling point, and calculate the ground contact time based on the second target sampling point. The judgment and detection module is used to obtain a valid airtime sample set based on the take-off time and the ground contact time, remove outliers from the valid airtime sample set, and obtain the final valid airtime sample set to detect whether the race walker's movements are standardized.

[0015] Furthermore, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a real-time detection program for race walking foot take-off time based on plantar pressure signals, which is stored in the memory and can run on the processor. When the real-time detection program for race walking foot take-off time based on plantar pressure signals is executed by the processor, it implements the steps of the real-time detection method for race walking foot take-off time based on plantar pressure signals as described above.

[0016] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a real-time detection program for race walking foot take-off time based on plantar pressure signals, and when the real-time detection program for race walking foot take-off time based on plantar pressure signals is executed by a processor, it implements the steps of the real-time detection method for race walking foot take-off time based on plantar pressure signals as described above.

[0017] In this invention, multi-channel plantar pressure signals of race walkers are sampled, and the total pressure of each foot at each sampling point is calculated based on the multi-channel plantar pressure signals to form a pressure time series curve. A sliding window method is used to detect local maxima in the pressure time series curve, obtaining a support peak sequence. Based on the support peak sequence, a gait transition window is determined. Within the gait transition window, the first-order difference value of the current foot pressure signal is calculated, and a first initial sampling point is obtained based on this first-order difference value. Starting from the first initial sampling point, a first target sampling point is obtained by searching backwards, and the takeoff time is calculated based on the first target sampling point. Within the gait transition window, the first-order difference value of the opposite foot pressure signal is calculated, and a second initial sampling point is obtained based on this first-order difference value. The last low-level sampling point before the pressure rises from the second initial sampling point is taken as the second target sampling point, and the ground contact time is calculated based on the second target sampling point. Based on the takeoff time and the ground contact time, an effective airtime sample set is obtained, and outliers are removed to obtain the final effective airtime sample set. This invention enables real-time monitoring and accurate identification of the airborne state of both feet in race walking, providing technical support for intelligent detection and scientific training in race walking. Attached Figure Description

[0018] Figure 1 This is a flowchart of a preferred embodiment of the method for real-time detection of the time of two feet leaving the ground in race walking based on plantar pressure signals according to the present invention; Figure 2 This is a technical roadmap of the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals, according to the present invention. Figure 3 This is a schematic diagram illustrating the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals, and the calculation of ground contact time, ground departure time, and time of two feet in the air at a certain pace. Figure 4 This is a schematic diagram illustrating the calculation of ground contact time, ground departure time, and airtime of both feet at another pace using the real-time detection method for race walking based on plantar pressure signals according to the present invention. Figure 5 This invention provides a scatter plot of the airtime at the beginning stage of the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals at a pace of 2 minutes and 0 seconds. Figure 6 This invention provides a real-time detection method for the time it takes for both feet to leave the ground during race walking based on plantar pressure signals. The scatter plot shows the time in the air during the middle stage at a pace of 2 minutes and 0 seconds per kilometer. Figure 7 This invention provides a real-time detection method for the time it takes for both feet to leave the ground during race walking based on plantar pressure signals. The scatter plot shows the time in the air at the end of the race walking phase at a pace of 2 minutes and 0 seconds. Figure 8This invention provides a real-time detection method for the time it takes for both feet to leave the ground during race walking based on plantar pressure signals. The scatter plot shows the time in the air at the beginning of the race walking phase at a pace of 1 minute and 50 seconds. Figure 9 This invention provides a real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals, using a scatter plot of the time in the air during the middle stage at a pace of 1 minute 50 seconds per kilometer. Figure 10 This invention provides a real-time detection method for the time it takes for both feet to leave the ground during race walking based on plantar pressure signals. The scatter plot shows the time in the air at the end of the race walking phase at a pace of 1 minute and 50 seconds. Figure 11 This invention provides a real-time detection method for the time it takes for both feet to leave the ground during race walking based on plantar pressure signals. The scatter plot shows the time in the air at the beginning of the race walking phase at a pace of 1 minute and 40 seconds per kilometer. Figure 12 This invention provides a real-time detection method for the time it takes for both feet to leave the ground during race walking based on plantar pressure signals. The scatter plot shows the time in the air during the middle stage at a pace of 1 minute and 40 seconds per kilometer. Figure 13 This invention provides a real-time detection method for the time it takes for both feet to leave the ground during race walking based on plantar pressure signals. The scatter plot shows the time in the air at the end of the race walking phase at a pace of 1 minute and 40 seconds per kilometer. Figure 14 This is a statistical result graph of the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals, according to the present invention, showing the time of two feet in the air at different paces. Figure 15 This is a structural diagram of a preferred embodiment of the real-time detection system for the time of two feet leaving the ground in race walking based on plantar pressure signals according to the present invention. Figure 16 This is a structural diagram of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0019] This application provides a method, system, and terminal for real-time detection of foot-off-ground time in race walking based on plantar pressure signals. To make the objectives, technical solutions, and effects of this application clearer and more explicit, the following detailed description is provided with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining this application and are not intended to limit this application.

[0020] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0021] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0022] The preferred embodiment of the present invention describes a real-time detection method for the time of foot lift-off in race walking based on plantar pressure signals, such as... Figure 1 and Figure 2 As shown, the real-time detection method for the time of foot lift-off in race walking based on plantar pressure signals includes the following steps: Step S10: Sample multi-channel plantar pressure signals of race walkers using a pressure sensor array, calculate the total pressure of a single foot at each sampling point based on the multi-channel plantar pressure signals, and construct a pressure time-series curve.

[0023] Specifically, a multi-channel thin-film pressure sensor array installed on the foot pressure insole samples the multi-channel plantar pressure signals of race walkers at various sampling points. Based on the multi-channel plantar pressure signals at each sampling point, the total pressure of a single foot at each sampling point is calculated. ; in, Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the index of the sampling point. Indicates the current foot The pressure sensor channel is in the first Pressure signal at each sampling point This indicates the number of pressure sensor channels in a single shoe insole. The index indicates the number of pressure sensor channels in a single shoe insole. The current foot indicates either the left or right foot. Understandably, the analysis of plantar pressure in race walkers first requires the use of a multi-channel thin-film pressure sensor array placed inside the insole to collect data. This sensor array, based on the anatomical structure of the foot, arranges multiple pressure-sensitive units in key areas such as the heel, arch, forefoot, and toes, with each unit corresponding to an independent signal channel. As the race walker walks, the sensor in each channel records the pressure value experienced in that area in real time, thus obtaining a multi-channel plantar pressure signal. To obtain the total pressure experienced by a single foot at each sampling moment, the pressure values ​​from all channels at that moment need to be summed. In other words, at any given sampling moment, the pressure values ​​measured in all areas of the foot are added together to obtain the total pressure of the single foot at that sampling point.

[0024] Furthermore, the total pressure of each foot at each sampling point is summarized to form the pressure time-series curve of the sampling point.

[0025] In this embodiment, the total pressure on each foot calculated at each sampling point throughout the entire test process is organized and summarized in chronological order to create a pressure time-series curve for each sampling point. Specifically, the sampling time can be used as the horizontal axis, and the total pressure value of each foot at each sampling point can be used as the vertical axis to connect a series of discrete data points sequentially, forming a curve that changes continuously over time. This pressure time-series curve fully demonstrates the dynamic change of the total pressure on the sole of the foot of a race walker from one foot strike to the next. By analyzing this curve, the various stages of the gait cycle can be identified.

[0026] Step S20: Use the sliding window method to detect the local maximum value in the pressure time series curve to obtain the support peak sequence, and determine the gait transition window based on the support peak sequence.

[0027] The step of using the sliding window method to detect local maxima in the pressure time series curve to obtain a support peak sequence specifically includes: Using the sliding window method, sampling points that meet the preset candidate support peak conditions are selected from the pressure time series curve as candidate support peaks, and a candidate support peak sequence is formed. The candidate support peak sequence is screened, and the maximum value existing in the local region where each support peak alternates is retained. The maximum value is taken as the support peak, and a support peak sequence is formed based on a preset adjustment rule. The preset candidate support peak conditions are as follows: ; in, Indicates the half width of the sliding window. This represents the support peak threshold coefficient. This represents the historical average pressure value of the current foot throughout the entire testing process. This indicates taking the maximum value. Indicates the current foot is at the sampling point The former Pressure values ​​at each point Indicates the current foot is at the sampling point The former Pressure values ​​at each point Indicates the current foot is at the sampling point The pressure value at that location, Indicates the current foot is at the sampling point After Pressure values ​​at each point; The preset adjustment rule is as follows: ; in, To achieve the minimum gait period in race walking, This indicates the first support peak in the support peak sequence. This indicates the second support peak in the support peak sequence. This indicates the last support peak in the support peak sequence. This indicates the number of support peaks in the support peak sequence. Indicates the first peak in the support peak sequence The time for each support peak Indicates the first peak in the support peak sequence The time of each support peak.

[0028] In this embodiment, the kinematic law of alternating support between the left and right feet in race walking is used to determine the gait transition window, limiting the detection range to the gait transition interval and reducing global clutter interference.

[0029] A gait transition window is established based on the support peaks in the total pressure time-series curves of the left and right feet. A support peak refers to the position where the pressure on a particular foot significantly increases during the support phase. In race walking, the left and right feet alternate in support; therefore, when a left foot pressure peak is followed by a right foot pressure peak, this corresponds to the transition from left foot leaving the ground to right foot touching the ground; similarly, when a right foot pressure peak is followed by a left foot pressure peak, it corresponds to the transition from right foot leaving the ground to left foot touching the ground. This method restricts event recognition to a reasonable left-right foot alternation window, avoiding blindly searching for event points throughout the entire pressure time-series curve and reducing misjudgments. The specific method for automatic support peak recognition is to use a sliding window approach to detect local maxima in the pressure time-series curve, forming a support peak sequence.

[0030] When screening candidate support peaks, only the presence of a maximum value within the local region where each support peak alternates is retained; this maximum value is denoted as a support peak and a support peak sequence is formed. At the same time, the supporting peak sequence is judged and adjusted to meet the following conditions: Furthermore, the time interval between any two adjacent support peaks is greater than the minimum gait period of race walking. : ;in, The preferred value is 300ms (milliseconds).

[0031] Furthermore, the gait transition window includes: a gait transition window of left foot off the ground and right foot on the ground, and a gait transition window of right foot off the ground and left foot on the ground; The step of determining the gait transition window based on the support peak sequence specifically includes: Based on the order of the left and right foot support peaks in the support peak sequence, the first right foot support peak that appears after any left foot support peak is taken as the paired right foot support peak. Add a preset starting window offset to the position of the left foot support peak as the left boundary of the window, and subtract a preset ending window offset from the position of the paired right foot support peak as the right boundary of the window to construct a gait transition window from left foot off the ground to right foot touching the ground. The position of the right foot support peak plus the starting window offset is used as the left boundary of the window, and the position of the left foot support peak that first appears after the right foot support peak is subtracted from the ending window offset as the right boundary of the window, thus constructing a gait transition window from right foot off the ground to left foot touching the ground. The starting window offset and the ending window offset are preset sampling points used to eliminate pressure fluctuation interference near the support peak.

[0032] In this embodiment, the gait transition window is determined by the support peak, limiting event recognition to within the gait transition window and thus reducing misjudgments. Based on the kinematic laws of alternating support by the left and right feet in race walking, a correspondence between the support peaks of the left and right feet is established. For the left foot's first... Supporting peaks Its corresponding right foot support peak satisfy: ; This defines the gait transition window from left foot off the ground to right foot touching the ground. for: ; Similarly, the gait transition window from right foot off the ground to left foot touching the ground. for: ; in, This indicates that in the right foot support peak sequence, it corresponds to the i-th support peak of the left foot. The corresponding number of the right foot support peak. This indicates the first peak greater than 1 found in the right foot support peak sequence. The peak position, p represents the index of the peak in the right foot sequence. and These are the start window offset and end window offset, used to eliminate pressure fluctuation interference near the support peak. Preferred values ​​are... , (Corresponds to 200ms).

[0033] Step S30: Calculate the first-order difference value of the current foot pressure signal within the gait conversion window. Obtain the first initial sampling point based on the first-order difference value of the current foot pressure signal. Search backward from the first initial sampling point to obtain the first target sampling point. Calculate the time of takeoff based on the first target sampling point.

[0034] Specifically, within the gait transition window, the first-order difference value of the current foot pressure signal is calculated: ; in, This represents the first-order difference value of the current foot pressure signal. Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the index of the sampling point. Represents the gait transition window; Based on the first-order difference value of the current foot pressure signal, the condition is first satisfied within the gait transition window. The first initial sampling point, where, Indicates the threshold of the rate of pressure drop. Indicates the first peak in the support peak sequence The total pressure of a single foot supporting a peak, This indicates the number of consecutively decreasing verification points. Indicates the first initial sampling point; Starting from the first initial sampling point, search backwards to find the first point that satisfies... The first target sampling point, where, This represents the low-level pressure threshold coefficient. Indicates the number of stable verification points. Indicates the first target sampling point; Calculate the time of departure from the ground based on the first target sampling point: ; in, Indicates the time of liftoff. Indicates the sampling time interval.

[0035] In this embodiment, in the current gait transition window Internally, the first-order difference (derivative) of the current foot pressure signal is calculated, and the rate of pressure change is used to replace the static pressure value to avoid baseline drift caused by insole adhesion. And based on the first-order difference value, find the first sampling point within the window that satisfies the following conditions. : ; in, The preferred value is the pressure drop rate threshold. , The optimal value is the number of verification points that decrease continuously. (Corresponding to 50ms); Next, from Begin searching backwards to find the first sampling point that satisfies the following conditions. : ;in, The preferred value is the low-pressure threshold coefficient. , To ensure a stable number of validation points, the optimal value is... (Corresponding to 100ms), finally, the liftoff time is calculated as follows: .

[0036] Step S40: Calculate the first-order difference value of the contralateral foot pressure signal within the gait conversion window. Obtain the second initial sampling point based on the first-order difference value of the contralateral foot pressure signal. Take the last low-level sampling point before the pressure rises at the second initial sampling point as the second target sampling point. Calculate the ground contact time based on the second target sampling point.

[0037] Specifically, within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated: ; in, This represents the first-order difference value of the side foot pressure signal. Indicates the opposite foot. Indicates the opposite foot in the 1st position Total pressure per foot at each sampling point Indicates the opposite foot in the 1st position Total pressure per foot at each sampling point Indicates the index of the sampling point. Represents the gait transition window; Based on the first-order difference value of the lateral foot pressure signal, the condition is obtained that the condition is first satisfied within the gait transition window. The second initial sampling point, where, This indicates the preset pressure rise rate threshold. This indicates the number of continuously increasing verification points. Indicates the first peak in the support peak sequence The total pressure of a single foot supporting a peak, Indicates the second initial sampling point; The last low-order sampling point before the pressure of the second initial sampling point increases at a rate greater than the preset rate threshold is taken as the second target sampling point: ;in, Indicate the second target sampling point; calculate the ground contact time based on the second target sampling point: ;in, Indicates the moment of contact with the ground. Indicates the sampling time interval.

[0038] In this embodiment, within the same gait transition window Inside, calculate the first-order difference of the pressure signal on the opposite foot: Find the first sampling point within the window that meets the following conditions. : ;in, Recommended value for the rate of pressure rise threshold. , Recommended value for continuously increasing verification points .

[0039] The moment of contact with the ground is defined as the last low-level sampling point before the pressure rises rapidly (the rate of pressure rise exceeds a preset threshold): Finally, the time of contact was: .

[0040] Step S50: Based on the takeoff time and the ground contact time, obtain a valid takeoff time sample set, remove outliers from the valid takeoff time sample set, and obtain the final valid takeoff time sample set to detect whether the race walker's movements are standardized.

[0041] The process of obtaining a valid takeoff time sample set based on the takeoff time and the ground contact time, removing outliers from the valid takeoff time sample set, and obtaining the final valid takeoff time sample set specifically includes: Based on the takeoff time and the ground contact time, a single valid takeoff time sample is obtained: ; in, This represents a single valid takeoff time sample. Indicates the moment of contact with the ground. Indicates the time of liftoff; By aggregating all individual valid takeoff time samples, a set of valid takeoff time samples under the same pace condition is obtained. ,in, This represents the first sample in the set of valid vacancy time samples. This represents the second sample in the set of valid vacancy time samples. This represents the first and last sample in the set of valid vacancy time samples. This indicates the number of valid vacancy time samples; Calculate the mean and standard deviation of the effective takeoff time sample set, and based on the mean and standard deviation, use 3... The principle is to construct a final effective range, and outliers in the effective takeoff time sample set are removed based on the final effective range to obtain the final effective takeoff time sample set.

[0042] It is understood that, in this embodiment, the single takeoff time is calculated as follows: ;like If the opposite foot touches the ground prematurely, it indicates a double-support phase, which is considered an invalid jump and is not included in the statistics; if Once a valid gait is determined, it enters the outlier screening stage to eliminate invalid samples caused by occasional gait jerking or instantaneous sensor noise.

[0043] In the outlier screening process, based on 3 Outlier screening is performed according to the principle: for the same pace conditions... 1 valid take-off time sample Calculate the sample mean and standard deviation : ; ; According to 3 Principle, eliminate those exceeding Outliers in the range: ; The following samples of valid vacancy times are saved separately for manual review: ; Where f represents the index of the effective vacancy time sample, This represents the f-th sample in the set of valid vacancy time samples. This represents the final valid vacancy time sample.

[0044] Furthermore, the final retained valid airtime samples are used to detect whether the walker's movements are standardized. Specifically, after obtaining the final set of valid airtime samples, each airtime value in the set is compared with a preset airtime threshold. If any valid airtime sample is greater than or equal to the airtime threshold, it is determined that the walker has violated the airtime rule during the corresponding gait cycle. If all valid airtime samples are less than the airtime threshold, it is determined that the walker's movements comply with the walking rules. The airtime threshold is set according to the walking rules (e.g., the minimum time corresponding to a visible airtime).

[0045] Furthermore, the effective airtime sample set can be statistically processed to calculate its maximum value, average value, or the proportion of samples exceeding a preset threshold; when the maximum value or average value exceeds the airtime threshold, or the proportion exceeds the allowed violation proportion threshold, the race walker's action is determined to be non-standard; otherwise, it is determined to be standard.

[0046] Based on the above comparisons or statistical judgments, the final output is the detection result of whether the race walker's movements are standardized.

[0047] The following specific experimental procedure demonstrates the effectiveness of the real-time detection method for race walking foot-off-ground time based on plantar pressure signals proposed in this invention: In the experimental verification process, a single-factor repeated measures design was adopted. The independent variable was race walking pace (3 levels), and the dependent variables were the plantar pressure signal collected by the insoles and the calculated duration of foot lift-off. The experiment was conducted under the guidance of a race walking coach throughout to ensure the standardization of movements and the controllability of fouls. The initial experiment collected basic information from a professional athlete (race walker): the subject's gender, age, height, weight, athletic level, years of specialized training, and other basic information were recorded. Anatomical parameters such as lower limb length, thigh circumference, and calf circumference were measured and recorded. The athlete was supervised by the coach during warm-up throughout the experiment to avoid sports injuries and ensure that the subject's body reached the optimal state for exercise.

[0048] The calibrated smart insoles were placed flat inside the subject's specialized race walking shoes, and their position was adjusted to ensure a perfect fit to the foot. Kinesiology tape was used to secure the insoles and data transmission module, preventing slippage and wobbling during exercise and ensuring no restriction on normal gait or joint movement. The orientation of the main control circuit board was determined. Inertial sensing units were worn on the lateral femur and tibia of both lower limbs of the subject. The subject completed a trial race walk at a comfortable, regular training pace to adapt to the insoles. After the testers confirmed normal data acquisition and no discomfort experienced by the subject, the formal testing began.

[0049] like Figure 3 and Figure 4 The diagram illustrates the calculation of ground contact time, ground takeoff time, and airtime at different paces. Specifically, it demonstrates the correspondence between total plantar pressure and ground takeoff and ground contact events during race walking. It uses pressure values ​​(e.g., Pascals or Newtons) at different time points and special markers (e.g., ±100, >20000, <10000) to explain that when the pressure value is below a certain ground takeoff threshold, it is considered a foot takeoff, and when it is above a certain ground contact threshold, it is considered a foot contact. This provides a basic criterion for subsequent gait transition window identification based on pressure signals, calculation of airtime, and detection of proper movement.

[0050] Figures 5-13 These graphs show the calculation of the time spent in the air during different paces and phases. They are used to display the scatter distribution of airtime during race walking under different test conditions. The horizontal axis is "time within a phase (s)" and the vertical axis is "airtime (ms)". Each graph contains two sets of scatter points (the first set and the second set), corresponding to different test subjects, different feet, or different repeated experiments.

[0051] Specifically, Figure 5 This is a scatter plot of the calculated takeoff time at the beginning of the pace at 2 minutes and 0 seconds. Figure 6 This is a scatter plot of the calculated takeoff time during the middle phase at a pace of 2 minutes and 02 seconds. Figure 7 This is a scatter plot of the calculated takeoff time at the end of the phase at a pace of 2 minutes and 02 seconds. Figure 8 This is a scatter plot of the calculated takeoff time at the beginning of the pace at a speed of 1 minute and 50 seconds. Figure 9 This is a scatter plot of the calculated airtime during the middle phase at a pace of 1 minute and 50 seconds. Figure 10 This is a scatter plot of the calculated airtime at the end of the phase at a pace of 1 minute and 50 seconds. Figure 11 This is a scatter plot of the calculated takeoff time at the beginning of the pace at a speed of 1 minute and 40 seconds. Figure 12 This is a scatter plot of the calculated airtime during the middle phase at a pace of 1 minute and 40 seconds. Figure 13 This is a scatter plot showing the calculated airtime at the end of the phase at a pace of 1 minute and 40 seconds. Figures 5-13 Both are used for detecting the standardization of race walking movements: by statistically analyzing the scatter distribution of airtime at different stages, it determines whether the actual airtime exceeds the threshold allowed by the race walking rules (e.g., 30–50 ms), thereby identifying whether there are any violations of airtime rules. (Statistics) Figures 5-13 The calculation results are shown in the table below.

[0052] Table 1 shows the descriptive statistics of takeoff time for each speed and stage group. The results indicate that the mean takeoff time varies significantly under different speed conditions. At slow speeds, the takeoff times for the start, middle, and end stages are 32.49 ms, 33.33 ms, and 35.19 ms, respectively; at medium speeds, the takeoff times for the three stages are 40.50 ms, 40.24 ms, and 39.15 ms, respectively; and at fast speeds, the takeoff times for the three stages are 45.16 ms, 44.75 ms, and 48.15 ms, respectively. Overall, the takeoff time increases as the time to reach 800 meters decreases.

[0053] Table 1: Descriptive statistics of takeoff time for each speed-stage group

[0054] As shown in Table 2, after summarizing the overall speed conditions, the average airtime under slow, medium, and fast conditions were 33.35ms, 40.06ms, and 45.73ms, respectively, indicating that the increase in race walking speed led to a longer airtime.

[0055] Table 2: Overall descriptive statistics of takeoff time under different speed conditions

[0056] Furthermore, to analyze the impact of different speed conditions on takeoff time, statistical analysis was performed on the three sets of speed data. For example... Figure 14 As shown, the statistical results of the time of both feet off the ground under different paces are presented. There are significant differences in the time of airborne time under the three speed conditions, indicating that different speed conditions have a significant impact on the time of airborne time.

[0057] To analyze whether there are differences in airtime between the start and finish phases of the race walking event at the same pace, a statistical analysis was conducted. No significant differences were found between the start and middle phases, or between the middle and finish phases. These results indicate that the airtime of the participants generally increases as the race progresses, with a significant increase in the finish phase compared to the start. This phenomenon may be related to changes in rhythm later in the exercise, fatigue accumulation, or decreased stability of technical movement control.

[0058] As can be seen from the above experimental results, the present invention can accurately and in real time identify race walking airborne violations, and has good application value in competition and training. It can provide data support for race walking technique correction, quantitative training and intelligent detection. In the future, the system's ability to monitor the evolution of technical movements under fatigue state can be further improved by extending the experimental distance and expanding the sample size.

[0059] Furthermore, such as Figure 15As shown, based on the above-mentioned real-time detection method for race walking foot-to-ground time based on plantar pressure signals, the present invention also provides a real-time detection system for race walking foot-to-ground time based on plantar pressure signals, wherein the real-time detection system for race walking foot-to-ground time based on plantar pressure signals includes: The single-foot total pressure calculation module 51 is used to sample the multi-channel plantar pressure signal of the race walker through the pressure sensor array, calculate the single-foot total pressure at each sampling point based on the multi-channel plantar pressure signal, and form a pressure time series curve. The support peak identification module 52 is used to detect local maximum values ​​in the pressure time series curve using the sliding window method, obtain the support peak sequence, and determine the gait transition window based on the support peak sequence; The takeoff time determination module 53 is used to calculate the first-order difference value of the current foot pressure signal within the gait transition window, obtain the first initial sampling point based on the first-order difference value of the current foot pressure signal, search backward from the first initial sampling point to obtain the first target sampling point, and calculate the takeoff time based on the first target sampling point. The ground contact time determination module 54 is used to calculate the first-order difference value of the contralateral foot pressure signal within the gait transition window, obtain the second initial sampling point based on the first-order difference value of the contralateral foot pressure signal, take the last low-level sampling point before the pressure rises at the second initial sampling point as the second target sampling point, and calculate the ground contact time based on the second target sampling point. The judgment and detection module 55 is used to obtain a valid airtime sample set based on the take-off time and the ground contact time, remove outliers from the valid airtime sample set, and obtain the final valid airtime sample set to detect whether the race walker's movements are standardized.

[0060] Furthermore, such as Figure 16 As shown, based on the above-mentioned real-time detection method and system for race walking foot lift-off time based on plantar pressure signals, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 16 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0061] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 may also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a real-time detection program 40 for the time it takes for two feet to leave the ground in race walking based on plantar pressure signals. This real-time detection program 40 for the time it takes for two feet to leave the ground in race walking based on plantar pressure signals can be executed by the processor 10, thereby realizing the real-time detection method for the time it takes for two feet to leave the ground in race walking based on plantar pressure signals in this application.

[0062] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals.

[0063] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0064] In one embodiment, when the processor 10 executes the real-time detection program 40 in the memory 20 for race walking foot-off-ground time based on plantar pressure signals, the following steps are performed: Multi-channel plantar pressure signals of race walkers are sampled by a pressure sensor array, and the total pressure of a single foot at each sampling point is calculated based on the multi-channel plantar pressure signals to form a pressure time series curve. The local maximum value in the pressure time series curve is detected by the sliding window method to obtain the support peak sequence, and the gait transition window is determined based on the support peak sequence. Within the gait transition window, calculate the first-order difference value of the current foot pressure signal. Based on the first-order difference value of the current foot pressure signal, obtain the first initial sampling point. Starting from the first initial sampling point, search backward to obtain the first target sampling point. Calculate the time of takeoff based on the first target sampling point. Within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated. Based on the first-order difference value of the contralateral foot pressure signal, the second initial sampling point is obtained. The last low-level sampling point before the pressure rises at the second initial sampling point is taken as the second target sampling point. The ground contact time is calculated based on the second target sampling point. Based on the takeoff time and the ground contact time, a valid takeoff time sample set is obtained. Outliers are removed from the valid takeoff time sample set to obtain the final valid takeoff time sample set, in order to detect whether the race walker's movements are standardized.

[0065] Specifically, the process of sampling multi-channel plantar pressure signals from race walkers using a pressure sensor array, calculating the total pressure on each foot at each sampling point based on the multi-channel plantar pressure signals, and constructing a pressure time-series curve includes: By using a multi-channel thin-film pressure sensor array mounted on the foot pressure insole, the multi-channel plantar pressure signals of race walkers are sampled at various sampling points. Based on the multi-channel plantar pressure signals at each sampling point, the total pressure of a single foot at each sampling point is calculated. ; in, Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the index of the sampling point. Indicates the current foot The pressure sensor channel is in the first Pressure signal at each sampling point This indicates the number of pressure sensor channels in a single shoe insole. The index indicates the number of pressure sensor channels in a single shoe insole. The current foot indicates either the left or right foot. The total pressure of each foot at each sampling point is summarized to form the pressure time series curve of the sampling point.

[0066] Specifically, the method of using a sliding window to detect local maxima in the pressure time series curve to obtain a support peak sequence includes: Using the sliding window method, sampling points that meet the preset candidate support peak conditions are selected from the pressure time series curve as candidate support peaks, and a candidate support peak sequence is formed. The candidate support peak sequence is screened, and the maximum value existing in the local region where each support peak alternates is retained. The maximum value is taken as the support peak, and a support peak sequence is formed based on a preset adjustment rule. The preset candidate support peak conditions are as follows: ; in, Indicates the half width of the sliding window. This represents the support peak threshold coefficient. This represents the historical average pressure value of the current foot throughout the entire testing process. This indicates taking the maximum value. Indicates the current foot is at the sampling point The former Pressure values ​​at each point Indicates the current foot is at the sampling point The former Pressure values ​​at each point Indicates the current foot is at the sampling point The pressure value at that location, Indicates the current foot is at the sampling point After Pressure values ​​at each point; The preset adjustment rule is as follows: ; in, To achieve the minimum gait period in race walking, This indicates the first support peak in the support peak sequence. This indicates the second support peak in the support peak sequence. This indicates the last support peak in the support peak sequence. This indicates the number of support peaks in the support peak sequence. Indicates the first peak in the support peak sequence The time for each support peak Indicates the first peak in the support peak sequence The time of each support peak.

[0067] The gait transition window includes: a gait transition window with the left foot off the ground and the right foot touching the ground, and a gait transition window with the right foot off the ground and the left foot touching the ground; The step of determining the gait transition window based on the support peak sequence specifically includes: Based on the order of the left and right foot support peaks in the support peak sequence, the first right foot support peak that appears after any left foot support peak is taken as the paired right foot support peak. Add a preset starting window offset to the position of the left foot support peak as the left boundary of the window, and subtract a preset ending window offset from the position of the paired right foot support peak as the right boundary of the window to construct a gait transition window from left foot off the ground to right foot touching the ground. The position of the right foot support peak plus the starting window offset is used as the left boundary of the window, and the position of the left foot support peak that first appears after the right foot support peak is subtracted from the ending window offset as the right boundary of the window, thus constructing a gait transition window from right foot off the ground to left foot touching the ground. The starting window offset and the ending window offset are preset sampling points used to eliminate pressure fluctuation interference near the support peak.

[0068] Specifically, the process of calculating the first-order difference value of the current foot pressure signal within the gait transition window, obtaining a first initial sampling point based on the first-order difference value of the current foot pressure signal, searching backward from the first initial sampling point to obtain a first target sampling point, and calculating the takeoff time based on the first target sampling point includes: Within the gait transition window, calculate the first-order difference value of the current foot pressure signal: ; in, This represents the first-order difference value of the current foot pressure signal. Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the index of the sampling point. Represents the gait transition window; Based on the first-order difference value of the current foot pressure signal, the condition is first satisfied within the gait transition window. The first initial sampling point, where, Indicates the threshold of the rate of pressure drop. Indicates the first peak in the support peak sequence The total pressure of a single foot supporting a peak, This indicates the number of consecutively decreasing verification points. Indicates the first initial sampling point; Starting from the first initial sampling point, search backwards to find the first point that satisfies... The first target sampling point, where, This represents the low-level pressure threshold coefficient. Indicates the number of stable verification points. Indicates the first target sampling point; Calculate the time of departure from the ground based on the first target sampling point: ; in, Indicates the time of liftoff. Indicates the sampling time interval.

[0069] Specifically, within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated. Based on this first-order difference value, a second initial sampling point is obtained. The last low-order sampling point before the pressure at the second initial sampling point rises at a rate greater than a preset rate threshold is taken as the second target sampling point. The ground contact time is calculated based on the second target sampling point, specifically including: Within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated: ; in, This represents the first-order difference value of the side foot pressure signal. Indicates the opposite foot. Indicates the opposite foot in the 1st position Total pressure per foot at each sampling point Indicates the opposite foot in the 1st position Total pressure per foot at each sampling point Indicates the index of the sampling point. Represents the gait transition window; Based on the first-order difference value of the lateral foot pressure signal, the condition is obtained that the condition is first satisfied within the gait transition window. The second initial sampling point, where, This indicates the preset pressure rise rate threshold. This indicates the number of continuously increasing verification points. Indicates the first peak in the support peak sequence The total pressure of a single foot supporting a peak, Indicates the second initial sampling point; The last low-order sampling point before the pressure of the second initial sampling point increases at a rate greater than the preset rate threshold is taken as the second target sampling point: ; in, Indicates the second target sampling point; Calculate the ground contact time based on the second target sampling point: ; in, Indicates the moment of contact with the ground. Indicates the sampling time interval.

[0070] Specifically, the process of obtaining a valid takeoff time sample set based on the takeoff time and the ground contact time, and removing outliers from the valid takeoff time sample set to obtain the final valid takeoff time sample set, includes: Based on the takeoff time and the ground contact time, a single valid takeoff time sample is obtained: ; in, This represents a single valid takeoff time sample. Indicates the moment of contact with the ground. Indicates the time of liftoff; By aggregating all individual valid takeoff time samples, a set of valid takeoff time samples under the same pace condition is obtained. ,in, This represents the first sample in the set of valid vacancy time samples. This represents the second sample in the set of valid vacancy time samples. This represents the first and last sample in the set of valid vacancy time samples. This indicates the number of valid vacancy time samples; Calculate the mean and standard deviation of the effective takeoff time sample set, and based on the mean and standard deviation, use 3... The principle is to construct a final effective range, and outliers in the effective takeoff time sample set are removed based on the final effective range to obtain the final effective takeoff time sample set.

[0071] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a real-time detection program for race walking foot take-off time based on plantar pressure signals, and the real-time detection program for race walking foot take-off time based on plantar pressure signals, when executed by a processor, implements the steps of the real-time detection method for race walking foot take-off time based on plantar pressure signals as described above.

[0072] In summary, this invention provides a real-time detection method, system, terminal, and storage medium for the time of two feet leaving the ground in race walking based on plantar pressure signals. The method includes: sampling multi-channel plantar pressure signals from race walkers; calculating the total pressure of a single foot at each sampling point based on the multi-channel plantar pressure signals to form a pressure time-series curve; detecting local maxima in the pressure time-series curve using a sliding window method to obtain a support peak sequence; determining a gait transition window based on the support peak sequence; calculating the first-order difference value of the current foot pressure signal within the gait transition window; and obtaining a first initial... Starting from the first initial sampling point, a first target sampling point is obtained by searching backwards. The takeoff time is calculated based on the first target sampling point. Within the gait transition window, the first-order difference value of the pressure signal of the opposite foot is calculated. Based on this first-order difference value, a second initial sampling point is obtained. The last low-level sampling point before the pressure rises from the second initial sampling point is taken as the second target sampling point. The ground contact time is calculated based on the second target sampling point. Based on the takeoff time and the ground contact time, a valid airtime sample set is obtained, and outliers are removed to obtain the final valid airtime sample set. This invention enables real-time monitoring and accurate identification of the airtime state of both feet in race walking, providing technical support for intelligent detection and scientific training in race walking.

[0073] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0074] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0075] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A real-time detection method for the time of foot lift-off in race walking based on plantar pressure signals, characterized in that, The real-time detection method for race walking foot-off-ground time based on plantar pressure signals includes: Multi-channel plantar pressure signals of race walkers are sampled by a pressure sensor array, and the total pressure of a single foot at each sampling point is calculated based on the multi-channel plantar pressure signals to form a pressure time series curve. The local maximum value in the pressure time series curve is detected by the sliding window method to obtain the support peak sequence, and the gait transition window is determined based on the support peak sequence. Within the gait transition window, calculate the first-order difference value of the current foot pressure signal. Based on the first-order difference value of the current foot pressure signal, obtain the first initial sampling point. Starting from the first initial sampling point, search backward to obtain the first target sampling point. Calculate the time of takeoff based on the first target sampling point. Within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated. Based on the first-order difference value of the contralateral foot pressure signal, the second initial sampling point is obtained. The last low-level sampling point before the pressure rises at the second initial sampling point is taken as the second target sampling point. The ground contact time is calculated based on the second target sampling point. Based on the takeoff time and the ground contact time, a valid airtime sample set is obtained. Outliers are removed from the valid airtime sample set to obtain the final valid airtime sample set, in order to detect whether the race walker's movements are standardized. The gait transition window includes: a gait transition window with the left foot off the ground and the right foot touching the ground, and a gait transition window with the right foot off the ground and the left foot touching the ground; The step of determining the gait transition window based on the support peak sequence specifically includes: Based on the order of the left and right foot support peaks in the support peak sequence, the first right foot support peak that appears after any left foot support peak is taken as the paired right foot support peak. Add a preset starting window offset to the position of the left foot support peak as the left boundary of the window, and subtract a preset ending window offset from the position of the paired right foot support peak as the right boundary of the window to construct a gait transition window from left foot off the ground to right foot touching the ground. The position of the right foot support peak plus the starting window offset is used as the left boundary of the window, and the position of the left foot support peak that first appears after the right foot support peak is subtracted from the ending window offset as the right boundary of the window, thus constructing a gait transition window from right foot off the ground to left foot touching the ground. The starting window offset and the ending window offset are preset sampling points used to eliminate pressure fluctuation interference near the support peak. The process of calculating the first-order difference value of the current foot pressure signal within the gait transition window, obtaining a first initial sampling point based on the first-order difference value of the current foot pressure signal, searching backward from the first initial sampling point to obtain a first target sampling point, and calculating the ground clearance time based on the first target sampling point specifically includes: Within the gait transition window, calculate the first-order difference value of the current foot pressure signal: ； in, This represents the first-order difference value of the current foot pressure signal. Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the index of the sampling point. This represents the gait transition window; Based on the first-order difference value of the current foot pressure signal, the condition is first satisfied within the gait transition window. The first initial sampling point, where, Indicates the threshold of the rate of pressure drop. Indicates the first peak in the support peak sequence The total pressure of a single foot supporting a peak, This indicates the number of consecutively decreasing verification points. Indicates the first initial sampling point; Starting from the first initial sampling point, search backwards to find the first point that satisfies... The first target sampling point, where, This represents the low-level pressure threshold coefficient. Indicates the number of stable verification points. Indicates the first target sampling point; Calculate the time of departure from the ground based on the first target sampling point: ； in, Indicates the time of liftoff. Indicates the sampling time interval.

2. The real-time detection method for the time of foot lift-off in race walking based on plantar pressure signals according to claim 1, characterized in that, The process of sampling multi-channel plantar pressure signals from race walkers using a pressure sensor array, calculating the total pressure of a single foot at each sampling point based on the multi-channel plantar pressure signals, and constructing a pressure time-series curve specifically includes: By using a multi-channel thin-film pressure sensor array mounted on the foot pressure insole, the multi-channel plantar pressure signals of race walkers are sampled at various sampling points. Based on the multi-channel plantar pressure signals at each sampling point, the total pressure of a single foot at each sampling point is calculated. ； in, Indicates the current foot is in the 1st position. Total pressure per foot at each sampling point Indicates the index of the sampling point. Indicates the current foot The pressure sensor channel is in the first Pressure signal at each sampling point This indicates the number of pressure sensor channels in a single shoe insole. The index indicates the number of pressure sensor channels in a single shoe insole. The current foot indicates either the left or right foot. The total pressure of each foot at each sampling point is summarized to form the pressure time series curve of the sampling point.

3. The real-time detection method for the time of foot lift-off in race walking based on plantar pressure signals according to claim 2, characterized in that, The step of using the sliding window method to detect local maxima in the pressure time series curve to obtain a support peak sequence specifically includes: Using the sliding window method, sampling points that meet the preset candidate support peak conditions are selected from the pressure time series curve as candidate support peaks, and a candidate support peak sequence is formed. The candidate support peak sequence is screened, and the maximum value existing in the local region where each support peak alternates is retained. The maximum value is taken as the support peak, and a support peak sequence is formed based on a preset adjustment rule. The preset candidate support peak conditions are as follows: ； in, Indicates the half width of the sliding window. This represents the support peak threshold coefficient. This represents the historical average pressure value of the current foot throughout the entire testing process. This indicates taking the maximum value. Indicates the current foot is at the sampling point The former Pressure values ​​at each point Indicates the current foot is at the sampling point The former Pressure values ​​at each point Indicates the current foot is at the sampling point The pressure value at that location, Indicates the current foot is at the sampling point After Pressure values ​​at each point; The preset adjustment rule is as follows: ； in, To achieve the minimum gait period in race walking, This indicates the first support peak in the support peak sequence. This indicates the second support peak in the support peak sequence. This indicates the last support peak in the support peak sequence. This indicates the number of support peaks in the support peak sequence. Indicates the first peak in the support peak sequence The time for each support peak Indicates the first peak in the support peak sequence The time of each support peak.

4. The real-time detection method for the time of foot lift-off in race walking based on plantar pressure signals according to claim 1, characterized in that, Within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated. Based on this first-order difference value, a second initial sampling point is obtained. The last low-order sampling point before the pressure at the second initial sampling point rises at a rate greater than a preset rate threshold is taken as the second target sampling point. The ground contact time is calculated based on the second target sampling point, specifically including: Within the gait transition window, the first-order difference value of the contralateral foot pressure signal is calculated: ； in, This represents the first-order difference value of the side foot pressure signal. Indicates the opposite foot. Indicates the opposite foot in the 1st position Total pressure per foot at each sampling point Indicates the opposite foot in the 1st position Total pressure per foot at each sampling point Indicates the index of the sampling point. Represents the gait transition window; Based on the first-order difference value of the lateral foot pressure signal, the condition is obtained that the condition is first satisfied within the gait transition window. The second initial sampling point, where, This indicates the preset pressure rise rate threshold. This indicates the number of continuously increasing verification points. Indicates the first peak in the support peak sequence The total pressure of a single foot supporting a peak, Indicates the second initial sampling point; The last low-order sampling point before the pressure of the second initial sampling point increases at a rate greater than the preset rate threshold is taken as the second target sampling point: ； in, Indicates the second target sampling point; Calculate the ground contact time based on the second target sampling point: ； in, Indicates the moment of contact with the ground. Indicates the sampling time interval.

5. The real-time detection method for the time of foot lift-off in race walking based on plantar pressure signals according to claim 1, characterized in that, The process of obtaining a valid takeoff time sample set based on the takeoff time and the ground contact time, removing outliers from the valid takeoff time sample set, and obtaining the final valid takeoff time sample set specifically includes: Based on the takeoff time and the ground contact time, a single valid takeoff time sample is obtained: ； in, This represents a single valid takeoff time sample. Indicates the moment of contact with the ground. Indicates the time of liftoff; By aggregating all individual valid takeoff time samples, a set of valid takeoff time samples under the same pace condition is obtained. ,in, This represents the first sample in the set of valid vacancy time samples. This represents the second sample in the set of valid vacancy time samples. This represents the first and last sample in the set of valid vacancy time samples. This indicates the number of valid empty time samples; Calculate the mean and standard deviation of the effective takeoff time sample set, and based on the mean and standard deviation, use 3... The principle is to construct a final effective range, and outliers in the effective takeoff time sample set are removed based on the final effective range to obtain the final effective takeoff time sample set.

6. A real-time detection system for the time of foot lift-off in race walking based on plantar pressure signals, characterized in that, The real-time detection system for race walking foot-to-ground time based on plantar pressure signals is used to implement the real-time detection method for race walking foot-to-ground time based on plantar pressure signals according to any one of claims 1-5. The real-time detection system for race walking foot-to-ground time based on plantar pressure signals includes: The single-foot total pressure calculation module is used to sample multi-channel plantar pressure signals of race walkers through a pressure sensor array, calculate the single-foot total pressure at each sampling point based on the multi-channel plantar pressure signals, and form a pressure time series curve. The support peak identification module is used to detect local maxima in the pressure time series curve using the sliding window method, obtain the support peak sequence, and determine the gait transition window based on the support peak sequence. The takeoff time determination module is used to calculate the first-order difference value of the current foot pressure signal within the gait transition window, obtain the first initial sampling point based on the first-order difference value of the current foot pressure signal, search backward from the first initial sampling point to obtain the first target sampling point, and calculate the takeoff time based on the first target sampling point. The ground contact time determination module is used to calculate the first-order difference value of the contralateral foot pressure signal within the gait transition window, obtain the second initial sampling point based on the first-order difference value of the contralateral foot pressure signal, take the last low-level sampling point before the pressure rises at the second initial sampling point as the second target sampling point, and calculate the ground contact time based on the second target sampling point. The judgment and detection module is used to obtain a valid airtime sample set based on the take-off time and the ground contact time, remove outliers from the valid airtime sample set, and obtain the final valid airtime sample set to detect whether the race walker's movements are standardized.

7. A terminal, characterized in that, The terminal includes: a memory, a processor, and a real-time detection program for race walking double-foot take-off time based on plantar pressure signals, stored in the memory and executable on the processor. When the real-time detection program for race walking double-foot take-off time based on plantar pressure signals is executed by the processor, it implements the steps of the real-time detection method for race walking double-foot take-off time based on plantar pressure signals as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a real-time detection program for the time of two feet leaving the ground in race walking based on plantar pressure signals. When the real-time detection program for the time of two feet leaving the ground in race walking based on plantar pressure signals is executed by a processor, it implements the steps of the real-time detection method for the time of two feet leaving the ground in race walking based on plantar pressure signals as described in any one of claims 1-5.

Images