Gait detection method, hardware and application thereof

Abstract

The invention relates to a gait detection method, hardware and application thereof, and the method comprises the steps: obtaining user basic information, and configuring a confidence data space based on basic parameters; matching sensing equipment for the user, and acquiring gait signals of the user in different motion modes by the corresponding sensing equipment; intercepting a credible gait signal based on the credible data space, and obtaining corresponding feature information; acquiring a gait detection result based on the feature information; implementing hardware by using the method; the method is applied to a VR scene, access of gait detection data is achieved through a sensing device, a gait detection result is output through a head-mounted display, and a user achieves online gait and / or action correction. According to the method, gait signals in different motion modes are obtained, credible data are intercepted in a credible data space, and after feature information is obtained based on the credible data, a gait detection result in the motion mode including but not limited to walking is obtained; on-line gait and / or action correction can be realized in combination with VR equipment and a dynamic gait detection result.

Description

Technical Field

[0001] The present invention relates to the technical field of calculation, extrapolation or counting, and in particular to a gait detection method, hardware and application thereof. Background Art

[0002] Gait refers to the posture and behavioral characteristics of the human body when walking, which involves behavioral habits, occupation, education, age and gender, and is also affected by a variety of diseases. As people pay more and more attention to health, are more willing to invest more time and energy in various sports, and science and technology are developing, more and more fitness enthusiasts, medical workers, etc. are investing in the field of gait research and analysis, hoping to reveal the key links and influencing factors of gait abnormalities through biomechanics and kinematics, so as to obtain better sports performance or obtain data representing physical fitness.

[0003] In the prior art, during gait detection, the subject is generally required to stand and be scanned, and walk in a normal posture on a three-dimensional dynamic walkway board for about 2 minutes, and then the gait detection data is output by a computer. This gait detection method has been proven to be effective in detecting deformation of the longitudinal axis of the body.

[0004] But in fact, the movement patterns of the human body during exercise are complex and diverse. In addition to understanding physical problems, more users hope to understand their own gait characteristics when performing different sports, and then improve the force position and step frequency in a targeted manner, correct wrong movements, and ultimately achieve the purpose of reducing sports injuries and shortening post-exercise recovery time. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a gait detection method, hardware and application thereof.

[0006] The technical solution adopted by the present invention is a gait detection method, which comprises the following steps: S1: Obtain user basic information and configure a trust data space based on the basic parameters; S2 matches the sensor device for the user, and the corresponding sensor device collects the user's gait signals in different motion modes; S3 intercepts the credible gait signal based on the confidence data space and obtains the corresponding feature information; S4 obtains gait detection results based on the feature information.

[0007] Preferably, in S1, the basic user information includes basic physiological data and extreme values ​​of body amplitude in different motion modes. In any motion mode, the space between the maximum value and the minimum value is the confidence data space.

[0008] Preferably, in S2, the sensing device includes a foot sensor and a hand sensor; the foot sensor is provided in conjunction with the foot wearable device, and the hand sensor is provided in conjunction with the hand wearable device.

[0009] Preferably, the gait signals collected corresponding to different motion modes include ups and downs data and pressure data at the foot sensor, and ups and downs data and acceleration data at the hand sensor.

[0010] Preferably, in S4, the gait signal in the confidence data space is obtained, and the undulation data at the foot sensor and the hand-worn device are matched. If the data exceeds the preset group and cannot be matched, the data is deleted and S2 is repeated. Otherwise, the wave points and valley points in each group of undulation data are extracted, and the connecting line fitting function between adjacent wave points and valley points corresponding to any motion mode is obtained to obtain the gait detection results corresponding to different motion modes of each user.

[0011] Preferably, in S4, the user's gait assistance preference information is obtained based on the corresponding pressure data of the foot sensor and the acceleration data of the hand sensor.

[0012] Preferably, a tracking device is provided in conjunction with the sensing device, and the tracking device tracks the user, obtains corresponding verification feature information, inputs the information into the long short-term memory network, and obtains the user's timing features in the collection of S2. If the features correspond to the features of the credible gait signal in S3, then S2 is credible data, otherwise it returns to S2.

[0013] An application of the gait detection method is applied in a VR scenario, where a sensor device is used to access gait detection data, and a head display is used to output gait detection results, so that users can achieve online gait and / or movement correction.

[0014] A computer-readable storage medium stores a gait detection program, which implements the gait detection method when executed by a processor.

[0015] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the gait detection method is implemented.

[0016] The present invention relates to a gait detection method, hardware and application thereof, which obtain basic information of a user, configure a confidence data space based on basic parameters; match a sensor device for the user, and the corresponding sensor device collects the gait signal of the user in different motion modes; intercept the credible gait signal based on the confidence data space to obtain the corresponding feature information; obtain the gait detection result based on the feature information; implement the hardware with the method; and apply it to a VR scene, implement the access of gait detection data with the sensor device, output the gait detection result with a head display, and implement online gait and / or motion correction for the user.

[0017] The beneficial effects of the present invention are that gait signals under different motion modes are acquired and trusted data are intercepted in a trusted data space. After acquiring feature information based on the trusted data, gait detection results under motion modes including but not limited to walking are obtained; online gait and / or motion correction can be achieved by combining VR equipment and dynamic gait detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0019] The present invention is further described in detail below in conjunction with embodiments, but the protection scope of the present invention is not limited thereto.

[0020] The present invention relates to a gait detection method, which comprises the following steps: (1) Obtaining basic user information and configuring a trusted data space based on the basic parameters; (2) matching a sensor device for the user, and the corresponding sensor device collects the user's gait signals in different motion modes; (3) intercepting credible gait signals based on the confidence data space and obtaining corresponding feature information; (4) Obtain gait detection results based on feature information.

[0021] The following is a detailed description of the steps.

[0022] (1) Obtaining basic user information and configuring a trusted data space based on the basic parameters; The user's basic information includes basic physiological data and extreme values ​​of body amplitude in different exercise modes. In any exercise mode, the space between the maximum and minimum values ​​is the confidence data space.

[0023] In the present invention, basic physiological data should at least include the user's height and basic dimensions, which define the reasonable position and displacement value of the user's head in different movement modes, and these verticals should match the sensor devices at other positions of the body; At the same time, it is necessary to limit the user's body amplitude extremes in different sports modes, such as the maximum and minimum opening amplitude of the two legs during running at different speeds, the maximum and minimum swinging amplitude of the two arms, the maximum and minimum height of the two feet off the ground, etc.

[0024] (2) matching a sensor device for the user, and the corresponding sensor device collects the user's gait signals in different motion modes; The sensing device includes a foot sensor and a hand sensor; the foot sensor is arranged in conjunction with the foot wearable device, and the hand sensor is arranged in conjunction with the hand wearable device.

[0025] The gait signals collected corresponding to different motion modes include the ups and downs data and pressure data at the foot sensor, and the ups and downs data and acceleration data at the hand sensor.

[0026] Different from the gait detection in the prior art, the present invention not only collects foot data, but also further collects hand data, aligns the data by acquiring the ups and downs data at the foot sensor and the ups and downs data at the hand sensor, and prompts different movement modes through the acceleration data of the hand sensor, and finally obtains the percentage of bipedal imbalance through the pressure data of the footstep sensor; Based on this, the foot sensor includes but is not limited to the integration of a height sensor and a pressure sensor, and the hand sensor includes but is not limited to the integration of a posture sensor and a height sensor.

[0027] (3) intercepting credible gait signals based on the confidence data space and obtaining corresponding feature information; In the present invention, the obviously unreliable data outside the trust data space is considered as noise and deleted, and the gait signal in the trust data space after the data is stabilized is taken as the reliable gait signal, and the corresponding feature information comes from the sensor data set of the foot sensor and the hand sensor collected after the ups and downs data at the foot sensor and the ups and downs data of the hand sensor are aligned (synchronized) as described above; In the specific implementation process, the characteristic information includes but is not limited to step frequency, stride, jumping ability, running posture (such as height off the ground), hand swinging coordination, left and right foot symmetry, etc.

[0028] (4) Obtaining gait detection results based on feature information; In S4, the gait signal in the confidence data space is obtained, and the undulation data at the foot sensor and the hand-worn device are matched. If the data exceeds the preset group and cannot be matched, the data is deleted and S2 is repeated. Otherwise, the wave points and valley points in each group of undulation data are extracted, and the connecting line fitting function between adjacent wave points and valley points corresponding to any motion mode is obtained to obtain the gait detection results corresponding to different motion modes of each user.

[0029] In S4, the user's gait assistance preference information is obtained based on the corresponding pressure data of the foot sensor and the acceleration data of the hand sensor.

[0030] In the present invention, in practical applications, considering that the undulation data is the most intuitive signal data of human body movement, the correspondence between the foot and hand sensor data is achieved. However, if the amount of corresponding data obtained based on the acquisition frequency is too small, the acquisition is considered invalid and needs to be re-acquired.

[0031] When the amount of data collected meets the analysis requirements, the peaks and valleys of the fluctuation data are intercepted. The corresponding motion mode means that the amplitude and width of the peaks and valleys are obviously different in different motion modes. We are more concerned about people's fluctuation state and judge the rationality of the process based on the state of the endpoints. For example, in a reasonable aerobic running process, if the amplitude of the fluctuation is large, it means that the user consumes too much energy in ineffective longitudinal work, and at this time the k value (slope) of the fitting function of the connecting line between adjacent wave points and valley points will be significantly greater than the recommended value, based on which the corresponding gait detection results are obtained.

[0032] In the present invention, user gait assistance preference information is used to expand richer gait detection results, including but not limited to hand swing coordination efficiency, left and right foot symmetry, etc. The former can guide the user's step frequency and breathing by adjustment, while the latter can guide the user to consciously adjust the landing position and strength of both feet.

[0033] Furthermore, in order to make the detection results more convincing and to better adjust the detection results for the setting of the adjustment parameters in the fitting function, a tracking device is set; here, when applied to a VR scenario, the existing cameras in the experience device can be used directly to track the user and obtain continuous image or signal data as verification feature information, and the long short-term memory network can be used to obtain the time series features collected by the user, and correspond them with the features of the credible gait signal to guide the output of the gait detection results.

[0034] The present invention also relates to an application of the gait detection method, which is applied in a VR scenario, wherein a sensor device is used to access gait detection data, and a head display is used to output gait detection results, so that users can achieve online gait and / or movement correction.

[0035] In the present invention, due to the application of VR equipment, the information obtained by the sensor device can be fed back to the VR headset in real time after detection. By reasonably adjusting the gait and / or movement, the detection feedback of the next detection cycle can be obtained, thereby realizing online gait and / or movement correction.

[0036] In the present invention, further, the current device can also be used to track sports performance, including but not limited to the calculation of sports consumption based on basic physiological data and detection values ​​in the confidence data space.

[0037] The present invention also relates to a computer-readable storage medium on which a gait detection program is stored, and when the program is executed by a processor, the gait detection method is implemented.

[0038] The present invention also relates to a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the gait detection method is implemented.

[0039] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0040] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0041] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0042] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0043] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0044] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A gait detection method, characterized in that: The method comprises the following steps: S1: Obtain user basic information and configure a trust data space based on the basic parameters; S2 matches the sensor device for the user, and the corresponding sensor device collects the user's gait signals in different motion modes; S3 intercepts the credible gait signal based on the confidence data space and obtains the corresponding feature information; S4 obtains gait detection results based on the feature information.

2. A gait detection method according to claim 1, characterized in that: In S1, the user's basic information includes basic physiological data and extreme values ​​of body amplitude in different exercise modes. In any exercise mode, the space between the maximum and minimum values ​​is the confidence data space.

3. A gait detection method according to claim 1, characterized in that: In S2, the sensing device includes a foot sensor and a hand sensor; the foot sensor is provided in conjunction with the foot wearable device, and the hand sensor is provided in conjunction with the hand wearable device.

4. A gait detection method according to claim 3, characterized in that: The gait signals collected corresponding to different motion modes include the ups and downs data and pressure data at the foot sensor, and the ups and downs data and acceleration data at the hand sensor.

5. A gait detection method according to claim 4, characterized in that: In S4, the gait signal in the confidence data space is obtained, and the undulation data at the foot sensor and the hand-worn device are matched. If the data exceeds the preset group and cannot be matched, the data is deleted and S2 is repeated. Otherwise, the wave points and valley points in each group of undulation data are extracted, and the connecting line fitting function between adjacent wave points and valley points corresponding to any motion mode is obtained to obtain the gait detection results corresponding to different motion modes of each user.

6. A gait detection method according to claim 4, characterized in that: In S4, the user's gait assistance preference information is obtained based on the corresponding pressure data of the foot sensor and the acceleration data of the hand sensor.

7. A gait detection method according to claim 1, characterized in that: A tracking device is provided in conjunction with the sensing device. The tracking device tracks the user, obtains corresponding verification feature information, inputs the information into the long short-term memory network, and obtains the user's time series features in the collection of S2. If the features correspond to the features of the credible gait signal in S3, the data in S2 is credible, otherwise it returns to S2.

8. An application of the gait detection method according to any one of claims 1 to 7, characterized in that: Applied in VR scenarios, gait detection data is accessed through sensor devices, gait detection results are output through head displays, and users can achieve online gait and / or movement correction.

9. A computer-readable storage medium, characterized in that: A gait detection program is stored thereon, and when the program is executed by a processor, the gait detection method described in any one of claims 1 to 7 is implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the gait detection method described in any one of claims 1 to 7 is implemented.

Images