CN111035393B - Three-dimensional gait data processing method, system, server and storage medium - Google Patents

Abstract

The application is suitable for the technical field of computers, and provides a three-dimensional gait data acquisition method, which comprises the following steps: after a gait information acquisition instruction is monitored, original three-dimensional gait data acquired by each somatosensory sensor in a preset somatosensory sensor array within preset time is synchronously acquired, the original three-dimensional gait data are sent to a data processing server, the original three-dimensional gait data are acquired by each somatosensory sensor in the preset somatosensory sensor array within preset time, and the gait data can be efficiently and accurately acquired.

Description

Three-dimensional gait data processing method, system, server and storage medium

technical field

The present application belongs to the field of computer technology, and in particular relates to a method, system, server and storage medium for processing three-dimensional gait data.

Background technique

Gait data refers to the motion data of various parts of the body when a human walks in a natural state, which is a complex human behavior feature. Since gait data provides an important basis for studying people's health status and living habits, how to obtain gait data efficiently and accurately becomes more and more important.

SUMMARY OF THE INVENTION

In view of this, the embodiments of the present application provide a three-dimensional gait data processing method, system, server, and storage medium, so as to obtain different data efficiently and accurately.

A first aspect of the embodiments of the present application provides a three-dimensional gait data processing method, which is applied to a collection server, and the three-dimensional gait data collection method includes:

After the gait information collection instruction is monitored, the original three-dimensional gait data of the monitored object is obtained synchronously, and the original three-dimensional gait data includes the said object collected by each somatosensory sensor in the preset somatosensory sensor array within a preset period of time. Monitor the 3D gait data of the subject;

The raw three-dimensional gait data is sent to a data processing server, and the data processing server processes the raw three-dimensional gait data to obtain three-dimensional gait data of the monitored object.

A second aspect of the embodiments of the present application provides a three-dimensional gait data processing method, which is applied to a data processing server, and the three-dimensional gait data processing method includes:

Acquiring raw three-dimensional gait data sent by the collection server, where the raw three-dimensional gait data includes three-dimensional gait data collected by each somatosensory sensor in a preset somatosensory sensor array within a preset period of time;

Based on the timestamp information of the original 3D gait data, overlapping 3D gait data is determined, where the original 3D gait data includes human skeleton joint point data; the overlapping 3D gait data includes any two of the somatosensory sensor arrays. Multi-frame overlapping human skeleton joint point data collected by two adjacent somatosensory sensors;

According to the spatial distance between the human skeleton joint point data of any two adjacent frames, the overlapping human skeleton joint point data of multiple frames are fused to obtain target three-dimensional gait data.

In an optional implementation manner, before determining the overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data, the method further includes:

Determine the abnormal bone joint point data in the human bone joint point data according to the preset reference distance between each bone joint point in the human bone structure;

performing data compensation and denoising processing on the abnormal bone joint point data to obtain corrected bone joint point data;

Correspondingly, determining the overlapping 3D gait data based on the timestamp information of the original 3D gait data includes:

Based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the modified skeleton joint point data is determined.

In an optional implementation manner, determining the abnormal skeleton joint point data in the human skeleton joint point data according to a preset reference distance between each skeleton joint point in the human skeleton structure includes:

According to the timestamp information of the original three-dimensional gait data, sort the human skeleton joint point data collected by each of the somatosensory sensors in the somatosensory sensor array, and obtain multi-frame human skeleton joint point data with time series respectively. ;

Calculate the distance between any two adjacent bone joint point data in each frame of human bone joint point data;

Abnormal bone joint point data in the human bone joint point data is determined according to the distance and a preset reference distance between each bone joint point in the human bone structure.

In an optional implementation manner, before the time stamp information based on the original three-dimensional gait data is determined, the multi-frame overlapping human skeleton joint point data in the modified bone joint point data is determined. ,include:

According to the inclination angle of each of the somatosensory sensors in the somatosensory sensor array, coordinate transformation is performed on each of the modified bone joint point data, to obtain standard bone joint point data in the same preset coordinate system;

Correspondingly, the determining, based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of the multiple frames in the skeletal joint point data includes:

Based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the standard skeleton joint point data is determined.

In an optional implementation manner, before performing coordinate transformation on each of the corrected bone joint point data according to the inclination angle of each of the somatosensory sensors in the somatosensory sensor array, the method further includes:

acquiring human skeleton joint point data in the original three-dimensional gait data;

Perform a least squares fitting process on the human skeleton joint point data to obtain the inclination angle of each of the somatosensory sensors.

A third aspect of the embodiments of the present application provides a three-dimensional gait data processing system, including: a collection server, a somatosensory sensor array communicatively connected to the collection server, and a data processing server communicatively connected to the collection server;

The somatosensory sensor array includes a plurality of somatosensory sensors arranged in a preset arrangement, and each of the somatosensory sensors is independent of each other;

The acquisition server is configured to synchronously acquire raw three-dimensional gait data after monitoring the gait information acquisition instruction, where the raw three-dimensional gait data includes data collected by each somatosensory sensor in the somatosensory sensor array within a preset time period. three-dimensional gait data, sending the original three-dimensional gait data to a data processing server;

a data processing server, configured to acquire the original three-dimensional gait data sent by the acquisition server, and determine overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data; the original three-dimensional gait data includes a human body Skeletal joint point data; the overlapping three-dimensional gait data includes multi-frame overlapping human skeleton joint point data collected by any two adjacent somatosensory sensors in the somatosensory sensor array;

According to the spatial distance between the human skeleton joint point data of any two adjacent frames, the overlapping human skeleton joint point data of multiple frames are fused to obtain target three-dimensional gait data.

A fourth aspect of the embodiments of the present application provides a three-dimensional gait data processing method, including:

After monitoring the gait information collection instruction, the acquisition server synchronously acquires raw three-dimensional gait data, where the raw three-dimensional gait data includes three-dimensional gait data collected by each somatosensory sensor in the somatosensory sensor array within a preset time period, sending the original three-dimensional gait data to a data processing server;

The data processing server acquires the original three-dimensional gait data sent by the acquisition server, and determines overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data; the original three-dimensional gait data includes human skeleton joint points data; the overlapping three-dimensional gait data includes multi-frame overlapping human skeleton joint point data collected by any two adjacent somatosensory sensors in the somatosensory sensor array;

According to the spatial distance between the human skeleton joint point data of any two adjacent frames, the overlapping human skeleton joint point data of multiple frames are fused to obtain target three-dimensional gait data.

A fifth aspect of the embodiments of the present application provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, which is implemented when the processor executes the computer program The steps of the three-dimensional gait data acquisition method described in the first aspect of the above embodiment, or the steps of implementing the three-dimensional gait data processing method described in the second aspect of the above embodiment when the processor executes the computer program.

A sixth aspect of an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, realizes the three-dimensional gait described in the first aspect of the above embodiment The steps of the data acquisition method, or the steps of implementing the three-dimensional gait data processing method described in the second aspect above when the processor executes the computer program. Compared with the prior art, the three-dimensional gait data acquisition method provided by the first aspect of the embodiments of the present application has the beneficial effect that, after monitoring the gait information acquisition instruction, synchronously acquires the gait information from the preset somatosensory sensor array. The raw three-dimensional gait data collected by the somatosensory sensor within a preset time period, and the raw three-dimensional gait data is sent to the data processing server, with the help of each somatosensory sensor in the preset somatosensory sensor array within the preset time period Collecting the original three-dimensional gait data can efficiently and accurately acquire the gait data.

Compared with the prior art, the beneficial effects of the second to sixth aspects of the embodiments of the present application are the same as those of the first aspect of the embodiments of the present application compared with the prior art, which will not be repeated here.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only for the present application. In some embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

1 is a system structure diagram of a three-dimensional gait data processing system provided by a first embodiment of the present application;

Fig. 2 is an array diagram of the somatosensory sensor array in Fig. 1;

Fig. 3 is the realization flow chart of the three-dimensional gait data acquisition method provided by the second embodiment of the present application;

Fig. 4 is the realization flow chart of the three-dimensional gait data processing method provided by the third embodiment of the present application;

Fig. 5 is the realization flow chart of the three-dimensional gait data processing method provided by the fourth embodiment of the present application;

Fig. 6 is the concrete realization flow chart of S502 in Fig. 5;

Fig. 7 is the realization flow chart of the three-dimensional gait data processing method provided by the fifth embodiment of the present application;

Fig. 8 is the realization flow chart of the three-dimensional gait data processing method provided by the sixth embodiment of the present application;

9 is a schematic structural diagram of a collection server provided by an embodiment of the present application;

10 is a schematic structural diagram of a data processing server provided by an embodiment of the present application;

FIG. 11 is a schematic diagram of a server provided by an embodiment of the present application.

Detailed ways

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It should be noted that the gait data refers to the motion state of each skeleton of the body when a human walks in a natural state, which is a complex behavioral feature. Since gait data is different from fingerprints, face, heart rate, EEG and other biometrics that can only be obtained by close contact, as a long-distance non-contact biometrics, it plays an important role in the study of human health and living habits.

At present, common gait data collection methods include a gait information collection method based on wearable sensor equipment and a gait information collection method based on color images; among them, the gait information collection method based on wearable sensor equipment is complex due to the complex wearing of the equipment. It is bulky and will have an impact on the gait of the object to be collected. On the other hand, because the acquisition equipment is expensive, it is not conducive to large-scale data collection. The gait information collection based on color images is limited by the influence of ambient light and other factors. Moreover, the color extraction method of color images has extremely poor ability to resist light and the interference of the same color system. In principle, it is difficult to distinguish the far and near areas of different objects isolate.

In view of the above problems, the present application proposes a three-dimensional gait data processing method, system, server and storage medium, aiming to obtain human body motion data under natural gait. state for acquisition and testing. A somatosensory sensor refers to a sensor that detects and perceives human body structures through 3D photography or measurement technology. 3D shooting or measurement technology is actually a relatively mature technology, with a variety of solutions, such as single-color camera, dual-color camera, optical interference, ultrasonic, structured light speckle and TOF (measurement of the time of flight of light) and so on. At present, the more mature somatosensory sensor is the Kinect product of MicroSoft. It has a powerful function of extracting joint points of human bones, and many academic researches in the field of gait use this device as a tool for collecting joint point motion information.

In order to illustrate the technical solutions described in the present application, the following specific embodiments are used for description. As shown in FIG. 1 , it is a system structure diagram of the three-dimensional gait data processing system provided by the first embodiment of the present application. As can be seen from FIG. 1 , the three-dimensional gait data processing system 10 provided by the embodiment of the present application includes: a collection server 101 , a somatosensory sensor array 102 communicatively connected to the collection server 101 , and a data processing server communicatively connected to the collection server 101 . 103; of which,

The somatosensory sensor array 102 includes a plurality of somatosensory sensors 1021 arranged in a preset arrangement, and each of the somatosensory sensors 1021 is independent of each other.

It should be noted that the arrangement of the somatosensory sensor array 102 is deployed by testers in advance according to experience and test needs, and there is no fixed requirement for the distance between each of the somatosensory sensors.

For example, in an optional implementation manner, as shown in FIG. 2 , it is an array diagram of the somatosensory sensor array in FIG. 1 . As can be seen from FIG. 2 , in this embodiment, the entire array 102 of somatosensory sensors includes a preset number (for example, 6) somatosensory sensors 1021 , and the distance between every two adjacent somatosensory sensors 1021 is 2.6 meters. And all the somatosensory sensors 1021 are deployed on ceiling suspension rods, and the distance between the ceiling suspension rods and the ground is greater than a preset human height distance, such as 2.65 meters.

It can be seen from the above analysis that this embodiment collects three-dimensional gait data for a human body within a preset range in a natural motion state through a somatosensory sensor array pre-deployed in the human activity space, which overcomes the limitation of the measurement range of a single sensor and realizes the Collect 3D gait data without disturbing the user.

In this embodiment, each of the somatosensory sensors is a Kinect sensor. It should be noted that each of the somatosensory sensors may also be other somatosensory sensors such as Intel RealSense, which are not specifically limited in the implementation of this application.

The acquisition server 101 is configured to synchronously acquire the original three-dimensional gait data of the monitored object after monitoring the gait information acquisition instruction, where the original three-dimensional gait data includes each somatosensory sensor in the somatosensory sensor array in the pre-predicted state. Set the three-dimensional gait data of the monitored object collected within the time period, and send the original three-dimensional gait data to the data processing server to instruct the data processing server to process the original three-dimensional gait data to obtain the monitored object. 3D gait data;

The data processing server 102 is configured to acquire the original three-dimensional gait data sent by the collection server, and determine overlapping three-dimensional gait data based on timestamp information of the original three-dimensional gait data; the original three-dimensional gait data includes: Human bone joint point data; the overlapping three-dimensional gait data includes multi-frame overlapping human bone joint point data collected by any two adjacent somatosensory sensors in the somatosensory sensor array;

According to the spatial distance between the human skeleton joint point data of any two adjacent frames, the overlapping human skeleton joint point data of multiple frames are fused to obtain target three-dimensional gait data.

It can be seen from the above analysis that in this embodiment of the present application, after monitoring the gait information collection instruction, the collection server synchronously acquires the three-dimensional gait data collected by each somatosensory sensor in the pre-deployed somatosensory sensor array within a preset period of time, and the said The raw three-dimensional gait data is sent to the data processing server, and the data processing server determines, based on the timestamp information of the raw three-dimensional gait data, the overlapping of multiple frames collected by any two adjacent somatosensory sensors in the somatosensory sensor array According to the spatial distance between the human skeleton joint point data of any two adjacent frames, the overlapping human skeleton joint point data of multiple frames are fused to obtain the target three-dimensional gait data. It can quickly and accurately obtain the three-dimensional gait data of the human body.

As shown in FIG. 3 , it is a flowchart of the realization of the three-dimensional gait data acquisition method provided by the second embodiment of the present application. The embodiments of the present application are implemented and implemented by hardware or software of a collection server. Details are as follows:

S301 , after monitoring the gait information collection instruction, synchronously acquire original three-dimensional gait data of the monitored object, where the original three-dimensional gait data includes all data collected by each somatosensory sensor in a preset somatosensory sensor array within a preset time period. The three-dimensional gait data of the monitored object.

It can be understood that the gait information collection instruction can be triggered by a staff member through an operation interface provided by the collection server, or can be triggered by other terminal devices or servers. For example, in an optional implementation manner, the gait information collection instruction is triggered by a control server, the control server sends a gait information collection instruction to the collection server, and the collection server monitors the different information After collecting the instruction, synchronously collect the three-dimensional gait data collected by each somatosensory sensor in the preset somatosensory sensor array within a preset time period. The gait information collection instruction includes the preset duration.

It should be noted that, in some application scenarios, usually each of the somatosensory sensors may collect a lot of the three-dimensional gait data within the preset time period, and it is impossible to obtain more data at the same time through one collection server. the three-dimensional gait data, therefore, the three-dimensional gait data can usually be acquired through multiple acquisition servers. For example, obtaining the three-dimensional gait data collected by a corresponding somatosensory sensor through a collection server can improve the efficiency of data acquisition and reduce the probability of failure of the collection server.

S302: Send the raw three-dimensional gait data to a data processing server to instruct the data processing server to process the raw three-dimensional gait data to obtain three-dimensional gait data of the monitored object.

It can be understood that the collection server and the somatosensory sensor array are usually arranged at the collection site, and the data processing server can be arranged at any place. After the collection server obtains the original three-dimensional gait data, it will The original three-dimensional gait data is sent to the data processing server for subsequent use.

It can be seen from the above analysis that the three-dimensional gait data acquisition method provided by the embodiment of the present application, after monitoring the gait information acquisition instruction, synchronously acquires the original data collected by each somatosensory sensor in the preset somatosensory sensor array within a preset period of time. three-dimensional gait data, and the raw three-dimensional gait data is sent to the data processing server. With the help of each somatosensory sensor in the preset somatosensory sensor array, the raw three-dimensional gait data is collected within a preset period of time, which can efficiently Accurately acquire gait data.

As shown in FIG. 4 , it is an implementation flowchart of the three-dimensional gait data processing method provided by the third embodiment of the present application. The embodiments of the present application are implemented by hardware or software of a data processing server. Details are as follows:

S401: Acquire raw three-dimensional gait data sent by a collection server, where the raw three-dimensional gait data includes three-dimensional gait data collected by each somatosensory sensor in a preset somatosensory sensor array within a preset time period.

It can be understood that the original three-dimensional gait data is the three-dimensional gait data collected by each of the somatosensory sensors within a preset period of time, and the three-dimensional gait data collected by each of the somatosensory sensors at different collection moments are different, And the three-dimensional gait data collected by each of the somatosensory sensors at the corresponding collection moment has time stamp information.

S402, based on the timestamp information of the original three-dimensional gait data, determine overlapping three-dimensional gait data, where the original three-dimensional gait data includes human skeleton joint point data; the overlapping three-dimensional gait data includes data in the somatosensory sensor array Multi-frame overlapping human skeleton joint point data collected by any two adjacent somatosensory sensors.

Specifically, based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the human skeleton joint point data collected by any two adjacent somatosensory sensors can be located.

S403 , according to the spatial distance between the human skeleton joint point data in any two adjacent frames, perform fusion processing on the human skeleton joint point data overlapping multiple frames to obtain target three-dimensional gait data.

Understandably, each frame of the human skeleton joint point data includes all the human skeleton joint point data, and calculate the difference between any two adjacent frames of the human skeleton joint point data in the multi-frame overlapping human skeleton joint point data. According to the spatial distance, the overlapping skeleton joint point data of multiple frames can be filtered, and the overlapping skeleton joint point data can be filtered out, so that the multi-frame human skeleton joint point data can be converted into multiple frames. In the process of fusion, the three-dimensional gait data of the target is obtained.

It can be seen from the above analysis that in this embodiment, multiple frames of overlapping human skeleton joint point data are determined based on the timestamp information of the original three-dimensional gait data, and according to the difference between any two adjacent frames of the human skeleton joint point data Spatial distance, the multi-frame overlapping of the human skeleton joint point data is fused to obtain the target three-dimensional gait data. Further, overlapping 3D gait data can be filtered out from the original 3D gait data, and the original 3D gait data can be fused into complete data collected within a preset time period, so that more complete and accurate 3D gait data can be obtained.

As shown in FIG. 5 , it is an implementation flowchart of the three-dimensional gait data processing method provided by the fourth embodiment of the present application. It can be seen from FIG. 5 that, compared with the embodiment shown in FIG. 4 , the specific implementation processes of S501 and S401 and S505 and S403 are the same in this embodiment, the difference is that S502 to S503 are included before S504, and S504 and S402 The specific implementation process is different. It should be noted that S501 and S502 are in a sequential execution relationship. Details are as follows:

S502: Determine abnormal bone joint point data in the human bone joint point data according to a preset reference distance between each bone joint point in the human bone structure.

It can be understood that the distance between each skeleton joint point in the human skeleton structure is usually within a certain preset range. In this embodiment, the reference distance between each skeleton joint point in the human skeleton structure is preset, and the reference distance is: The average value of the distance between the joint points of each skeleton of the human body obtained from a large number of experimental data.

In an optional implementation manner, the continuous multiple frames of the human skeleton joint point data may be selected, and the distance between each skeleton joint point data in the human skeleton joint point data of each frame may be calculated respectively, and the calculated The obtained distances are compared with the reference distances between the skeletal joint points in the preset human skeleton structure. When there are multiple consecutive frames corresponding to the human skeleton joint point data, there are the same skeleton joint point data and other If the absolute value of the difference between the distance between the bone joint point data and the reference distance between each bone joint point in the preset human skeleton structure is greater than the preset distance threshold, it means that the bone joint point data is abnormal Bone joint point data.

Specifically, as shown in FIG. 6 , it is a specific implementation flowchart of S502 in FIG. 5 . It can be seen from FIG. 6 that S502 includes S5021 to S5023. Details are as follows:

S5021, according to the timestamp information of the original three-dimensional gait data, sort the data of the human skeleton joint points collected by each of the somatosensory sensors in the somatosensory sensor array, and obtain a multi-frame human skeleton joint with time series respectively. point data.

Understandably, sorting based on timestamp information can improve the accuracy and efficiency of multi-frame human skeleton joint point data analysis.

S5022: Calculate the distance between any two adjacent bone joint point data in each frame of human bone joint point data, respectively.

It is understandable that the distance between the data of two adjacent bone joint points usually has the smallest change rate with the change of human motion, so the abnormal bone joint point data can be determined by calculating the distance between any two adjacent bone joint point data. .

S5023: Determine abnormal bone joint point data in the human bone joint point data according to the distance and a preset reference distance between each bone joint point in the human bone structure.

Specifically, when the absolute value of the difference between the distance between the skeletal joint point data and the data of two adjacent skeletal joint points and the reference distance is greater than the preset distance threshold, it is determined that The current bone joint point data is abnormal bone joint point data.

S503, performing data compensation and denoising processing on the abnormal bone joint point data to obtain corrected bone joint point data.

It should be noted that the abnormal bone joint point data is processed according to a preset denoising and compensation method. For example, the preset denoising and compensation method is a Gaussian filtering processing method, and the Gaussian filtering processing method is used. The abnormal bone joint point data is denoised, the abnormal bone joint point data is eliminated and the data is smoothed to obtain corrected bone joint point data.

S504 , based on the timestamp information of the original three-dimensional gait data, determine the overlapping human skeleton joint point data of multiple frames in the modified skeleton joint point data.

It can be seen from the above analysis that the modified skeletal joint point data obtained by denoising and compensating the abnormal data in the original three-dimensional gait data in this embodiment can effectively alleviate the collection caused by the somatosensory sensor itself. to the distortion data.

As shown in FIG. 7 , it is an implementation flowchart of the three-dimensional gait data processing method provided by the fifth embodiment of the present application. As can be seen from FIG. 7 , compared with the embodiment shown in FIG. 5 , the specific implementation processes of S701-S703 and S501-S503 and S706 and S505 are the same, the difference is that S704 and S705 and S504 are also included before S705 The specific implementation process is different. It should be noted that S703 and S704 are in a sequential execution relationship. Details are as follows:

S704, according to the inclination angle of each of the somatosensory sensors in the somatosensory sensor array, perform coordinate transformation on each of the modified skeleton joint point data respectively to obtain standard skeleton joint point data in the same preset coordinate system.

It can be understood that, due to unavoidable errors in the process of installing the somatosensory sensors and errors generated in the production process of the somatosensory sensors, each of the somatosensory sensors has a slight difference in the angle between the ground and the ground. In this embodiment, the angle between each of the somatosensory sensors and the ground is referred to as the inclination angle. And the original bone joint point data collected by each somatosensory sensor is based on its corresponding spatial coordinate system. Therefore, coordinate transformation is performed according to the tilt angle, and the modified bone joint point data is converted into the same preset. The standard skeletal joint point data in the coordinate system can provide a more accurate data basis for subsequent research.

S705 , based on the timestamp information of the original three-dimensional gait data, determine the overlapping human skeleton joint point data of multiple frames in the standard skeleton joint point data.

It can be seen from the above analysis that in this embodiment, the modified bone joint point data is coordinately transformed according to the inclination angle of each somatosensory sensor to obtain the standard bone joint point data in the same preset coordinate system, which can obtain more accurate bone joint point data. 3D gait data.

As shown in FIG. 8 , it is an implementation flowchart of the three-dimensional gait data processing method provided by the sixth embodiment of the present application. It can be seen from FIG. 8 that, compared with the embodiment shown in FIG. 7 , the specific implementation processes of S801-S803 and S701-S703 and S806-S808 and S704-S706 are the same, the difference is that S804 is also included before S806 ~S805. It should be noted that S804 and S803 are in a parallel execution relationship. Details are as follows:

S804: Acquire human skeleton joint point data in the original three-dimensional gait data.

S805 , performing least squares fitting processing on the human skeleton joint point data to obtain the inclination angle of each of the somatosensory sensors.

The present application proposes to use relatively stable skeleton joint point data in the human skeleton joint point data. For example, after a large amount of data analysis, it is found that the SpineBase joint point data is relatively stable during travel. Based on the z-axis data and y-axis data of the relatively stable joint point data, the least squares method is used to fit the straight line y=k*x+b, and the fitted straight line slope k is the corresponding relatively stable joint point data The tangent of the tilt angle.

It can be seen from the above analysis that in this embodiment, the least squares method is used to fit and process the data of the joint points of the human skeleton to obtain the inclination angle of each of the somatosensory sensors. Errors caused by installing each of the somatosensory sensors can be solved easily and quickly.

FIG. 9 is a schematic structural diagram of a collection server provided by an embodiment of the present application. It can be seen from FIG. 9 that the collection server 9 provided in this embodiment includes:

The acquisition module 901 is configured to synchronously acquire raw three-dimensional gait data after monitoring the gait information acquisition instruction, where the raw three-dimensional gait data includes the three-dimensional data collected by each somatosensory sensor in the somatosensory sensor array within a preset period of time. Gait data.

The sending module 902 is configured to send the original three-dimensional gait data to a data processing server.

As shown in FIG. 10 , it is a schematic structural diagram of a data processing server provided by an embodiment of the present application. As can be seen from FIG. 10 , the data processing server 10 provided by this embodiment of the present application includes:

The first determination module 1001 is configured to acquire the original three-dimensional gait data sent by the collection server, and determine overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data; the original three-dimensional gait data including human skeleton joint point data; the overlapping three-dimensional gait data includes multi-frame overlapping human skeleton joint point data collected by any two adjacent somatosensory sensors in the somatosensory sensor array;

The first obtaining module 1002 is configured to perform fusion processing on the overlapping human skeleton joint point data of multiple frames according to the spatial distance between the human skeleton joint point data in any two adjacent frames to obtain target three-dimensional gait data.

In an optional implementation manner, it also includes:

The second determining module is configured to determine the abnormal bone joint point data in the human bone joint point data according to the preset reference distance between each bone joint point in the human bone structure;

The second obtaining module is used for performing data compensation and denoising processing on the abnormal skeleton joint point data to obtain corrected skeleton joint point data;

Correspondingly, the first determining module is specifically used for:

Based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the modified skeleton joint point data is determined.

In an optional implementation, the second determining module includes:

a sorting unit, configured to sort the human skeleton joint point data collected by each of the somatosensory sensors in the somatosensory sensor array according to the timestamp information of the original three-dimensional gait data, and obtain multiple frames with time series respectively Human skeleton joint point data;

a calculation unit, used to calculate the distance between any two adjacent skeleton joint point data in each frame of human skeleton joint point data;

The determining unit is configured to determine abnormal bone joint point data in the human bone joint point data according to the distance and a preset reference distance between each bone joint point in the human bone structure.

In an optional implementation manner, it also includes:

a conversion module, configured to perform coordinate transformation on each of the modified bone joint point data according to the inclination angle of each of the somatosensory sensors in the somatosensory sensor array, to obtain standard bone joint point data in the same preset coordinate system;

Correspondingly, the first determining module is specifically used for:

Based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the standard skeleton joint point data is determined.

In an optional implementation manner, it also includes:

an acquisition module, used for acquiring the human skeleton joint point data in the original three-dimensional gait data;

The processing module is configured to perform least squares fitting processing on the human skeleton joint point data to obtain the inclination angle of each of the somatosensory sensors.

FIG. 11 is a schematic diagram of a server provided by an embodiment of the present application. As shown in FIG. 11 , the server 2 of this embodiment includes a processor 20 , a memory 21 , and a computer program 22 stored in the memory 21 and executable on the processor 20 , such as a program for remotely controlling a terminal. When the processor 20 executes the computer program 22, it implements the steps in the above-mentioned embodiments of the three-dimensional gait data acquisition method or the steps in the three-dimensional gait data processing method embodiments, such as steps 301 to 302 shown in FIG. 3 , or steps 301 to 302 shown in FIG. Steps 401 to 403 shown.

Exemplarily, the computer program 22 may be divided into one or more modules/units, which are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 22 in the server 2 . For example, the computer program 22 can be divided into a collection module and a transmission module (modules in a virtual device), and the specific functions of each module are as follows:

The acquisition module is used for synchronously acquiring raw three-dimensional gait data after monitoring the gait information acquisition instruction, where the raw three-dimensional gait data includes the three-dimensional steps collected by each somatosensory sensor in the somatosensory sensor array within a preset period of time state data;

The sending module is used for sending the original three-dimensional gait data to a data processing server.

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit, and the above-mentioned integrated units may adopt hardware. It can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working processes of the units and modules in the above-mentioned system, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other manners. For example, the apparatus/terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units. Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple communication units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated modules/units, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. . Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable media Electric carrier signals and telecommunication signals are not included.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the above-mentioned embodiments, those of ordinary skill in the art should understand that: it can still be used for the above-mentioned implementations. The technical solutions described in the examples are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the application, and should be included in the within the scope of protection of this application.

Claims (8)

1. a three-dimensional gait data processing method, is characterized in that, is applied to data processing server, and described three-dimensional gait data processing method comprises: Acquiring raw three-dimensional gait data sent by the collection server, where the raw three-dimensional gait data includes three-dimensional gait data collected by each somatosensory sensor in a preset somatosensory sensor array within a preset period of time; Based on the timestamp information of the original 3D gait data, overlapping 3D gait data is determined, where the original 3D gait data includes human skeleton joint point data; the overlapping 3D gait data includes any two of the somatosensory sensor arrays. Multiple frames of overlapping human skeleton joint point data collected by adjacent somatosensory sensors; According to the spatial distance between the human skeleton joint point data of any two adjacent frames, the overlapping human skeleton joint point data of multiple frames are fused to obtain the target three-dimensional gait data; Before determining the overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data, the method further includes: Determine the abnormal bone joint point data in the human bone joint point data according to the preset reference distance between each bone joint point in the human bone structure; performing data compensation and denoising processing on the abnormal bone joint point data to obtain corrected bone joint point data; Correspondingly, determining the overlapping 3D gait data based on the timestamp information of the original 3D gait data includes: Based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the modified skeleton joint point data is determined. 2 . The three-dimensional gait data processing method according to claim 1 , wherein, according to a preset reference distance between each skeleton joint point in the human skeleton structure, the 3D gait data processing method in the human skeleton joint point data is determined. 3 . Abnormal bone joint point data, including: According to the timestamp information of the original three-dimensional gait data, the human skeleton joint point data collected by each of the somatosensory sensors in the somatosensory sensor array is sorted and sorted to obtain multi-frame human skeleton joint point data with time series respectively. ; Calculate the distance between any two adjacent bone joint point data in each frame of human bone joint point data; Abnormal bone joint point data in the human bone joint point data is determined according to the distance and a preset reference distance between each bone joint point in the human bone structure. 3 . The three-dimensional gait data processing method according to claim 1 , wherein, in the time stamp information based on the original three-dimensional gait data, the multi-frames in the modified skeletal joint point data are determined. 4 . Before overlapping the human skeleton joint point data, include: According to the inclination angle of each of the somatosensory sensors in the somatosensory sensor array, coordinate transformation is performed on each of the modified bone joint point data, to obtain standard bone joint point data in the same preset coordinate system; Correspondingly, the determining, based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of the multiple frames in the skeletal joint point data includes: Based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the standard skeleton joint point data is determined. 4 . The three-dimensional gait data processing method according to claim 3 , wherein, according to the inclination angle of each of the somatosensory sensors in the somatosensory sensor array, each of the modified skeletal joint point data is separately processed. 5 . Before coordinate transformation, it also includes: acquiring human skeleton joint point data in the original three-dimensional gait data; Perform a least squares fitting process on the human skeleton joint point data to obtain the inclination angle of each of the somatosensory sensors. 5. A three-dimensional gait data processing system, comprising: a collection server, a somatosensory sensor array communicatively connected to the collection server, and a data processing server communicatively connected to the collection server; The somatosensory sensor array includes a plurality of somatosensory sensors arranged in a preset arrangement, and each of the somatosensory sensors is independent of each other; The acquisition server is configured to synchronously acquire raw three-dimensional gait data after monitoring the gait information acquisition instruction, where the raw three-dimensional gait data includes data collected by each somatosensory sensor in the somatosensory sensor array within a preset time period. three-dimensional gait data, sending the original three-dimensional gait data to a data processing server; a data processing server, configured to acquire the original three-dimensional gait data sent by the acquisition server, and determine overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data; the original three-dimensional gait data includes a human body Skeletal joint point data; the overlapping three-dimensional gait data includes multi-frame overlapping human skeleton joint point data collected by any two adjacent somatosensory sensors in the somatosensory sensor array; The data processing server is further configured to perform fusion processing on the overlapping human skeleton joint point data of multiple frames according to the spatial distance between the human skeleton joint point data in any two adjacent frames to obtain target three-dimensional gait data; Before determining the overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data, the method further includes: Determine the abnormal bone joint point data in the human bone joint point data according to the preset reference distance between each bone joint point in the human bone structure; performing data compensation and denoising processing on the abnormal bone joint point data to obtain corrected bone joint point data; Correspondingly, determining the overlapping 3D gait data based on the timestamp information of the original 3D gait data includes: Based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the modified skeleton joint point data is determined. 6. a three-dimensional gait data processing method, is characterized in that, comprises: After monitoring the gait information collection instruction, the acquisition server synchronously acquires the original three-dimensional gait data, where the original three-dimensional gait data includes the three-dimensional gait data collected by each somatosensory sensor in the somatosensory sensor array within a preset period of time, The original 3D gait data is sent to the data processing server; The data processing server acquires the original three-dimensional gait data sent by the acquisition server, and determines overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data; the original three-dimensional gait data includes human skeleton joint points data; the overlapping three-dimensional gait data includes multi-frame overlapping human skeleton joint point data collected by any two adjacent somatosensory sensors in the somatosensory sensor array; The data processing server performs fusion processing on the overlapping human skeleton joint point data of multiple frames according to the spatial distance between the human skeleton joint point data in any two adjacent frames to obtain target three-dimensional gait data; Before determining the overlapping three-dimensional gait data based on the timestamp information of the original three-dimensional gait data, the method further includes: Determine the abnormal bone joint point data in the human bone joint point data according to the preset reference distance between each bone joint point in the human bone structure; performing data compensation and denoising processing on the abnormal bone joint point data to obtain corrected bone joint point data; Correspondingly, determining the overlapping 3D gait data based on the timestamp information of the original 3D gait data includes: Based on the timestamp information of the original three-dimensional gait data, the overlapping human skeleton joint point data of multiple frames in the modified skeleton joint point data is determined. 7. A server, comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the computer program as claimed in claim 1 when the processor executes the computer program -4 any one of the steps of the three-dimensional gait data processing method. 8. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program is implemented by a processor when the computer program is executed as described in any one of claims 1-4. Describe the steps of the three-dimensional gait data processing method.

Images