CN116881666B - Motion data acquisition and processing method, system and storage medium - Google Patents
Motion data acquisition and processing method, system and storage medium Download PDFInfo
- Publication number
- CN116881666B CN116881666B CN202310988507.1A CN202310988507A CN116881666B CN 116881666 B CN116881666 B CN 116881666B CN 202310988507 A CN202310988507 A CN 202310988507A CN 116881666 B CN116881666 B CN 116881666B
- Authority
- CN
- China
- Prior art keywords
- data
- sporter
- data acquisition
- actual
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000033001 locomotion Effects 0.000 title claims abstract description 74
- 238000003672 processing method Methods 0.000 title claims description 14
- 238000012545 processing Methods 0.000 claims abstract description 52
- 238000012360 testing method Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000012937 correction Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000037147 athletic performance Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- RTZKZFJDLAIYFH-UHFFFAOYSA-N ether Substances CCOCC RTZKZFJDLAIYFH-UHFFFAOYSA-N 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012911 target assessment Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method, a system and a storage medium for acquiring and processing motion data, wherein the method for acquiring and processing the motion data comprises the following steps: s1: randomly extracting n test sporters, wherein each test sporter respectively performs p kinds of sports in a target scene, and the target scene is provided with m different places; s2: acquiring sample information corresponding to a c-th motion type of each test sporter from an i-th place to a j-th place, wherein the sample information comprises test sporter identity information and time information, and the time information obeys the regular distribution; s3: for the obtained total p m 2 Parameter estimation is carried out on the sample information; s4: acquiring time data of the actual sporter moving in the target scene; s5: and carrying out data deduction and classification according to the time data to obtain the actual movement type of the actual sporter. The invention can automatically distinguish the sports projects participated by the actual sporter.
Description
Technical Field
The present invention relates to the field of data acquisition and processing technologies, and in particular, to a method, a system, and a storage medium for acquiring and processing motion data.
Background
Under the background that China continuously promotes the deep development of 'sports strong nations', the physical health condition of each special group (such as students, practitioners in special industries and the like) is more and more emphasized. For example, to promote students to strengthen physical exercises and improve physical fitness level, some schools, especially colleges, have scheduled extracurricular running tasks and counted extracurricular running into athletic performances for students, and certain universities require the universities to complete running mileage 400 km (walking, running, riding to make a deduction of running mileage according to 2:1, 1:1, 5:1, respectively) for four years. Meanwhile, as the living standard is improved and the health Chinese concept is gradually deepened into the mind, the general masses pay more and more attention to the self health level and actively participate in physical exercise, wherein aerobic exercise is an important constituent item.
The aerobic exercise project data mainly comprises information such as exercise project type, exercise time, exercise mileage and the like, and the existing three main exercise data acquisition and processing methods and the technical problems thereof are as follows:
firstly, a card swiping mode is adopted, specifically, a card swiping device is installed at different places of a sporter in different scenes such as a campus, a park, a training field and the like in a way, the sporter carries a card with a built-in chip to each point for swiping the card when moving, and the card reading device reads information of the sporter and uploads the information to a system to generate movement data by the system. The problems with this solution are: (1) the method can not distinguish which exercise items actually participated by the sporter particularly belong to walking, running, riding and the like, and has lower data accuracy and data value; (2) for sportsmen, the sportsmen need to carry cards and the like, and the inconvenience of use is easily caused by card loss and card management; (3) under the use scene with the moving object examination, the cheating behavior that the sporter carries the card of other people to replace the movement of other people cannot be prevented; (4) under the condition of unstable network, the response of uploading data by a sporter to swipe the card is slower, and the situation of queuing to swipe the card is easy to cause.
Secondly, a mode of recording data by using a mobile phone APP is adopted, the specific method is that a sporter carries a smart phone when moving and opens a specific APP, and the APP automatically records the type of movement and the movement data and uploads the movement data to a system. The problems with this solution are: (1) for sportsmen, smart phones must be carried in the running process, and groups without smart phones, such as children, old people and the like, cannot use the smart phones; (2) the mobile phone positioning has the problems of data errors, invalid data and the like caused by inaccuracy; (3) under the use scene with the moving object examination, the cheating actions such as the movement of a sporter instead of others, the cracking of APP software and the like cannot be prevented.
Thirdly, the wearing equipment such as a sport bracelet is adopted for recording data, and the implementation and the defects of the mode are similar to those of the second mode.
Disclosure of Invention
In view of the foregoing, the present invention is directed to a method, system, and storage medium for motion data acquisition and processing.
The technical scheme of the invention is as follows:
in one aspect, a method for acquiring and processing motion data is provided, including the following steps:
s1: randomly extracting n test sporters, wherein each test sporter respectively performs p motion types under a target scene, the target scene is provided with m different places, and m is an integer greater than or equal to 2;
s2: sample information corresponding to the c-th exercise type from the i-th place to the j-th place of each test exercise person is obtained and recorded as S c(ij) The sample information comprises test sporter identity information and time information, and the time information obeys the regular distribution;
s3: for the obtained totalParameter estimation is carried out on the sample information to obtain +.>Group estimation parameter->
S4: acquiring time data of the actual sporter moving in the target scene;
s5: and carrying out data deduction and classification according to the time data to obtain the actual movement type of the actual sporter.
Preferably, in step S3, parameter estimation is performed by the following formula:
wherein:is a mathematical expectation; t is t k(ij) The time taken for the kth athlete from the ith location to the jth location;is the variance.
Preferably, when the number p of the sports types is greater than 1, a step of performing a difference check on the sample information of each location is further included between the step S3 and the step S4.
Preferably, the difference test is performed:
the confidence is recorded as alpha, and the time t from the ith place to the jth place of any sporter is assumed to belong to the distribution of the type c sports;
calculating a time parameter interval C corresponding to the reject domain of the hypothesis c (t) time parameter confidence interval C 'when assumption is made' c (t)；
The conditions for the differential test are: for any integer c.epsilon.1, p],q∈[1,p]C is not equal to q and satisfies C' c(ij) ∈C q(ij) 。
Preferably, when the condition for the difference test is not satisfied, the dot pitch of each different site is adjusted or the movement type is adjusted.
Preferably, in step S5, when data estimation and classification are performed:
calculating the time t and p motion types of the actual sporter between every two different placesSubject to parameters ofIn the case of the normal distribution of (2), the sample points fall within the interval +.>Probability P of (2) 1 、P 2 、P 3 、…、P p ；
Taking the minimum value in all probabilities as P min Compare it to confidence α:
if P min >Alpha, marking the corresponding data as invalid data;
if P min And if the value is less than or equal to alpha, recording the corresponding exercise type as the actual exercise type of the actual exerciser between two different places.
Preferably, the method further comprises the step of updating a sample information database by using the obtained actual sporter movement data as sample information, and returning to the step S3 to perform parameter estimation again.
On the other hand, the system also provides a sports data acquisition and processing system, which comprises a data acquisition and processing terminal, wherein the data acquisition and processing terminal is arranged at m different places of a sports person's way in sports, and m is an integer greater than or equal to 2;
the data acquisition processing terminal is used for identifying the identity of the sporter, acquiring and storing the motion data of different places of the sporter in the motion process, and processing and obtaining the actual motion type of the actual sporter according to the motion data;
the data acquisition processing terminal is provided with m storage areas, and each storage area is provided with p (m-1) sub-storage areas; when the data acquisition processing terminal stores the motion data of each different place of the path when the sporter moves, each sub-storage area is used for storing the motion data of the sporter which reaches the current place from the rest m-1 places in p kinds of motions;
when the data acquisition and processing terminal obtains the actual motion type of the actual sporter according to the motion data processing, the data acquisition and processing method is adopted for processing.
Preferably, the data acquisition processing terminal is further configured to determine whether the sample point data is failure delay upload data, and perform sample reconstruction and data correction on the failure delay upload data, where the condition for determining whether the sample point data is failure delay upload data is that: for the same athlete, there is sample data in any sample of the rest of the sites that is later than the current sample point sampling time.
In another aspect, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the method for motion data acquisition processing of any one of the above.
The beneficial effects of the invention are as follows:
according to the invention, the initial sample and the observed value are established by testing the sporter, and then the data inference classification is carried out on the actual sporter, so that the actual movement type of the actual sporter can be more accurately identified.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a schematic diagram of sub-storage areas and corresponding sample data for an ith location according to an embodiment;
FIG. 2 is a schematic diagram illustrating sample reconstruction and data correction memory operations according to one embodiment.
Detailed Description
The invention will be further described with reference to the drawings and examples. It should be noted that, without conflict, the embodiments and technical features of the embodiments in the present application may be combined with each other. It is noted that all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless otherwise indicated. The use of the terms "comprising" or "includes" and the like in this disclosure is intended to cover a member or article listed after that term and equivalents thereof without precluding other members or articles.
In one aspect, the invention provides a method, a system and a storage medium for acquiring and processing motion data, comprising the following steps:
s1: randomly extracting n test sporters, wherein each test sporter respectively performs p motion types under a target scene, the target scene is provided with m different places, and m is an integer greater than or equal to 2.
In a specific embodiment, the number n of the test exercisers is greater than or equal to 30, and the more the number of the test exercisers is, the more initial samples and observed values are established, the more accurate the normal distribution estimation parameters are obtained later, so that the accuracy of the inference and classification of the subsequent data can be improved.
S2: sample information corresponding to the c-th exercise type from the i-th place to the j-th place of each test exercise person is obtained and recorded as S c(ij) The sample information includes test athlete identity information and time information, the time information subject to a positive-going distribution.
S3: for the obtained totalParameter estimation is carried out on the sample information to obtain +.>Group estimation parameter->
In a specific embodiment, the parameter estimation is performed by:
wherein:is a mathematical expectation; t is t k(ij) The time taken for the kth athlete from the ith location to the jth location;is the variance.
In order to improve the accuracy of the subsequent data deduction and classification, optionally, when the number p of the types of motion is greater than 1, the method further comprises the step of performing a difference test on the sample information of each place, and when the difference test is performed:
the confidence is recorded as alpha, and the time t from the ith place to the jth place of any sporter is assumed to belong to the distribution of the type c sports;
calculating a time parameter interval C corresponding to the reject domain of the hypothesis c (t) time parameter confidence interval C 'when assumption is made' c (t)；
The conditions for the differential test are: for any integer c.epsilon.1, p],q∈[1,p]C is not equal to q and satisfies C' c(ij) ∈C q(ij) 。
And when the condition of the difference test is not met, adjusting the point position distance or the movement type of each different point.
S4: and acquiring time data of the actual sporter moving in the target scene.
S5: and carrying out data deduction and classification according to the time data to obtain the actual movement type of the actual sporter.
In a specific embodiment, the data is extrapolated and categorized:
calculating compliance parameters of the actual sporter in t and p exercise types at each time between two different placesIn the case of the normal distribution of (2), the sample points fall within the interval +.>Probability P of (2) 1 、P 2 、P 3 、…、P p ；
Taking the minimum value in all probabilities as P min Compare it to confidence α:
if P min >Alpha, marking the corresponding data as invalid data;
if P min And if the value is less than or equal to alpha, recording the corresponding exercise type as the actual exercise type of the actual exerciser between two different places.
In a specific embodiment, the exercise data collecting and processing method further includes a step of taking the obtained exercise data of the actual exercise person as sample information, updating a sample information database, and returning to the step S3 to perform parameter estimation again.
On the other hand, the invention also provides a sports data acquisition and processing system, which comprises a data acquisition and processing terminal, wherein the data acquisition and processing terminal is arranged at m different places of a sports path of a sporter, and m is an integer greater than or equal to 2;
the data acquisition processing terminal is used for identifying the identity of the sporter, acquiring and storing the motion data of different places of the sporter in the motion process, and processing and obtaining the actual motion type of the actual sporter according to the motion data;
the data acquisition processing terminal is provided with m storage areas, and each storage area is provided with p (m-1) sub-storage areas; when the data acquisition processing terminal stores the motion data of each different place of the path when the sporter moves, each sub-storage area is used for storing the motion data of the sporter which reaches the current place from the rest m-1 places in p kinds of motions;
when the data acquisition and processing terminal obtains the actual motion type of the actual sporter according to the motion data processing, the data acquisition and processing method is adopted for processing.
In a specific embodiment, the data acquisition processing terminal is further configured to determine whether the sample point data is failure delay upload data, perform sample reconstruction and data correction on the failure delay upload data, and determine whether one sample point data is failure delay upload data if: for the same athlete, there is sample data in any sample of the rest of the sites that is later than the current sample point sampling time.
In another aspect, the present invention also provides a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the method for motion data acquisition and processing of any one of the above.
In a specific embodiment, the motion data acquisition and processing method and the motion data acquisition and processing system of the invention are adopted for motion recognition, and specifically comprise the following steps:
(1) The data acquisition and processing terminals are arranged at m different places of the path of the sportsman during exercise, and a plurality of terminals can be arranged at the same place, wherein m is more than or equal to 2, the sportsman participates in exercise such as walking, running, riding and the like, and the number of exercise types is more than or equal to 1.
(2) And responding to the time synchronization request of the terminal, allocating storage areas for each place, wherein the total number of the storage areas is m, dividing each storage area into p (m-1) sub-storage areas, and storing exercise data of the players which are involved in p exercises and reach the current place from the rest m-1 places.
(3) An initial sample is taken. And randomly extracting n test exercisers under the use scene, and respectively performing p types of exercises, wherein n is more than or equal to 30, and recording the time consumed by n exercisers in p exercises from the rest m-1 places to the current place as sample points, wherein the time obeys the special but unknown-parameter n-ether distribution.
(4) The data acquisition processing terminal captures the test sportsman, performs face recognition and identity recognition, reports sportsman information and terminal information, and achieves the accuracy of the terminalInter-data, record the sample corresponding to the c-th movement type from the i-th place to the j-th place as S c(ij) Sample data is stored in the sub-storage area. Each sub-storage area of the ith place and corresponding sample data are shown in FIG. 1.
(5) For sum upThe samples of the individual memory areas are subjected to parameter estimation by the formula (1) -formula (2) to obtain +.>Group estimation parameter->
(6) When p is>And 1, carrying out difference test on the initial sample parameters of each place to confirm that the p groups of groups have obvious difference between any two groups of groups so as to improve the accuracy of data classification. Specifically, the method comprises the following steps: the confidence is recorded as alpha, and the time t from the ith place to the jth place of any sporter is assumed to belong to the distribution of the type c sports; calculating a time parameter interval C corresponding to the reject domain of the hypothesis c (t) time parameter confidence interval C 'when assumption is made' c (t); the conditions for the differential test are: for any integer c.epsilon.1, p],q∈[1,p]C is not equal to q and satisfies C' c(ij) ∈C q(ij) 。
(7) For the case that the difference checking condition is not satisfied, the point position distance needs to be set reasonably or the movement type needs to be adjusted.
(8) The data acquisition processing terminal acquires and reports the actual sporter data.
(9) And responding to the reported data and carrying out data inference classification. Specific: calculating compliance parameters of actual sporter in t and p sports types at time between every two different placesIn the case of the normal too distribution of (2), the sample points fall within the interval Probability P of (2) 1 、P 2 、P 3 、…、P p And take the minimum value P min If P min >Alpha, marking the corresponding data as invalid data; if P min And if the value is less than or equal to alpha, recording the corresponding exercise type as the actual exercise type of the actual exerciser between two different places.
(10) And calculating detailed exercise record data according to the exercise type, exercise duration, exercise mileage, height weight of an exercise person and the like, writing the exercise record data into a disk, storing an exercise record data address in sample point data, and referencing the same exercise record by samples of all places of the same exercise path of the exercise person.
(11) And counting the collected sample points of the common sporter into the sub-storage area of the deduced exercise type of the place, and carrying out parameter estimation again on the sample of the current sub-storage area.
(12) Sample reconstruction and data correction based on time addressing under terminal network failure. When a network failure of a certain terminal occurs, the data cannot be uploaded on time, so that a sporter who passes through the terminal passes through other places again, and a sample of a storage area corresponding to a first place which passes through again is polluted. After the normal data of the fault terminal is recovered and re-uploaded, the storage area needs to be subjected to time addressing and sample reconstruction, and relevant data record correction is carried out, and the condition for judging whether one sample point data is the fault delayed uploading data is as follows: for the same athlete, there is sample data in any sample of the rest of the sites that is later than the current sample point sampling time.
The specific method for reconstructing the sample and correcting the data is as follows: assuming m=5, the number of 5 places is recorded as 1-5, one or more sporters perform a motion with unknown motion type of which the route is '1-3-2-3-4-5', if the 3 rd point network fails to upload the 3 rd point data in time, the samples generating the error sample points have S c(12) 、S c(24) Sample with missing sample pointsWith S c(13) 、S c(23) And c is the motion type after the deduction and classification of the corresponding road section data.
Since the sequence of the sample points counted into the sample does not affect the properties of the sample, S of the sample point deletion c(13) 、S c(23) Only the data which is delayed to upload is processed according to the steps (9) - (11); for samples that produce erroneous sample points, there is S c(12) 、S c(24) The processing mode is that the error sample point is taken out for correction and then is processed according to the steps (9) - (11), and the parameter estimation is carried out again on the sample after the error sample point is deleted, so as to obtain S c(12) The specific steps are as follows:
first, from sample S c(12) The sample point record with the error removed is moved to the correct sample S c(32) And processing according to steps (9) - (11);
then, recording the index of the error sample point position (namely the position of the error start) which is processed first in the error sample points, forming a reconstructed sample by using all sample points from the initial position of the sample to the current position, and carrying out parameter estimation again;
finally, the remaining sample points from the index position to the last sample position are processed according to steps (9) - (11) to correct the error data. A schematic of the sample reconstruction and data correction memory operations is shown in fig. 2.
In the above embodiments, the method and system of the present invention, in combination, enable motion recognition with the following advantages:
1. by utilizing the data acquisition and processing terminal, the face identification can be carried out, the sporter is easier and more convenient, and equipment such as a card, a mobile phone, a bracelet and the like is not required to be carried.
2. The cheating behavior can be avoided under the condition of target assessment: the terminal can limit that only the true person of the person can be successfully identified when brushing the face through the living body detection function, and the cheating action of substituting the movement of the other person is avoided; the face recognition terminal software is private and safe, does not need to be published and released externally like an APP, and avoids the risks that the system is cracked and interface attack cheating is carried out.
3. Sample point data are stored in the classified sub-storage areas, so that performance consumption caused by clustering operation frequently performed under the condition of uniformly storing a large sample amount is reduced.
4. For various exercise types participated by the sporter, automatic deducing and classifying can be carried out on exercise segments, the high accuracy of deducing and classifying is ensured through the verification of the difference verification conditions, the acquired exercise data is more accurate and refined, and the value of the exercise data is improved.
5. After the terminal has network fault, the fault tolerance performance of the acquisition terminal to the network fault is improved through sample reconstruction and data record correction in the sub-storage area.
In summary, the invention can automatically distinguish the sports items actually participated by the sporter, and by setting the data acquisition processing terminal, specific peripheral equipment (such as a card, a mobile phone, a bracelet and the like) is not needed, thereby preventing cheating and improving fault tolerance performance and the like. Compared with the prior art, the invention has obvious progress.
The present invention is not limited to the above-mentioned embodiments, but is intended to be limited to the following embodiments, and any modifications, equivalents and modifications can be made to the above-mentioned embodiments without departing from the scope of the invention.
Claims (9)
1. The motion data acquisition and processing method is characterized by comprising the following steps of:
s1: randomly extracting n test sporters, wherein each test sporter respectively performs p motion types under a target scene, the target scene is provided with m different places, and m is an integer greater than or equal to 2;
s2: acquiring the c-th exercise type corresponding to each test exercise person from the i-th place to the j-th placeSample information and record it as S c(ij) The sample information comprises test sporter identity information and time information, and the time information obeys the regular distribution;
s3: for the obtained totalParameter estimation is carried out on the sample information to obtain +.>Group estimation parameter->
S4: acquiring time data of the actual sporter moving in the target scene;
s5: carrying out data deduction and classification according to the time data to obtain the actual motion type of the actual sporter; when data is inferred and classified:
calculating compliance parameters of the actual sporter in t and p exercise types at each time between two different placesIn the case of the normal distribution of (2), the sample points fall within the interval +.>Probability P of (2) 1 、P 2 、P 3 、…、P p ；
Taking the minimum value in all probabilities as P min Compare it to confidence α:
if P min >Alpha, marking the corresponding data as invalid data;
if P min And if the value is less than or equal to alpha, recording the corresponding exercise type as the actual exercise type of the actual exerciser between two different places.
2. The motion data acquisition and processing method according to claim 1, wherein in step S3, parameter estimation is performed by:
wherein:is a mathematical expectation; t is t k(ij) The time taken for the kth athlete from the ith location to the jth location; />Is the variance.
3. The exercise data acquisition and processing method according to claim 1, further comprising a step of performing a difference check on sample information of each place between step S3 and step S4 when the number p of exercise types is greater than 1.
4. A method of motion data acquisition and processing according to claim 3, wherein the difference test is performed by:
the confidence is recorded as alpha, and the time t from the ith place to the jth place of any sporter is assumed to belong to the distribution of the type c sports;
calculating a time parameter interval C corresponding to the reject domain of the hypothesis c (t) time parameter confidence interval C 'when assumption is made' c (t)；
The conditions for the differential test are: for any integer c.epsilon.1, p],q∈[1,p]C is not equal to q and satisfies C' c(ij) ∈C q(ij) 。
5. The method according to claim 4, wherein when the condition for the difference test is not satisfied, the dot pitch or the type of movement of each of the different sites is adjusted.
6. The exercise data acquisition and processing method according to claim 1, further comprising the step of re-performing parameter estimation by using the obtained actual exercise data as sample information, updating a sample information database, and returning to step S3.
7. The exercise data acquisition and processing system is characterized by comprising a data acquisition and processing terminal, wherein the data acquisition and processing terminal is arranged at m different places of an exercise path of an exercise person, and m is an integer greater than or equal to 2;
the data acquisition processing terminal is used for identifying the identity of the sporter, acquiring and storing the motion data of different places of the sporter in the motion process, and processing and obtaining the actual motion type of the actual sporter according to the motion data;
the data acquisition processing terminal is provided with m storage areas, and each storage area is provided with p (m-1) sub-storage areas; when the data acquisition processing terminal stores the motion data of each different place of the path when the sporter moves, each sub-storage area is used for storing the motion data of the sporter which reaches the current place from the rest m-1 places in p kinds of motions;
when the data acquisition and processing terminal obtains the actual motion type of the actual sporter according to the motion data processing, the data acquisition and processing method is adopted for processing according to any one of the motion data acquisition and processing methods in claims 1-6.
8. The motion data acquisition and processing system according to claim 7, wherein the data acquisition and processing terminal is further configured to determine whether the sample point data is failure delay upload data, and perform sample reconstruction and data correction on the failure delay upload data, and determine whether one sample point data is failure delay upload data is provided by: for the same athlete, there is sample data in any sample of the rest of the sites that is later than the current sample point sampling time.
9. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the steps of the motion data acquisition processing method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310988507.1A CN116881666B (en) | 2023-08-08 | 2023-08-08 | Motion data acquisition and processing method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310988507.1A CN116881666B (en) | 2023-08-08 | 2023-08-08 | Motion data acquisition and processing method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116881666A CN116881666A (en) | 2023-10-13 |
| CN116881666B true CN116881666B (en) | 2024-02-13 |
Family
ID=88254995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310988507.1A Active CN116881666B (en) | 2023-08-08 | 2023-08-08 | Motion data acquisition and processing method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116881666B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021217913A1 (en) * | 2020-04-30 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Motion recognition feedback method and apparatus, and computer device and storage medium |
| CN116192917A (en) * | 2023-02-28 | 2023-05-30 | 王娜 | Comprehensive observation and forecast platform for ocean pasture |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230205951A1 (en) * | 2021-12-23 | 2023-06-29 | Baidu Usa Llc | Simulation obstacle vehicles with driving styles |
-
2023
- 2023-08-08 CN CN202310988507.1A patent/CN116881666B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021217913A1 (en) * | 2020-04-30 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Motion recognition feedback method and apparatus, and computer device and storage medium |
| CN116192917A (en) * | 2023-02-28 | 2023-05-30 | 王娜 | Comprehensive observation and forecast platform for ocean pasture |
Non-Patent Citations (2)
| Title |
|---|
| Yo-Ping Huang ; Hung-Jin Chen.Using the transformed data to construct an extension-based fuzzy inference model.Ninth IEEE International Conference on Fuzzy Systems. FUZZ- IEEE 2000.2002,全文. * |
| 基于图像序列的运动目标分类研究;庞首颜;中国优秀硕士学位论文全文数据库信息科技辑;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116881666A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898642B (en) | Key point detection method and device, electronic equipment and storage medium | |
| CN106653001A (en) | Baby crying identifying method and system | |
| CN113440789B (en) | Intelligent counting method and system for multi-person rope skipping test | |
| CN110110726A (en) | The recognition methods of power equipment nameplate, device, computer equipment and storage medium | |
| L'Heureux et al. | A gamification framework for sensor data analytics | |
| CN111860101A (en) | Training method and device for face key point detection model | |
| CN113010557A (en) | Method and system for randomly answering questions by using psychological evaluation system scale | |
| CN115331314A (en) | Exercise effect evaluation method and system based on APP screening function | |
| CN111382627B (en) | Method for judging peer and related products | |
| CN116881666B (en) | Motion data acquisition and processing method, system and storage medium | |
| CN110007764A (en) | A kind of gesture skeleton recognition methods, device, system and storage medium | |
| AU2021240278A1 (en) | Face identification methods and apparatuses | |
| CN111325255B (en) | Specific crowd delineating method and device, electronic equipment and storage medium | |
| JP7164456B2 (en) | Discrimination device, information provision system, discrimination method, and information provision method | |
| CN105469116A (en) | Picture recognition and data extension method for infants based on man-machine interaction | |
| CN113537407B (en) | Image data evaluation processing method and device based on machine learning | |
| CN111090742B (en) | Question-answer pair evaluation method, question-answer pair evaluation device, storage medium and equipment | |
| CN114491156A (en) | Method for intelligently pushing approximate object based on video image | |
| CN110889313B (en) | Student state acquisition method and device and computer readable storage medium | |
| CN115116087A (en) | Action assessment method, system, storage medium and electronic equipment | |
| CN110660479A (en) | AI training and diagnosis system for dynamic medical image | |
| CN112132239A (en) | Training method, device, equipment and storage medium | |
| CN112185548B (en) | Intelligent traditional Chinese medicine diagnosis method and device based on neural network algorithm | |
| CN109978861A (en) | Marrow grey matter detection method, device, equipment and computer readable storage medium | |
| CN109102143A (en) | A kind of yield monitoring method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |