CN114611770A - Dash training test timing method based on machine vision - Google Patents

Dash training test timing method based on machine vision Download PDF

Info

Publication number
CN114611770A
CN114611770A CN202210176409.3A CN202210176409A CN114611770A CN 114611770 A CN114611770 A CN 114611770A CN 202210176409 A CN202210176409 A CN 202210176409A CN 114611770 A CN114611770 A CN 114611770A
Authority
CN
China
Prior art keywords
athlete
current
line
information
steps
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.)
Pending
Application number
CN202210176409.3A
Other languages
Chinese (zh)
Inventor
余秋燕
黄日辉
余秋仙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujian Hengzhi Information Technology Co ltd
Original Assignee
Fujian Hengzhi Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fujian Hengzhi Information Technology Co ltd filed Critical Fujian Hengzhi Information Technology Co ltd
Priority to CN202210176409.3A priority Critical patent/CN114611770A/en
Publication of CN114611770A publication Critical patent/CN114611770A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Operations Research (AREA)
  • Human Resources & Organizations (AREA)
  • Pure & Applied Mathematics (AREA)
  • Economics (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Development Economics (AREA)
  • Algebra (AREA)
  • Game Theory and Decision Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Artificial Intelligence (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

The invention discloses a dash training test timing method based on machine vision, which relates to the technical field of dash training tests and comprises the following steps: the method comprises the steps that the identity of a sportsman is verified in advance based on a mobile terminal, and the specified track for the current sportsman to enter a train is completed; acquiring the line touch image information of a starting line of an athlete after starting a command by the mobile terminal, and judging whether the athlete rushes to run or not; if no racing is performed currently, the whole course crossing detection of the athletes is carried out, wherein the whole course crossing detection comprises the steps of respectively acquiring whether the athletes on the appointed track cross the line or not in real time; if the current athlete does not cross the line, respectively acquiring finish line punching information of the current athlete, acquiring a line punching timestamp, and determining the score of the current athlete; the invention realizes the sprint training test, has high training test precision and fair test, solves the error of personnel identity verification, reduces a large amount of human organizations, has low investment, can trace the training and examination data, and is convenient for assisting and guiding more scientific training through the data.

Description

Dash training test timing method based on machine vision
Technical Field
The invention relates to the technical field of sprint training tests, in particular to a sprint training test timing method based on machine vision.
Background
The machine vision technology is widely applied to the industries of food and beverage, cosmetics, pharmacy, building materials, chemical industry, metal processing, electronic manufacturing, packaging, automobile manufacturing and the like, and replaces artificial vision to realize detection, measurement and control; the machine vision technology mainly uses a computer to simulate the visual function of a human, extracts information from an image of an objective object, processes and understands the information, and finally is used for actual detection, measurement and control.
At present, in sports race sprint training, most of 50-meter and 100-meter tests adopt manual identity verification and manual meter pinching for timing, each race track is subjected to meter pinching timing by special personnel, and finally, final scores are gathered manually to obtain the final scores.
Therefore, a need exists for a machine vision based sprint training test timing method.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a sprint training test timing method based on machine vision, so as to overcome the technical problems in the prior related art.
The technical scheme of the invention is realized as follows:
a dash training test timing method based on machine vision comprises the following steps:
step S1, the identity of the athlete is verified in advance based on the mobile terminal, and the current athlete entering the designated track is completed;
step S2, the mobile terminal acquires the start line touch line image information of the athlete after starting the order, and judges whether the athlete rushes to run;
step S3, if there is no race robbing, the whole course crossing detection of the athlete is carried out, which includes respectively obtaining whether the athlete of the appointed race track crosses the line in real time;
step S4, if the current athlete does not cross the line, respectively obtaining finish line punching information of the current athlete, obtaining a line punching time stamp and determining the score of the current athlete;
wherein said determining the performance of the current athlete further comprises the steps of:
and step S5, performing ascending, descending and sequencing on the achievements of all the current athletes.
The method for verifying the identity of the athlete based on the mobile terminal comprises the following steps:
step S101, a mobile terminal collects face information of a current athlete and carries out identification and verification;
and step S102, acquiring the identity information of the athlete, and matching the identity information with the designated track.
Wherein, whether race is robbed or not is judged, and the method comprises the following steps:
step S201, a mobile terminal collects a running line and line touch real-time video stream of an athlete after starting a command;
step S202, decomposing the video stream, generating an image, and acquiring whether the position of the athlete in the image is robbed for running after starting to give a command;
and step S203, if the current athlete rushes to run, canceling the current sprint training and restarting to give a command.
Wherein, the whole course crossing detection of the athlete comprises the following steps:
step S301, configuring a high-altitude point position camera on the current track, and acquiring track video information in real time, wherein the track video information comprises the marking and tracking of the current athlete;
step S302, transmitting the collected serial channel information to the mobile terminal, wherein the method comprises the following steps:
step S303, if the current athlete has a cross-track, canceling the current marked athlete score;
and step S304, if the current athlete has no crosswalk, the performance of the current athlete is qualified.
The method for acquiring the finish line dash information of the current athlete comprises the following steps:
step S401, configuring a terminal camera on the terminal line, and collecting the terminal line dash information of the athlete in real time;
step S402, transmitting the collected endpoint line flushing information to a mobile terminal, wherein the information comprises the image and the time stamp information of the current athlete;
and step S403, acquiring the scores of the athletes.
Wherein, still include the following step:
and step S6, recording and storing the current sprint training.
The invention has the beneficial effects that:
the invention relates to a dash training test timing method based on machine vision, which is characterized in that the identity of a sportsman is verified based on a mobile terminal in advance, the specified track of the current sportsman is listed, the mobile terminal acquires the start line touch line image information of the sportsman after starting a command, judges whether the sportsman rushes, if the sportsman does not rush, the whole course crossing detection of the sportsman is carried out, if the current sportsman does not cross the line, the finish line dash information of the current sportsman is respectively acquired, a dash timestamp is acquired, the score of the current sportsman is determined, and the dash training test is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flow chart of a machine vision-based sprint training test timing method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
According to an embodiment of the invention, a sprint training test timing method based on machine vision is provided.
As shown in fig. 1, the machine vision-based sprint training test timing method according to the embodiment of the present invention includes the following steps:
step S1, the identity of the athlete is verified in advance based on the mobile terminal, and the current athlete entering the designated track is completed;
the method for verifying the identity of the athlete based on the mobile terminal comprises the following steps:
step S101, a mobile terminal collects face information of a current athlete and carries out identification and verification;
and step S102, acquiring the identity information of the athlete, and matching the identity information with the designated track.
According to the technical scheme, a face recognition technology can be adopted for face information recognition and verification, face modeling is carried out by pre-collecting face characteristic information of athletes, a unified face information base is constructed, face information is collected by a camera arranged in a mobile terminal, face characteristic data are extracted and transmitted into the face information base to carry out face characteristic comparison, recognition results and personnel information are obtained, and personnel identity verification is completed.
In addition, the athlete swipes the face to check and record the personnel, if the check fails, voice prompt is carried out, otherwise, the mobile terminal displays the information of the personnel, and the athlete is prompted to enter the designated track through voice.
Step S2, the mobile terminal acquires the start line touch line image information of the athlete after starting the order, and judges whether the athlete rushes to run;
wherein, whether race is robbed or not is judged, and the method comprises the following steps:
step S201, a mobile terminal collects a running line and line touch real-time video stream of an athlete after starting a command;
step S202, decomposing the video stream, generating an image, and acquiring whether the position of the athlete in the image is robbed for running after starting to give a command;
and step S203, if the current athlete rushes to run, canceling the current sprint training and restarting to give a command.
According to the technical scheme, the built-in camera of the mobile terminal collects the starting line video stream in real time, decomposes the video stream and generates each frame of picture to be stored, and the picture generated in the starting period is obtained through image processing to mark whether the position of the athlete rushes to run to touch the line or not and feed back the result of the rushing.
In addition, during the period of starting the order, the order information is broadcasted in a voice mode, during the countdown period of starting the order, if the athlete rushes to run, the prompt is broadcasted in the voice mode, the athlete can run the starting line again, the order is broadcasted again by the operator, the racing is allowed to be performed once every person, the prompt is broadcasted in the voice mode when the athlete exceeds the starting line, and the athlete cancels the qualification of the competition.
In addition, step S3, if there is no race snatching currently, performing the athlete whole course crossing detection, which includes respectively obtaining whether the athlete of the designated race track crosses the line in real time;
wherein, the whole course crossing detection of the athlete comprises the following steps:
s301, configuring a high-altitude point position camera on the current track, and acquiring track video information in real time, wherein the track video information comprises marking and tracking of the current athlete;
step S302, transmitting the collected serial channel information to the mobile terminal, wherein the method comprises the following steps:
step S303, if the current athlete has a cross road, canceling the currently marked athlete score;
and step S304, if the current athlete has no crosswalk, the performance of the current athlete is qualified.
According to the technical scheme, the high-altitude point position camera marks and tracks athletes of each current track, characteristics of the athletes are bound with track relevance, lines are drawn on two sides of the track, a real-time video stream is obtained through a video analysis technology, a video is decomposed and pictures are generated to be stored, whether marked personnel cross the lines or not is judged through analyzing the pictures through an image processing technology, and line crossing results are fed back.
In addition, after the order is sent out, if athletes cross a channel in the running process, voice broadcasting is used for reminding, the score of the athlete is cancelled, and the competition continues.
Step S4, if the current athlete does not cross the line, respectively obtaining finish line punching information of the current athlete, obtaining a line punching time stamp and determining the score of the current athlete;
the method for acquiring the finish line dash information of the current athlete comprises the following steps:
step S401, configuring a terminal camera on the terminal line, and collecting the terminal line dash information of the athlete in real time;
step S402, transmitting the collected endpoint line flushing information to a mobile terminal, wherein the information comprises the image and the time stamp information of the current athlete;
and step S403, acquiring the scores of the athletes.
According to the technical scheme, the terminal camera acquires a real-time video stream by adopting a machine vision video analysis technology, analyzes the video and generates a picture to be stored in real time, analyzes whether the generated picture has a contact line of an athlete by utilizing an image processing technology, records a contact line timestamp and a contact line picture if the generated picture has the contact line, and acquires the score of the athlete.
In addition, the athletes pass through the finish line, the contact time stamps are automatically identified and recorded, the competition is finished, and meanwhile, the final achievement is converted according to the contact time stamps of each athlete.
And step S5, performing ascending, descending and sequencing on the achievements of all the current athletes.
Wherein, still include the following step:
and step S6, recording and storing the current sprint training.
By means of the scheme, the identity of the athlete is verified on the basis of the mobile terminal in advance, the current athlete is listed in the appointed track, the mobile terminal acquires the line-starting touch line image information of the athlete after starting the order, whether the athlete rushes to run or not is judged, if the athlete does not rush to run currently, the whole-course track crossing detection of the athlete is carried out, if the current athlete does not cross the line, the line-starting line-punching information of the current athlete is respectively acquired, the line-punching timestamp is acquired, the score of the current athlete is determined, the sprint training test is realized, the training test precision is high, the test is fair, the error of the identity verification of the athlete is solved, a large amount of manpower organizations is reduced, the investment is low, in addition, the training and checking data can be traced, and the assistance and the more scientific training can be conveniently guided through the data.
According to the technical scheme, a multimodal Gaussian distribution model technology can be adopted when the image is processed, each pixel point of the model image is modeled according to superposition of a plurality of Gaussian distributions with different weights, each Gaussian distribution corresponds to a state which can possibly generate colors presented by the pixel points, and the weights and distribution parameters of the Gaussian distributions are updated along with time. When processing color images, it is assumed that the image pixels R, G, B have three color channels that are independent of each other and have the same variance.
Wherein, for an observed data set of a random variable X, it is expressed as: { x1,x2,…,xN}；
Wherein x ist＝(rt,gt,bt) For a sample of the pixel at time t, then a single sample point xtThe obeyed mixed Gaussian distribution probability density function is expressed as:
Figure BDA0003520436320000061
Figure BDA0003520436320000062
Figure BDA0003520436320000063
wherein each new pixel value XtAnd comparing the current K models according to the following formula, and directly finding a distribution model matched with a new pixel value, namely the mean deviation of the new pixel value and the current K models is within 2.5 sigma and expressed as:
|Xt-μi,t-1|≤2.5σi,t-1；
in addition, if the matched mode meets the background requirement, the pixel belongs to the background, otherwise, the pixel belongs to the foreground.
In addition, each pattern weight is updated as follows, wherein a is the learning rate, and for the matched pattern Mk,t1, otherwise Mk,tThe weights for each mode are then normalized, as:
wk,t＝(1-α)*wk,t-1+α*Mk,t；
wherein, the mean value mu and the standard deviation sigma of the unmatched mode are unchanged, and the parameters of the matched mode are updated as follows:
ρ＝α*η(Xt∣μk,σk)；
μt＝(1-ρ)*μt-1+ρ*Xt；
Figure BDA0003520436320000064
in addition, if there is no pattern match in the first step, the pattern with the smallest weight is replaced, i.e. the mean value of the pattern is the current pixel value, the standard deviation is an initial larger value, and the weight is a smaller value.
In summary, the present invention can achieve the following effects: the method comprises the steps of verifying the identity of a sportsman based on a mobile terminal in advance, completing the listing of the current sportsman on a designated track, acquiring the start line touch line image information of the sportsman after starting a command by the mobile terminal, judging whether the sportsman rushes to run or not, detecting the whole track crossing of the sportsman if the current sportsman does not run to run, respectively acquiring the finish line touch line information of the current sportsman if the current sportsman does not cross the track, acquiring a touch line timestamp, determining the score of the current sportsman, realizing a sprint training test, achieving high training test precision and fair and testing, solving the error of personal identity verification, reducing a large amount of human organizations, having low investment, enabling training and checking data to be traceable, and facilitating assistance and guiding more scientific training through the data.
While the foregoing is directed to the preferred embodiment of the present invention, other and further embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (7)

1. A dash training test timing method based on machine vision is characterized by comprising the following steps:
the method comprises the steps that the identity of a sportsman is verified in advance based on a mobile terminal, and the specified track for the current sportsman to enter a train is completed;
acquiring the line touch image information of a starting line of an athlete after starting a command by the mobile terminal, and judging whether the athlete rushes to run or not;
if no racing is performed currently, the whole course crossing detection of the athletes is carried out, wherein the whole course crossing detection comprises the steps of respectively acquiring whether the athletes on the appointed track cross the line or not in real time;
and if the current athlete does not cross the line, respectively acquiring finish line punching information of the current athlete, acquiring a line punching time stamp and determining the performance of the current athlete.
2. The machine vision based sprint training trial timing method of claim 1 wherein the step of determining the current athlete's performance further includes the steps of:
and (4) performing ascending, descending and sequencing on the achievements of all the current athletes.
3. The machine vision based sprint training test timing method of claim 2 wherein the verification of athlete identity based on the mobile terminal comprises the steps of:
the mobile terminal collects face information of a current athlete and carries out identification and verification;
and acquiring the identity information of the athlete, and matching the identity information with the designated track.
4. The machine vision based sprint training test timing method of claim 3 wherein said determining if a sprint is occurring comprises the steps of:
the method comprises the steps that a mobile terminal collects a real-time video stream of a running line and a line touch of an athlete after starting a command;
decomposing the video stream to generate an image, and acquiring whether the position of the athlete in the image is robbed or not after starting to give a command;
if the athlete rushes to run, the current sprint training is cancelled, and starting to give a command again.
5. The machine vision based sprint training test timing method of claim 4 wherein said performing athlete's full range cross-track detection comprises the steps of:
configuring a high-altitude point position camera on the current track, and acquiring track video information in real time, wherein the track video information comprises marking and tracking of the current athlete;
transmitting the collected serial channel information to a mobile terminal, wherein the method comprises the following steps:
if the current athlete has a cross road, canceling the current marked athlete score;
if the current athlete has no cross-track, the performance of the current athlete is qualified.
6. The machine vision-based sprint training test timing method of claim 5 wherein the step of obtaining finish line strike information for a current athlete includes the steps of:
a finishing line is provided with a finishing camera to collect finishing line impact information of the athlete in real time;
transmitting the collected finishing line impact information to a mobile terminal, wherein the finishing line impact information comprises an image of a current athlete and timestamp information;
and acquiring the performance of the athlete.
7. The machine vision based sprint training test timing method of claim 6 further including the steps of:
and recording and storing the current sprint training.
CN202210176409.3A 2022-02-25 2022-02-25 Dash training test timing method based on machine vision Pending CN114611770A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210176409.3A CN114611770A (en) 2022-02-25 2022-02-25 Dash training test timing method based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210176409.3A CN114611770A (en) 2022-02-25 2022-02-25 Dash training test timing method based on machine vision

Publications (1)

Publication Number Publication Date
CN114611770A true CN114611770A (en) 2022-06-10

Family

ID=81859678

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210176409.3A Pending CN114611770A (en) 2022-02-25 2022-02-25 Dash training test timing method based on machine vision

Country Status (1)

Country Link
CN (1) CN114611770A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116453067A (en) * 2023-06-20 2023-07-18 广州思林杰科技股份有限公司 Sprinting timing method based on dynamic visual identification

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116453067A (en) * 2023-06-20 2023-07-18 广州思林杰科技股份有限公司 Sprinting timing method based on dynamic visual identification
CN116453067B (en) * 2023-06-20 2023-09-08 广州思林杰科技股份有限公司 Sprinting timing method based on dynamic visual identification

Similar Documents

Publication Publication Date Title
Tolentino et al. Static sign language recognition using deep learning
CN105426827B (en) Living body verification method, device and system
US10803762B2 (en) Body-motion assessment device, dance assessment device, karaoke device, and game device
CN109325456A (en) Target identification method, device, target identification equipment and storage medium
CN107833328B (en) Access control verification method and device based on face recognition and computing equipment
CN106611160A (en) CNN (Convolutional Neural Network) based image hair identification method and device
Suzuki et al. Enhancement of gross-motor action recognition for children by CNN with OpenPose
CN110969073B (en) Facial expression recognition method based on feature fusion and BP neural network
CN110517261A (en) Seat belt status detection method, device, computer equipment and storage medium
CN108717789A (en) A kind of the acquisition mask method and device of vehicle sample
CN115205764B (en) Online learning concentration monitoring method, system and medium based on machine vision
CN110751675A (en) Urban pet activity track monitoring method based on image recognition and related equipment
CN114611770A (en) Dash training test timing method based on machine vision
CN111598047B (en) Face recognition method
CN112101315A (en) Deep learning-based exercise judgment guidance method and system
CN115546688A (en) Long jump evaluation method, device, electronic equipment and storage medium
CN109545027A (en) A kind of practical traning platform, crew's simulation training method and device
CN114581990A (en) Intelligent running test method and device
CN107516350A (en) Mobile morning run Work attendance method and system based on virtual route
CN114639152A (en) Multi-modal voice interaction method, device, equipment and medium based on face recognition
CN110263678A (en) A kind of face direction determination process and system
CN114565976A (en) Training intelligent test method and device
CN106625711A (en) Method for positioning intelligent interaction of robot
CN111659124A (en) Intelligent identification system for playing chess
CN111563443A (en) Continuous motion action accuracy evaluation method

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