CN110075494A - A kind of sensor-based tennis ball speed estimating system - Google Patents
A kind of sensor-based tennis ball speed estimating system Download PDFInfo
- Publication number
- CN110075494A CN110075494A CN201910327830.8A CN201910327830A CN110075494A CN 110075494 A CN110075494 A CN 110075494A CN 201910327830 A CN201910327830 A CN 201910327830A CN 110075494 A CN110075494 A CN 110075494A
- Authority
- CN
- China
- Prior art keywords
- ball speed
- estimating system
- sensor
- batting
- axis
- 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
Links
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B60/00—Details or accessories of golf clubs, bats, rackets or the like
- A63B60/46—Measurement devices associated with golf clubs, bats, rackets or the like for measuring physical parameters relating to sporting activity, e.g. baseball bats with impact indicators or bracelets for measuring the golf swing
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B69/00—Training appliances or apparatus for special sports
- A63B69/38—Training appliances or apparatus for special sports for tennis
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/30—Speed
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/40—Acceleration
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/803—Motion sensors
Abstract
The invention discloses a kind of sensor-based tennis ball speed estimating systems, including motion sensor and estimating system, the motion sensor is mounted at tennis racket dabber position, wherein the motion sensor is made of a three axis accelerometer and a three-axis gyroscope, the reading of acceleration and gyroscope that the motion sensor acquisition is swung the bat, the motion sensor is connect by bluetooth with mobile terminal, and acquisition data are transferred on the mobile terminal, the estimating system in the mobile terminal data processing will be carried out to acquisition numerical value and ball speed calculates;In the present invention by multi-group data comparing result from the point of view of, sensor-based tennis ball speed estimating system is higher by 10.8% than similar representative products precision in the market, and use cost is lower, practicability is stronger, simultaneously because motion sensor small volume itself, be not in cause additional obstruction to bear user in use, influence the problems such as calculating numerical value.
Description
Technical field
The invention belongs to technical fields, and in particular to a kind of sensor-based tennis ball speed estimating system.
Background technique
With being growing more intense for tennis sports, the speed and vigor of batting is increasingly pursued in tennis, strong to connect
Service can help sportsman to have the initiative in hands, and opponent is forced to make a fault, and then create the chance of score, and tennis is most in recent years
High serve speed is broken again and again the attention for embodying sportsman for tennis ball speed.
There are mainly two types of methods for tennis ball speed estimation at present: the first is the method based on machine vision, and this method needs
Multiple high-speed cameras, video camera real-time capture tennis track to be installed in tennis court, and be calculated by machine vision algorithm
Tennis ball speed, this method precision is high, but involves great expense, and installation is complicated and difficult, and the representative products of this method are hawkeye systems
System;Second is sensor-based method, and this method needs install motion sensor on tennis racket, the motion sensor
Acquisition user swings the bat data, and then estimates that tennis ball is fast by mathematical model, compared with machine vision method, sensor, method valence
Lattice are cheap, easy for assemble or unload, but precision is relatively low;The representative products of this method are Zepp, therefore tennis ball speed estimates upper pole
It needs one kind, and cost is relatively low and the accurate evaluation method of calculation of measured data, thus it is proposed that a kind of sensor-based net
Ball ball speed estimating system.
Summary of the invention
The purpose of the present invention is to provide a kind of sensor-based tennis ball speed estimating systems, to solve above-mentioned background skill
The existing tennis ball speed measuring method higher operating costs proposed in art, and the lower problem of data precision.
To achieve the above object, the invention provides the following technical scheme: a kind of sensor-based tennis ball speed estimation system
System, including motion sensor and estimating system, the motion sensor are mounted at tennis dabber position, wherein the movement
Sensor is made of a three axis accelerometer and a three-axis gyroscope, acceleration that motion sensor acquisition is swung the bat and
The motion sensor is connect by bluetooth with mobile terminal, and acquisition data is transferred to the movement by the reading of gyroscope
On end, the estimating system in the mobile terminal data processing will be carried out to acquisition numerical value and ball speed calculates.
Preferably, the estimating system passes through the reading (a of accelerometer X-axisx) bat to detect;After there is batting, seek
Look for batting time started (tstart), tstartAppear in the reading (g of gyroscope Y-axisy) maximum absolute value at, i.e. max | gy(t)
|, by finding max | gy(t) |, batting time started (t can be foundstart), in batting time started (tstart) after, we
Find gyroscope Y-axis (gy) reading inflection point, the inflection point corresponding time be batting end time (tend), and extract
[tstart-1s,tstart+ 1s] sensing data in range is as batting data;Then it after extracting batting data, sometimes passes
Sensor data can be saturated, and the estimating system carries out Interpolation compensation to sensing data using CubicSpline interpolation method;Finally
It will currently be batted classification using random forests algorithm are as follows: service, forehand stroke, backhand, for service, the estimating system
A service ball speed model is proposed to calculate ball speed, for positive and negative forehand hit, the estimating system proposes two ball speed models,
For beginner, the estimating system will calculate ball speed, for veteran player, the estimating system physics with regression model
Model is fast to calculate ball.
Compared with prior art, the beneficial effects of the present invention are:
In the present invention by multi-group data comparing result from the point of view of, sensor-based tennis ball speed estimating system compares market
Upper similar representative products precision is high by 10.8%, and use cost is lower, and practicability is stronger, simultaneously because this body of motion sensor
Product is smaller, is not in cause additional obstruction to bear user in use, influences the problems such as calculating numerical value.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.
Fig. 1 is overall flow structural schematic diagram of the invention;
Fig. 2 is gyroscope Y-axis (g of the inventiony) the numerical value change figure in impact;
Fig. 3 is the column statistical chart that tennis ball speed calculates numerical value comparison in the present invention;
Fig. 4 is motion sensor in the present invention in the fixed position display diagram of tennis racket;
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the orientation of the instructions such as term "vertical", "upper", "lower", "horizontal"
Or positional relationship is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of description of the present invention and simplification of the description, and
It is not that the device of indication or suggestion meaning or element must have a particular orientation, be constructed and operated in a specific orientation, therefore
It is not considered as limiting the invention.
In the description of the present invention, it is also necessary to which explanation is unless specifically defined or limited otherwise, term " setting ",
" installation ", " connected ", " connection " shall be understood in a broad sense, for example, it may be fixedly connected, may be a detachable connection or one
Connect to body;It can be mechanical connection, be also possible to be electrically connected;It can be directly connected, it can also be indirect by intermediary
It is connected, can also be the connection inside two elements.It for the ordinary skill in the art, can be as the case may be
Understand the concrete meaning of above-mentioned term in the present invention.
Fig. 1-Fig. 3 is please referred to, the present invention provides a kind of technical solution: a kind of sensor-based tennis ball speed estimation system
System, motion sensor is mounted at tennis dabber position, wherein motion sensor is by a three axis accelerometer and one three
Axis gyroscope composition, the reading of acceleration and gyroscope that motion sensor acquisition is swung the bat, by motion sensor by bluetooth with
Mobile terminal connection, and acquisition data are transferred on mobile terminal, the estimating system in mobile terminal will carry out data to acquisition numerical value
Processing and ball speed calculate.
In the present embodiment, it is preferred that estimating system specifically includes the following steps:
Batting detection: pass through the reading (a of accelerometer X-axisx) bat to detect;
Data are extracted: after there is batting, finding batting time started (tstart), tstartAppear in the reading of gyroscope Y-axis
(gy) maximum absolute value at, i.e. max | gy(t) |, by finding max | gy(t) |, batting time started (t can be foundstart),
In batting time started (tstart) after, we find gyroscope Y-axis (gy) reading inflection point, the inflection point corresponding time be hit
Ball end time (tend), and extract in [tstart-1s,tstart+ 1s] sensing data in range is as batting data;
Data processing: after extracting batting data, sometimes sensing data can be saturated, and estimating system uses
CubicSpline interpolation method carries out Interpolation compensation to sensing data;
Service classification: it will currently be batted classification using random forests algorithm are as follows: service, forehand stroke, backhand, for
Service, estimating system propose a service ball speed model to calculate ball speed, and for positive and negative forehand hit, estimating system proposes two
Ball speed model, for beginner, estimating system will calculate ball speed with regression model, for veteran player, estimating system object
Reason model is fast to calculate ball.
In the present embodiment, it is preferred that service ball speed calculation using models formula are as follows:
vb_serve=k | gy(tstart)|+b
Wherein, vb_serveIt is service ball speed, k and b are model parameter, respectively 0.025 and 20.06. gy(tstart) it is top
Spiral shell instrument Y-axis is in reading when starting of batting.
In the present embodiment, it is preferred that the regression model of positive and negative handball speed are as follows:
vb_out=k | gy(tstart)|+b
Wherein, vb_outIt is positive and negative forehand hit ball speed;K and b be model parameter, respectively 0.039 and 3.94; gy(tstart)
It is gyroscope Y-axis in reading when starting of batting.
In the present embodiment, it is preferred that the physical model of positive and negative handball speed are as follows:
Wherein, vb_outIt is positive and negative forehand hit ball speed;M is tennis quality, about 50 grams;M is racket quality, about 300 grams;
RswingIt is radius of swinging the bat, is 0.72 meter;gy(tstart) it is gyroscope Y-axis in reading when starting of batting;e,kHF、bHFFor model
Parameter is divided into not: 0.16,0.236,65.83.tendIt is the batting end time;a′z(t) it is accelerometer Z after Coordinate Adjusting
Axis reading, a 'z(t) it can be acquired by following formula:
Wherein azIt (t) is reading of the accelerometer Z axis in t moment, gy(tstart) it is gyroscope Y-axis when batting beginning
Reading.
In the present embodiment, it is preferred that accelerometer measures range: ± 160m/s2;Gyroscope measurement range: ± 2000 °/
S, two sensor sample frequencies are 100Hz.
Wherein the present invention proposes one group of specific tennis ball speed contrast number, tennis ball speed estimating system acquisition in the present invention
The tennis data of 7 users in this 7 users, there is 3 coaches, 1 tennis enthusiast, 3 beginners, and tennis ball speed is estimated
Calculation system is fixed on UG sensor and Zepp sensor on the racket of user, and is equipped with PlaySight system at one
Tennis court acquires tennis data, which includes six high-speed cameras, is similar to hawkeye system, and the system is logical
It crosses machine vision algorithm identification tennis track and calculates tennis ball speed, and use the ball speed of PlaySight system-computed as true value
Assess the precision of tennis ball speed estimating system and Zepp system, tennis ball speed estimating system acquire altogether 569 services and
1416 positive and negative forehand hits.
It is final using staying a proof method testing accuracy, experimental result such as Fig. 3, the Fig. 3 are divided into three classes result: service essence
Degree, positive and negative forehand hit precision, service+positive and negative forehand hit precision;The histogram of different lines represents different user, and user 1~3 is
Coach, user 4 are tennis enthusiasts, and user 5~7 is beginner, and the height of histogram represents systematic error, and Phy label represents
The physical model of proposition, Reg label represent the regression model proposed, and Zepp label represents Zepp system, the column of Zepp in Fig. 4
Figure is higher than the histogram of Phy and Reg, illustrates that Zepp error is higher than the physical model and regression model proposed in the present invention, this hair
The error of the tennis ball speed estimating system of bright proposition are as follows: 5.6 ± 4.8 miles per hours, precision are as follows: 88.2%, Zepp system
Error are as follows: 8.3 ± 5.1 miles per hours, precision are as follows: 77.4%, and the tennis ball speed estimating system ratio Zepp system accuracy proposed
High by 10.8%, for coach (user 1~3), physical model precision is higher than regression model;For beginner (user 5~7), return
Model accuracy is returned to be higher than physical model;For tennis enthusiast (user 4), two model accuracies are similar, therefore present invention object
Reason model is fast come the ball for calculating veteran player, and the ball speed of new hand player is calculated with regression model.
Wherein in the present invention: the cubicspline interpolation that is proposed in entire tennis ball speed estimating system and random gloomy
Woods is all that existing statistics and machine learning algorithm belong to existing mature technology, details are not described herein its specific algorithmic procedure.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (7)
1. a kind of sensor-based tennis ball speed estimating system, it is characterised in that:, will including motion sensor and estimating system
The motion sensor is mounted at tennis racket dabber position, wherein the motion sensor is by a three axis accelerometer and one
A three-axis gyroscope composition, the reading of acceleration and gyroscope that the motion sensor acquisition is swung the bat, by the motion-sensing
Device is connect by bluetooth with mobile terminal, and acquisition data is transferred on the mobile terminal, the estimating system in the mobile terminal
Data processing will be carried out to acquisition numerical value and ball speed calculates.
2. a kind of sensor-based tennis ball speed estimating system according to claim 1, it is characterised in that: the estimation
System specifically includes the following steps:
Batting detection: pass through the reading (a of accelerometer X-axisx) bat to detect;
Data are extracted: after there is batting, finding batting time started (tstart), tstartAppear in the reading (g of gyroscope Y-axisy)
Maximum absolute value at, i.e. max | gy(t) |, by finding max | gy(t) |, batting time started (t can be foundstart),
Bat time started (tstart) after, we find gyroscope Y-axis (gy) reading inflection point, the inflection point corresponding time be batting knot
Beam time (tend), and extract in [tstart-1s,tstart+ 1s] sensing data in range is as batting data;
Data processing: after extracting batting data, sometimes sensing data can be saturated, and the estimating system uses
CubicSpline interpolation method carries out Interpolation compensation to sensing data;
Service classification: it will currently be batted classification using random forests algorithm are as follows: service, forehand stroke, backhand, for sending out
Ball, the estimating system propose a service ball speed model to calculate ball speed, and for positive and negative forehand hit, the estimating system is mentioned
Two ball speed models out, for beginner, the estimating system will calculate ball speed with regression model, for veteran player, institute
It states estimating system and calculates ball speed with physical model.
3. a kind of sensor-based tennis ball speed estimating system according to claim 2, it is characterised in that: the service
Ball speed calculation using models formula are as follows:
vb_serve=k | gy(tstart)|+b
Wherein, vb_serveIt is service ball speed, k and b are model parameter, respectively 0.025 and 20.06.
gy(tstart) it is gyroscope Y-axis in reading when starting of batting.
4. a kind of sensor-based tennis ball speed estimating system according to claim 2, it is characterised in that: described positive and negative
The regression model of handball speed are as follows:
vb_out=k | gy(tstart)|+b
Wherein, vb_outIt is positive and negative forehand hit ball speed;K and b be model parameter, respectively 0.039 and 3.94;
gy(tstart) it is gyroscope Y-axis in reading when starting of batting.
5. a kind of sensor-based tennis ball speed estimating system according to claim 2, it is characterised in that: described positive and negative
The physical model of handball speed are as follows:
Wherein, vb_outIt is positive and negative forehand hit ball speed;M is tennis quality, about 50 grams;M is racket quality, about 300 grams;Rswing
It is radius of swinging the bat, is 0.72 meter;gy(tstart) it is gyroscope Y-axis in reading when starting of batting;e,kHF、bHFFor model parameter,
It is divided into not: 0.16,0.236,65.83.tendIt is the batting end time;a′zIt (t) is that accelerometer Z axis after Coordinate Adjusting is read
Number.
6. a kind of sensor-based tennis ball speed estimating system according to claim 1, it is characterised in that: a 'z
(t) it can be acquired by following formula:
Wherein azIt (t) is reading of the accelerometer Z axis in t moment, gy(tstart) it is gyroscope Y-axis in reading when starting of batting.
7. a kind of sensor-based tennis ball speed estimating system according to claim 1, it is characterised in that: the acceleration
Degree meter measurement range: ± 160m/s2;The gyroscope measurement range: ± 2000 °/s, two sensor sample frequencies are
100Hz。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910327830.8A CN110075494A (en) | 2019-04-23 | 2019-04-23 | A kind of sensor-based tennis ball speed estimating system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910327830.8A CN110075494A (en) | 2019-04-23 | 2019-04-23 | A kind of sensor-based tennis ball speed estimating system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110075494A true CN110075494A (en) | 2019-08-02 |
Family
ID=67416182
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910327830.8A Pending CN110075494A (en) | 2019-04-23 | 2019-04-23 | A kind of sensor-based tennis ball speed estimating system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110075494A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101158883A (en) * | 2007-10-09 | 2008-04-09 | 深圳先进技术研究院 | Virtual gym system based on computer visual sense and realize method thereof |
CN102446359A (en) * | 2010-10-12 | 2012-05-09 | 深圳泰山在线科技有限公司 | Small ball sport processing method based on computer and system thereof |
CN103721393A (en) * | 2012-10-12 | 2014-04-16 | 邓禄普体育用品株式会社 | Tennis swing analyzing device and method |
US20160184681A1 (en) * | 2013-01-24 | 2016-06-30 | Wilson Sporting Goods Co. | Ball bat barrel with luminescent interior |
US20180229078A1 (en) * | 2011-08-29 | 2018-08-16 | Icuemotion Llc | Inertial sensor motion tracking and stroke analysis system |
-
2019
- 2019-04-23 CN CN201910327830.8A patent/CN110075494A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101158883A (en) * | 2007-10-09 | 2008-04-09 | 深圳先进技术研究院 | Virtual gym system based on computer visual sense and realize method thereof |
CN102446359A (en) * | 2010-10-12 | 2012-05-09 | 深圳泰山在线科技有限公司 | Small ball sport processing method based on computer and system thereof |
US20180229078A1 (en) * | 2011-08-29 | 2018-08-16 | Icuemotion Llc | Inertial sensor motion tracking and stroke analysis system |
CN103721393A (en) * | 2012-10-12 | 2014-04-16 | 邓禄普体育用品株式会社 | Tennis swing analyzing device and method |
US20160184681A1 (en) * | 2013-01-24 | 2016-06-30 | Wilson Sporting Goods Co. | Ball bat barrel with luminescent interior |
Non-Patent Citations (1)
Title |
---|
李新,乔爱民: "三次样条插值在称重仪表误差补偿中的应用", 《电子设计工程》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10369409B2 (en) | Dynamic sampling in sports equipment | |
US10607349B2 (en) | Multi-sensor event system | |
US7887440B2 (en) | Method for matching a golfer with a particular club style | |
US7041014B2 (en) | Method for matching a golfer with a particular golf club style | |
CN104225890B (en) | Motion analyzing apparatus | |
CN105792903B (en) | Golf simulator and golf simulation method | |
US20150018111A1 (en) | Interpretation of characteristics of a golf swing using motion analysis | |
US20130331199A1 (en) | Method for matching a golfer with a particular golf club style | |
KR101972526B1 (en) | golf swing correcting system | |
CN110227243A (en) | Table tennis practice intelligent correcting system and its working method | |
Torigoe et al. | Strike Activity Detection and Recognition Using Inertial Measurement Unit towards Kendo Skill Improvement Support System. | |
CN110075494A (en) | A kind of sensor-based tennis ball speed estimating system | |
US10918920B2 (en) | Apparatus and methods to track movement of sports implements | |
US10695632B2 (en) | Apparatus and methods to track movement of sports implements | |
TWI770787B (en) | Hand-held motion analysis sysyem and method | |
CN114788951A (en) | Hand-held motion analysis system and method | |
CN112007340A (en) | Table tennis match referee and player training system and method based on acceleration sensor | |
KR101088452B1 (en) | Screen Golf System and Screen Golf Simulator for Fitting Golf Club Manufacturing and Golf Swing Analysis | |
CN202920940U (en) | Device for detecting ping-pong throwing height | |
KR20150116325A (en) | System and Method for simulating Golf using Depth Information | |
CN113713360B (en) | Volleyball hitting counting method and device | |
Sekkas et al. | MobiXeyes: Real-time stereo vision technology for racket sports | |
CN114724271B (en) | Timing system suitable for snooker event | |
US20230233922A1 (en) | Smart putter for automatic putter game scoring | |
CN112147367A (en) | Method for determining the direction of the spin axis of a rotating fixture |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190802 |