CN106372657B - Method and device for correcting motion data deviation based on image recognition - Google Patents
Method and device for correcting motion data deviation based on image recognition Download PDFInfo
- Publication number
- CN106372657B CN106372657B CN201610761469.6A CN201610761469A CN106372657B CN 106372657 B CN106372657 B CN 106372657B CN 201610761469 A CN201610761469 A CN 201610761469A CN 106372657 B CN106372657 B CN 106372657B
- Authority
- CN
- China
- Prior art keywords
- motion data
- motion
- mean value
- data
- arithmetic mean
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012937 correction Methods 0.000 claims abstract description 26
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method for correcting motion data deviation based on image recognition, which comprises the following steps: shooting a full-interface image on the motion instrument interface through an external camera device to form a preset image recorded with motion data of a user after testing motion; identifying the motion data of the preset image, extracting the motion data, and storing the extracted motion data in a motion data table in a memory; and performing weighted operation on the motion data and a plurality of historical motion data prestored in a motion data table, comparing standard motion data according to the latest motion arithmetic mean value after operation, and performing deviation correction according to the compared result. According to this method, the deviation of the motion data of the user can be corrected.
Description
Technical Field
The invention relates to the field of motion data measurement, in particular to a method and a device for motion data deviation correction based on image recognition.
Background
In the process of testing the motion data, the problem of motion data deviation is frequently encountered, however, when the motion data deviation is solved, some situations of inaccurate test are frequently encountered, deviation correction needs to be carried out on the motion data, however, the existing deviation correction method is not accurate enough, and the user experience is poor.
Disclosure of Invention
Based on the method and the device, the invention provides a method and a device for correcting the motion data deviation based on image recognition.
A method of motion data bias correction based on image recognition, the method comprising:
shooting a full-interface image on the motion instrument interface through an external camera device to form a preset image recorded with motion data of a user after testing motion;
identifying the motion data of the preset image, extracting the motion data, and storing the extracted motion data in a motion data table in a memory;
and performing weighted operation on the motion data and a plurality of historical motion data prestored in a motion data table, comparing standard motion data according to the latest motion arithmetic mean value after operation, and performing deviation correction according to the compared result.
In one embodiment, the step of performing a weighted operation on the motion data and a plurality of historical motion data pre-stored in a motion data table includes:
the motion data NXWith a plurality of historical motion data N1、N2、N3.., performing weighting operation on all motion data to obtain the latest motion arithmetic mean value NMean value of=（N1+N2+N3+NX）/X；
Or, the motion data Nx and the maximum value N in a plurality of historical motion data are usedmaxMinimum value NminPerforming weighting operation to obtain the latest motion arithmetic mean value NMean value of=（Nmax+Nmin +NX）/3；
Or, the motion data Nx and the arithmetic mean value N of the selected part of the motion data in a plurality of historical motion dataPartial mean valuePerforming weighting operation to obtain the latest moving arithmetic mean value NMean value of=（NX+NPartial mean value）/2。
In one embodiment, the step of identifying the motion data of the preset image and extracting the motion data includes:
performing binary classification on the preset image based on a binary parameter classification method, wherein the result obtained by classification is picture data and digital data;
the digital data is extracted as motion data.
In one embodiment, the method further comprises:
and carrying the motion data after the deviation correction in user information, and displaying the motion data again on a motion interface.
In one embodiment, the method further comprises:
if a plurality of deviation corrected motion data exist, screening the motion data through a deviation value selection part;
and displaying the screened motion data.
An apparatus for image recognition based motion data bias correction, the apparatus comprising:
the interface image forming part is used for shooting a full interface image on the interface of the sports instrument through an external camera device so as to form a preset image recorded with the motion data of the user after testing the motion;
the interface image identification part is used for identifying the motion data of the preset image, extracting the motion data and storing the extracted motion data in a motion data table in a memory;
and the adjustment operation numerical value part is used for performing weighted operation on the motion data and a plurality of historical motion data prestored in the motion data table, comparing standard motion data according to the latest motion arithmetic mean value after operation, and performing deviation correction according to the compared result.
In one embodiment, the adjusting operand value portion includes:
a first arithmetic unit for dividing the motion data NXWith a plurality of historical motion data N1、N2、N3.., performing weighting operation on all motion data to obtain the latest motion arithmetic mean value NMean value of=（N1+N2+N3+NX）/X；
A second arithmetic unit for comparing the motion data Nx with a maximum value N of a plurality of historical motion datamaxAnd a minimum value NminPerforming weighting operation to obtain the latest motion arithmetic mean value NMean value of=（Nmax+Nmin +NX）/3；
A third operation unit for calculating the arithmetic mean N of the motion data Nx and the selected part of the motion data in the plurality of historical motion dataPartial mean valuePerforming weighting operation to obtain the latest moving arithmetic mean value NMean value of=（NX+NPartial mean value）/2。
In one embodiment, the interface image recognition unit includes:
the classification unit is used for carrying out binary classification on the preset images based on a binary parameter classification method, and the classified results are picture data and digital data;
an extraction unit for extracting the digital data as motion data.
In one embodiment, the apparatus further comprises:
and the display unit is used for carrying the motion data after the deviation correction in the user information and displaying the motion data again on the motion interface.
In one embodiment, the apparatus further comprises:
if a plurality of deviation corrected motion data exist, screening the motion data through a deviation value selection part;
and displaying the screened motion data.
Has the advantages that:
the invention discloses a method for correcting motion data deviation based on image recognition, which comprises the following steps:
shooting a full-interface image on the motion instrument interface through an external camera device to form a preset image recorded with motion data of a user after testing motion; identifying the motion data of the preset image, extracting the motion data, and storing the extracted motion data in a motion data table in a memory; and performing weighted operation on the motion data and a plurality of historical motion data prestored in a motion data table, comparing standard motion data according to the latest motion arithmetic mean value after operation, and performing deviation correction according to the compared result. According to this method, the deviation of the motion data of the user can be corrected.
Drawings
Fig. 1 is a flow chart of a method for motion data bias correction based on image recognition according to the present invention.
Fig. 2 is a block diagram of an apparatus for motion data bias correction based on image recognition according to 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 operation principle 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 embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a method for motion data deviation correction based on image recognition includes:
s100: shooting a full-interface image on the motion instrument interface through an external camera device to form a preset image recorded with motion data of a user after testing motion;
s200: identifying the motion data of the preset image, extracting the motion data, and storing the extracted motion data in a motion data table in a memory;
s300: and performing weighted operation on the motion data and a plurality of historical motion data prestored in a motion data table, comparing standard motion data according to the latest motion arithmetic mean value after operation, and performing deviation correction according to the compared result.
In one embodiment, the step of performing a weighted operation on the motion data and a plurality of historical motion data pre-stored in a motion data table includes:
the motion data NXWith a plurality of historical motion data N1、N2、N3.., performing weighting operation on all motion data to obtain the latest motion arithmetic mean value NMean value of=（N1+N2+N3+NX）/X；
Or, the motion data Nx and the maximum value N in a plurality of historical motion data are usedmaxMinimum value NminPerforming weighting operation to obtain the latest motion arithmetic mean value NMean value of=（Nmax+Nmin +NX）/3；
Or, the motion data Nx and the arithmetic mean value N of the selected part of the motion data in a plurality of historical motion dataPartial mean valuePerforming weighting operation to obtain the latest moving arithmetic mean value NMean value of=（NX+NPartial mean value）/2。
In one embodiment, the step of identifying the motion data of the preset image and extracting the motion data includes:
performing binary classification on the preset image based on a binary parameter classification method, wherein the result obtained by classification is picture data and digital data;
the digital data is extracted as motion data.
In one embodiment, the method further comprises:
and carrying the motion data after the deviation correction in user information, and displaying the motion data again on a motion interface.
In one embodiment, the method further comprises:
if a plurality of deviation corrected motion data exist, screening the motion data through a deviation value selection part;
and displaying the screened motion data.
Referring to fig. 2, an apparatus for motion data deviation correction based on image recognition includes:
the interface image forming part 10 is used for shooting a full interface image on the interface of the sports instrument through an external camera device so as to form a preset image recorded with the motion data of the user after testing the motion;
an interface image recognition part 20 for recognizing the motion data of the preset image, extracting the motion data, and storing the extracted motion data in a motion data table in a memory;
and an adjustment operation numerical part 30 for performing a weighted operation on the motion data and a plurality of historical motion data pre-stored in the motion data table, comparing the standard motion data according to the latest motion arithmetic mean value after the operation, and performing deviation correction according to the compared result.
In one embodiment, the adjusting operand value portion includes:
a first arithmetic unit for dividing the motion data NXWith a plurality of historical motion data N1、N2、N3.., performing weighting operation on all motion data to obtain the latest motion arithmetic mean value NMean value of=（N1+N2+N3+NX）/X；
A second arithmetic unit for comparing the motion data Nx with a maximum value N of a plurality of historical motion datamaxAnd a minimum value NminPerforming weighting operation to obtain the latest motion arithmetic mean value NMean value of=（Nmax+Nmin +NX）/3；
A third operation unit for calculating the arithmetic mean N of the motion data Nx and the selected part of the motion data in the plurality of historical motion dataPartial mean valuePerforming weighting operation to obtain the latest moving arithmetic mean value NMean value of=（NX+NPartial mean value）/2。
In one embodiment, the interface image recognition unit includes:
the classification unit is used for carrying out binary classification on the preset images based on a binary parameter classification method, and the classified results are picture data and digital data;
an extraction unit for extracting the digital data as motion data.
In one embodiment, the apparatus further comprises:
and the display unit is used for carrying the motion data after the deviation correction in the user information and displaying the motion data again on the motion interface.
In one embodiment, the apparatus further comprises:
if a plurality of deviation corrected motion data exist, screening the motion data through a deviation value selection part;
and displaying the screened motion data.
The invention discloses a method for correcting motion data deviation based on image recognition, which comprises the following steps: shooting a full-interface image on the motion instrument interface through an external camera device to form a preset image recorded with motion data of a user after testing motion; identifying the motion data of the preset image, extracting the motion data, and storing the extracted motion data in a motion data table in a memory; and performing weighted operation on the motion data and a plurality of historical motion data prestored in a motion data table, comparing standard motion data according to the latest motion arithmetic mean value after operation, and performing deviation correction according to the compared result. According to this method, the deviation of the motion data of the user can be corrected.
The operation principle of the present invention is described in detail above, and the description of the operation principle is only used to help understand the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (8)
1. A method for user data bias correction based on image recognition, the method comprising:
shooting a full-interface image on a terminal interface through an external camera device to form a preset image recorded with motion data of a user after motion;
identifying the motion data of the preset image, extracting the motion data, and storing the extracted motion data in a memory;
weighting the motion data and a plurality of historical motion data prestored in a motion data table, comparing the standard motion data according to the arithmetic mean value of the latest motion data after operation, and performing deviation correction according to the compared result;
the step of performing weighted operation on the motion data and a plurality of pieces of historical motion data prestored in a motion data table comprises:
the motion data NXWith a plurality of historical motion data N1、N2、N3.., performing weighting operation on all motion data to obtain the latest motion arithmetic mean value NMean value of=（N1+N2+N3… +NX) X; wherein X is the number of items of motion data acquired during calculation of the arithmetic mean;
or, the motion data Nx and the maximum value N in a plurality of historical motion data are usedmaxMinimum value NminPerforming weighting operation to obtain the latest motion arithmetic mean value NMean value of=（Nmax+Nmin +NX）/3；
Or, the motion data Nx and the arithmetic mean value N of the selected part of the motion data in a plurality of historical motion dataPartial mean valuePerforming weighting operation to obtain the latest moving arithmetic mean value NMean value of=（NX+NPartial mean value）/2。
2. The method of claim 1, wherein the step of identifying motion data of the preset image and performing motion data extraction comprises:
performing binary classification on the preset image based on a binary parameter classification method, wherein the result obtained by classification is picture data and digital data;
the digital data is extracted as motion data.
3. The method of claim 1, further comprising:
and carrying the motion data after the deviation correction in user information, and displaying the motion data again on a motion interface.
4. The method of claim 1, further comprising:
if a plurality of deviation corrected motion data exist, screening the motion data through a deviation value selection part;
and displaying the screened motion data.
5. An apparatus for image recognition based motion data bias correction, the apparatus comprising:
the interface image forming part is used for shooting a full interface image on a terminal interface through an external camera device so as to form a preset image recorded with motion data of a user after testing motion;
the interface image identification part is used for identifying the motion data of the preset image, extracting the motion data and storing the extracted motion data in a motion data table in a memory;
the adjustment operation numerical value part is used for carrying out weighted operation on the motion data and a plurality of historical motion data prestored in a motion data table, comparing standard motion data according to the latest motion arithmetic mean value after operation, and carrying out deviation correction according to the compared result;
the adjustment arithmetic value part includes:
a first arithmetic unit forIn the motion data NXWith a plurality of historical motion data N1、N2、N3.., performing weighting operation on all motion data to obtain the latest motion arithmetic mean value NMean value of=（N1+N2+N3+NX) X; wherein X is the number of items of motion data acquired during calculation of the arithmetic mean;
a second arithmetic unit for comparing the motion data Nx with a maximum value N of a plurality of historical motion datamaxMinimum value NminPerforming weighting operation to obtain the latest motion arithmetic mean value NMean value of=（Nmax+Nmin +NX）/3；
A third operation unit for calculating the arithmetic mean N of the motion data Nx and the selected part of the motion data in the plurality of historical motion dataPartial mean valuePerforming weighting operation to obtain the latest moving arithmetic mean value NMean value of=（NX+NPartial mean value）/2。
6. The apparatus according to claim 5, wherein the interface image recognizing section includes:
the classification unit is used for carrying out binary classification on the preset images based on a binary parameter classification method, and the classified results are picture data and digital data;
an extraction unit for extracting the digital data as motion data.
7. The apparatus of claim 5, further comprising:
and the display unit is used for carrying the motion data after the deviation correction in the user information and displaying the motion data again on the motion interface.
8. The apparatus of claim 5, further comprising:
if a plurality of deviation corrected motion data exist, screening the motion data through a deviation value selection part; and displaying the screened motion data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610761469.6A CN106372657B (en) | 2016-08-30 | 2016-08-30 | Method and device for correcting motion data deviation based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610761469.6A CN106372657B (en) | 2016-08-30 | 2016-08-30 | Method and device for correcting motion data deviation based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106372657A CN106372657A (en) | 2017-02-01 |
| CN106372657B true CN106372657B (en) | 2022-03-18 |
Family
ID=57901552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610761469.6A Active CN106372657B (en) | 2016-08-30 | 2016-08-30 | Method and device for correcting motion data deviation based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106372657B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1427244A (en) * | 2001-11-19 | 2003-07-02 | 精工电子有限公司 | Motion-detecting height gauge |
| CN102016605A (en) * | 2008-05-08 | 2011-04-13 | L-3通讯公司 | Accelerometer and method for error compensation |
| CN202650224U (en) * | 2012-06-28 | 2013-01-02 | 临城县供电有限责任公司 | Power Image Recognition Meter Reading Instrument |
| CN105311813A (en) * | 2014-07-31 | 2016-02-10 | 精工爱普生株式会社 | Exercise analysis system, exercise analysis apparatus, and exercise analysis method |
| CN105631412A (en) * | 2015-12-23 | 2016-06-01 | 深圳市金立通信设备有限公司 | Data recording method and terminal |
-
2016
- 2016-08-30 CN CN201610761469.6A patent/CN106372657B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1427244A (en) * | 2001-11-19 | 2003-07-02 | 精工电子有限公司 | Motion-detecting height gauge |
| CN102016605A (en) * | 2008-05-08 | 2011-04-13 | L-3通讯公司 | Accelerometer and method for error compensation |
| CN202650224U (en) * | 2012-06-28 | 2013-01-02 | 临城县供电有限责任公司 | Power Image Recognition Meter Reading Instrument |
| CN105311813A (en) * | 2014-07-31 | 2016-02-10 | 精工爱普生株式会社 | Exercise analysis system, exercise analysis apparatus, and exercise analysis method |
| CN105631412A (en) * | 2015-12-23 | 2016-06-01 | 深圳市金立通信设备有限公司 | Data recording method and terminal |
Non-Patent Citations (2)
| Title |
|---|
| 《一种带误差校正的横波速度预测方法》;黄为清等;《地球物理学进展》;20111231;第26卷(第6期);第2184-2189页 * |
| 《网页内容过滤的关键技术分析》;胡辉等;《网络与通信技术》;20160731(第7期);第138-139页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106372657A (en) | 2017-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109325954B (en) | Image segmentation method and device and electronic equipment | |
| CN106650662B (en) | Target object shielding detection method and device | |
| WO2020024744A1 (en) | Image feature point detecting method, terminal device, and storage medium | |
| KR101747216B1 (en) | Apparatus and method for extracting target, and the recording media storing the program for performing the said method | |
| CN110827249A (en) | Electronic equipment backboard appearance flaw detection method and equipment | |
| CN109522775B (en) | Face attribute detection method and device and electronic equipment | |
| CN111027450A (en) | Bank card information identification method and device, computer equipment and storage medium | |
| US11301669B2 (en) | Face recognition system and method for enhancing face recognition | |
| US20150339523A1 (en) | Image processing apparatus, image processing method, and storage medium | |
| CN110047513B (en) | Video monitoring method and device, electronic equipment and storage medium | |
| CN108734720A (en) | Detector for moving object, its control method and computer readable storage medium | |
| CN109255797B (en) | Image processing device and method, and electronic equipment | |
| CN109791774B (en) | Recording medium, sound evaluation method, and sound evaluation device | |
| CN109643455B (en) | Camera calibration method and terminal | |
| CN109934789A (en) | Image de-noising method, device and electronic equipment | |
| CN109241907A (en) | Mask method, device and electronic equipment | |
| CN106506982A (en) | A kind of method for obtaining photometric parameter, device and terminal unit | |
| CN106886796B (en) | Icon position identification method and device and terminal equipment | |
| CN106485246B (en) | Character identifying method and device | |
| JP2008299834A (en) | Photographic subject tracking program and photographic subject tracking device | |
| CN108426521A (en) | A kind of quality determining method and device of component | |
| CN111046747A (en) | Crowd counting model training method, crowd counting method, device and server | |
| CN106372657B (en) | Method and device for correcting motion data deviation based on image recognition | |
| JP7619474B2 (en) | Class boundary detection device, control method, and program | |
| JP2020113155A5 (en) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |