CN112101273B - Data preprocessing method based on 2D framework - Google Patents
Data preprocessing method based on 2D framework Download PDFInfo
- Publication number
- CN112101273B CN112101273B CN202011010439.4A CN202011010439A CN112101273B CN 112101273 B CN112101273 B CN 112101273B CN 202011010439 A CN202011010439 A CN 202011010439A CN 112101273 B CN112101273 B CN 112101273B
- Authority
- CN
- China
- Prior art keywords
- joint
- time
- image
- bone length
- 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 23
- 238000007781 pre-processing Methods 0.000 title claims abstract description 15
- 230000002146 bilateral effect Effects 0.000 claims abstract description 7
- 230000001133 acceleration Effects 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 210000000988 bone and bone Anatomy 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 2
- 238000013506 data mapping Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a data preprocessing method based on a 2D skeleton, which screens skeleton data according to human body characteristics and mainly comprises the steps of 1) filtering and detecting inaccurate joint points by using skeleton length according to the bilateral symmetry characteristics of a human body; 2) and filtering and detecting inaccurate joint points by using frame difference according to the characteristic that the human body acceleration has an upper limit. By the preprocessing method, the reliability of the whole skeleton data can be improved.
Description
Technical Field
The invention relates to the technical field of data processing of 2D frameworks, in particular to a data preprocessing method based on a 2D framework.
Background
With the development of economy, cameras are increasingly popular, and are not only used for road monitoring, but also used for monitoring at home or in schools. Human action recognition exposes the corners in the fields of monitoring and the like, and in addition to utilizing traditional RGB image data as input data, the appearance of depth cameras and human posture estimation algorithms provides another form of input data, namely skeleton data. For example, although the human body posture estimation method such as openpos can provide reliable skeleton data, there are some cases where the detection point is inaccurate.
In response to this need, we propose to use human body properties to filter out detected inaccurate joint points to improve the overall confidence of the data.
Aiming at data preprocessing, a plurality of schemes are provided in the academic circles at home and abroad. The technical scheme which is closer to the invention comprises the following steps: the invention patent (application number: 201911268767.1, name: a general flow method and system for data preprocessing) describes a method for processing data by determining a data calculation mode according to a data mapping relation; the invention patent (application number: 201911348312.0, name: data preprocessing method, apparatus, computer device, and storage medium) describes a method for replacing missing values with historical data averages for weather data. The prior art has no preprocessing method aiming at the skeleton data and does not fully utilize the characteristics of the human body.
In summary, the current data preprocessing method based on the 2D skeleton has the following disadvantages: 1) there is no pretreatment method for the scaffold; 2) the characteristics of the human body are not fully utilized.
Disclosure of Invention
Aiming at the defects of the current data preprocessing method based on the 2D framework, the invention provides a data preprocessing method based on the 2D framework.
The technical scheme of the invention is as follows:
a data preprocessing method based on a 2D framework is characterized by comprising the following steps:
step 1: the known skeleton Data is Data ═ vi|i=1,2,…,N},vi={(xit,yit) 1,2, …, T, joint symmetry Map<vl,vr>|l=1,2,…,N,r=1,2,…,N,vlAnd vrIs a pair of joints representing bilateral symmetry, and the inherent joint relationship E ═ arch pitch<vi,vj>1,2, …, N, j 1,2, …, N and i ≠ j and joint viAnd vjThere is a physical bone connection between }, vjThe j-th joint is shown as being,<vi,vj>denotes the ith joint viAnd j-th joint vjThe edge on the space (x) existing between themit,yit) Denotes the ith joint viCoordinates in the image collected at the T-th moment, wherein T represents the number of image sequences, and N represents the total number of joints;
step 2: the method for filtering and detecting inaccurate joint points by using the characteristics of unchanged length and bilateral symmetry of human bones comprises the following specific steps:
step 2.1: for the<vi,vj>E, calculating the bone length B by using the formula (1)it;
Step 2.2: calculating the standard deviation BS of the bone lengthi;
BSi=σ({Bit|t=1,2,…,T}) (2)
In the formula, σ (·) represents a standard deviation calculation;
step 2.3: for the<vl,vr>E.g. Map, if BSl<BSrCalculating vlAverage bone length of, wherein BSlIs a joint vlStandard deviation of bone length, BSrIs a joint vrStandard deviation of bone length of (a);
BAl=mean({Blt|t=1,2,…,T}) (3)
where mean (-) represents the mean calculation, BltRepresents a joint vlBone length at time t;
step 2.4: if B is presentrt<αmin*BAlOr Brt>αmax*BAlThen x is setrt=0,yrt0, wherein αminAnd alphamaxRespectively represent upper and lower threshold values, BrtIs a joint vrBone length at time t, xrtIs a joint vrAbscissa value, y, in the image at time trtIs a joint vrOrdinate values in the image at time t;
step 2.5: for the<vl,vr>E.g. Map, if BSr<BSlCalculating vrAverage bone length of (d);
BAr=mean({Brt|t=1,2,…,T}) (4)
in the formula, mean (-) represents the mean calculation;
step 2.7: if B is presentlt<αmin*BArOr Blt>αmax*BArThen x is setlt=0,ylt=0,xltIs a joint vlAbscissa value, y, in the image at time tltIs a joint vlOrdinate values in the image at time t;
and step 3: the method filters points with inaccurate detection by utilizing the characteristic that the human motion acceleration has an upper limit, so the frame difference cannot be suddenly increased, and comprises the following specific steps:
step 3.1: calculating the frame difference M using equation (5)it:
Step 3.2: if M isit>β*Mi(t-1)Then x is setit=0,yitWhere β is a threshold coefficient, Mi(t-1)Is a joint viFrame difference, x, at time t-1itIs a joint viAbscissa value, y, in the image at time titIs a joint viOrdinate values in the image at time t.
The invention has the advantages that: aiming at the 2D skeleton data, the data is preprocessed by fully utilizing the human body characteristics. Obviously wrong joint points in the joint point detection result are removed according to the left-right symmetry of the human body and the characteristic that the acceleration has the upper limit, so that the overall reliability of the data is improved, and the accuracy of motion recognition is finally improved.
Detailed Description
The present invention will be further described with reference to the following examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
A data preprocessing method based on a 2D framework comprises the following specific steps:
step 1: the known skeleton Data is Data ═ vi|i=1,2,…,N},vi={(xit,yit) 1,2, …, T, joint symmetry Map<vl,vr>|l=1,2,…,N,r=1,2,…,N,vlAnd vrIs a pair of joints representing bilateral symmetry, and the inherent joint relationship E ═ arch pitch<vi,vj>1,2, …, N, j 1,2, …, N and i ≠ j and joint viAnd vjThere is a physical bone connection between }, vjThe j-th joint is shown as being,<vi,vj>denotes the ith joint viAnd j-th joint vjThe edge on the space (x) existing between themit,yit) Denotes the ith joint viCoordinates in the image collected at the T-th moment, wherein T represents the number of image sequences, and N represents the total number of joints;
step 2: the method for filtering and detecting inaccurate joint points by using the characteristics of unchanged length and bilateral symmetry of human bones comprises the following specific steps:
step 2.1: for the<vi,vj>E, calculating the bone length B by using the formula (1)it;
Step 2.2: calculating the standard deviation BS of the bone lengthi;
BSi=σ({Bit|t=1,2,…,T}) (2)
In the formula, σ (·) represents a standard deviation calculation;
step 2.3: for the<vl,vr>E.g. Map, if BSl<BSrCalculating vlAverage bone length of, wherein BSlIs a joint vlStandard deviation of bone length, BSrIs a joint vrStandard deviation of bone length of (a);
BAl=mean({Blt|t=1,2,…,T}) (3)
where mean (-) represents the mean calculation, BltRepresents a joint vlBone length at time t;
step 2.4: if B is presentrt<αmin*BAlOr Brt>αmax*BAlThen x is setrt=0,yrt0, wherein αminAnd alphamaxRespectively represent upper and lower threshold values, BrtIs a joint vrBone length at time t, xrtIs a joint vrAbscissa value, y, in the image at time trtIs a joint vrOrdinate values in the image at time t;
in the present embodiment, αmin=0.4,αmax=1.6;
Step 2.5: for the<vl,vr>E.g. Map, if BSr<BSlCalculating vrAverage bone length of (d);
BAr=mean({Brt|t=1,2,…,T}) (4)
in the formula, mean (-) represents the mean calculation;
step 2.7: if B is presentlt<αmin*BArOr Blt>αmax*BArThen x is setlt=0,ylt=0,xltIs a joint vlAbscissa value, y, in the image at time tltIs a joint vlOrdinate values in the image at time t; and step 3: the method filters points with inaccurate detection by utilizing the characteristic that the human motion acceleration has an upper limit, so the frame difference cannot be suddenly increased, and comprises the following specific steps:
step 3.1: calculating the frame difference M using equation (5)it:
Step 3.2: if M isit>β*Mi(t-1)Then x is setit=0,yitWhere β is a threshold coefficient, Mi(t-1)Is a joint viFrame difference, x, at time t-1itIs a joint viAbscissa value, y, in the image at time titIs a joint viOrdinate values in the image at time t;
in the present embodiment, β ═ 5.
Claims (1)
1. A data preprocessing method based on a 2D framework comprises the following technical scheme:
step 1: the known skeleton Data is Data ═ vi|i=1,2,…,N},vi={(xit,yit) 1,2, …, T, joint symmetry Map<vl,vr>|l=1,2,…,N,r=1,2,…,N,vlAnd vrIs a pair of joints representing bilateral symmetry, and the inherent joint relationship E ═ arch pitch<vi,vj>|i=1,2,…,N,j=1,2, …, N and i ≠ j and joint viAnd vjThere is a physical bone connection between }, vjThe j-th joint is shown as being,<vi,vj>denotes the ith joint viAnd j-th joint vjThe edge on the space (x) existing between themit,yit) Denotes the ith joint viCoordinates in the image collected at the T-th moment, wherein T represents the number of image sequences, and N represents the total number of joints;
step 2: the method for filtering and detecting inaccurate joint points by using the characteristics of unchanged length and bilateral symmetry of human bones comprises the following specific steps:
step 2.1: for the<vi,vj>E, calculating the bone length B by using the formula (1)it;
Step 2.2: calculating the standard deviation BS of the bone lengthi;
BSi=σ({Bit|t=1,2,…,T}) (2)
In the formula, σ (·) represents a standard deviation calculation;
step 2.3: for the<vl,vr>E.g. Map, if BSl<BSrCalculating vlAverage bone length of, wherein BSlIs a joint vlStandard deviation of bone length, BSrIs a joint vrStandard deviation of bone length of (a);
BAl=mean({Blt|t=1,2,…,T}) (3)
where mean (-) represents the mean calculation, BltRepresents a joint vlBone length at time t;
step 2.4: if B is presentrt<αmin*BAlOr Brt>αmax*BAlThen x is setrt=0,yrt0, wherein αminAnd alphamaxRespectively represent upper and lower threshold values, BrtIs a joint vrBone length at time t, xrtIs a joint vrAbscissa value, y, in the image at time trtIs a joint vrOrdinate values in the image at time t;
step 2.5: for the<vl,vr>E.g. Map, if BSr<BSlCalculating vrAverage bone length of (d);
BAr=mean({Brt|t=1,2,…,T}) (4)
in the formula, mean (-) represents the mean calculation;
step 2.7: if B is presentlt<αmin*BArOr Blt>αmax*BArThen x is setlt=0,ylt=0,xltIs a joint vlAbscissa value, y, in the image at time tltIs a joint vlOrdinate values in the image at time t;
and step 3: the method filters points with inaccurate detection by utilizing the characteristic that the human motion acceleration has an upper limit, so the frame difference cannot be suddenly increased, and comprises the following specific steps:
step 3.1: calculating the frame difference M using equation (5)it:
Step 3.2: if M isit>β*Mi(t-1)Then x is setit=0,yitWhere β is a threshold coefficient, Mi(t-1)Is a joint viFrame difference, x, at time t-1itIs a joint viAbscissa value, y, in the image at time titIs a joint viOrdinate values in the image at time t.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011010439.4A CN112101273B (en) | 2020-09-23 | 2020-09-23 | Data preprocessing method based on 2D framework |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011010439.4A CN112101273B (en) | 2020-09-23 | 2020-09-23 | Data preprocessing method based on 2D framework |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112101273A CN112101273A (en) | 2020-12-18 |
CN112101273B true CN112101273B (en) | 2022-04-29 |
Family
ID=73755972
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011010439.4A Active CN112101273B (en) | 2020-09-23 | 2020-09-23 | Data preprocessing method based on 2D framework |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112101273B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105930767A (en) * | 2016-04-06 | 2016-09-07 | 南京华捷艾米软件科技有限公司 | Human body skeleton-based action recognition method |
CN107301370A (en) * | 2017-05-08 | 2017-10-27 | 上海大学 | A kind of body action identification method based on Kinect three-dimensional framework models |
CN111652124A (en) * | 2020-06-02 | 2020-09-11 | 电子科技大学 | Construction method of human behavior recognition model based on graph convolution network |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2721008A1 (en) * | 2008-04-11 | 2009-10-15 | Terraspark Geosciences, Llc | Visulation of geologic features using data representations thereof |
-
2020
- 2020-09-23 CN CN202011010439.4A patent/CN112101273B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105930767A (en) * | 2016-04-06 | 2016-09-07 | 南京华捷艾米软件科技有限公司 | Human body skeleton-based action recognition method |
CN107301370A (en) * | 2017-05-08 | 2017-10-27 | 上海大学 | A kind of body action identification method based on Kinect three-dimensional framework models |
CN111652124A (en) * | 2020-06-02 | 2020-09-11 | 电子科技大学 | Construction method of human behavior recognition model based on graph convolution network |
Also Published As
Publication number | Publication date |
---|---|
CN112101273A (en) | 2020-12-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109949341B (en) | Pedestrian target tracking method based on human skeleton structural features | |
CN109285179A (en) | A kind of motion target tracking method based on multi-feature fusion | |
CN102075686B (en) | Robust real-time on-line camera tracking method | |
CN104408460A (en) | A lane line detecting and tracking and detecting method | |
CN111368717B (en) | Line-of-sight determination method, line-of-sight determination device, electronic apparatus, and computer-readable storage medium | |
CN106056053A (en) | Human posture recognition method based on skeleton feature point extraction | |
CN111931733B (en) | Human body posture detection method based on depth camera | |
CN107248174A (en) | A kind of method for tracking target based on TLD algorithms | |
CN111462191A (en) | Non-local filter unsupervised optical flow estimation method based on deep learning | |
CN107066963B (en) | A kind of adaptive people counting method | |
CN105374049B (en) | Multi-corner point tracking method and device based on sparse optical flow method | |
CN109887029A (en) | A kind of monocular vision mileage measurement method based on color of image feature | |
WO2010060287A1 (en) | An obstacle detecting method based on monocular vision and the device thereof | |
CN115116132B (en) | Human behavior analysis method for depth perception in Internet of things edge service environment | |
CN113744315B (en) | Semi-direct vision odometer based on binocular vision | |
CN116778290A (en) | Radar vision data association method based on deep learning algorithm | |
CN112101273B (en) | Data preprocessing method based on 2D framework | |
WO2014172875A1 (en) | Moving object detection | |
CN112926496B (en) | Neural network for predicting image definition, training method and prediction method | |
CN112330675B (en) | Traffic road image atmospheric visibility detection method based on AOD-Net | |
CN117315547A (en) | Visual SLAM method for solving large duty ratio of dynamic object | |
CN110766093A (en) | Video target re-identification method based on multi-frame feature fusion | |
CN110781712A (en) | Human head space positioning method based on human face detection and recognition | |
JP2010032415A (en) | Infrared image tracking apparatus | |
CN115049552A (en) | Infrared small target detection method based on structure tensor weighted local contrast measurement |
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 | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Data Preprocessing Method Based on 2D Skeleton Effective date of registration: 20231127 Granted publication date: 20220429 Pledgee: Zhejiang Lishui Liandu Rural Commercial Bank Co.,Ltd. Pledgor: ZHEJIANG HAOTENG ELECTRON TECHNOLOGY CO.,LTD. Registration number: Y2023980067610 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right |