CN115050095A - Human body posture prediction method based on Gaussian process regression and progressive filtering - Google Patents

Human body posture prediction method based on Gaussian process regression and progressive filtering Download PDF

Info

Publication number
CN115050095A
CN115050095A CN202210628615.3A CN202210628615A CN115050095A CN 115050095 A CN115050095 A CN 115050095A CN 202210628615 A CN202210628615 A CN 202210628615A CN 115050095 A CN115050095 A CN 115050095A
Authority
CN
China
Prior art keywords
human body
position state
joint point
gaussian process
process regression
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
CN202210628615.3A
Other languages
Chinese (zh)
Inventor
徐杰威
毛城
杨旭升
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.)
Zhejiang University of Technology ZJUT
Original Assignee
Zhejiang University of Technology ZJUT
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 Zhejiang University of Technology ZJUT filed Critical Zhejiang University of Technology ZJUT
Priority to CN202210628615.3A priority Critical patent/CN115050095A/en
Publication of CN115050095A publication Critical patent/CN115050095A/en
Pending legal-status Critical Current

Links

Images

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
    • 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
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the field of human body posture prediction, in particular to a human body posture prediction method based on Gaussian process regression and progressive filtering, wherein a state transition model is established by utilizing the Gaussian process regression method, and the reliability of measured information is checked by using a predicted value so as to improve the accuracy of prior information; estimating the position state based on a progressive filtering method to achieve faster and more accurate performance; and finally, predicting the position states of all the joint points of the human body. The invention has the beneficial effects that: compared with the existing human body posture prediction, the method is based on Gaussian process regression and progressive filtering, the accuracy of state prediction is effectively improved, and the robustness of adverse factors such as errors of the sensor is improved.

Description

Human body posture prediction method based on Gaussian process regression and progressive filtering
Technical Field
The invention relates to the field of human body posture prediction, in particular to a human body posture prediction method based on Gaussian process regression and progressive filtering.
Background
The human body posture prediction has important application value in the fields of human-computer interaction, behavior recognition, video monitoring, sports games and the like. In particular, with the development of artificial intelligence, 3D vision and other technologies, human posture prediction technology is applied in the fields of industry, agriculture, sports and the like, for example, for collecting athlete motion information, and combining human physiology, physics and artificial intelligence methods, thereby forming intelligent human motion prediction.
Due to the complexity and randomness of human motion, it is difficult for conventional modeling methods to accurately describe the motion of the human body. With the development of AI technologies such as deep learning, a plurality of effective methods such as a recurrent neural network and Gaussian process regression are provided for human motion prediction. On the other hand, the visual sensor is a sensor commonly used in the field of human body posture prediction at present, however, the visual sensor is easily affected by factors such as ambient light, shading and the like, and uncertainty of visual human body posture detection is caused. In turn, it is difficult for the conventional kalman filtering method to obtain a satisfactory noise suppression effect. Because the human body posture prediction model, the visual posture detection and other aspects have uncertainty, the human body posture prediction precision is greatly reduced. At present, no technology exists for robustly and accurately solving the problem of human body posture prediction in complex scenes and motion.
For example, chinese patent CN113569627A, published 2021, 10 months and 29 days, discloses a human body posture prediction model training method, which comprises: acquiring a labeled training set and an unlabeled training set, wherein the labeled training set comprises a plurality of first human body images containing labeled data, and the labeled data is used for representing real posture information in the first human body images; inputting the first human body image into a generator in a human body posture prediction model to obtain a corresponding first human body posture prediction result, and calculating a first loss value of the generator according to the labeling data and the first human body posture prediction result; inputting the second human body image into a generator to obtain a corresponding second human body posture prediction result; calculating a second loss value corresponding to the discriminator in the human body posture prediction model according to the first human body image, the annotation data, the second human body image and the second human body posture prediction result; and optimizing the generator and the discriminator according to the first loss value and the second loss value to obtain a human body posture prediction model. According to the technical scheme, the human body posture is predicted according to the image, a large number of human body image labeling samples need to be prepared in advance, the sample labeling is time-consuming and labor-consuming, and the accuracy is limited.
Disclosure of Invention
In order to overcome the defects of uncertainty of measurement information caused by illumination sensitive change of a sensor and the like, difficulty in modeling of human body movement and the like, the invention provides a human body posture prediction method based on Gaussian process regression and progressive filtering.
The technical scheme adopted by the invention is as follows: a human body posture prediction method based on Gaussian process regression and progressive filtering comprises the following steps:
step 1) using the collected three-dimensional position states and corresponding postures of each human body joint point as a training data set, and respectively establishing a position state transfer model of each human body joint point by utilizing Gaussian process regression;
step 2) determining the initial position state of the jth personal body joint point
Figure RE-DEST_PATH_IMAGE001
And initial covariance
Figure RE-RE-DEST_PATH_IMAGE002
，
Figure RE-DEST_PATH_IMAGE003
，
Figure RE-RE-DEST_PATH_IMAGE004
The number of the monitored human body joint points is obtained;
step 3) establishing an observation model to obtain a measurement value of the sensor at the moment k to the jth personal body joint point
Figure RE-DEST_PATH_IMAGE005
And zero mean and covariance of
Figure RE-RE-DEST_PATH_IMAGE006
Measurement noise of
Figure RE-DEST_PATH_IMAGE007
；
Step 4) reading the measurement information of the sensor to obtain the position state of the j-th personal body joint point at the k moment
Figure RE-RE-DEST_PATH_IMAGE008
Measured value of
Figure RE-216519DEST_PATH_IMAGE005
Based on the measured value of the sensor read
Figure RE-133659DEST_PATH_IMAGE005
And the predicted value of the position state output by the observation model is the prior estimated position state, and the measured value at the moment k is judged
Figure RE-975713DEST_PATH_IMAGE005
If the position is not in the confidence interval of the predicted value, the step 5) is carried out, and if the position is not in the confidence interval, the measured value is replaced by the priori estimated position state
Figure RE-370922DEST_PATH_IMAGE005
Re-executing step 4);
step 5) progressive introduction of measurement values
Figure RE-185295DEST_PATH_IMAGE005
Correcting the current position state to obtain the position state
Figure RE-73004DEST_PATH_IMAGE008
Estimated value and covariance of
Figure RE-DEST_PATH_IMAGE009
Judging whether the over-estimation condition occurs or not, if the over-estimation condition does not occur, continuing to correct, otherwise, skippingStep 5) is carried out;
step 6) using the position state transition model to obtain the position state of the j-th personal body joint point at the current moment according to the step 5)
Figure RE-340037DEST_PATH_IMAGE008
And its covariance
Figure RE-538937DEST_PATH_IMAGE009
Predicting the position state of the jth individual's body joint point at the next time
Figure RE-RE-DEST_PATH_IMAGE010
And its covariance
Figure RE-DEST_PATH_IMAGE011
；
And 7) repeating the steps 4) to 6) for each human body joint point to finish posture prediction.
Preferably, in step 1), the training data set is collected
Figure RE-RE-DEST_PATH_IMAGE012
In which
Figure RE-DEST_PATH_IMAGE013
In order to input a set of vectors,
Figure RE-RE-DEST_PATH_IMAGE014
in order to output the set of vectors,
Figure RE-DEST_PATH_IMAGE015
indicating the amount of data, and the new input is recorded as the position state at the k-th time
Figure RE-RE-DEST_PATH_IMAGE016
Selecting a predetermined kernel function
Figure RE-DEST_PATH_IMAGE017
Using Gaussian process regression to establish
Figure RE-RE-DEST_PATH_IMAGE018
The position state transition model of each joint point of the human body is as follows:
Figure RE-RE-DEST_PATH_IMAGE020
wherein the content of the first and second substances,
Figure RE-DEST_PATH_IMAGE021
representing the state transition function, k =1,2, … being a discrete time sequence,
Figure RE-RE-DEST_PATH_IMAGE022
is the position state of the human body joint point,
Figure RE-DEST_PATH_IMAGE023
、
Figure RE-RE-DEST_PATH_IMAGE024
and
Figure RE-DEST_PATH_IMAGE025
coordinate values of the human body joint point at the moment of k +1 on an x axis, a y axis and a z axis respectively,
Figure RE-RE-DEST_PATH_IMAGE026
、
Figure RE-DEST_PATH_IMAGE027
and
Figure RE-RE-DEST_PATH_IMAGE028
the speeds of the human body joint points at the moment k on the x axis, the y axis and the z axis respectively,
Figure RE-DEST_PATH_IMAGE029
zero mean and covariance of
Figure RE-RE-DEST_PATH_IMAGE030
Gaussian noise.
Preferably, said bits are used in step 6)Setting state transition model for predicting position state of each joint point of human body at next moment
Figure RE-581717DEST_PATH_IMAGE010
And its variance
Figure RE-DEST_PATH_IMAGE031
The method comprises the following steps:
Figure RE-RE-DEST_PATH_IMAGE032
and
Figure RE-DEST_PATH_IMAGE033
。
preferably, in step 3), the observation model is established as follows:
Figure RE-DEST_PATH_IMAGE035
wherein the content of the first and second substances,
Figure RE-RE-DEST_PATH_IMAGE036
，
Figure RE-696785DEST_PATH_IMAGE005
the measurement value of the sensor for the joint point j at the time k is shown.
Preferably, in step 5), the measurement values are introduced progressively
Figure RE-451114DEST_PATH_IMAGE005
The method for correcting the current position state comprises the following steps:
step 51) setting iteration parameters
Figure RE-DEST_PATH_IMAGE037
Setting the initial value to be 0, setting the maximum value of the gradual lead-in measurement updating step number to be N, and setting the iteration step length
Figure RE-RE-DEST_PATH_IMAGE038
Iteration parameter
Figure RE-DEST_PATH_IMAGE039
，
Figure RE-RE-DEST_PATH_IMAGE040
Representing the number of iterations;
step 52) calculating
Figure RE-DEST_PATH_IMAGE041
At the time of the second iteration, the position state measurement value of the j-th human joint point at the k moment
Figure RE-RE-DEST_PATH_IMAGE042
Predicted value, covariance of
Figure RE-DEST_PATH_IMAGE043
And covariance
Figure RE-RE-DEST_PATH_IMAGE044
：
Figure RE-RE-DEST_PATH_IMAGE046
Figure RE-RE-DEST_PATH_IMAGE048
Figure RE-RE-DEST_PATH_IMAGE050
Wherein the content of the first and second substances,
Figure RE-DEST_PATH_IMAGE051
and
Figure RE-RE-DEST_PATH_IMAGE052
respectively corresponding sigma points and weight values;
step 53) measuring value of position state of j-th individual body joint point at time k
Figure RE-437394DEST_PATH_IMAGE042
In the first place
Figure RE-23096DEST_PATH_IMAGE041
Secondary filter gain
Figure RE-DEST_PATH_IMAGE053
：
Figure RE-RE-DEST_PATH_IMAGE054
；
Step 54) calculating the position state of the jth personal body joint point at the time k
Figure RE-452940DEST_PATH_IMAGE008
And its covariance
Figure RE-756883DEST_PATH_IMAGE009
In the first place
Figure RE-32006DEST_PATH_IMAGE041
The value of the sub-iteration:
Figure RE-DEST_PATH_IMAGE055
，
Figure RE-RE-DEST_PATH_IMAGE056
；
step 55) judging whether the over-estimation condition occurs or not, if not, judging that the over-estimation condition occurs
Figure RE-737794DEST_PATH_IMAGE040
After adding 1, the correction is continued from step 52), otherwise, step 6) is entered.
Preferably, in step 55), the method for determining whether the over-estimation condition occurs includes:
order to
Figure RE-DEST_PATH_IMAGE057
If, if
Figure RE-RE-DEST_PATH_IMAGE058
And is provided with
Figure RE-DEST_PATH_IMAGE059
If not, judging that the overestimation condition does not occur, otherwise, judging that the overestimation condition occurs.
Preferably, the monitored joints of the human body are one or more of a nodding joint, a thoracic joint, a shoulder joint, an elbow joint, a wrist joint, a sacral joint, a hip joint, a knee joint, and an ankle joint.
Preferably, the position state and the measurement value both refer to three-dimensional coordinate values in a rectangular coordinate system.
Preferably, the Gaussian noise in step 2)
Figure RE-RE-DEST_PATH_IMAGE060
Is zero mean and covariance of
Figure RE-DEST_PATH_IMAGE061
The noise of the gaussian noise of (a),
preferably, in step 4), the predicted position state of the observation model is a position state of the joint point j predicted by the observation model created by the gaussian process regression method
Figure RE-RE-DEST_PATH_IMAGE062
And its covariance
Figure RE-DEST_PATH_IMAGE063
。
The invention has the beneficial effects that: compared with the existing human body posture prediction, the method is based on Gaussian process regression and progressive filtering, the accuracy of state prediction is effectively improved, and the robustness of adverse factors such as errors of the sensor is improved.
Other features and advantages of the present invention will be disclosed in more detail in the following detailed description of the invention and the accompanying drawings.
Drawings
The invention is further described below with reference to the accompanying drawings:
fig. 1 is a schematic flow chart of a human body posture prediction method according to an embodiment of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention are explained and illustrated below with reference to the drawings of the embodiments of the present invention, but the following embodiments are only preferred embodiments of the present invention, and not all embodiments. Based on the embodiments in the implementation, other embodiments obtained by those skilled in the art without any creative effort belong to the protection scope of the present invention.
In the following description, the appearances of the indicating orientation or positional relationship such as the terms "inner", "outer", "upper", "lower", "left", "right", etc. are only for convenience in describing the embodiments and for simplicity in description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and are not to be construed as limiting the present invention.
Example (b):
a method for predicting a human body posture based on gaussian process regression and progressive filtering, please refer to fig. 1, which includes:
step 1) using the collected three-dimensional position states and corresponding postures of each human body joint point as a training data set, and respectively establishing a position state transfer model of each human body joint point by utilizing Gaussian process regression;
step 2) determining the initial position state of the jth personal body joint point
Figure RE-200524DEST_PATH_IMAGE001
And initial covariance
Figure RE-929446DEST_PATH_IMAGE002
，
Figure RE-70577DEST_PATH_IMAGE003
，
Figure RE-568554DEST_PATH_IMAGE004
For the number of joint points of the body being monitored, Gaussian noise
Figure RE-340201DEST_PATH_IMAGE060
Is zero mean and covariance of
Figure RE-290840DEST_PATH_IMAGE061
Gaussian noise of (2);
step 3) establishing an observation model to obtain a measurement value of the sensor at the moment k to the jth personal body joint point
Figure RE-235662DEST_PATH_IMAGE005
And zero mean and covariance of
Figure RE-588146DEST_PATH_IMAGE006
Of (2) measuring noise
Figure RE-530694DEST_PATH_IMAGE007
；
Step 4) reading the measurement information of the sensor to obtain the position state of the j-th personal body joint point at the time k
Figure RE-968629DEST_PATH_IMAGE008
Measured value of
Figure RE-451563DEST_PATH_IMAGE005
Based on the measured value of the sensor read
Figure RE-924132DEST_PATH_IMAGE005
And a predicted value of the position state output by the observation model, wherein the predicted value of the position state is the prior estimated position state, and the measured value at the moment k is judged
Figure RE-37582DEST_PATH_IMAGE005
Whether the estimated position is within the confidence interval of the predicted value, if the estimated position is within the confidence interval, the step 5) is carried out, and if the estimated position is not within the confidence interval, the measured position is replaced by the priori estimated position stateValue of
Figure RE-25129DEST_PATH_IMAGE005
Re-executing step 4);
step 5) progressive introduction of measurement values
Figure RE-249437DEST_PATH_IMAGE005
Correcting the current position state to obtain the position state
Figure RE-310934DEST_PATH_IMAGE008
Estimated value and covariance of
Figure RE-595285DEST_PATH_IMAGE009
Judging whether an over-estimation condition occurs or not, if not, continuing to correct, otherwise, jumping out of the step 5);
step 6) using a position state transition model to obtain the position state of the jth personal body joint point at the current moment according to the step 5)
Figure RE-70129DEST_PATH_IMAGE008
And its covariance
Figure RE-98128DEST_PATH_IMAGE009
Predicting the position state of the jth individual's body joint point at the next time
Figure RE-279710DEST_PATH_IMAGE010
And its covariance
Figure RE-531700DEST_PATH_IMAGE011
；
And 7) repeating the steps 4) to 6) for each human body joint point to finish posture prediction.
In this embodiment, one or more of the human joints being monitored are nodding, thoracic, shoulder, elbow, wrist, sacral, hip, knee, and ankle. The position state and the measurement value both refer to three-dimensional coordinate values in a rectangular coordinate system. The embodiment predicts the human body posture not the posture which the human body will but is not made at a certain moment in the future, but predicts the correct human body posture according to the measurement value of the included noise of the posture which the human body has made. In which the human body posture is to the position and posture of the human body part, not just the posture of the human body. Human body gestures play an important role in the fields of human-computer interaction, behavior recognition, video surveillance, sports games and the like.
In step 1), a training data set has been collected
Figure RE-431523DEST_PATH_IMAGE012
Wherein
Figure RE-997633DEST_PATH_IMAGE013
In order to input a set of vectors,
Figure RE-299302DEST_PATH_IMAGE014
in order to output the set of vectors,
Figure RE-742701DEST_PATH_IMAGE015
indicating the amount of data, and the new input is recorded as the position state at the k-th time
Figure RE-129820DEST_PATH_IMAGE016
Selecting a predetermined kernel function
Figure RE-499621DEST_PATH_IMAGE017
Using Gaussian process regression to establish
Figure RE-390217DEST_PATH_IMAGE018
The position state transition model of each joint point of the human body is as follows:
Figure RE-RE-DEST_PATH_IMAGE064
wherein, the first and the second end of the pipe are connected with each other,
Figure RE-249588DEST_PATH_IMAGE021
indicating a state transitionThe function, k =1,2, … is a discrete time series,
Figure RE-858424DEST_PATH_IMAGE022
is the position state of the human body joint point,
Figure RE-94234DEST_PATH_IMAGE023
、
Figure RE-104915DEST_PATH_IMAGE024
and
Figure RE-72871DEST_PATH_IMAGE025
coordinate values of the human body joint point at the moment of k +1 on an x axis, a y axis and a z axis respectively,
Figure RE-169003DEST_PATH_IMAGE026
、
Figure RE-942924DEST_PATH_IMAGE027
and
Figure RE-808112DEST_PATH_IMAGE028
the speeds of the human body joint points at the moment k on the x axis, the y axis and the z axis respectively,
Figure RE-946969DEST_PATH_IMAGE029
zero mean and covariance of
Figure RE-592714DEST_PATH_IMAGE030
Gaussian noise.
In step 3), the established observation model is as follows:
Figure RE-842430DEST_PATH_IMAGE035
wherein the content of the first and second substances,
Figure RE-827703DEST_PATH_IMAGE036
，
Figure RE-137462DEST_PATH_IMAGE005
the measurement value of the joint point j by the sensor at the time k is shown.
In step 5), the measurement values are introduced progressively
Figure RE-270503DEST_PATH_IMAGE005
The method for correcting the current position state comprises the following steps:
step 51) setting iteration parameters
Figure RE-323910DEST_PATH_IMAGE037
Setting the initial value to be 0, setting the maximum value of the gradual lead-in measurement updating step number to be N, and setting the iteration step length
Figure RE-163690DEST_PATH_IMAGE038
Iteration parameter
Figure RE-644349DEST_PATH_IMAGE039
，
Figure RE-999107DEST_PATH_IMAGE040
Representing the number of iterations;
step 52) calculating the position state measurement value of the jth human body joint point at the k moment in the (m + 1) th iteration
Figure RE-856205DEST_PATH_IMAGE042
Predicted value, covariance of
Figure RE-550492DEST_PATH_IMAGE043
And covariance
Figure RE-264370DEST_PATH_IMAGE044
：
Figure RE-309686DEST_PATH_IMAGE046
Figure RE-DEST_PATH_IMAGE065
Figure RE-RE-DEST_PATH_IMAGE066
Wherein the content of the first and second substances,
Figure RE-770142DEST_PATH_IMAGE051
and
Figure RE-318935DEST_PATH_IMAGE052
respectively corresponding sigma points and weight values;
step 53) measuring value of position state of j-th individual body joint point at time k
Figure RE-406977DEST_PATH_IMAGE042
In the first place
Figure RE-736327DEST_PATH_IMAGE041
Secondary filter gain
Figure RE-935227DEST_PATH_IMAGE053
：
Figure RE-338526DEST_PATH_IMAGE054
；
Step 54) calculating the position state of the jth personal body joint point at the time k
Figure RE-597469DEST_PATH_IMAGE008
And its covariance
Figure RE-414116DEST_PATH_IMAGE009
In the first place
Figure RE-151128DEST_PATH_IMAGE041
The value of the sub-iteration:
Figure RE-674513DEST_PATH_IMAGE055
，
Figure RE-166674DEST_PATH_IMAGE056
；
step 55) judging whether the over-estimation condition occurs or not, if not, judging that the over-estimation condition occurs
Figure RE-142720DEST_PATH_IMAGE040
After adding 1, the correction is continued from step 52), otherwise, step 6) is entered.
In step 55), the method for judging whether the over-estimation condition occurs comprises the following steps:
order to
Figure RE-683423DEST_PATH_IMAGE057
If, if
Figure RE-326894DEST_PATH_IMAGE058
And is
Figure RE-724377DEST_PATH_IMAGE059
If so, judging that the over-estimation condition does not occur, otherwise, judging that the over-estimation condition occurs.
Step 6), predicting the position state of each joint point of the human body at the next moment by using the position state transition model
Figure RE-453299DEST_PATH_IMAGE010
And its variance
Figure RE-532113DEST_PATH_IMAGE031
The method comprises the following steps:
Figure RE-30091DEST_PATH_IMAGE032
and
Figure RE-598475DEST_PATH_IMAGE033
。
while the invention has been described with reference to specific embodiments thereof, it will be understood by those skilled in the art that the invention is not limited thereto, and may be embodied in many different forms without departing from the spirit and scope of the invention as set forth in the following claims. Any modification which does not depart from the functional and structural principles of the present invention is intended to be included within the scope of the claims.

Claims (10)

1. A human body posture prediction method based on Gaussian process regression and progressive filtering is characterized in that,
the method comprises the following steps:
step 1) using the collected three-dimensional position states and corresponding postures of each human body joint point as a training data set, and respectively establishing a position state transfer model of each human body joint point by utilizing Gaussian process regression;
step 2) determining the initial position state of the jth personal body joint point
Figure DEST_PATH_IMAGE002
And initial covariance
Figure DEST_PATH_IMAGE004
，
Figure DEST_PATH_IMAGE006
，
Figure DEST_PATH_IMAGE008
The number of the monitored human body joint points is obtained;
step 3) establishing an observation model to obtain a measurement value of the sensor at the moment k to the jth personal body joint point
Figure DEST_PATH_IMAGE010
And zero mean and covariance of
Figure DEST_PATH_IMAGE012
Of (2) measuring noise
Figure DEST_PATH_IMAGE014
；
Step 4) reading the measurement information of the sensor to obtain the position state of the j-th personal body joint point at the time k
Figure DEST_PATH_IMAGE016
Measured value of
Figure 357876DEST_PATH_IMAGE010
Based on the read measured values of the sensors
Figure 478279DEST_PATH_IMAGE010
And a predicted value of the position state output by the observation model, wherein the predicted value of the position state is the prior estimated position state, and the measured value at the moment k is judged
Figure 461278DEST_PATH_IMAGE010
If the position is not in the confidence interval of the predicted value, the step 5) is carried out, and if the position is not in the confidence interval, the measured value is replaced by the priori estimated position state
Figure 325329DEST_PATH_IMAGE010
Re-executing step 4);
step 5) progressive introduction of measurement values
Figure 342964DEST_PATH_IMAGE010
Correcting the current position state to obtain the position state
Figure 867224DEST_PATH_IMAGE016
Estimated value and covariance of
Figure DEST_PATH_IMAGE018
Judging whether an over-estimation condition occurs or not, if not, continuing to correct, otherwise, jumping out of the step 5);
step 6) using the position state transition model to obtain the position state of the j-th personal body joint point at the current moment according to the step 5)
Figure DEST_PATH_IMAGE020
And its covariance
Figure DEST_PATH_IMAGE022
Predicting the position state of the jth individual's body joint point at the next time
Figure DEST_PATH_IMAGE024
And its covariance
Figure DEST_PATH_IMAGE026
；
And 7) repeating the steps 4) to 6) for each human body joint point to finish posture prediction.
2. The human body posture prediction method based on Gaussian process regression and progressive filtering according to claim 1,
step 1), collected training data set
Figure DEST_PATH_IMAGE028
Wherein
Figure DEST_PATH_IMAGE030
In order to input a set of vectors,
Figure DEST_PATH_IMAGE032
in order to output the set of vectors,
Figure DEST_PATH_IMAGE034
indicating the amount of data, and the new input is recorded as the position state at the k-th time
Figure DEST_PATH_IMAGE036
Selecting a predetermined kernel function
Figure DEST_PATH_IMAGE038
Using Gaussian process regression to establish
Figure DEST_PATH_IMAGE040
The position state transition model of each joint point of the human body is as follows:
Figure DEST_PATH_IMAGE042
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE044
representing the state transition function, k =1,2, … are discrete time sequences,
Figure DEST_PATH_IMAGE046
is the position state of the human body joint point,
Figure DEST_PATH_IMAGE048
、
Figure DEST_PATH_IMAGE050
and
Figure DEST_PATH_IMAGE052
coordinate values of the human body joint point at the moment of k +1 on an x axis, a y axis and a z axis respectively,
Figure DEST_PATH_IMAGE054
、
Figure DEST_PATH_IMAGE056
and
Figure DEST_PATH_IMAGE058
the speeds of the human body joint points at the moment k on the x axis, the y axis and the z axis respectively,
Figure DEST_PATH_IMAGE060
zero mean and covariance of
Figure DEST_PATH_IMAGE062
Gaussian noise.
3. The human body posture prediction method based on Gaussian process regression and progressive filtering according to claim 2,
predicting the position state of each joint point of the human body at the next moment by using the position state transition model in the step 6)
Figure DEST_PATH_IMAGE064
And variance thereof
Figure DEST_PATH_IMAGE066
The method comprises the following steps:
Figure DEST_PATH_IMAGE068
and
Figure DEST_PATH_IMAGE070
。
4. the human body posture prediction method based on Gaussian process regression and progressive filtering according to any one of claims 1 to 3,
in step 3), the established observation model is as follows:
Figure DEST_PATH_IMAGE072
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE074
，
Figure DEST_PATH_IMAGE076
the measurement value of the joint point j by the sensor at the time k is shown.
5. The human body posture prediction method based on Gaussian process regression and progressive filtering according to any one of claims 1 to 3,
in step 5), the measurement values are introduced progressively
Figure 263087DEST_PATH_IMAGE010
The method for correcting the current position state comprises the following steps:
step 51) setting iteration parameters
Figure DEST_PATH_IMAGE078
Setting the initial value to be 0, setting the maximum value of the gradual lead-in measurement updating step number to be N, and setting the iteration step length
Figure DEST_PATH_IMAGE080
Iteration parameter
Figure DEST_PATH_IMAGE082
，
Figure DEST_PATH_IMAGE084
Representing the number of iterations;
step 52) calculating
Figure DEST_PATH_IMAGE086
At the time of the second iteration, the position state measurement value of the jth individual body joint point at the k moment
Figure DEST_PATH_IMAGE088
Predicted value, covariance of
Figure DEST_PATH_IMAGE090
And covariance
Figure DEST_PATH_IMAGE092
：
Figure DEST_PATH_IMAGE094
Figure DEST_PATH_IMAGE096
Figure DEST_PATH_IMAGE098
Wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE100
and
Figure DEST_PATH_IMAGE102
respectively corresponding sigma points and weight values;
step 53) measuring value of position state of j-th individual body joint point at time k
Figure DEST_PATH_IMAGE104
In the first place
Figure DEST_PATH_IMAGE106
Secondary filter gain
Figure DEST_PATH_IMAGE108
：
Figure DEST_PATH_IMAGE110
；
Step 54) calculating the position state of the j-th personal body joint point at the time k
Figure 374569DEST_PATH_IMAGE016
And its covariance
Figure 512290DEST_PATH_IMAGE018
In the first place
Figure 974495DEST_PATH_IMAGE086
The value of the sub-iteration:
Figure DEST_PATH_IMAGE112
，
Figure DEST_PATH_IMAGE114
；
step 55) judging whether the over-estimation condition occurs or not, if not, judging that the over-estimation condition occurs
Figure 604191DEST_PATH_IMAGE084
After adding 1, the correction is continued from step 52), otherwise, step 6) is entered.
6. The human body posture prediction method based on Gaussian process regression and progressive filtering according to claim 5,
in step 55), the method for determining whether the over-estimation condition occurs comprises the following steps:
order to
Figure DEST_PATH_IMAGE116
If, if
Figure DEST_PATH_IMAGE118
And is
Figure DEST_PATH_IMAGE120
If so, judging that the over-estimation condition does not occur, otherwise, judging that the over-estimation condition occurs.
7. The human body posture prediction method based on Gaussian process regression and progressive filtering according to any one of claims 1 to 3,
one or more of a human joint nod, thoracic, shoulder, elbow, wrist, sacral, hip, knee, and ankle that are monitored.
8. The human body posture prediction method based on Gaussian process regression and progressive filtering according to any one of claims 1 to 3,
and the position state and the measurement value both refer to three-dimensional coordinate values under a rectangular coordinate system.
9. The human body posture prediction method based on Gaussian process regression and progressive filtering according to any one of claims 1 to 3,
gaussian noise in step 2)
Figure DEST_PATH_IMAGE122
Is zero mean and covariance of
Figure DEST_PATH_IMAGE124
Gaussian noise.
10. The human body posture prediction method based on Gaussian process regression and progressive filtering according to any one of claims 1 to 3,
in step 4), the predicted position state of the observation model refers to the position state of the joint point j predicted by the observation model established by the Gaussian process regression method
Figure DEST_PATH_IMAGE126
And its covariance
Figure DEST_PATH_IMAGE128
。
CN202210628615.3A 2022-06-06 2022-06-06 Human body posture prediction method based on Gaussian process regression and progressive filtering Pending CN115050095A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210628615.3A CN115050095A (en) 2022-06-06 2022-06-06 Human body posture prediction method based on Gaussian process regression and progressive filtering

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210628615.3A CN115050095A (en) 2022-06-06 2022-06-06 Human body posture prediction method based on Gaussian process regression and progressive filtering

Publications (1)

Publication Number Publication Date
CN115050095A true CN115050095A (en) 2022-09-13

Family

ID=83159469

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210628615.3A Pending CN115050095A (en) 2022-06-06 2022-06-06 Human body posture prediction method based on Gaussian process regression and progressive filtering

Country Status (1)

Country Link
CN (1) CN115050095A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116627262A (en) * 2023-07-26 2023-08-22 河北大学 VR interactive device control method and system based on data processing

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116627262A (en) * 2023-07-26 2023-08-22 河北大学 VR interactive device control method and system based on data processing
CN116627262B (en) * 2023-07-26 2023-10-13 河北大学 VR interactive device control method and system based on data processing

Similar Documents

Publication Publication Date Title
CN110070074B (en) Method for constructing pedestrian detection model
CN110660083B (en) Multi-target tracking method combined with video scene feature perception
CN109341703B (en) Visual SLAM algorithm adopting CNNs characteristic detection in full period
CN113091738B (en) Mobile robot map construction method based on visual inertial navigation fusion and related equipment
CN108961308B (en) Residual error depth characteristic target tracking method for drift detection
CN111259735B (en) Single-person attitude estimation method based on multi-stage prediction feature enhanced convolutional neural network
CN114676956A (en) Old man's risk early warning system that tumbles based on multidimensional data fusion
Cheng et al. A vision-based robot grasping system
CN114495267A (en) Old people falling risk assessment method based on multi-dimensional data fusion
CN109409418A (en) A kind of winding detection method based on bag of words
CN111462184B (en) Online sparse prototype tracking method based on twin neural network linear representation model
CN109934849A (en) Online multi-object tracking method based on track metric learning
CN115050095A (en) Human body posture prediction method based on Gaussian process regression and progressive filtering
CN109544632B (en) Semantic SLAM object association method based on hierarchical topic model
CN110163112B (en) Examinee posture segmentation and smoothing method
CN112785630A (en) Multi-target track exception handling method and system in microscopic operation
CN116524062A (en) Diffusion model-based 2D human body posture estimation method
Mohedano et al. Camera localization usingtrajectories and maps
CN112036291A (en) Kinematic data model construction method based on motion big data and deep learning
CN112270357A (en) VIO vision system and method
Yuan et al. Robust instruments position estimation using improved kernelized correlation filter for substation patrol robots
CN113743341B (en) Human body posture real-time estimation method based on self-adaptive model
Xie et al. Research on Human Pose Capture Based on the Deep Learning Algorithm
Cui et al. Mobile Big Data Analytics for Human Behavior Recognition in Wireless Sensor Network Based on Transfer Learning
CN115342817B (en) Method, system, equipment and medium for monitoring track tracking state of unmanned tracked vehicle

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