CN114241009B - Target tracking method, target tracking system, storage medium and electronic equipment - Google Patents

Target tracking method, target tracking system, storage medium and electronic equipment Download PDF

Info

Publication number
CN114241009B
CN114241009B CN202111595522.7A CN202111595522A CN114241009B CN 114241009 B CN114241009 B CN 114241009B CN 202111595522 A CN202111595522 A CN 202111595522A CN 114241009 B CN114241009 B CN 114241009B
Authority
CN
China
Prior art keywords
target
tracking
err
image
acquiring
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
Application number
CN202111595522.7A
Other languages
Chinese (zh)
Other versions
CN114241009A (en
Inventor
黄立
余哲
张佳
李攀
唐金龙
薛源
刘华斌
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.)
Puzhou Technology Co ltd
Original Assignee
Puzhou Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Puzhou Technology Co ltd filed Critical Puzhou Technology Co ltd
Priority to CN202111595522.7A priority Critical patent/CN114241009B/en
Publication of CN114241009A publication Critical patent/CN114241009A/en
Application granted granted Critical
Publication of CN114241009B publication Critical patent/CN114241009B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Studio Devices (AREA)

Abstract

The invention relates to the technical field of target tracking, and particularly provides a target tracking method, a target tracking system, a storage medium and electronic equipment, wherein the method comprises the following steps: acquiring a tracking target image, and calculating the off-target quantity of a tracking target and an image center in the image based on the tracking target image; acquiring an off-target quantity compensation number based on the off-target quantity, and calculating a holder pre-estimation based on the off-target quantity compensation number and the off-target quantity; controlling a motor positioned on the cradle head to work based on the obtained pre-estimated cradle head so as to control a camera to track a target; according to the invention, the off-target quantity compensation number is introduced when the target is tracked, the calculated tripod head pre-estimation is based on the off-target quantity compensation number and the off-target quantity, and then the motor on the tripod head is controlled to work through the tripod head pre-estimation, so that the precision of target tracking is improved and the lag distance of target tracking is reduced compared with the traditional mode of tracking the target by the off-target quantity.

Description

Target tracking method, target tracking system, storage medium and electronic equipment
Technical Field
The present invention relates to the field of target tracking technologies, and in particular, to a target tracking method, a target tracking system, a storage medium, and an electronic device.
Background
The cloud deck target tracking algorithm is widely applied in the industry, and tracking performance becomes an important index for judging tracking effect in the industry.
The existing cradle head equipment on the market has obvious hysteresis, poor tracking precision and the like when tracking a high-speed target. For example, in the industry, when the cradles produced by unmanned aerial vehicle manufacturers such as Dajiang and daotong are compared, there are obvious problems of delay, poor tracking precision and the like when tracking a high-speed target, and the problems also cause inaccurate results obtained by some functions arranged on an aircraft nacelle, such as the calibration of the target by laser irradiation in the military nacelle, and the nacelle tracking precision is poor, so that the laser cannot be normally irradiated on the high-speed target, and the calibration work cannot be normally completed. In addition, when the nacelle measures a distance to a high-speed moving target, there is a problem that the distance measurement sensor cannot irradiate the target due to a poor tracking accuracy, and a distance measurement result is erroneous. Accordingly, the application provides a target tracking method, a target tracking system, a storage medium and electronic equipment.
Disclosure of Invention
The invention provides a target tracking method, a target tracking system, a storage medium and electronic equipment, which are used for solving the problems of hysteresis and poor tracking precision of the conventional holder equipment when tracking a high-speed target.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a method of target tracking, the method comprising:
acquiring a tracking target image, and calculating the off-target quantity of a tracking target and an image center in the image based on the tracking target image;
acquiring an off-target quantity compensation number based on the off-target quantity, and calculating a holder pre-estimation based on the off-target quantity compensation number and the off-target quantity;
and controlling a motor positioned on the cradle head to work based on the obtained pre-estimated cradle head so as to control a camera to track a target.
Further, the off-target amount compensation number is obtained by the formula (1):
Figure 77105DEST_PATH_IMAGE001
（1）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure 811712DEST_PATH_IMAGE002
compensating the off-target quantity at the current moment;
Figure 106427DEST_PATH_IMAGE003
the target off-target quantity at the current moment;
Figure 533866DEST_PATH_IMAGE004
the target off-target amount at the last moment;
k is the discrete time.
Further, the off-target amount compensation number is obtained by the formula (2):
Figure 15663DEST_PATH_IMAGE005
（2）/>
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure 694906DEST_PATH_IMAGE006
compensating the off-target amount;
Figure 968761DEST_PATH_IMAGE007
is the off-target amount;
Figure 448327DEST_PATH_IMAGE008
is a proportionality constant;
Figure 682999DEST_PATH_IMAGE009
is an integral constant;
Figure 759409DEST_PATH_IMAGE010
is a differential constant.
Further, the off-target compensation number is obtained by a nonlinear function compensation method, and the method specifically comprises the following steps:
acquiring off-target quantity of a plurality of groups of tracking targets and tracking angular speed of a holder;
relationship function based on off-target quantity of tracking target and tracking angular velocity acquisition of cradle head
Figure 763137DEST_PATH_IMAGE011
；
Acquiring the tracking angular velocity at the current moment and based on a preset function
Figure 532379DEST_PATH_IMAGE011
Obtaining a miss distance compensation number, wherein the miss distance compensation number is obtained by a formula (3);
Figure 988768DEST_PATH_IMAGE012
（3）。
further, the cloud pre-estimate is obtained by equation (4):
Figure 868868DEST_PATH_IMAGE013
（4）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure 461523DEST_PATH_IMAGE014
pre-measuring for the cloud;
Figure 667246DEST_PATH_IMAGE006
compensating the off-target amount;
Figure 610931DEST_PATH_IMAGE007
is the off-target amount;
k is a compensation factor.
Further, the compensation factor K is obtained by the following method:
acquiring a target variable based on the tracking target;
selecting corresponding sensor data based on the acquired target variable, and selecting a preset threshold value based on the type of the sensor data;
the compensation factor K is acquired based on the target variable, the sensor data, and the set threshold.
Further, at least three thresholds are set.
A pan-tilt target tracking system, comprising:
the acquisition unit is used for acquiring a target image and the off-target quantity of a tracking target and an image center in the image;
the estimating unit is used for obtaining the cloud deck pre-estimation;
and the cradle head control unit is used for controlling the work of the cradle head motor according to the acquired pre-estimated cradle head.
A storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the above-described target tracking method.
An electronic device, the computer means comprising a processor which when executing a computer program stored in a memory implements the steps of the above-described object tracking method.
In summary, compared with the prior art, the invention has the following beneficial effects:
according to the invention, the off-target quantity compensation number is introduced when the target is tracked, the calculated tripod head pre-estimation is based on the off-target quantity compensation number and the off-target quantity, and then the motor on the tripod head is controlled to work through the tripod head pre-estimation, so that the precision of target tracking is improved and the lag distance of target tracking is reduced compared with the traditional mode of tracking the target by the off-target quantity.
Drawings
FIG. 1 is a flow chart of one embodiment of the disclosed object tracking method.
FIG. 2 is a flow chart of another embodiment of the disclosed object tracking method.
FIG. 3 is a flow chart of a further embodiment of the disclosed object tracking method.
Fig. 4 is a block diagram of a target tracking system according to the present disclosure.
FIG. 5 is a block diagram illustrating a configuration of a prediction unit in the object tracking system according to the present invention.
Fig. 6 is a block diagram of a control unit of a pan-tilt in the target tracking system disclosed by the invention.
FIG. 7 is a flow chart of the operation of the object tracking system of the present disclosure.
FIG. 8 is a graph of tracking accuracy versus time for a prior art target tracking method
Fig. 9 is a graph of tracking accuracy versus time for the disclosed target tracking method.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making creative efforts based on the embodiments of the present invention are included in the protection scope of the present invention.
The cloud deck target tracking algorithm is widely applied in the industry, and tracking performance becomes an important index for judging tracking effect in the industry.
The existing cradle head equipment on the market has obvious hysteresis, poor tracking precision and the like when tracking a high-speed target. Based on the above problems, the application provides a target tracking method, a target tracking system, a storage medium and electronic equipment.
It should be noted that the target tracking method disclosed by the invention can be operated on a tripod head device, and can also be operated in other servo equipment for tracking a target, and the target tracking method disclosed by the invention is described by taking tripod head tracking as an example.
Example 1
An embodiment of the present invention provides a target tracking method, including:
step S100, a tracking target image is obtained, and the off-target quantity of a tracking target and an image center in the image is calculated based on the tracking target image;
step S200, acquiring a target-off quantity compensation number based on the target-off quantity, and calculating a holder pre-estimation based on the target-off quantity compensation number and the target-off quantity;
step S300, controlling a motor on a cradle head to work based on the obtained pre-estimated cradle head so as to control a camera to track a target;
in this embodiment, a tracking target is acquired through a tracking target detection unit located on a pan-tilt and a tracking target image is acquired, in this step, the tracking target detection unit mainly includes an image acquisition device and a visual detection algorithm, the visual detection algorithm is in the prior art, details are not described here, the image acquisition device may be a camera system disposed on the pan-tilt or the pod, after the image containing the tracking target is acquired by the image acquisition device, the image is identified through the visual detection algorithm, and the off-target amount of the tracking target in the image at the moment from the center of the image is output, that is, the distance between the image of the tracking target and the center of the image at the moment;
in step S200, calculating a target-off amount compensation number based on the target-off amount obtained in step S100, and calculating a pan-tilt pre-estimation value according to the target-off amount compensation number and the target-off amount, wherein the pan-tilt pre-estimation value is used as a motion parameter for controlling the pan-tilt motor;
because the tracking target is continuously changed, the traditional target tracking algorithm only can lead the image acquisition device on the tripod head to aim at the position of the tracking target at the last moment only according to the working mode of the tripod head motor with the off-target quantity, and the target cannot be accurately tracked according to the change rule of the tracking target, namely the change of the image acquisition device always lags behind the tracking target by one moment;
for example, an image of a tracking target at a point A is acquired by an image acquisition device at a moment K, in a traditional algorithm, the image acquisition device is aligned to the position of the point A under the control of a tripod head at a moment K+1, the tracking target is moved to a point B at a moment K+1, the tracking target and the center of the image always have off-target quantity in the image acquired by the image acquisition device, after the tripod head pre-estimated quantity is introduced in the method, the tripod head can control the position of the image acquisition device aligned to the point B according to the motion rule of the tracking target, so that the tracking precision of the tripod head is improved.
As a preferred implementation manner in this embodiment, the off-target amount compensation number is obtained by the formula (1):
Figure 435667DEST_PATH_IMAGE015
（1）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure 290620DEST_PATH_IMAGE002
compensating the off-target quantity at the current moment; />
Figure 277031DEST_PATH_IMAGE003
The target off-target quantity at the current moment;
Figure 973591DEST_PATH_IMAGE004
the target off-target amount at the last moment; k is the discrete time;
in the present embodiment, the off-target amount compensation number at the present time is obtained by adding the off-target amount compensation number at the previous time to the off-target amount at the present time, for example, the off-target amount obtained at the K time is
Figure 195494DEST_PATH_IMAGE003
The offset compensation number of the off-target amount at the previous moment, namely the moment K-1 is +.>
Figure 621796DEST_PATH_IMAGE004
The off-target amount compensation number at time K is +.>
Figure 779108DEST_PATH_IMAGE002
The off-target quantity compensation number at the first moment is the off-target quantity.
As another preferable implementation manner in this embodiment, the off-target amount compensation number is obtained by the formula (2):
Figure 822019DEST_PATH_IMAGE016
（2）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure 722979DEST_PATH_IMAGE006
compensating the off-target amount; />
Figure 410313DEST_PATH_IMAGE007
Is the off-target amount; />
Figure 128739DEST_PATH_IMAGE008
Is a proportionality constant; />
Figure 534312DEST_PATH_IMAGE009
Is an integral constant; />
Figure 238963DEST_PATH_IMAGE010
Is a differential constant;
in this embodiment, the off-target compensation number may be obtained by a PID compensation method, the off-target compensation number may be obtained by compensating the error of the off-target amount and the error rate of change as input, collecting a plurality of sets of off-target amounts to form discrete data, substituting the collected off-target amounts into the formula (2), obtaining a functional relationship between the off-target compensation number and the off-target amount, and calculating the off-target compensation number according to the off-target amount at a certain moment by using the functional relationship between the off-target compensation number and the off-target amount;
in the manner of the present embodiment of the invention,
Figure 911296DEST_PATH_IMAGE008
、/>
Figure 675990DEST_PATH_IMAGE009
and->
Figure 162335DEST_PATH_IMAGE010
All are preset values and +.>
Figure 670676DEST_PATH_IMAGE008
、/>
Figure 191657DEST_PATH_IMAGE009
And->
Figure 861672DEST_PATH_IMAGE010
All adjusted in tracking control based on the actual tracking target,/->
Figure 100893DEST_PATH_IMAGE008
The magnitude of the numerical value determines the response speed of the tracking process, whether the tracking error can be compensated rapidly, and the tracking error has anti-interference capability, but due to +.>
Figure 616188DEST_PATH_IMAGE008
Excessive force can cause concussion, during actual control, +.>
Figure 522833DEST_PATH_IMAGE008
The value range of (2) is +.>
Figure 98170DEST_PATH_IMAGE008
The value is preferably 0.7 to 0.8 times; that is, during tracking control, +.>
Figure 818827DEST_PATH_IMAGE008
The values of (2) vary in each calculation and are simultaneously dependent on +.>
Figure 403393DEST_PATH_IMAGE006
Determination of the outcome of->
Figure 164544DEST_PATH_IMAGE008
Numerical value of>
Figure 176362DEST_PATH_IMAGE006
Recording this +.>
Figure 859016DEST_PATH_IMAGE008
The value is recorded as->
Figure 512852DEST_PATH_IMAGE017
At this time, the->
Figure 597351DEST_PATH_IMAGE008
The value of (2) is 0.7-0.8 times +.>
Figure 45650DEST_PATH_IMAGE017
；/>
Figure 746759DEST_PATH_IMAGE009
For the integral constant +.>
Figure 938706DEST_PATH_IMAGE009
The value can gradually correct the compensation error during tracking compensation>
Figure 18657DEST_PATH_IMAGE009
The larger the value, the faster the error correction speed, but too large is liable to cause overshoot, i.e. overcompensation, so that overcompensation and excessive tracking effect become worse, in this embodiment +.>
Figure 768350DEST_PATH_IMAGE009
The value range of (2) is +.>
Figure 832121DEST_PATH_IMAGE008
The numerical value is between 0.001 times and 0.05 times.
Figure 686814DEST_PATH_IMAGE010
Is a differential constant +.>
Figure 886851DEST_PATH_IMAGE010
Has a damping effect as a differential constant in the algorithm, in this embodiment +_>
Figure 676952DEST_PATH_IMAGE010
The value is->
Figure 352653DEST_PATH_IMAGE008
From 0 to 1 times of (a).
As a further preferred implementation manner in this embodiment, as shown in fig. 2, the off-target compensation number may also be obtained by a nonlinear function compensation method, which specifically includes the following steps:
step S211, obtaining off-target quantity of a plurality of groups of tracking targets and tracking angular speed of a cradle head;
step S212, obtaining a relation function based on the off-target quantity of the tracked target and the tracking angular velocity of the cradle head
Figure 620824DEST_PATH_IMAGE011
；
Step S213, obtaining the tracking angular velocity at the current moment and based on a preset function
Figure 940947DEST_PATH_IMAGE011
Obtaining a miss distance compensation number, wherein the miss distance compensation number is obtained by a formula (3):
Figure 292162DEST_PATH_IMAGE018
（3）
in this embodiment, firstly, a plurality of sets of off-target amounts and tracking angular velocities of a pan-tilt are collected to form a plurality of sets of discrete data, wherein the off-target amounts and the tracking angular velocities of the pan-tilt have a one-to-one relationship with respect to a mapping relationship, for example, the collected off-target amounts and the tracking angular velocities at time K, and then the off-target amounts and the tracking angular velocities corresponding thereto are brought into a preset function, for example,
Figure 64946DEST_PATH_IMAGE019
obtaining the off-target quantity by a function fitting method>
Figure 136807DEST_PATH_IMAGE007
And angular velocity
Figure 436071DEST_PATH_IMAGE020
Obtaining the off-target compensation number according to the tracking angular velocity at the current moment by bringing the tracking angular velocity at the current moment into the formula (3) to obtain a result which is the off-target compensation number;
in some examples, the preset function may also be exponential, e.g.,
Figure 585553DEST_PATH_IMAGE021
；
in some examples, the way to bring the off-target amount and the tracking angular velocity corresponding thereto into the preset function to obtain the formula (3) may be by importing the off-target amount and the tracking angular velocity corresponding thereto into MATLAB software, and obtaining the formula (3) by fitting of the MATLAB software.
Further, as a preferred implementation manner in this embodiment, the cloud pre-estimation is obtained by the formula (4):
Figure 111212DEST_PATH_IMAGE022
（4）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure 111398DEST_PATH_IMAGE014
pre-measuring for the cloud; />
Figure 874955DEST_PATH_IMAGE006
Compensating the off-target amount; />
Figure 36815DEST_PATH_IMAGE007
Is the off-target amount; k is a compensation factor;
in the present embodiment, the off-target amount obtained in the above step is used
Figure 49770DEST_PATH_IMAGE007
And->
Figure 729013DEST_PATH_IMAGE006
Taking the cloud pre-estimated value into a formula (4), and obtaining the cloud pre-estimated value through the formula (3)>
Figure 737289DEST_PATH_IMAGE014
Then pre-estimate +.>
Figure 476575DEST_PATH_IMAGE014
Substitute for off-target in the prior art>
Figure 711247DEST_PATH_IMAGE007
Controlling a motor on the cradle head;
in this embodiment, cloud pre-estimation
Figure 787657DEST_PATH_IMAGE014
For controlling the motor on the cradle head, for example, in the prior art, when the off-target amount at the K moment is obtained, and when the motor on the cradle head is controlled to rotate at the K+1 moment, the center of the image acquisition device on the cradle head is aligned with the position of the target at the K moment by rotating the motor by a preset angle, and in the invention, the off-target amount is estimated by the cloud
Figure 56964DEST_PATH_IMAGE014
Substitute for off-target amount->
Figure 707431DEST_PATH_IMAGE007
The image acquisition device on the cradle head is controlled to be equivalent to the position of a predicted tracking target at the moment K+1, so that the center of the image acquisition device is aligned with the predicted position, thereby reducing hysteresis and improving precision;
as a further implementation manner in this embodiment, as shown in fig. 3, the compensation factor K is obtained by the following method:
step S221, acquiring a target variable based on the tracking target;
step S222, selecting corresponding sensor data based on the acquired target variable, and selecting a preset threshold value based on the type of the sensor data;
step S223, acquiring a compensation factor K based on the target variable, the sensor data and the set threshold value;
in this embodiment, firstly, a suitable target variable is selected according to the actual situation of the tracking target, and in this step, the target variable obtains the obtained data by a sensor of the pan-tilt self, for example, the angular speed of the pan-tilt motor, the movement speed of the pan-tilt or the distance between the pan-tilt and the tracking target; selecting a proper threshold according to the acquired target variable;
in this embodiment, the threshold is a value range of the target variable, and the threshold is preset by a technician;
then debugging the cradle head based on the target variable and the sensor data to obtain tracking parameters, and obtaining compensation factors according to the obtained sensor data at the current moment and a preset threshold value;
the compensation factor K can be obtained according to a linear fitting method, a nonlinear fitting method and the like; for example, when the holder is debugged, a plurality of groups of sensor data and tracking parameters with one-to-one mapping relation are obtained, the sensor data and the tracking parameters are imported into MATLAB to be fitted into a mapping function of the sensor data and the tracking parameters, and when the tracking parameters are obtained, the tracking parameters can be obtained based on the obtained sensor data;
then selecting proper tracking parameters as compensation factors K according to the threshold range of the current sensor data;
in this embodiment, the objective is to dynamically adjust the value of the compensation factor K according to the input target variable to adapt to the change of the tracked target to better track the target, because in the tracking system, the speed of the tracked target, the angle of the pan-tilt and other factors have an influence on the tracking precision, and the sound box factors can be obtained through the sensor, and the corresponding parameters and corresponding sensor data when the sound box factors are debugged to the optimal state under different conditions are fitted to obtain a function curve of the tracked parameters and the variable, so as to dynamically adjust the value of the compensation factor K;
in this embodiment, the compensation factor K is a tracking parameter at the current time;
for example, firstly, the tracking parameter value is set to 0 manually, the off-target Err in the tracking process can be obtained according to the sensor data in the holder, the variance of the off-target Err obtained in 10 seconds in the tracking process is calculated, and then the value of the tracking parameter is gradually increased by the same method to test the trackingThe effect is that the variance of the miss distance Err obtained within 10 seconds in the tracking process is obtained, if the variance is reduced, the numerical value of the tracking parameter is more reasonable, and when the variance is not obviously changed or is increased after the numerical value of the tracking parameter is increased, the numerical value of the tracking parameter set last time is the optimal parameter, the numerical value of the optimal tracking parameter under different conditions is recorded, and the numerical value of the tracking parameter is recorded as
Figure 554033DEST_PATH_IMAGE023
When the compensation factor K is selected, selecting the numerical value of the tracking parameter corresponding to the current condition;
it should be noted that the compensation factor K may also be obtained by other means, for example, by tracking parameters within different threshold ranges
Figure 575079DEST_PATH_IMAGE023
Then obtaining a compensation factor K through a formula (5); />
Figure 433314DEST_PATH_IMAGE024
Formula (5)
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure 639036DEST_PATH_IMAGE025
for different threshold values, ++>
Figure 848300DEST_PATH_IMAGE026
Tracking parameters in different threshold ranges;
for example, a pan-tilt angular velocity sensor is selected as a target variable, 10km/h,30km/h and 80km/h are selected as thresholds, and tracking and debugging are performed to obtain tracking parameters K1, K2 and K3. At this time, the formula (4) is obtained as a compensation factor calculation formula:
Figure 141878DEST_PATH_IMAGE027
；
as a preferred implementation manner in this embodiment, at least three thresholds are set.
Example 2
As shown in fig. 4, the present invention also discloses a pan-tilt target tracking system, which includes:
an acquiring unit 410, configured to acquire an image of a target and a miss distance between a tracking target in the image and a center of the image;
the estimating unit 420 is configured to obtain a pan-tilt pre-estimation;
the pan-tilt control unit 430 is configured to control the pan-tilt motor to work according to the obtained pan-tilt pre-estimation;
in this embodiment, the acquiring unit 410 acquires image data of the tracking target, and acquires the off-target amount between the tracking target and the image center according to the image data, where the acquiring unit 410 may be a tracking target detector in the prior art, and is provided with an image acquisition device and a visual detection algorithm, where the visual detection algorithm identifies the tracking target and calculates the off-target amount according to the image acquired by the image acquisition device, and the acquiring unit 410 sends the acquired off-target amount to the estimating unit 420;
the estimating unit 420 calculates a cloud estimated value according to the off-target amount of the acquiring unit 410 and transmits the cloud estimated value to the pan-tilt control unit 430, and the pan-tilt control unit 430 controls the motor of the pan-tilt to work;
in some examples, as shown in fig. 5, the estimating unit 420 includes:
a tracking predictor 421 for constructing a functional relationship between the off-target compensation number and the off-target to calculate the off-target compensation number, and calculating a cloud pre-estimation value according to the off-target compensation number and the off-target;
a tracking parameter compensator 422 for calculating a compensation factor;
in some examples, as shown in fig. 6, the pan/tilt control unit 430 includes:
a target tracking controller 431, configured to obtain a control amount of the motor on the pan-tilt, where the target tracking controller 431 calculates the control amount of the motor on the pan-tilt according to the estimated cloud amount input by the estimating unit 420;
the pan-tilt servo controller 432 outputs a feeding amount of the motor on the pan-tilt according to the control amount calculated by the target tracking controller 431, and is used for controlling the rotation of the pan-tilt motor;
in this embodiment, as shown in fig. 7, the control flow of the pan-tilt target tracking system is as follows:
when the cradle head is started, carrying out cradle head self-checking, after the cradle head self-checking is finished, acquiring an image through an acquisition unit 410, selecting a tracking target in the image, at this time, starting tracking the target by a target tracking system, tracking the target by the acquisition unit 410, calculating the off-target amount of the tracking target, then sending the off-target amount to a tracking predictor 421 and a tracking parameter compensator 422, acquiring sensor data of the cradle head by the tracking parameter compensator 422, analyzing the relation between the sensor data and the off-target amount, calculating a compensation factor according to the sensor data, sending the calculated compensation factor to a target tracking controller 431 by the tracking parameter compensator 422, calculating the control amount of a motor by the tracking parameter compensator 422 according to the acquired compensation factor and the off-target amount compensation amount, and sending the control amount of the motor to the cradle head servo controller 432 by the cradle head servo controller 432, wherein the calculated compensation factor is sent to the cradle head servo controller 432;
the acquisition unit 410 acquires an image and calculates the off-target amount while the motor is operating.
Example 3
A storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the target tracking method of any one of the embodiments 1.
Example 4
An electronic device, the computer means comprising a processor which when executing a computer program stored in a memory implements the steps of the object tracking method according to any one of the embodiments 1.
In summary, the invention discloses a target tracking method, a system, a storage medium and an electronic device, wherein the method comprises the following steps:
step S100, a tracking target image is obtained, and the off-target quantity of a tracking target and an image center in the image is calculated based on the tracking target image;
step S200, acquiring a target-off quantity compensation number based on the target-off quantity, and calculating a holder pre-estimation based on the target-off quantity compensation number and the target-off quantity;
step S300, controlling a motor on a cradle head to work based on the obtained pre-estimated cradle head so as to control a camera to track a target;
according to the invention, the off-target quantity compensation number is introduced when the target is tracked, the cloud deck pre-estimation is calculated based on the off-target quantity compensation number and the off-target quantity, and then the motor on the cloud deck is controlled to work through the cloud deck pre-estimation, so that the accuracy of target tracking is improved and the lag distance of target tracking is reduced compared with the traditional mode of tracking the target by the off-target quantity;
as shown in fig. 8 and 9, the tracking accuracy achieved by the object tracking method disclosed by the present invention is higher than that achieved by the object tracking method in the prior art.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
In one typical configuration of an embodiment of the present invention, a terminal, a device serving a network, and a computing device include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash memory (flash-RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data.
Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include non-transitory computer-readable media (transmission-media), such as modulated data signals and carrier waves.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above. The specific working process of the above-described device may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. The embodiments of the present disclosure are intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims (5)

1. A method of target tracking, the method comprising:
acquiring a tracking target image, and calculating the off-target quantity of a tracking target and an image center in the image based on the tracking target image;
acquiring an off-target quantity compensation number based on the off-target quantity, and calculating a holder pre-estimation based on the off-target quantity compensation number and the off-target quantity;
controlling a motor positioned on the cradle head to work based on the obtained pre-estimated cradle head so as to control a camera to track a target;
the off-target amount compensation number is obtained by the formula (1):
Err b (k)＝Err b (k-1)+Err(k) (1)
wherein Err b (k) Compensating the off-target quantity at the current moment;
err (k) is the off-target amount at the current time;
Err b (k-1) is the off-target amount at the previous time;
k is the discrete time;
or, the off-target amount compensation number is obtained by the formula (2):
Figure FDA0004183505220000011
wherein Err b Compensating the off-target amount;
err is the off-target amount;
kp is a proportionality constant;
ki is the integration constant;
kd is a differential constant;
or, the off-target compensation number is obtained by a nonlinear function compensation method, which comprises the following specific steps:
acquiring off-target quantity of a plurality of groups of tracking targets and tracking angular speed of a holder;
acquiring a relation function f (w) based on the off-target quantity of the tracking target and the tracking angular speed of the cradle head;
acquiring the tracking angular velocity at the current moment and acquiring a miss distance compensation number based on a relation function f (w), wherein the miss distance compensation number is acquired by a formula (3);
Err b ＝f(w) (3)；
the pre-estimated amount of the cradle head is obtained by a formula (4):
Err Ture ＝Err+K×Err b (4)
wherein Err Ture Pre-estimating a cloud deck;
Err b compensating the off-target amount;
err is the off-target amount;
k is a compensation factor;
the compensation factor K is obtained by the following method:
acquiring a target variable based on the tracking target;
selecting corresponding sensor data based on the acquired target variable, and selecting a preset threshold value based on the type of the sensor data;
the compensation factor K is obtained based on the target variable, the sensor data and a preset threshold.
2. The target tracking method according to claim 1, wherein the threshold is set with at least three.
3. A pan-tilt target tracking system for implementing the target tracking method of any of claims 1-2, comprising:
the acquisition unit is used for acquiring a target image and the off-target quantity of a tracking target and an image center in the image;
the estimating unit is used for obtaining the cloud deck pre-estimation;
and the cradle head control unit is used for controlling the work of the cradle head motor according to the acquired pre-estimated cradle head.
4. A storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the object tracking method according to any one of claims 1-2.
5. An electronic device, the computer means comprising a processor, characterized in that the processor, when executing a computer program stored in a memory, implements the steps of the object tracking method according to any of claims 1-2.
CN202111595522.7A 2021-12-24 2021-12-24 Target tracking method, target tracking system, storage medium and electronic equipment Active CN114241009B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111595522.7A CN114241009B (en) 2021-12-24 2021-12-24 Target tracking method, target tracking system, storage medium and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111595522.7A CN114241009B (en) 2021-12-24 2021-12-24 Target tracking method, target tracking system, storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN114241009A CN114241009A (en) 2022-03-25
CN114241009B true CN114241009B (en) 2023-06-02

Family

ID=80762396

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111595522.7A Active CN114241009B (en) 2021-12-24 2021-12-24 Target tracking method, target tracking system, storage medium and electronic equipment

Country Status (1)

Country Link
CN (1) CN114241009B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102736636A (en) * 2012-06-12 2012-10-17 中国科学院光电技术研究所 Feed-forward control method based on angle information in tracking system
CN106444386A (en) * 2016-11-29 2017-02-22 凯迈（洛阳）测控有限公司 Tracking target-missing quality time-delay compensation control method of photoelectric equipment
CN108871374A (en) * 2018-03-26 2018-11-23 中国科学院西安光学精密机械研究所 A kind of method of miss distance Time delay measurement precision in raising photoelectric follow-up

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5469894B2 (en) * 2008-07-05 2014-04-16 株式会社トプコン Surveying device and automatic tracking method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102736636A (en) * 2012-06-12 2012-10-17 中国科学院光电技术研究所 Feed-forward control method based on angle information in tracking system
CN106444386A (en) * 2016-11-29 2017-02-22 凯迈（洛阳）测控有限公司 Tracking target-missing quality time-delay compensation control method of photoelectric equipment
CN108871374A (en) * 2018-03-26 2018-11-23 中国科学院西安光学精密机械研究所 A kind of method of miss distance Time delay measurement precision in raising photoelectric follow-up

Also Published As

Publication number Publication date
CN114241009A (en) 2022-03-25

Similar Documents

Publication Publication Date Title
CN109444932B (en) Vehicle positioning method and device, electronic equipment and storage medium
EP0621586B1 (en) Optical disk drive
CN111385474B (en) Target object tracking method and device, storage medium and electronic device
CN114241009B (en) Target tracking method, target tracking system, storage medium and electronic equipment
US20150149105A1 (en) Accuracy compensation system, method, and device
US20190258255A1 (en) Control device, imaging system, movable object, control method, and program
CN109633860A (en) Automatically adjust method, lens position adjusting device and the projector of lens location
CN103063228A (en) Gyroscope static calibration method
US20220289184A1 (en) Method and Device for Scheduling a Trajectory of a Vehicle
CN110989691B (en) Cloud deck control method and device, storage medium, electronic equipment and unmanned aerial vehicle
CN112834249B (en) Steering parameter detection method, device, equipment and storage medium
WO2018188441A1 (en) Imaging method, device and system
CN109947116B (en) Positioning method and device for unmanned vehicle
US7751289B2 (en) Optical disc apparatus and information recording method thereby
KR20210076412A (en) Apparatus and method for evaluating vehicle sensor performance
CN110058605A (en) Unmanned plane power-line patrolling control method
CN114987478A (en) Vehicle lane changing method, device, storage medium and processor
CN110673123B (en) Target object ranging method and device
CN112179377B (en) Pan-tilt error compensation method and device, pan-tilt camera and readable storage medium
CN115256047B (en) Method and device for detecting thermal elongation of main shaft of numerical control machine tool and numerical control machine tool
CN114147707A (en) Robot docking method and device based on visual identification information
GB2513179A (en) Device and method for controlling the transport of a tape within a tape transport system
WO2021031091A1 (en) Method and apparatus for detecting operating status of device, and computer readable medium
CN101315784A (en) Optical disc apparatus and data recording method thereof
CN116500889B (en) Servo motor position precise control method and device based on space-time two-dimensional optimization

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
CB02 Change of applicant information

Address after: 430070 North of Floor 3, Building 2, No. 5, Huanglongshan South Road, Fozuling Street, Donghu New Technology Development Zone, Wuhan, Hubei Province (Wuhan Area of Free Trade Zone)

Applicant after: Puzhou Technology Co.,Ltd.

Address before: Room 201, Building A, 1 Qianwan Road, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong Province

Applicant before: Puzhou Technology (Shenzhen) Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant