CN102135761B - Fuzzy self-adaptive control system for parameters of visual sensor - Google Patents
Fuzzy self-adaptive control system for parameters of visual sensor Download PDFInfo
- Publication number
- CN102135761B CN102135761B CN 201110003449 CN201110003449A CN102135761B CN 102135761 B CN102135761 B CN 102135761B CN 201110003449 CN201110003449 CN 201110003449 CN 201110003449 A CN201110003449 A CN 201110003449A CN 102135761 B CN102135761 B CN 102135761B
- Authority
- CN
- China
- Prior art keywords
- interface
- signal output
- fuzzy
- input
- signal
- 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.)
- Expired - Fee Related
Links
- 230000000007 visual effect Effects 0.000 title abstract description 4
- 230000008859 change Effects 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 3
- 230000011664 signaling Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000001105 regulatory effect Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 230000009194 climbing Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000009699 differential effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013341 scale-up Methods 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention provides a fuzzy self-adaptive control system for parameters of a visual sensor. The system is characterized in that a signal output end of a detection device is connected with a signal input end of an input interface; a signal output end of the input interface is connected with a signal input end of a fuzzy controller; a signal output end of the fuzzy controller is connected with asignal input end of an output interface; a signal output end of the output interface is connected with a signal input end of an execution mechanism; a signal output end of the execution mechanism is connected with a signal input end of a control object; and a signal output end of the control object is connected with a signal input end of the control object. The system has the advantages that a fuzzy self-adaptive control algorithm does not adopt human eye observation, system time and other unreliable factors; closed loop control on parameters of the visual sensor is realized; input parametersare fuzzified, set parameters of the video sensor have high setting speed through the fuzzy controller; and the parameters are regulated and set in real time. The input parameter is calculated through the fuzzy controller, so that the best image quality and effect can be acquired for the sensor.
Description
Technical field
What the present invention relates to is a kind of adaptive fuzzy control system of vision sensor parameter, is applicable to technical fields such as security monitoring, intelligent transportation, HD video meeting, the diagnosis of high definition medical video, long-distance education.
Background technology
In common rig camera, the vision sensor of its daylighting front end generally all adopts preset parameter to control and regulate at present.Adopt many cover preset parameters to adapt to various situations for senior rig camera.Tradition vision sensor parameter is set the method that adopts artificial setting and system's automatic setting to combine.Its input source has three classes: 1. human eye identification, differentiate according to human eye, and manually the parameter of vision sensor to be regulated, this control method advantage is the sensation that the result of adjustment relatively meets human eye.Its shortcoming is to satisfy the needs of numerous human eyes.2. vision sensor is taken in, and is directed to the shortcoming of manual setting, and the vision sensor parameter is set and introduced the function of automatic setting.Though this automatic setting has remedied the deficiency of manual setting to a certain extent, can't set some parameter.3. system time input changes according to system time, and embedded system CPU selects the parameter under the corresponding time to set in the vision sensor parameter list.These parameters regulated according to light in advance in the different time periods.This solution relatively is fit under the more controlled situation of extraneous light condition, as indoor situation.For outdoor environment, the set time adopts preset parameter then can't satisfy.
Summary of the invention
What the present invention proposed is a kind of adaptive fuzzy control system of vision sensor parameter, and its purpose is to improve by this system the output quality of vision sensor under complex environment.
Technical solution of the present invention: its structure is to comprise fuzzy controller, IO interface, pick-up unit, topworks and control object, wherein the signal input part of the signal output part of pick-up unit and input interface joins, the signal output part of input interface and the signal input part of fuzzy controller join, the signal output part of fuzzy controller and the signal input part of output interface join, the signal output part of output interface and the signal input part of topworks join, the signal output part of topworks and the signal input part of control object join, and the signal output part of control object and the signal input part of pick-up unit join.
Advantage of the present invention: soluble problem comprises following aspect: 1. the abandoning tradition solution dependence of non-light signal to external world, the fuzzy self-adaption control algolithm of vision sensor parameter does not adopt unreliable factors such as human eye is watched, system time.The control importation of this programme is fully from the optical input signals of video sensor front end, as light-inletting quantity, contrast, color, colour temperature, aberration, saturation degree, parameter such as backlight.These input quantities are real-time, objective fully.Meet real-time condition based on these real parameters.2. realize the closed-loop control of vision sensor parameter, closed-loop control is finished by the central processing unit (CPU) of embedded system fully.Embedded system is carried out calculation of parameter and setting in real time according to input signal.This full cut-off ring control structure and original open loop control (input of human eye equipment or system time input-embedded system-vision sensor) are essentially different; 3. the Fuzzy Calculation of video sensor parameter: embedded system is handled device the input parameter of video sensor is carried out obfuscation, passes through the setup parameter that fuzzy controller (inference machine and knowledge base) obtains video sensor then.Human body psycho-visual perception experience that fuzzy controller is integrated is so the result of its output meets most of terminal users' vision requirement; 4. there is certain uncertainty in the external environment of video sensor, and this is the research object of video sensor parameter adaptive control system just.Here so-called " uncertainty " to refer to describe the mathematical model of controlled device and environment thereof be not completely specified, wherein comprise some X factors and enchancement factor; 5. the setting speed of vision sensor parameter is fast, and parameter is regulated and set is real-time.This adapts to the light cataclysm of external environment condition fully, and situation such as is moved in the position.Embedded system provides sufficient system resource (1GHzCPU travelling speed etc.) operation FUZZY ALGORITHMS FOR CONTROL, guarantees the real-time of vision sensor control;
6. quality and best results.The setting of vision sensor parameter is to draw according to the input parameter of the sensor at that time algorithm by fuzzy controller.This parameter that calculates in real time makes sensor obtain best picture quality and effect.
Description of drawings
Fig. 1 is structured flowchart of the present invention.
Fig. 2 is the structural representation of fuzzy controller.
Fig. 3 is the structural representation of inference machine
Fig. 4 is the illustration of the single output of dual input fuzzy controller.
Fig. 5 is vision sensor Fuzzy control system Organization Chart.
Fig. 6 is that system ambiguous controller is realized the synoptic diagram I.
Fig. 7 is that system ambiguous controller is realized the synoptic diagram II.
Fig. 8 is deviation curve e (t) synoptic diagram.
Fig. 9 is the structural representation of parameter self-tuning Fuzzy control system.
Embodiment
Described control object, the control object of native system is vision sensor.This vision sensor be multivariable, nonlinear, the time become, control object high-order, at random.For such non-linear of vision sensor and the time object that becomes be difficult to set up precise math model, so fuzzy control strategy is the solution that comparatively suits.
Described pick-up unit, pick-up unit comprise that sensor and change send device (having now), and for detection of various non electrical quantities, as brightness, colour temperature, aberration etc., and conversion is enlarged into the electric signal of standard.
Described topworks, topworks are fuzzy controller applies devices from control action to controlled device.Topworks in the native system is made up of the main circuit in the vision sensor and drive part.
Described IO interface, IO interface are the bridges that the central processing unit of realization FUZZY ALGORITHMS FOR CONTROL is connected with controlled system.Input interface is connected with pick-up unit, and detection signal is converted to the digital signal that central controller can be identified and handle.Output interface is converted to the desired signal of topworks to the digital signal of central controller output, and this outputs signal to topworks controlled device is applied control action.In native system, IO interface is all by the I of standard
2C circuit and its driving circuit are formed.
Described fuzzy controller, fuzzy controller are the cores of Fuzzy control system, are realized by the fuzzy control software of ARM central processing unit and operation in the above.
Contrast accompanying drawing 2, fuzzy controller is become by defuzzification interface, knowledge base, inference machine and ambiguity solution interface group.Corresponding joining of signal input part of first signal output part of knowledge base, secondary signal output terminal, the 3rd signal output part and gelatinization interface, inference machine, ambiguity solution interface wherein, the signal output part of gelatinization interface and the signal input part of inference machine join, and the signal input part of the signal output part of inference machine and ambiguity solution interface joins.
Described defuzzification interface is that the accurate semaphore that fuzzy controller is obtained by input channel is converted into the fuzzy quantity that the reasoning function receives.
Described knowledge base comprises database and rule base.Deposit all fuzzy subsets' that use definition in the database.In the controller reasoning process, database provides data necessary to inference machine.When defuzzification interface and ambiguity solution interface, database also provides the necessary data of relevant domain to them.Rule base is deposited fuzzy control rule.Fuzzy control rule is the knowledge model that controlled device is controlled based on the control experience of manual operator long-term accumulation and this domain expert's relevant knowledge.
Contrast accompanying drawing 3
Fuzzy controller is with the output valve of controlled device and the error between setting value is designated as input variable X and error rate is designated as input variable Y, and the fuzzy controller output variable is designated as Z.The set of the language value of X, Y, Z also claims the diction collection, is made as respectively:
X：{Aii＝1，2，...m}
Fuzzy control rule can be expressed as so:
If X be A1 and B1 then Z be C11 otherwise
If X be A1 and B2 then Z be C12 otherwise
If X be A1 and Bn then Z be C1n otherwise
If X be A2 and B1 then Z be C21 otherwise
If X be A2 and Bn then Z be C2n otherwise
If X be Am and B1 then Z be Cm1 otherwise
If X be Am and Bn then Z be Cmn otherwise (.1)
The represented rule of formula (.1) is a usefulness otherwise the multistage fuzzy condition statement that connects, total m * n section, and each section be with and connect the two-dimentional fuzzy reasoning statement of front condition.
(X * Y * Z) can regard a converter as, when being input as A and B, conversion is output as C to fuzzy relation R ∈ F.For the multistage fuzzy condition statement of this group fuzzy condition statement composition of formula (.1), the wherein represented fuzzy relation R of each section
IjFor:
R
Ij=R
Ij((A
i) and (B
j) ∧ (C
Ij))=R
Ij(A
I, B
j, C
Ij) (.2)
Total fuzzy relation is:
If a certain moment be input as A ' and B ', then export C ' and be:
C’＝(A’×B’)·R (.3)
Formula (.3) is exactly the composition rule of the fuzzy reasoning of fuzzy controller employing.Various reasoning algorithms all can be obtained fuzzy relation R earlier by formula (.2) according to rule base, carry out reasoning by formula (.3) then and try to achieve control output.But as field X, when Y, Z contained than multielement, it is huge that R becomes, and make troubles for storage, calculating, so the FUZZY ALGORITHMS FOR CONTROL of native system adopts simple and direct method to carry out compose operation.
The ambiguity solution interface is opposite with defuzzification interface, and ambiguity solution is to the transfer process of accurately measuring by fuzzy quantity.
Central controller must be converted to the receptible accurate amount of topworks to the control action that obtains from fuzzy reasoning.
Contrast accompanying drawing 4, question blank are the corresponding relations that the point on the input domain arrives the output domain, are that calculated off-line obtains through the process of obfuscation, fuzzy reasoning and ambiguity solution.When fuzzy controller carried out at off-line, it was just passable only need to table look-up, thereby has accelerated on-line operation speed greatly.Input quantity is error e and error change amount ec.In each sampling instant, input quantity e and ec are carried out the range conversion, namely error e multiply by scale factor k1, and error change amount ec multiply by scale factor k2, quantizes then.The physical signalling value of input is converted to the point of input on the domain, obtains exporting point on the domain by question blank then, multiply by scale factor k3 again and carry out the range conversion, just obtain exporting the desired physical quantity of hardware interface.
Contrast accompanying drawing 5, the framework of vision sensor Fuzzy control system comprises vision sensor and ARM central processing unit, fuzzy controller, empirical model database, control algolithm, communications protocol.Wherein, corresponding the joining of signal I/O end of the signal output/input end of vision sensor and ARM central processing unit.What the ARM central processing unit adopted is to be the SoC chip of core with ARM9, and its dominant frequency can run to 500MHz.Fuzzy controller, empirical model database, control algolithm, communications protocol all realize at the ARM central processing unit.
Contrast accompanying drawing 6. determines that the structure of fuzzy controller is to set up the prerequisite of fuzzy control rule, and different structures has multi-form rule.Select the version of fuzzy controller (FLC), also should adapt with the manual control experience.In native system, controlled device is that the vision sensor setting conforms to the expert knowledge library definite value to the requirement of system, namely requires system to control to realize that with many close-loop feedback system's visual pattern output is best.The fuzzy controller of system is to be input with integration EI of the error E of controlled volume (brightness, contrast, color, saturation degree, sharpness, gamma, white balance, backlight compensation, supply frequency, exposure, focusing), error rate EC and error etc., and the control object vision sensor is set at output.
Contrast accompanying drawing 7, the fuzzy controller in the system be one and be changed to the input of controller with the sum of errors error of controlled variable, and with the single argument fuzzy controller of the output that is changed to controller of controlled quentity controlled variable.K1 among the figure, K2, K3 is three parameters of fuzzy controller, be respectively the quantizing factor (coefficient of proportional action) of error, the scale factor (total enlargement factor) that the quantizing factor of error change (coefficient of the differential action) and controlled quentity controlled variable change, K1, K2 increases, the proportional action, the differential action that are equivalent to controller strengthen, and K3 increases, and then is equivalent to the total enlargement factor of controller and strengthens.
if{E＝A
i and EC＝B
i}then Δu＝Ci，i＝1，2，...n (2.1)
E wherein, EC and Δ u are respectively the error of controlled variable, the linguistic variable that error change and controlled quentity controlled variable change; And Ai, Bi and Ci for the language value on its corresponding domain are: NB, NM, NS, NO, PS, PM, PB.Fuzzy control rules as the table * shown in.
Wherein: P-just, N-is negative, B-is big, among the M-, S-is little, O-zero.
By control law (2.1) formula, according to approximate principle, can calculate corresponding to E, the Δ u of EC uses function f ' be expressed as:
Δu＝f’(E，EC) (2.2)
If the actual error of n sampling instant controlled variable is e (n), when error change is ec (n), it is quantized and obfuscation, can obtain two independent fuzzy sets in its corresponding domain:
E(n)＝INT(K
1e(n)+0.5) (2.3)
EC(n)＝INT(K
2ec(n)+0.5) (2.4)
Substitution (2.2) formula has
Δu(n)＝f’[INT(K
1e(n)+0.5)，INT(K
2ec(n)+0.5)]
＝f[K
1e(n)，K
2ec(n)] (2.5)
It is adjudicated and takes advantage of scale factor K
3, obtain actual controlled quentity controlled variable and change:
Δu(n)＝K
3D{f[K
1e(n)，K
2ec(n)]}(2.6)
D[in the formula] the expression judgement.Thereby have
If the input-output characteristic of controlled process is described by following formula:
y＝g(u) (2.8)
Then have:
As seen three of Fuzzy Controller parameters are all influential to the output characteristics of system.K wherein
1, K
2Be the output that changes controller by the value of adjusting linguistic variable, and K
3Then be equivalent to proportional gain effect in the classical control system.
Further describe the relation of Fuzzy Controller parameter and system performance below:
← K
1And K
2Influence to dynamic performance
By formula (2.3) and (2.4) as can be known, if K
1, K
2Change, then the language value that changes on the corresponding domain of Shi Ji error or error also will change.In general, K
1And K
2Be worth more big, the language value that corresponding sum of errors error changes also more greatly, vice versa.Can be found out by fuzzy controller state table 1, error change get under the constant condition of language value, it is more big that error is got the language value, the language value that the output of corresponding controllers (controlled quentity controlled variable variation) is got also more greatly; And get under the constant condition of language value in error, error changes the language value get more greatly, and the language value that the output of corresponding controllers is got is more little.Therefore, K
1Influence to system dynamic characteristic is: K
1More big, the adjusting dead band of system is more little, and system's climbing speed is more big.But K
1Got senior general and made system produce bigger overshoot, the adjusting time is increased, also can produce vibration when serious, made the system can not steady operation.And K
2To the influence of system dynamic characteristic just in time with K
1On the contrary, K
2More big, the reaction of system is just more blunt; K
2More little, the reaction of system is more sensitive, and climbing speed is big.And too small K
2Also will cause the overshoot that system is bigger, and make the adjusting time of system long, also will producing when serious vibrates makes the system can not stable operation.
↑ K
1, K
2To the systematic steady state Effect on Performance
For Fuzzy control system, its steady state (SS) can be described as:
E is zero and EC is zero (2.10)
Language value zero correspondence certain scope, when the sum of errors error change all enters its language value
During the corresponding scope of zero, system just enters steady state (SS).The stable state span that can be obtained e and ec by formula (2.3) and (2.4) is
|K
1 e(∞)|＜0.5，|K
2 ec(∞)|＜0.5 (2.11)
By formula (2.12) as seen, in Fuzzy control system, generally can not eliminate steady-state error and error change amount, but can be by increasing K
1, K
2Value they are reduced.But for guaranteeing the performance of entire system optimum, also to take into account K
1, K
2Dynamic property influence to system.
→ K
3The influence of system performance
K
3Be equivalent to the proportional gain in the classical control system, general K
3More big, the climbing speed of system is more fast.But K
3Cross senior general and produce bigger overshoot, can produce vibration when serious and making the system can not steady operation.But K
3The general steady-state error that can not influence system, it is smaller that namely the stable state of system is subjected to the influence of output gain of system.
Fuzzy Controller parameter self-tuning algorithm, as the above analysis, the fuzzy controller of employing preset parameter can not obtain excellent system and dynamically reach steady-state behaviour in system's operational process, therefore must carry out on-line automatic adjustment to each parameter of regulator according to the input and output signal of system.For coherent system dynamically and the different requirements of stable state to parameter adjustment, and reduce the complicacy of adjustment, we come setting parameter K according to the requirement of systematic steady state performance index
1And K
2, and by the identification to system's output state, come setting parameter K online
3, make system obtain excellent dynamic performance.
← parameter K
1, K
2Adjust
By formula (2.12) as can be known, if the steady-state error that requires system then must make less than δ (a little positive number)
Any requirement is not done in the variation of steady-state error in the performance index of General System.At K
1Under certain condition, K
2Influence the sensitivity of system's dynamic response, for making system a desirable dynamic response, K are arranged
2Must and K
1Coordination is got up, and we adopt the fuzzy control rule of table 1, and is generally desirable
K
2＝(1.5～2.5)K
1 (3.2)
↑ parameter K
3Adjust
In control system, because given the changing of input, perhaps object parameters changes, and external disturbance perhaps takes place, system output (controlled variable) all will depart from its stationary value, the curve description of deviation e (t)=Y (t)-common available Fig. 8 of R (t) of it and new steady-state value.
At a point, e depart from steady-state value (| e|=0) bigger, and
Trend towards near steady-state value, in order to improve closing rate, wish that control action is big.At the b point, e is near steady-state value, and
For making the unlikely steady-state value of breaking through of e (t) cause new fluctuation, and be stable at rapidly | the e|=0 place, wish K
3Reach smallerly.C point, deviation e be for just, and
Wish control action big (control action is determined by table 1).At the d point, although e still for just,
The trend steady-state value is stabilized in rapidly for making e (t) | and the e|=0 place, wish K
3Smaller slightly.Other each point K
3But the value similar analysis of parameter.
The design of similar FUZZY ALGORITHMS FOR CONTROL, regulator parameter also is one group of fuzzy condition statement from adjusting,
Can be expressed as
if{E＝A
j and EC＝B
j}then K＝C
j，j＝1，2，...n (3.3)
E wherein, EC represent the linguistic variable that the sum of errors error of controlled volume changes, A respectively
j, B
jLanguage value on its corresponding domain, as NB, NM, NS, NO, PS, PM, PB etc., K represent the linguistic variable of scale-up factor, C
jFor the language value on its corresponding domain, as B, M, S, VB (Very Big) etc.
Formula (3.1)～(3.3) are exactly Fuzzy Controller parameter self-tuning algorithm.In native system, Fuzzy Controller is actually a secondary Fuzzy control system, and low one-level is carried out control action, and higher one-level is carried out the parameter adjustment effect.In native system, have the Fuzzy control system block diagram of parameter self-tuning algorithm as shown in Figure 9.
As regulator parameter K
1, K
2, K
3When changing with image parameter, the output characteristics that has from the Fuzzy control system of setting algorithm has all reached perfect condition.Governing speed that it should be noted that the voltage Fuzzy Controller must be faster than the speed of current regulator.Because the output of system requires the voltage constant of DC side, so when the output of voltage, current regulator departed from stable state or default and changes, the output of voltage regulator should reach stable state prior to the output of current regulator.The method that solves is the K that guarantees in adjustment process in the voltage regulator
1Control action be greater than K in the current regulator
1Control action.
Claims (1)
1. the adaptive fuzzy control system of vision sensor parameter, it is characterized in that comprising fuzzy controller, IO interface, pick-up unit, topworks and control object, wherein the signal input part of the signal output part of pick-up unit and input interface joins, the signal output part of input interface and the signal input part of fuzzy controller join, the signal output part of fuzzy controller and the signal input part of output interface join, the signal output part of output interface and the signal input part of topworks join, the signal output part of topworks and the signal input part of control object join, and the signal output part of control object and the signal input part of pick-up unit join; The structure of described fuzzy controller comprises defuzzification interface, knowledge base, inference machine and ambiguity solution interface, corresponding joining of signal input part of first signal output part of knowledge base, secondary signal output terminal, the 3rd signal output part and defuzzification interface, inference machine, ambiguity solution interface wherein, the signal output part of defuzzification interface and the signal input part of inference machine join, and the signal input part of the signal output part of inference machine and ambiguity solution interface joins; When fuzzy controller carried out at off-line, it was just passable only need to table look-up, and has accelerated processing speed greatly; Question blank is the corresponding relation that the point on the input domain arrives the output domain, is that calculated off-line obtains through the process of obfuscation, fuzzy reasoning and ambiguity solution; Input quantity is error e and error change amount ec; In each sampling instant, input quantity e and ec are carried out the range conversion, namely error e multiply by scale factor k1, and error change amount ec multiply by scale factor k2, quantizes then; The physical signalling value of input is converted to the point of input on the domain, obtains exporting point on the domain by question blank then, multiply by scale factor k3 again and carry out the range conversion, just obtain exporting the desired physical quantity of hardware interface; Described fuzzy controller is an input that is changed to controller with the sum of errors error of controlled variable, and with the single argument fuzzy controller of the output that is changed to controller of controlled quentity controlled variable, k1, k2, k3 is three parameters of fuzzy controller, be respectively the quantizing factor of error, the scale factor that the quantizing factor of error change and controlled quentity controlled variable change.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110003449 CN102135761B (en) | 2011-01-10 | 2011-01-10 | Fuzzy self-adaptive control system for parameters of visual sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110003449 CN102135761B (en) | 2011-01-10 | 2011-01-10 | Fuzzy self-adaptive control system for parameters of visual sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102135761A CN102135761A (en) | 2011-07-27 |
| CN102135761B true CN102135761B (en) | 2013-08-21 |
Family
ID=44295565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110003449 Expired - Fee Related CN102135761B (en) | 2011-01-10 | 2011-01-10 | Fuzzy self-adaptive control system for parameters of visual sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102135761B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103941584A (en) * | 2013-12-03 | 2014-07-23 | 西北农林科技大学 | Temperature control method based on fuzzy self-adaptive controller |
| CN106979749B (en) * | 2016-11-02 | 2019-05-21 | 北京信息科技大学 | A kind of fuzzy self-adaption method of adjustment of optical strip image imaging parameters |
| CN109143855B (en) * | 2018-07-31 | 2021-04-02 | 西北工业大学 | Visual servo control method of unmanned gyroplane based on fuzzy SARSA learning |
| CN110794811B (en) * | 2019-11-07 | 2021-02-26 | 浙江工业大学 | Safety control method of networked motion control system with quantification |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1727839A (en) * | 2004-07-28 | 2006-02-01 | 发那科株式会社 | Method of and device for re-calibrating three-dimensional visual sensor in robot system |
| CN101109620A (en) * | 2007-09-05 | 2008-01-23 | 北京航空航天大学 | Method for standardizing structural parameter of structure optical vision sensor |
| CN101251765A (en) * | 2007-02-23 | 2008-08-27 | 三星电子株式会社 | Computer apparatus and power supply method thereof |
| CN202033611U (en) * | 2011-01-10 | 2011-11-09 | 穆科明 | Fuzzy adaptive control system for parameters of visual sensor |
-
2011
- 2011-01-10 CN CN 201110003449 patent/CN102135761B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1727839A (en) * | 2004-07-28 | 2006-02-01 | 发那科株式会社 | Method of and device for re-calibrating three-dimensional visual sensor in robot system |
| CN101251765A (en) * | 2007-02-23 | 2008-08-27 | 三星电子株式会社 | Computer apparatus and power supply method thereof |
| CN101109620A (en) * | 2007-09-05 | 2008-01-23 | 北京航空航天大学 | Method for standardizing structural parameter of structure optical vision sensor |
| CN202033611U (en) * | 2011-01-10 | 2011-11-09 | 穆科明 | Fuzzy adaptive control system for parameters of visual sensor |
Non-Patent Citations (2)
| Title |
|---|
| 周盈等.激光三角测量中图像传感器参量自适应调节.《激光技术》.2010,第34卷(第5期),628－631. * |
| 马琳等.自主车辆视觉***的摄像机动态自标定算法.《西安交通大学学报》.2005,(第10期), * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102135761A (en) | 2011-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102135761B (en) | Fuzzy self-adaptive control system for parameters of visual sensor | |
| US5268835A (en) | Process controller for controlling a process to a target state | |
| CN107608209A (en) | The feedforward of piezoelectric ceramic actuator and closed loop composite control method, system | |
| CN101825870B (en) | Method and system for controlling supply quantity of water-treatment flocculating agent | |
| CN106406083A (en) | Fuzzy control coal dressing method | |
| CN202033611U (en) | Fuzzy adaptive control system for parameters of visual sensor | |
| CN108646553A (en) | A method of statistics on-line monitoring closed-loop control system model quality | |
| CN110471285B (en) | Trend event driven fuzzy control method for zinc smelting roasting process | |
| CN203350635U (en) | Dynamic fuzzy control system | |
| EP4031939A1 (en) | Machine-learning-based quality prediction of manufactured fiber optic cable | |
| CN115993778A (en) | Fuzzy control method and device for temperature control system of high-low temperature test chamber | |
| CN105843078B (en) | Sliding-mode control and device | |
| CN114781249A (en) | High-density clarification tank dosage prediction and control method based on multidimensional scoring model | |
| CN112925207A (en) | Greenhouse environment temperature self-adaption method based on parameter identification | |
| CN113325696B (en) | Single neuron PID and model prediction combined hybrid control method applied to crosslinked cable production equipment | |
| CN109925992A (en) | It is a kind of based on multimode stage by stage continuously stir on-line monitoring method | |
| CN103412482A (en) | Dynamic fuzzy control system and control method thereof | |
| CN111538232A (en) | Unmanned driving anti-shaking positioning method and system based on adaptive neural fuzzy control | |
| CN107783416A (en) | A kind of control method of Dissolved Oxygen in Water content | |
| CN111077771A (en) | Self-tuning fuzzy PID control method | |
| CN109884884A (en) | A kind of method of adjustment and relevant apparatus of system Control platform | |
| CN116483003A (en) | Control method, device and equipment for coal water slurry manufacturing process | |
| Bello et al. | Control of a coagulation chemical dosing unit for water treatment plants using MMPC based on fuzzy weighting | |
| CN114277260A (en) | Online optimization control system for copper oxygen-enriched side-blown smelting process | |
| Staroverova et al. | Machine learning in the development of regulators: the specifics of data preparation and the choice of the ML model algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160725 Address after: Everwise Nanjing Road, Baixia High-tech Industrial Park in Jiangsu province 210014 No. 6 Chinese cloud innovation base building 6 layer B Patentee after: NANJING GMINNOVATION TECHNOLOGY Co.,Ltd. Address before: Guanghua Road, Baixia District Nanjing city Jiangsu province 210014 No. 1 Baixia high-tech park 5 floor C District of Nanjing Jammah Video Science and Technology Co Ltd Patentee before: Mu Keming Patentee before: Wang Xingguo Patentee before: Zhao Qiang |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130821 |