CN118225254A - Multi-parameter anomaly calibration system and method applied to thermal infrared imager - Google Patents
Multi-parameter anomaly calibration system and method applied to thermal infrared imager Download PDFInfo
- Publication number
- CN118225254A CN118225254A CN202410552357.4A CN202410552357A CN118225254A CN 118225254 A CN118225254 A CN 118225254A CN 202410552357 A CN202410552357 A CN 202410552357A CN 118225254 A CN118225254 A CN 118225254A
- Authority
- CN
- China
- Prior art keywords
- control behavior
- information
- behavior information
- focal plane
- control
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 87
- 238000012216 screening Methods 0.000 claims abstract description 16
- 238000013461 design Methods 0.000 claims abstract description 14
- 238000003384 imaging method Methods 0.000 claims description 33
- 230000000694 effects Effects 0.000 claims description 31
- 230000009471 action Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 9
- 230000003542 behavioural effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000033228 biological regulation Effects 0.000 abstract description 7
- 230000004069 differentiation Effects 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 142
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 241001394244 Planea Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/90—Testing, inspecting or checking operation of radiation pyrometers
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Image Processing (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention discloses a multi-parameter anomaly calibration system and method applied to a thermal infrared imager, and belongs to the technical field of thermal infrared imagers. Based on the internal structural design of the thermal infrared imager, generating a position label and an angle label of a focal plane, and recording control behavior information of a user side; randomizing the control behavior information into a plurality of groups, wherein each group forms a sub-set data cluster, analyzing the data quality, and carrying out quality screening on the control behavior information; classifying the control behavior information based on the screening result; evaluating the control behavior information through an evaluation index, and calibrating the control behavior based on an evaluation result; therefore, the method can make up the limitation of hardware, realize self-adaptive optimal regulation and control on software, and can realize the maximum range of unified index parameters based on the unified hardware limitation, so that the differentiation of the combination regulation and control of the software and the hardware is reduced as much as possible, and the abnormal calibration of the thermal infrared imager is realized.
Description
Technical Field
The invention relates to the technical field of thermal infrared imagers, in particular to a multi-parameter anomaly calibration system and method applied to the thermal infrared imagers.
Background
The infrared thermal imager realizes an imaging function through a focal plane array, and optimizes the induction behaviors of each detector unit in the focal plane array through software, so that focal plane compensation or calibration can be realized;
then, the focal plane hardware is limited, so that the compensation or calibration on the software is difficult to optimize based on the unified index parameters, and in many cases, the maximum limit optimization is realized on the software, but the selection of various control modes still exists on the hardware.
Disclosure of Invention
The invention aims to provide a multi-parameter anomaly calibration system and a multi-parameter anomaly calibration method applied to a thermal infrared imager so as to solve the problems in the background art.
In order to solve the technical problems, the invention provides the following technical scheme:
A multi-parameter anomaly calibration system applied to a thermal infrared imager comprises: the system comprises an operation log module, a data quality analysis module, a data processing module and a parameter calibration module;
The operation log module is used for generating a position label and an angle label of a focal plane based on the internal structural design of the thermal infrared imager and recording control behavior information of a user side;
The data quality analysis module is used for randomizing the control behavior information into a plurality of groups, forming a subset data cluster by each group, analyzing the data quality and carrying out quality screening on the control behavior information;
the data processing module classifies the control behavior information based on the screening result;
the parameter calibration module is used for evaluating the control behavior information through the evaluation index and calibrating the control behavior based on the evaluation result.
Further, the operation log module comprises a cache library unit and a tag pair unit;
The cache library unit is used for establishing an operation log cache library, wherein the operation log cache library stores control behavior information during each dynamic adjustment of imaging effect, and the control behavior information comprises position information of a focal plane and angle information of the focal plane; based on the internal structural design of the thermal infrared imager, respectively establishing a position tag and an angle tag of a focal plane in a unified form, wherein the position tag and the angle tag respectively have unique tag attributes;
The label pair unit is used for marking the ith position label as Let j-th angle label be/>Collecting control behavior information during the kth dynamic adjustment of imaging effect, generating a control behavior set, and recording asAnd/>Wherein/>E represents the total amount of control behavior information at the kth dynamic adjustment of imaging effect,/>, E represents the kth dynamic adjustment of imaging effectPosition tag representing focal plane/>And angle label of focal plane/>And (5) forming a label pair.
Further, the data quality analysis module comprises a subset construction unit and a quality analysis unit;
The subset forming unit is used for constructing a behavior representation two-dimensional coordinate system based on control behavior information, wherein the abscissa of the behavior representation two-dimensional coordinate system corresponds to a position label of a focal plane, and the ordinate of the behavior representation two-dimensional coordinate system corresponds to an angle label of the focal plane; marking control behavior information in the behavior representation two-dimensional coordinate system based on the behavior representation two-dimensional coordinate system; for control action set Each control behavior information in the control behavior information is randomly grouped to form a subset data cluster, and any subset data cluster is obtained and recorded as/>And/>，/>X represents the number of the subset data clusters, and y represents the total number of the subset data clusters; to control behavioural information/>As subset data clusters/>Respectively obtain subset data clusters/>Punctuation corresponding to each control behavior information and control behavior information/>Euclidean distance between corresponding punctuations, and based on the Euclidean distance, obtaining a subset data cluster/>Is denoted as/>；
The quality analysis unit is used for constructing a data quality iterative analysis model, and controlling a behavior set during each iterationA sample input is selected at will, and the sample input selected in each iteration is different;
Control behavior information As a sample input for the r-th iteration, a data quality value is calculated, and a specific calculation formula is as follows:
Wherein, Representing control behavior information/>Data quality value of/>A desired value representing a minimum intra-cluster distance;
Presetting a data quality threshold, and extracting control behavior information if the data quality value is greater than or equal to the data quality threshold And stores the output information set/>In the process, otherwise, the control behavior information/>, is removed；
Up to the control action setAfter each piece of control behavior information participates in iteration, the iteration is stopped.
Further, the data processing module comprises a first classifier unit and a second classifier unit;
the first classifier unit is used for outputting information sets Performing first behavior classification, traversing tag pairs with the same first classification references by taking the position information of the same focal plane as the first classification references, and generating a first classification set, which is recorded as/>Wherein/>Representing position information in focal plane/>Correspondingly generating a first classification set for the first classification reference;
The second classifier unit is used for outputting information sets Performing second behavior classification, traversing label pairs with the same second classification references by taking angle information of the same focal plane as the second classification references, and generating a second classification set, which is recorded as/>Wherein/>Represents angle information in focal plane/>For the second class reference, the generated second class set corresponds.
Further, the parameter calibration module comprises an index parameter unit and a calibration analysis unit;
The index parameter unit is used for establishing an evaluation index parameter category information base, and index parameter category information for evaluating the control effect is stored in the evaluation index parameter category information base; uniformly coding the evaluation index parameters to form an evaluation index parameter set with unique coding attribute, and recording the evaluation index parameter set as Wherein/>Represents the a-th evaluation index parameter, A represents the total number of evaluation index parameters;
the calibration analysis unit is used for evaluating the index parameter set Each of the evaluation index parameter pairs controls behavior information/>Evaluating to obtain control behavior information/>Is a mean value of the initial evaluation of (a); based on the initial evaluation mean value of each piece of control behavior information in the first classification set, obtaining position information/>Is denoted as/>; Based on the initial evaluation mean value of each piece of control behavior information in the second classification set, angle information/> isobtainedIs recorded as/>；
Respectively byAnd/>And calibrating the positions and angles of the focusing planes of the corresponding position labels and the angle labels.
The multi-parameter anomaly calibration method applied to the thermal infrared imager comprises the following steps of:
Step S100: based on the internal structural design of the thermal infrared imager, generating a position label and an angle label of a focal plane, and recording control behavior information of a user side;
step S200: randomizing the control behavior information into a plurality of groups, wherein each group forms a sub-set data cluster, analyzing the data quality, and carrying out quality screening on the control behavior information;
step S300: classifying the control behavior information based on the screening result;
Step S400: and evaluating the control behavior information through the evaluation index, and calibrating the control behavior based on the evaluation result.
Further, the specific implementation process of the step S100 includes:
Step S101: establishing an operation log cache, wherein the operation log cache stores control behavior information during each dynamic adjustment of imaging effect, and the control behavior information comprises position information of a focal plane and angle information of the focal plane; based on the internal structural design of the thermal infrared imager, respectively establishing a position tag and an angle tag of a focal plane in a unified form, wherein the position tag and the angle tag respectively have unique tag attributes;
Step S102: marking the ith position tag as Let j-th angle label be/>Collecting control behavior information during the kth dynamic adjustment of imaging effect, and generating a control behavior set which is recorded as/>And (2) andWherein/>E represents the total amount of control behavior information at the kth dynamic adjustment of imaging effect,/>, E represents the kth dynamic adjustment of imaging effectPosition tag representing focal plane/>And angle label of focal plane/>And (5) forming a label pair.
Further, the specific implementation process of the step S200 includes:
Step S201: constructing a behavior representation two-dimensional coordinate system based on control behavior information, wherein the abscissa of the behavior representation two-dimensional coordinate system corresponds to a position label of a focal plane, and the ordinate of the behavior representation two-dimensional coordinate system corresponds to an angle label of the focal plane; marking control behavior information in the behavior representation two-dimensional coordinate system based on the behavior representation two-dimensional coordinate system; for control action set Each control behavior information in the control behavior information is randomly grouped to form a subset data cluster, and any subset data cluster is obtained and recorded as/>And/>，/>X represents the number of the subset data clusters, and y represents the total number of the subset data clusters; to control behavioural information/>As subset data clusters/>Respectively obtain subset data clusters/>Punctuation corresponding to each control behavior information and control behavior information/>Euclidean distance between corresponding punctuations, and based on the Euclidean distance, obtaining a subset data cluster/>Is denoted as/>；
Step S202: constructing a data quality iterative analysis model, and controlling a behavior set during each iterationA sample input is selected at will, and the sample input selected in each iteration is different;
Control behavior information As a sample input for the r-th iteration, a data quality value is calculated, and a specific calculation formula is as follows:
Wherein, Representing control behavior information/>Data quality value of/>A desired value representing a minimum intra-cluster distance;
Presetting a data quality threshold, and extracting control behavior information if the data quality value is greater than or equal to the data quality threshold And stores the output information set/>In the process, otherwise, the control behavior information/>, is removed；
Up to the control action setAfter each piece of control behavior information participates in iteration, the iteration is stopped;
According to the method, in the imaging process, the infrared thermal imager is used, the imaging effect is different due to the change of different positions and different angles of a focal plane on hardware, and the defect on the hardware is optimized through different index parameters on software; the data quality iterative analysis model screens out the hardware control mode of the focal plane with similar characteristics through the similarity analysis of the intra-cluster distance; and then limited by hardware functions, and not satisfying control behaviors with similar characteristics, can exhibit the same imaging effect.
Further, the implementation process of the step S300 includes:
step S301: for output information set Performing behavior classification, traversing tag pairs with the same first classification references by taking the position information of the same focal plane as the first classification references, and generating a first classification set, which is recorded as/>Wherein/>Representing position information in focal plane/>Correspondingly generating a first classification set for the first classification reference;
step S302: traversing tag pairs with the same second classification references by taking the angle information of the same focal plane as the second classification references, and generating a second classification set which is recorded as Wherein/>Represents angle information in focal plane/>For the second class reference, the generated second class set corresponds.
Further, the specific implementation process of the step S400 includes:
Step S401: establishing an evaluation index parameter category information base, wherein index parameter category information for evaluating the control effect is stored in the evaluation index parameter category information base; uniformly coding the evaluation index parameters to form an evaluation index parameter set with unique coding attribute, and recording the evaluation index parameter set as Wherein/>Represents the a-th evaluation index parameter, A represents the total number of evaluation index parameters;
step S402: by evaluating sets of index parameters Each of the evaluation index parameter pairs controls behavior information/>Evaluating to obtain control behavior information/>Is a mean value of the initial evaluation of (a); based on the initial evaluation mean value of each piece of control behavior information in the first classification set, obtaining position information/>Is denoted as/>; Based on the initial evaluation mean value of each piece of control behavior information in the second classification set, angle information/> isobtainedIs recorded as/>；
Respectively byAnd/>Calibrating the positions and angles of the focusing planes of the corresponding position labels and the angle labels;
According to the method, each evaluation index parameter participates in the evaluation of the imaging effect in software, but the evaluation values always have differences due to the limitation of focal plane hardware, and the differences are difficult to optimize through unified index parameters; based on different states of the focal plane, the evaluation values of imaging effects of different index parameters are respectively obtained, and the unified index parameters in the maximum range can be limited based on unified hardware, so that the differentiation of combination regulation of software and hardware is reduced as much as possible; and/> Different optimal achievement evaluation values are obtained under unified index parameters which respectively form a maximum range by unified position limitation and unified angle limitation; furthermore, the position limitation and the angle limitation are combined, the unification on the hardware limitation is realized, and meanwhile, the self-adaptive optimal regulation and control on the software is realized by combining the unification of the hardware limitation.
Compared with the prior art, the invention has the following beneficial effects: the invention provides a multi-parameter anomaly calibration system and a multi-parameter anomaly calibration method applied to a thermal infrared imager, which are used for generating a position label and an angle label of a focal plane based on the internal structural design of the thermal infrared imager and recording control behavior information of a user side; randomizing the control behavior information into a plurality of groups, wherein each group forms a sub-set data cluster, analyzing the data quality, and carrying out quality screening on the control behavior information; classifying the control behavior information based on the screening result; evaluating the control behavior information through an evaluation index, and calibrating the control behavior based on an evaluation result; therefore, the method can make up the limitation of hardware, realize self-adaptive optimal regulation and control on software, and can realize the maximum range of unified index parameters based on the unified hardware limitation, so that the differentiation of the combination regulation and control of the software and the hardware is reduced as much as possible, and the abnormal calibration of the thermal infrared imager is realized.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a multi-parameter anomaly calibration system for a thermal infrared imager according to the present invention;
fig. 2 is a schematic step diagram of a multi-parameter anomaly calibration method applied to a thermal infrared imager.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions:
Referring to fig. 1, in a first embodiment: provided is a multi-parameter anomaly calibration system applied to a thermal infrared imager, which comprises: the system comprises an operation log module, a data quality analysis module, a data processing module and a parameter calibration module;
The operation log module is used for generating a position label and an angle label of a focal plane based on the internal structural design of the thermal infrared imager and recording control behavior information of a user side;
The operation log module comprises a cache library unit and a tag pair unit;
The cache library unit is used for establishing an operation log cache library, and the operation log cache library stores control behavior information during each dynamic adjustment of imaging effect, wherein the control behavior information comprises position information of a focal plane and angle information of the focal plane; based on the internal structural design of the thermal infrared imager, respectively establishing a position tag and an angle tag of a focal plane in a unified form, wherein the position tag and the angle tag respectively have unique tag attributes;
A tag pair unit for marking the ith position tag as Let j-th angle label be/>Collecting control behavior information during the kth dynamic adjustment of imaging effect, and generating a control behavior set which is recorded as/>And/>Wherein/>E represents the total amount of control behavior information at the kth dynamic adjustment of imaging effect,/>, E represents the kth dynamic adjustment of imaging effectPosition tag representing focal plane/>And angle label of focal plane/>A label pair is formed;
The data quality analysis module is used for randomizing the control behavior information into a plurality of groups, forming a subset data cluster by each group, analyzing the data quality and carrying out quality screening on the control behavior information;
the data quality analysis module comprises a subset forming unit and a quality analysis unit;
The subset forming unit is used for constructing a behavior representation two-dimensional coordinate system based on the control behavior information, wherein the abscissa of the behavior representation two-dimensional coordinate system corresponds to the position label of the focal plane, and the ordinate of the behavior representation two-dimensional coordinate system corresponds to the angle label of the focal plane; marking control behavior information in the behavior representation two-dimensional coordinate system based on the behavior representation two-dimensional coordinate system; for control action set Each control behavior information in the control behavior information is randomly grouped to form a subset data cluster, and any subset data cluster is obtained and recorded as/>And/>，/>X represents the number of the subset data clusters, and y represents the total number of the subset data clusters; to control behavioural information/>As subset data clusters/>Respectively obtain subset data clusters/>Punctuation corresponding to each control behavior information and control behavior information/>Euclidean distance between corresponding punctuations, and based on the Euclidean distance, obtaining a subset data cluster/>Is denoted as/>；
The quality analysis unit is used for constructing a data quality iterative analysis model, and controlling the behavior set during each iterationA sample input is selected at will, and the sample input selected in each iteration is different;
Control behavior information As a sample input for the r-th iteration, a data quality value is calculated, and a specific calculation formula is as follows:
Wherein, Representing control behavior information/>Data quality value of/>A desired value representing a minimum intra-cluster distance;
Presetting a data quality threshold, and extracting control behavior information if the data quality value is greater than or equal to the data quality threshold And stores the output information set/>In the process, otherwise, the control behavior information/>, is removed；
Up to the control action setAfter each piece of control behavior information participates in iteration, the iteration is stopped;
The data processing module classifies the control behavior information based on the screening result;
The data processing module comprises a first classifier unit and a second classifier unit;
A first classifier unit for outputting information sets Performing first behavior classification, traversing tag pairs with the same first classification references by taking the position information of the same focal plane as the first classification references, and generating a first classification set, which is recorded as/>Wherein/>Representing position information in focal plane/>Correspondingly generating a first classification set for the first classification reference;
A second classifier unit for outputting information sets Performing second behavior classification, traversing label pairs with the same second classification references by taking angle information of the same focal plane as the second classification references, and generating a second classification set, which is recorded as/>Wherein/>Represents angle information in focal plane/>Correspondingly generating a second classification set for the second classification reference;
The parameter calibration module is used for evaluating the control behavior information through the evaluation index and calibrating the control behavior based on the evaluation result
The parameter calibration module comprises an index parameter unit and a calibration analysis unit;
The index parameter unit is used for establishing an evaluation index parameter category information base, and index parameter category information for evaluating the control effect is stored in the evaluation index parameter category information base; uniformly coding the evaluation index parameters to form an evaluation index parameter set with unique coding attribute, and recording the evaluation index parameter set as Wherein/>Represents the a-th evaluation index parameter, A represents the total number of evaluation index parameters;
calibration analysis unit for evaluating index parameter set Each of the evaluation index parameter pairs controls behavior information/>Evaluating to obtain control behavior information/>Is a mean value of the initial evaluation of (a); based on the initial evaluation mean value of each piece of control behavior information in the first classification set, obtaining position information/>Is denoted as/>; Based on the initial evaluation mean value of each piece of control behavior information in the second classification set, angle information/> isobtainedIs recorded as/>；
Respectively byAnd/>And calibrating the positions and angles of the focusing planes of the corresponding position labels and the angle labels.
Referring to fig. 2, in the second embodiment: the multi-parameter anomaly calibration method applied to the thermal infrared imager comprises the following steps of:
Step S100: based on the internal structural design of the thermal infrared imager, generating a position label and an angle label of a focal plane, and recording control behavior information of a user side;
Specifically, an operation log buffer library is established, and control behavior information during each dynamic adjustment of imaging effect is stored in the operation log buffer library, wherein the control behavior information comprises focal plane position information and focal plane angle information; based on the internal structural design of the thermal infrared imager, respectively establishing a position tag and an angle tag of a focal plane in a unified form, wherein the position tag and the angle tag respectively have unique tag attributes;
Marking the ith position tag as Let j-th angle label be/>Collecting control behavior information during the kth dynamic adjustment of imaging effect, and generating a control behavior set which is recorded as/>And/>Wherein/>E represents the total amount of control behavior information at the kth dynamic adjustment of imaging effect,/>, E represents the kth dynamic adjustment of imaging effectPosition tag representing focal plane/>Angle label for sum focal planeA label pair is formed;
step S200: randomizing the control behavior information into a plurality of groups, wherein each group forms a sub-set data cluster, analyzing the data quality, and carrying out quality screening on the control behavior information;
Specifically, a behavior representation two-dimensional coordinate system is constructed based on control behavior information, the abscissa of the behavior representation two-dimensional coordinate system corresponds to a position label of a focal plane, and the ordinate of the behavior representation two-dimensional coordinate system corresponds to an angle label of the focal plane; marking control behavior information in the behavior representation two-dimensional coordinate system based on the behavior representation two-dimensional coordinate system; for control action set Each control behavior information in the control behavior information is randomly grouped to form a subset data cluster, and any subset data cluster is obtained and recorded as/>And/>，/>X represents the number of the subset data clusters, and y represents the total number of the subset data clusters; to control behavioural information/>As subset data clusters/>Respectively obtain subset data clusters/>Punctuation corresponding to each control behavior information and control behavior information/>Euclidean distance between corresponding punctuations, and based on the Euclidean distance, obtaining a subset data cluster/>Is denoted as/>；
Constructing a data quality iterative analysis model, and controlling a behavior set during each iterationA sample input is selected at will, and the sample input selected in each iteration is different;
Control behavior information As a sample input for the r-th iteration, a data quality value is calculated, and a specific calculation formula is as follows:
Wherein, Representing control behavior information/>Data quality value of/>A desired value representing a minimum intra-cluster distance;
Presetting a data quality threshold, and extracting control behavior information if the data quality value is greater than or equal to the data quality threshold And stores the output information set/>In the process, otherwise, the control behavior information/>, is removed；
Up to the control action setAfter each piece of control behavior information participates in iteration, the iteration is stopped;
step S300: classifying the control behavior information based on the screening result;
Specifically, for output information set Performing behavior classification, traversing tag pairs with the same first classification references by taking the position information of the same focal plane as the first classification references, and generating a first classification set, which is recorded as/>Wherein, the method comprises the steps of, wherein,Representing position information in focal plane/>Correspondingly generating a first classification set for the first classification reference;
Traversing tag pairs with the same second classification references by taking the angle information of the same focal plane as the second classification references, and generating a second classification set which is recorded as Wherein/>Represents angle information in focal plane/>Correspondingly generating a second classification set for the second classification reference;
Step S400: evaluating the control behavior information through an evaluation index, and calibrating the control behavior based on an evaluation result;
Specifically, an evaluation index parameter category information base is established, and index parameter category information for evaluating the control effect is stored in the evaluation index parameter category information base; uniformly coding the evaluation index parameters to form an evaluation index parameter set with unique coding attribute, and recording the evaluation index parameter set as Wherein/>Represents the a-th evaluation index parameter, A represents the total number of evaluation index parameters;
for example, index categories include sharpness, depth of field, distortion, and aberrations; meanwhile, parameters corresponding to each index category have the characteristic of diversification;
By evaluating sets of index parameters Each of the evaluation index parameter pairs controls behavior information/>Evaluating to obtain control behavior information/>Is a mean value of the initial evaluation of (a); based on the initial evaluation mean value of each piece of control behavior information in the first classification set, obtaining position information/>Is denoted as/>; Based on the initial evaluation mean value of each piece of control behavior information in the second classification set, angle information/> isobtainedIs recorded as/>；
Respectively byAnd/>Calibrating the positions and angles of the focusing planes of the corresponding position labels and the angle labels;
For example, when the imaging effect is dynamically adjusted for the 5 th time, the imaging effect under e=20 control actions is obtained through the regulation and control of a large number of control actions, the adaptive learning is performed on the basis of the 20 control actions on the algorithm, and finally the imaging effect is obtained And/>Corresponding location tag/>And angle tag/>The position and angle of the focal plane are calibrated.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention and is not intended to limit the present invention, but although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The multi-parameter anomaly calibration method applied to the thermal infrared imager is characterized by comprising the following steps of:
Step S100: based on the internal structural design of the thermal infrared imager, generating a position label and an angle label of a focal plane, and recording control behavior information of a user side;
step S200: randomizing the control behavior information into a plurality of groups, wherein each group forms a sub-set data cluster, analyzing the data quality, and carrying out quality screening on the control behavior information;
step S300: classifying the control behavior information based on the screening result;
Step S400: and evaluating the control behavior information through the evaluation index, and calibrating the control behavior based on the evaluation result.
2. The method for calibrating multi-parameter anomalies applied to thermal infrared imager according to claim 1, wherein the implementation process of step S100 comprises:
Step S101: establishing an operation log cache, wherein the operation log cache stores control behavior information during each dynamic adjustment of imaging effect, and the control behavior information comprises position information of a focal plane and angle information of the focal plane; based on the internal structural design of the thermal infrared imager, respectively establishing a position tag and an angle tag of a focal plane in a unified form, wherein the position tag and the angle tag respectively have unique tag attributes;
Step S102: marking the ith position tag as Let j-th angle label be/>Collecting control behavior information during the kth dynamic adjustment of imaging effect, and generating a control behavior set which is recorded as/>And (2) andWherein/>E represents the total amount of control behavior information at the kth dynamic adjustment of imaging effect,/>, E represents the kth dynamic adjustment of imaging effectPosition tag representing focal plane/>And angle label of focal plane/>And (5) forming a label pair.
3. The method for calibrating multi-parameter anomaly applied to thermal infrared imager according to claim 2, wherein the implementation process of step S200 comprises:
Step S201: constructing a behavior representation two-dimensional coordinate system based on control behavior information, wherein the abscissa of the behavior representation two-dimensional coordinate system corresponds to a position label of a focal plane, and the ordinate of the behavior representation two-dimensional coordinate system corresponds to an angle label of the focal plane; marking control behavior information in the behavior representation two-dimensional coordinate system based on the behavior representation two-dimensional coordinate system; for control action set Each control behavior information in the control behavior information is randomly grouped to form a subset data cluster, and any subset data cluster is obtained and recorded as/>And/>，/>X represents the number of the subset data clusters, and y represents the total number of the subset data clusters; to control behavioural information/>As subset data clusters/>Respectively obtain subset data clusters/>Punctuation corresponding to each control behavior information and control behavior information/>Euclidean distance between corresponding punctuations, and based on the Euclidean distance, obtaining a subset data cluster/>Is denoted as/>；
Step S202: constructing a data quality iterative analysis model, and controlling a behavior set during each iterationA sample input is selected at will, and the sample input selected in each iteration is different;
Control behavior information As a sample input for the r-th iteration, a data quality value is calculated, and a specific calculation formula is as follows:
Wherein, Representing control behavior information/>Data quality value of/>A desired value representing a minimum intra-cluster distance;
Presetting a data quality threshold, and extracting control behavior information if the data quality value is greater than or equal to the data quality threshold And stores the output information set/>In the process, otherwise, the control behavior information/>, is removed；
Up to the control action setAfter each piece of control behavior information participates in iteration, the iteration is stopped.
4. The method for calibrating multi-parameter anomalies applied to thermal infrared imager according to claim 3, wherein the implementation process of step S300 comprises:
step S301: for output information set Performing behavior classification, traversing tag pairs with the same first classification references by taking the position information of the same focal plane as the first classification references, and generating a first classification set, which is recorded as/>Wherein, the method comprises the steps of, wherein,Representing position information in focal plane/>Correspondingly generating a first classification set for the first classification reference;
step S302: traversing tag pairs with the same second classification references by taking the angle information of the same focal plane as the second classification references, and generating a second classification set which is recorded as Wherein/>Represents angle information in focal plane/>For the second class reference, the generated second class set corresponds.
5. The method for calibrating multi-parameter anomalies applied to thermal infrared imager according to claim 4, wherein the implementation process of step S400 comprises:
Step S401: establishing an evaluation index parameter category information base, wherein index parameter category information for evaluating the control effect is stored in the evaluation index parameter category information base; uniformly coding the evaluation index parameters to form an evaluation index parameter set with unique coding attribute, and recording the evaluation index parameter set as Wherein/>Represents the a-th evaluation index parameter, A represents the total number of evaluation index parameters;
step S402: by evaluating sets of index parameters Each of the evaluation index parameter pairs controls behavior information/>Evaluating to obtain control behavior information/>Is a mean value of the initial evaluation of (a); based on the initial evaluation mean value of each piece of control behavior information in the first classification set, obtaining position information/>Is denoted as/>; Based on the initial evaluation mean value of each piece of control behavior information in the second classification set, angle information/> isobtainedIs recorded as/>；
Respectively byAnd/>And calibrating the positions and angles of the focusing planes of the corresponding position labels and the angle labels.
6. A multi-parameter anomaly calibration system for a thermal infrared imager, the system comprising: the system comprises an operation log module, a data quality analysis module, a data processing module and a parameter calibration module;
The operation log module is used for generating a position label and an angle label of a focal plane based on the internal structural design of the thermal infrared imager and recording control behavior information of a user side;
The data quality analysis module is used for randomizing the control behavior information into a plurality of groups, forming a subset data cluster by each group, analyzing the data quality and carrying out quality screening on the control behavior information;
the data processing module classifies the control behavior information based on the screening result;
the parameter calibration module is used for evaluating the control behavior information through the evaluation index and calibrating the control behavior based on the evaluation result.
7. The multi-parameter anomaly calibration system for a thermal infrared imager according to claim 6, wherein: the operation log module comprises a cache library unit and a tag pair unit;
The cache library unit is used for establishing an operation log cache library, wherein the operation log cache library stores control behavior information during each dynamic adjustment of imaging effect, and the control behavior information comprises position information of a focal plane and angle information of the focal plane; based on the internal structural design of the thermal infrared imager, respectively establishing a position tag and an angle tag of a focal plane in a unified form, wherein the position tag and the angle tag respectively have unique tag attributes;
The label pair unit is used for marking the ith position label as Let j-th angle label be/>Collecting control behavior information during the kth dynamic adjustment of imaging effect, and generating a control behavior set which is recorded as/>And/>Wherein/>E represents the total amount of control behavior information at the kth dynamic adjustment of imaging effect,/>, E represents the kth dynamic adjustment of imaging effectPosition tag representing focal plane/>And angle label of focal plane/>And (5) forming a label pair.
8. The multi-parameter anomaly calibration system for a thermal infrared imager according to claim 7, wherein: the data quality analysis module comprises a subset forming unit and a quality analysis unit;
The subset forming unit is used for constructing a behavior representation two-dimensional coordinate system based on control behavior information, wherein the abscissa of the behavior representation two-dimensional coordinate system corresponds to a position label of a focal plane, and the ordinate of the behavior representation two-dimensional coordinate system corresponds to an angle label of the focal plane; marking control behavior information in the behavior representation two-dimensional coordinate system based on the behavior representation two-dimensional coordinate system; for control action set Each control behavior information in the control behavior information is randomly grouped to form a subset data cluster, and any subset data cluster is obtained and recorded as/>And/>，/>X represents the number of the subset data clusters, and y represents the total number of the subset data clusters; to control behavioural information/>As subset data clusters/>Respectively obtain subset data clusters/>Punctuation corresponding to each control behavior information and control behavior information/>Euclidean distance between corresponding punctuations, and based on the Euclidean distance, obtaining a subset data cluster/>Is denoted as/>；
The quality analysis unit is used for constructing a data quality iterative analysis model, and controlling a behavior set during each iterationA sample input is selected at will, and the sample input selected in each iteration is different;
Control behavior information As a sample input for the r-th iteration, a data quality value is calculated, and a specific calculation formula is as follows:
Wherein, Representing control behavior information/>Data quality value of/>A desired value representing a minimum intra-cluster distance;
Presetting a data quality threshold, and extracting control behavior information if the data quality value is greater than or equal to the data quality threshold And stores the output information set/>In the process, otherwise, the control behavior information/>, is removed；
Up to the control action setAfter each piece of control behavior information participates in iteration, the iteration is stopped.
9. The multi-parameter anomaly calibration system for a thermal infrared imager according to claim 8, wherein: the data processing module comprises a first classifier unit and a second classifier unit;
the first classifier unit is used for outputting information sets Performing first behavior classification, traversing tag pairs with the same first classification references by taking the position information of the same focal plane as the first classification references, and generating a first classification set, which is recorded as/>Wherein/>Representing position information in focal plane/>Correspondingly generating a first classification set for the first classification reference;
The second classifier unit is used for outputting information sets Performing second behavior classification, traversing label pairs with the same second classification references by taking angle information of the same focal plane as the second classification references, and generating a second classification set, which is recorded as/>Wherein/>Represents angle information in focal plane/>For the second class reference, the generated second class set corresponds.
10. The multi-parameter anomaly calibration system for a thermal infrared imager according to claim 9, wherein: the parameter calibration module comprises an index parameter unit and a calibration analysis unit;
The index parameter unit is used for establishing an evaluation index parameter category information base, and index parameter category information for evaluating the control effect is stored in the evaluation index parameter category information base; uniformly coding the evaluation index parameters to form an evaluation index parameter set with unique coding attribute, and recording the evaluation index parameter set as Wherein/>Represents the a-th evaluation index parameter, A represents the total number of evaluation index parameters;
the calibration analysis unit is used for evaluating the index parameter set Each of the evaluation index parameter pairs controls behavior information/>Evaluating to obtain control behavior information/>Is a mean value of the initial evaluation of (a); based on the initial evaluation mean value of each piece of control behavior information in the first classification set, obtaining position information/>Is denoted as/>; Based on the initial evaluation mean value of each piece of control behavior information in the second classification set, angle information/> isobtainedIs recorded as/>；
Respectively byAnd/>And calibrating the positions and angles of the focusing planes of the corresponding position labels and the angle labels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410552357.4A CN118225254B (en) | 2024-05-07 | 2024-05-07 | Multi-parameter anomaly calibration system and method applied to thermal infrared imager |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410552357.4A CN118225254B (en) | 2024-05-07 | 2024-05-07 | Multi-parameter anomaly calibration system and method applied to thermal infrared imager |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118225254A true CN118225254A (en) | 2024-06-21 |
| CN118225254B CN118225254B (en) | 2024-11-08 |
Family
ID=91511972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410552357.4A Active CN118225254B (en) | 2024-05-07 | 2024-05-07 | Multi-parameter anomaly calibration system and method applied to thermal infrared imager |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118225254B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190140619A (en) * | 2018-06-12 | 2019-12-20 | 중앙대학교 산학협력단 | Method and apparatus for generating feature subset in classifying multi-label pattern |
| US20230097665A1 (en) * | 2020-11-25 | 2023-03-30 | Hitachi, Ltd. | Tag domain presentation device, tag domain presentation method, and information processing system using the same |
| CN116305705A (en) * | 2021-12-20 | 2023-06-23 | 中国科学院沈阳自动化研究所 | Imaging system environment adaptability assessment method based on infrared simulation |
| CN116720118A (en) * | 2023-06-13 | 2023-09-08 | 平安科技（深圳）有限公司 | Label quality intelligent analysis method and device, electronic equipment and storage medium |
| CN117323578A (en) * | 2023-12-01 | 2024-01-02 | 深圳恩多克医疗有限公司 | Intelligent control method and system for infrared therapeutic apparatus |
| CN117563144A (en) * | 2023-12-04 | 2024-02-20 | 惠州市凌盛医疗科技有限公司 | Method and system for evaluating condition and predicting residual life of infrared therapeutic instrument |
-
2024
- 2024-05-07 CN CN202410552357.4A patent/CN118225254B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190140619A (en) * | 2018-06-12 | 2019-12-20 | 중앙대학교 산학협력단 | Method and apparatus for generating feature subset in classifying multi-label pattern |
| US20230097665A1 (en) * | 2020-11-25 | 2023-03-30 | Hitachi, Ltd. | Tag domain presentation device, tag domain presentation method, and information processing system using the same |
| CN116305705A (en) * | 2021-12-20 | 2023-06-23 | 中国科学院沈阳自动化研究所 | Imaging system environment adaptability assessment method based on infrared simulation |
| CN116720118A (en) * | 2023-06-13 | 2023-09-08 | 平安科技（深圳）有限公司 | Label quality intelligent analysis method and device, electronic equipment and storage medium |
| CN117323578A (en) * | 2023-12-01 | 2024-01-02 | 深圳恩多克医疗有限公司 | Intelligent control method and system for infrared therapeutic apparatus |
| CN117563144A (en) * | 2023-12-04 | 2024-02-20 | 惠州市凌盛医疗科技有限公司 | Method and system for evaluating condition and predicting residual life of infrared therapeutic instrument |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118225254B (en) | 2024-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190665B (en) | Universal image classification method and device based on semi-supervised generation countermeasure network | |
| KR20220095216A (en) | BBP-assisted defect detection flow for SEM images | |
| CN109726195B (en) | Data enhancement method and device | |
| Wu et al. | Application of adaptive machine learning systems in heterogeneous data environments | |
| CN116147130A (en) | Intelligent home control system and method thereof | |
| CN112348761B (en) | Equipment appearance image brightness adjusting method and device | |
| CN116229036A (en) | Data acquisition system, method, computer device and storage medium | |
| CN116312782A (en) | Spatial transcriptome spot region clustering method fusing image gene data | |
| CN115310554A (en) | Item allocation strategy, system, storage medium and device based on deep clustering | |
| CN111191742A (en) | Sliding window length self-adaptive adjustment method for multi-source heterogeneous data stream | |
| Zhang | Application of artificial intelligence recognition technology in digital image processing | |
| CN113297723A (en) | Mean shift-grey correlation analysis based optimization method for temperature measuring points of motorized spindle | |
| CN118225254B (en) | Multi-parameter anomaly calibration system and method applied to thermal infrared imager | |
| CN116721343A (en) | Cross-domain field cotton boll recognition method based on deep convolutional neural network | |
| CN110365404B (en) | Wavefront-free sensing self-adaptive system and method for improving convergence speed by using same | |
| CN113377991B (en) | Image retrieval method based on most difficult positive and negative samples | |
| CN114186589A (en) | Superconducting cable partial discharge mode identification method based on residual error network Resnet50 | |
| TWI802827B (en) | Method for correcting abnormal point cloud | |
| JP7192854B2 (en) | Arithmetic device, arithmetic method, program and discrimination system | |
| CN116822590A (en) | Forgetting measurement model based on GAN and working method thereof | |
| CN112580621B (en) | Identity card copying and identifying method and device, electronic equipment and storage medium | |
| CN109359694B (en) | Image classification method and device based on mixed collaborative representation classifier | |
| CN112766358A (en) | Training method of neural network for dust suction intensity control | |
| CN112613521A (en) | Multilevel data analysis system and method based on data conversion | |
| CN111882061B (en) | Convolutional neural network training method based on hierarchical random gradient descent |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |