CN110473183B - Evaluation method, device, electronic equipment and medium for visible light full-link simulation image - Google Patents
Evaluation method, device, electronic equipment and medium for visible light full-link simulation image Download PDFInfo
- Publication number
- CN110473183B CN110473183B CN201910716286.6A CN201910716286A CN110473183B CN 110473183 B CN110473183 B CN 110473183B CN 201910716286 A CN201910716286 A CN 201910716286A CN 110473183 B CN110473183 B CN 110473183B
- Authority
- CN
- China
- Prior art keywords
- image
- full
- index
- simulation
- evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 162
- 238000004088 simulation Methods 0.000 title claims abstract description 122
- 238000000034 method Methods 0.000 claims abstract description 42
- 230000003287 optical effect Effects 0.000 claims abstract description 25
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 238000003384 imaging method Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012634 optical imaging Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000003930 cognitive ability Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000013215 result calculation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides a method for evaluating a full-link simulation image facing visible light, which comprises the following steps: acquiring original optical image data of actual imaging of an in-orbit satellite; acquiring image data of a full-link simulation system corresponding to the original optical image; determining a first-level evaluation index, and evaluating the full-link simulation system according to the first-level evaluation index; acquiring an evaluation result of the full-link simulation system, and determining a secondary evaluation index corresponding to the evaluation result according to the evaluation result; and calculating an evaluation index of the image data of the full-link simulation system according to the secondary evaluation index calculation result. In this way, objective index evaluation at the corresponding level stage can be performed according to different remote sensing technology levels, target-oriented interpretation can be realized, an auxiliary support for problem analysis basis and simulation image availability conclusion can be provided, and the reproducibility of the simulation technology on the satellite imaging system performance can be effectively verified.
Description
Technical Field
The invention relates to the technical field of remote sensing, in particular to a method, a device, electronic equipment and a medium for evaluating a full-link simulation image oriented to visible light.
Background
The evaluation of the simulation result is an important link of the simulation technology, and along with the improvement of theory and technology and cognition capability, the repeated progress of cognition, practice, reconsideration and rerun practice, the reality of the simulation is gradually improved. According to different simulation objects, purposes and requirements, the requirements on simulation evaluation indexes are different, and an evaluation result is an important reference basis for determining whether the simulation result reaches the expected purpose or not and is also an important support for achievement popularization and application.
The development of the optical imaging full-link simulation system can provide technical support for the demonstration design, development process inspection and operation process evaluation of the remote sensing system. The full-link simulation image is a simulation output result of the optical imaging full-link simulation system, the simulation image is evaluated by taking a synchronous satellite observation image as a standard reference, and the evaluation index and the method are designed from the aspects of similarity and reliability, and finally, the availability conclusion of the simulation result is obtained, so that the reproduction capability of the simulation technology on the satellite imaging system performance can be verified. The prior art has the following defects:
1) The remote sensing image quality evaluation field forms some research results, but can not reflect the similarity degree and the credibility degree of the simulation image and the real shot image, and simultaneously has the problem that the evaluation index is not suitable for the simulation capability.
2) For applications such as target interpretation, although subjective evaluation can obtain reliable and accurate results, subjective evaluation consumes a lot of manpower and time, often has insufficient stability, and is unfavorable for real-time online evaluation and feedback processing of system automation. Therefore, the objective evaluation method with better consistency with subjective evaluation is required to be provided for the evaluation of the optical remote sensing full-link simulation image oriented to the target interpretation.
Disclosure of Invention
Therefore, in order to overcome the defects of the prior art, the invention provides a method, a device, electronic equipment and a medium for evaluating a full-link simulation image facing visible light.
In order to achieve the above purpose, a method for evaluating a full-link simulation image for visible light is provided, which comprises the following steps:
step 1) obtaining original optical image data of actual imaging of an in-orbit satellite;
step 2) obtaining image data of a full-link simulation system corresponding to the original optical image;
step 3) determining a first-level evaluation index, and evaluating the full-link simulation system according to the first-level evaluation index;
step 4) obtaining an evaluation result of the full-link simulation system, and determining a secondary evaluation index corresponding to the evaluation result according to the evaluation result;
and 5) calculating an evaluation index of the image data of the full-link simulation system according to the secondary evaluation index calculation result.
Preferably, the first level evaluation index in the step 3) includes, but is not limited to: confidence intervals of the full-link simulation system, wherein the confidence intervals comprise a low confidence interval, a middle confidence interval and a high confidence interval.
Preferably, the obtaining the evaluation result of the full-link simulation system in the step 4) further includes: and evaluating the confidence interval of the full-link simulation system.
Preferably, the secondary evaluation index in step 4) includes, but is not limited to: similarity index, consistency index, confidence index; the second-level evaluation index corresponding to the low confidence interval is a similarity index; the secondary evaluation index corresponding to the middle confidence interval is a consistency index; and the secondary evaluation index corresponding to the high confidence interval is a confidence index.
Preferably, the method comprises the steps of,
the calculation parameters of the similarity index include, but are not limited to: resolution similarity, geometric distortion;
the calculation parameters of the consistency index include, but are not limited to: MTF, signal-to-noise ratio, image mean, average gradient and standard deviation;
the calculation parameters of the confidence index include, but are not limited to: peak signal-to-noise ratio, fidelity, image correlation coefficient, and structural similarity.
Preferably, the step 5) further includes: and determining the weight of the secondary evaluation index by adopting an analytic hierarchy process and combining expert scoring.
Preferably, the step 5) further includes: and carrying out dimensionless and normalization processing on the secondary evaluation index calculation result to obtain a processing result, and then carrying out weighted calculation on the processing result to obtain an objective evaluation index for the visible light full-link simulation image.
The invention also provides an evaluation device for the visible light full-link simulation image, which comprises:
the first image extraction unit is used for acquiring original optical image data of actual imaging of the on-orbit satellite;
a second image extraction unit, configured to obtain image data of a full-link simulation system corresponding to the original optical image;
the first-level evaluation unit is used for determining a first-level evaluation index and evaluating the full-link simulation system according to the first-level evaluation index;
the second-level evaluation unit is used for acquiring an evaluation result of the first-level evaluation unit on the full-link simulation system; determining a secondary evaluation index corresponding to the evaluation result according to the evaluation result;
and the calculating unit is used for calculating the evaluation index of the image data of the full-link simulation system according to the secondary evaluation index.
The invention also provides an electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of evaluating a full link simulated image for visible light described above.
The invention also provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute the above-mentioned evaluation method for the visible light-oriented full-link simulation image.
Compared with the prior art, the invention can evaluate objective indexes of corresponding hierarchy stages according to different remote sensing technology hierarchies, can face target interpretation, provides auxiliary support for problem analysis basis and simulation image availability conclusion, can effectively verify the reproducibility of the simulation technology on satellite imaging system performance, and has great significance on actual work.
Drawings
Fig. 1 is a flowchart of an evaluation method for a full-link simulation image facing visible light provided by an embodiment of the present invention;
fig. 2 is a schematic diagram of a second-level evaluation index of the evaluation method for a full-link simulation image facing visible light according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of objective score calculation in the evaluation method for full-link simulation images facing visible light according to the embodiment of the present invention;
fig. 4 is a schematic diagram of processing the result of the evaluation index according to the embodiment of the evaluation method for the full-link simulation image for visible light by using the analytic hierarchy process according to the embodiment of the present invention;
fig. 5 is a schematic structural diagram of an evaluation device for a full-link simulation image for visible light according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Other advantages and effects of the present disclosure will become readily apparent to those skilled in the art from the following disclosure, which describes embodiments of the present disclosure by way of specific examples. It will be apparent that the described embodiments are merely some, but not all embodiments of the present disclosure. The disclosure may be embodied or practiced in other different specific embodiments, and details within the subject specification may be modified or changed from various points of view and applications without departing from the spirit of the disclosure. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the following claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present disclosure, one skilled in the art will appreciate that one aspect described herein may be implemented independently of any other aspect, and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. In addition, such apparatus may be implemented and/or such methods practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
It should also be noted that the illustrations provided in the following embodiments merely illustrate the basic concepts of the disclosure by way of illustration, and only the components related to the disclosure are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
Fig. 1 and fig. 3 are flowcharts of an evaluation method for a full-link simulation image for visible light according to an embodiment of the present invention, where the evaluation method may be applied in an implementation environment as shown in fig. 1. As shown in fig. 1 and 3, the method comprises the following steps:
acquiring original optical image data of actual imaging of an in-orbit satellite;
acquiring image data of a full-link simulation system corresponding to the original optical image;
determining a first-level evaluation index, and evaluating the full-link simulation system according to the first-level evaluation index;
acquiring an evaluation result of the full-link simulation system, and determining a secondary evaluation index corresponding to the evaluation result according to the evaluation result;
and calculating an evaluation index of the image data of the full-link simulation system according to the second-level evaluation index.
The step of acquiring original optical image data actually imaged by the in-orbit satellite and the step of acquiring image data of a full-link simulation system corresponding to the original optical image provide sample data for evaluation, the original optical image data being original data used as a reference, the image data of the full-link simulation system being object data used for evaluation.
In one embodiment, the original optical image data sampling criteria is an optical image data zero-order product of actual imaging by an in-orbit satellite. The simulation system image data respectively sampling standard is simulation image data generated by taking ground synchronous measurement data and satellite imaging auxiliary data as simulation input during satellite observation. The number of data obtained may be comprehensively considered according to the scale and efficiency of the evaluation requirement, and in one embodiment, the original optical image data and the image data of the simulation system respectively take five scenes corresponding to one another.
Because the simulation distance is always a few differences from the real world due to the limitation of the technical development level and the cognitive ability of the reality, the invention sets a secondary evaluation index for the full-link simulation system.
First, the first-level index is evaluated, and the stage of the optical full-link simulation algorithm system to be tested is judged, and is classified.
In one embodiment, the primary indicator includes a confidence interval setting to determine the confidence level of the full link simulation system.
In one embodiment, the confidence intervals are divided into a low confidence interval, a medium confidence interval, and a high confidence interval.
In one embodiment, the criteria for distinguishing between the low confidence interval, the mid confidence interval, and the high confidence interval are as follows:
low confidence interval: the interval full-link simulation method is just started, and the technical feasibility and the achievement availability of the interval full-link simulation method are explored; the full-link simulation method in the interval is difficult to complete the construction of a large-scale digital target range, and is difficult to unmixed with an error source generated by satellite observation, and is difficult to have a technical approach for reference;
medium confidence interval: the interval refers to a full-link simulation method which has a basic foundation, and models of each interval and each link in the research process are subjected to authenticity inspection, so that a digital target range with a large range can be built, and deep knowledge is provided for satellites and error sources generated by observation of the satellites;
high confidence interval: the interval means that in the full-link simulation process, the simulation granularity is fine enough, the considered elements are comprehensive enough, the simulation level of the influencing elements such as power, atmosphere, space time, radiation and the like is high enough, the model is accurate enough, and the error calculation is accurate.
In one embodiment, simulation parameters according to a full link simulation algorithm, for example, include, but are not limited to: the method comprises the steps of dividing confidence intervals of a full-link simulation algorithm to be tested, defining the score range of each confidence interval in a weighted average mode, and confirming the confidence intervals which fall in the corresponding score range and are placed in the corresponding confidence intervals, wherein the confidence intervals are evaluated at one stage.
In one embodiment, taking the percentile as an example, (0, 30) is a low confidence interval, (30, 70) is a medium confidence interval, and (70, 100) is a high confidence interval.
And after the first-level evaluation is finished, acquiring a second-level evaluation index in the corresponding confidence interval according to the corresponding confidence interval.
Low confidence interval: in the evaluation of the interval, the objective evaluation should pay more attention to geometric quality such as resolution, distortion, and the like. The confidence evaluation of this interval may be referred to as a "similarity evaluation".
Medium confidence interval: in the evaluation of the interval, objective evaluation should have both geometric and radiation similarity, and evaluation indexes such as MTF, signal to noise ratio and the like are added except for considering the geometric quality of the low confidence interval. The confidence assessment of the interval may be referred to as a "consistency assessment"
High confidence interval: in the evaluation of the interval, the objective evaluation should compare the image difference, and operators such as peak signal-to-noise ratio, structural similarity, laplace mean square error, full-image local maximum error, laplace fidelity and the like can be introduced. The evaluation should be performed first to complete the evaluation reliability analysis. The interval may implement a simulation confidence assessment.
The method of evaluating each confidence interval is described below in conjunction with fig. 2.
1) Secondary evaluation index evaluation (similarity evaluation) in low confidence interval:
(1) resolution similarity
Radial targets are deployed at the test site. The ground resolution (r) is calculated as:
wherein D is the distance from the center of the circle to the right separation position of the black and white lines; w is the width of a black-and-white line pair at the round edge; r is the radius of the circle.
The similarity of the resolution of the simulation image and the satellite image is recorded as S 1 Calculated from the following formula:
(2) geometric distortion
Selecting n simulated image and real shooting image pairs, and selecting m uniformly distributed ground control points on each pair of images; calculating the distance d' between every two control points on the simulation image and the actual distance d on the satellite image, and then the distortion between the two points is as follows: c= -d' -d-/d; the distortion value of the simulation system is as follows:
2) Secondary evaluation index evaluation (consistency evaluation) of the middle confidence interval:
and in the consistency evaluation stage, firstly, calculating single image characteristic evaluation parameters, then, comparing the simulation image parameter calculation result with a satellite image parameter calculation result according to the pressing formula, and finally, obtaining the consistency evaluation result of each parameter.
①MTF
In the edge image, supersampling the image of the bevel edge to obtain a finer black-white conversion straight line (ESF);
obtaining the change rate LSF of the straight line through the derivation of the straight line;
and then carrying out FFT conversion on the change rate to obtain the value of MTF:
(2) signal to noise ratio
The signal-to-noise ratio is used to characterize the extent to which an image is affected by noise. The image is divided into 3×3, 4×4, 5×5, etc. sub-blocks, which can be regarded as uniform and stable, and the signal to noise ratio can be calculated from the standard deviation and the mean of these sub-blocks. The calculation process is as follows:
calculating the local standard deviation and the mean value of each sub-block:
the local standard deviation formula is as follows:
wherein n is the block size; DN (digital subscriber line) i Is the DN value at position i; LM is local mean value, divide 150 intervals between local standard deviation minimum and 1.2 times of mean value, fall into corresponding interval according to standard deviation size each subblock, calculate and get the histogram with this. And counting the interval containing the most sub-blocks according to the histogram, and calculating the average value of standard deviations in the interval as a noise estimation value.
Signal estimation value
Is the average value of pixel values of the whole image, namely
Wherein N is the number of pixels of the whole image.
The signal-to-noise ratio SNR can be calculated on the basis of the noise and signal estimates by using the following equation:
(3) image mean
The image average is the gray average of the pixels and is reflected to the human eye as average brightness. It is defined as:
(4) average gradient
The average gradient can sensitively reflect the capability of the image to express the micro detail contrast, can be used for evaluating the definition degree of the image, and also can reflect the micro detail contrast and texture transformation characteristics in the image. The calculation formula is as follows:
in general, the larger the average gradient, the more image layers, representing the sharper the image. And thus can be used to evaluate the differences in the minuscule expressive power of the fused image.
(5) Standard deviation of
The standard deviation reflects the dispersion of the gray scale of the image relative to the average gray scale, and to some extent, can also be used to evaluate the magnitude of the image contrast. If the standard deviation is large, the gray level of the image is distributed, the contrast of the image is large, and more information can be seen. The standard deviation is small, the image contrast is small, the contrast is not large, the tone is single and uniform, and the information is not seen too much.
Secondary evaluation index evaluation (confidence evaluation) of high confidence interval:
(1) peak signal to noise ratio
The peak signal-to-noise ratio is a correlation quantity of the mean square error MSE, is a description of the fidelity of the image, adopts a mathematical statistics means, regards the gray level difference of the pixel of the simulation image as noise, regards the real shot image as a signal, and calculates the signal-to-noise ratio. The formulas of peak signal-to-noise ratio and mean square error are respectively:
wherein:
f (i, j), g (i, j) are gray values of the simulation image and the real image at the point (i, j), respectively, and n is the effective quantization bit number of the image.
(2) Fidelity (fidelity)
Fidelity describes the degree of consistency of a simulated image and a live image from a related perspective.
Wherein:
IF is fidelity; m, N-the number of rows and columns of the image; i, j-the position of the pixel point in the image; f (i, j) -the gray value of the satellite image at point (i, j); g (i, j) -simulating the gray value of the image at point (i, j).
(3) Image correlation coefficient
The image correlation coefficient is used for representing the similarity degree of the simulation image and the satellite real shot image, and the difference degree of the simulation image and the satellite real shot image can be found by comparing the correlation coefficients.
(4) Structural similarity
The structural similarity (SSIM, structural Similarity) algorithm proposes that the human eye has a strong ability to extract structural information from an image in nature, and they define the structural information as an attribute representing the structure of an object, regardless of the average brightness and contrast of the image. The SSIM algorithm divides the image information into three parts of brightness, contrast and structure, calculates the distortion of the three parts to obtain the whole distortion measure of the image blocks, and finally obtains the distortion of the whole image by using a mean value solving method. The theoretical basis of the algorithm is that the HVS is highly suitable for extracting structural information in visual scenes, so that the change of the structural information obtained by measurement is very close to the change of perceived image quality. Therefore, it can be considered that the front-to-rear image quality is not changed much, i.e., the quality loss is not large if the structural information is similar. The SSIM algorithm provides an objective evaluation method very close to the distortion of human eye perceived images.
S(x，y)＝f(l(x，y)，c(x，y)，s(x，y))
Wherein f (l, c, s) is a weighted integration function; l (x, y), c (x, y), s (x, y) are respectively a brightness function, a contrast function and a structure function; all three functions satisfy symmetry, boundary, and maximum uniqueness, defined as follows
Wherein mu x Sum mu y For satellite image and simulation image mean value delta x And delta y Standard deviation delta of satellite image and simulation image xy Is covariance. C1 C2 and C3 are constants and are determined from information such as brightness and contrast of an actual image.
Finally, simplifying the SSIM evaluation function to obtain
The above description is made of the evaluation method of each secondary evaluation index for each confidence interval.
In one embodiment, the invention further processes the evaluation results of the corresponding secondary evaluation index in each confidence interval when calculating the evaluation index of the image data.
In one embodiment, as shown in fig. 4, the evaluation results of the respective secondary evaluation indexes are processed in accordance with a hierarchical analysis method.
After the evaluation indexes are determined, the indexes are compared pairwise, and the indexes are rated according to the importance degree. For index and index importance comparison results, table 1 lists 9 importance levels and their assignments given by the analytic hierarchy process. And forming a judgment matrix according to the comparison results of every two. The scale method of judging matrix elements is as follows:
table 1 scale table
| Index i is compared with index j | Quantized value |
| Equally important | 1 |
| Slightly important | 3 |
| Is of great importance | 5 |
| Is of great importance | 7 |
| Extremely important | 9 |
| Intermediate value of two adjacent judgments | 2，4，6，8 |
The eigenvalue and eigenvector of the judgment matrix are obtained, the consistency of the matrix is verified, and consistency indexes are defined as follows:
random identity index RI:
the test coefficient CR, the formula is as follows:
in general, if CR <0.1, the decision matrix is considered to pass the consistency check, otherwise there is no satisfactory consistency.
If the judgment matrix has better consistency, the normalized feature vector corresponding to the maximum feature root is a weight vector.
W＝{w 1 ，w 2 ，...w n }
Then, final objective evaluation result calculation and processing are performed:
1) Dimensionless
Wherein, lambda i Non-dimensionality result of ith core capability index, Λ i ∈[0，1],R i ，T i ，x i The reference value, the tolerance value and the measured value of the ith core capability index respectively.
2) Normalization
If you record lambda i，max Is lambda type i The maximum value of (i) is the evaluation result O of each core capability index i Can be expressed as:
O i ＝Λ i /Λ i，max
3) Calculating an objective evaluation final result:
wherein omega i ＞0，O i ∈[0，1]，
O i For the i-th index evaluation result, n represents the number of objective evaluation index items participating in evaluation, ω i Is the weight coefficient of the i index.
Fig. 5 shows a block diagram of an evaluation apparatus for a full link simulation image for visible light according to an embodiment of the present disclosure. The training apparatus may be included in or implemented as a computing device. As shown in fig. 5, the apparatus includes: the first image extraction unit is used for acquiring original optical image data of actual imaging of the on-orbit satellite; a second image extraction unit, configured to obtain image data of a full-link simulation system corresponding to the original optical image; the first-level evaluation unit is used for determining a first-level evaluation index and evaluating the full-link simulation system according to the first-level evaluation index; the second-level evaluation unit is used for acquiring an evaluation result of the first-level evaluation unit on the full-link simulation system; determining a secondary evaluation index corresponding to the evaluation result according to the evaluation result; and the calculating unit is used for calculating the evaluation index of the image data of the full-link simulation system according to the secondary evaluation index.
Fig. 6 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present disclosure. As shown in fig. 6, a computer-readable storage medium M according to an embodiment of the present disclosure has stored thereon non-transitory computer-readable instructions O. When the non-transitory computer readable instructions O are executed by the processor, all or part of the steps of the method of evaluating a full link simulation image for visible light of the various embodiments of the disclosure described above are performed.
Fig. 7 shows a schematic block diagram of an electronic device 700 that may be used to implement an embodiment of the invention. As shown, the device 700 includes a Central Processing Unit (CPU) 701 that can perform various suitable actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM) 702 or loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 may also be stored. The CPU 701, ROM 702, and RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in device 700 are connected to I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The central processing unit 701 performs the various methods and processes described above, e.g., in some embodiments, the methods may be implemented as a computer software program tangibly embodied on a machine-readable medium, e.g., storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 700 via ROM 702 and/or communication unit 709. When the computer program is loaded into RAM 703 and executed by CPU 701, one or more steps of the method described above may be performed. Alternatively, in other embodiments, CPU 701 may be configured to perform the methods described above in any other suitable manner (e.g., by means of firmware).
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a load programmable logic device (CPLD), etc.
Program code for carrying out methods of the present invention may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Moreover, although operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the invention. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are exemplary forms of implementing the claims, and any modifications, equivalents, improvements or otherwise made within the spirit and principles of the invention are intended to be included within the scope of this invention. The foregoing is merely a preferred embodiment of the present invention, and it should be noted that it will be apparent to those skilled in the art that modifications and variations can be made without departing from the technical principles of the present invention, and these modifications and variations should also be regarded as the scope of the invention.
Claims (6)
1. A method for evaluating full-link simulation images facing visible light comprises the following steps:
step 1) obtaining original optical image data of actual imaging of an in-orbit satellite;
step 2) obtaining image data of a full-link simulation system corresponding to the original optical image;
step 3) determining a first-level evaluation index, and evaluating the full-link simulation system according to the first-level evaluation index;
step 4) obtaining an evaluation result of the full-link simulation system, and determining a secondary evaluation index corresponding to the evaluation result according to the evaluation result;
step 5) calculating an evaluation index of the image data of the full-link simulation system according to the secondary evaluation index calculation result;
dividing confidence intervals of the full-link simulation algorithm according to simulation parameters of the full-link simulation algorithm, limiting the score range of each confidence interval in a weighted average mode, and confirming the confidence intervals which fall into the corresponding score range and are placed in the corresponding confidence intervals, wherein the simulation parameters include but are not limited to: image element frame, overall sharpness, gray level balance, noise level, target shape fidelity, and target detail fidelity;
the first level evaluation index in step 3) includes, but is not limited to: confidence intervals of the full-link simulation system, wherein the confidence intervals comprise a low confidence interval, a middle confidence interval and a high confidence interval;
the step 4) of obtaining the evaluation result of the full-link simulation system further includes: evaluating a confidence interval to which the full-link simulation system belongs;
the secondary evaluation index in the step 4) includes, but is not limited to: similarity index, consistency index, confidence index; the second-level evaluation index corresponding to the low confidence interval is a similarity index; the secondary evaluation index corresponding to the middle confidence interval is a consistency index; the second-level evaluation index corresponding to the high confidence interval is a confidence index;
the calculation parameters of the similarity index include, but are not limited to: resolution similarity, geometric distortion;
the calculation parameters of the consistency index include, but are not limited to: MTF, signal-to-noise ratio, image mean, average gradient and standard deviation;
the calculation parameters of the confidence index include, but are not limited to: peak signal-to-noise ratio, fidelity, image correlation coefficient and structural similarity;
the resolution similarity is calculated by the following formula:
wherein S is 1 R is the resolution similarity of the simulation image and the satellite image Toilet and guard Ground resolution, r, of satellite image Imitation of Ground resolution for the simulated image;
the geometric distortion is calculated by the following formula:
wherein S is 2 The geometric distortion value is that n is the logarithm of the simulation image and the satellite image, c= |d '-d|/d, c is the distortion between two ground control points, d' is the distance between every two ground control points on the simulation image, d is the distance between every two ground control points on the satellite image, and m is the number of the ground control points;
fidelity is calculated by the following formula:
wherein TF is fidelity; m, N the number of rows and columns of the image; i. j is the position of the pixel point in the image respectively; f (i, j) is the gray value of the satellite image at point (i, j); g (i, j) is the gray value of the simulation image at the point (i, j);
the structural similarity is calculated by the following formula:
wherein SSIM is structural similarity, mu x Sum mu y The satellite image and the simulation image mean value delta respectively x And delta y Standard deviations of the satellite image and the simulation image are respectively, and C1 and C2 are constants.
2. The method of claim 1, wherein,
said step 5) further comprises: and determining the weight of the secondary evaluation index by adopting an analytic hierarchy process and combining expert scoring.
3. The method of claim 1, wherein said step 5) further comprises: and carrying out dimensionless and normalization processing on the secondary evaluation index calculation result to obtain a processing result, and then carrying out weighted calculation on the processing result to obtain an objective evaluation index for the visible light full-link simulation image.
4. An evaluation device for a full-link simulation image facing visible light is characterized by comprising:
the first image extraction unit is used for acquiring original optical image data of actual imaging of the on-orbit satellite;
a second image extraction unit, configured to obtain image data of a full-link simulation system corresponding to the original optical image;
the first-level evaluation unit is used for determining a first-level evaluation index, and evaluating the full-link simulation system according to the first-level evaluation index, wherein the first-level evaluation index comprises but is not limited to: confidence intervals of the full-link simulation system, wherein the confidence intervals comprise a low confidence interval, a middle confidence interval and a high confidence interval, the confidence intervals are divided according to simulation parameters of the full-link simulation algorithm, a weighted average mode is adopted to limit the score range of each confidence interval, the confidence intervals are confirmed to be placed in the corresponding confidence intervals within the corresponding score range, and the simulation parameters comprise but are not limited to: image element frame, overall sharpness, gray level balance, noise level, target shape fidelity, and target detail fidelity;
the second-level evaluation unit is used for acquiring an evaluation result of the first-level evaluation unit on the full-link simulation system; and determining a secondary evaluation index corresponding to the evaluation result according to the evaluation result, wherein the secondary evaluation index comprises but is not limited to: similarity index, consistency index, confidence index; the second-level evaluation index corresponding to the low confidence interval is a similarity index; the secondary evaluation index corresponding to the middle confidence interval is a consistency index; the secondary evaluation index corresponding to the high confidence interval is a confidence index, and the calculation parameters of the similarity index include, but are not limited to: resolution similarity, geometric distortion; the calculation parameters of the consistency index include, but are not limited to: MTF, signal-to-noise ratio, image mean, average gradient and standard deviation; the calculation parameters of the confidence index include, but are not limited to: peak signal-to-noise ratio, fidelity, image correlation coefficient and structural similarity;
the resolution similarity is calculated by the following formula:
wherein S is 1 R is the resolution similarity of the simulation image and the satellite image Toilet and guard Ground resolution, r, of satellite image Imitation of Ground resolution for the simulated image;
the geometric distortion is calculated by the following formula:
wherein S is 2 The geometric distortion value is that n is the logarithm of the simulation image and the satellite image, c= |d '-d|/d, c is the distortion between two ground control points, d' is the distance between every two ground control points on the simulation image, d is the distance between every two ground control points on the satellite image, and m is the number of the ground control points;
fidelity is calculated by the following formula:
wherein IF is fidelity; m, N the number of rows and columns of the image; i. j is the position of the pixel point in the image respectively; f (i, j) is the gray value of the satellite image at point (i, j); g (i, j) is the gray value of the simulation image at the point (i, j);
the structural similarity is calculated by the following formula:
wherein SSIM is structural similarity, mu x Sum mu y The satellite image and the simulation image mean value delta respectively x And delta y Standard deviations of a satellite image and a simulation image are respectively shown, and C1 and C2 are constants;
the computing unit is used for computing an evaluation index of the image data of the full-link simulation system according to the secondary evaluation index;
the second-level evaluation unit is used for evaluating the confidence interval to which the full-link simulation system belongs.
5. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of evaluating a full link simulation image for visible light of any one of claims 1-3.
6. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of evaluating a full link simulation image for visible light of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910716286.6A CN110473183B (en) | 2019-10-08 | 2019-10-08 | Evaluation method, device, electronic equipment and medium for visible light full-link simulation image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910716286.6A CN110473183B (en) | 2019-10-08 | 2019-10-08 | Evaluation method, device, electronic equipment and medium for visible light full-link simulation image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110473183A CN110473183A (en) | 2019-11-19 |
| CN110473183B true CN110473183B (en) | 2023-06-02 |
Family
ID=68509973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910716286.6A Active CN110473183B (en) | 2019-10-08 | 2019-10-08 | Evaluation method, device, electronic equipment and medium for visible light full-link simulation image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110473183B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700158B (en) * | 2021-01-07 | 2022-06-10 | 中国科学院空天信息创新研究院 | Multi-dimensional model-based algorithm efficiency evaluation method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8326046B2 (en) * | 2009-02-11 | 2012-12-04 | Ecole De Technologie Superieure | Method and system for determining structural similarity between images |
| CN109241591B (en) * | 2018-08-21 | 2022-05-17 | 哈尔滨工业大学 | Anti-ship missile combat effectiveness evaluation and decision-making assistance method |
-
2019
- 2019-10-08 CN CN201910716286.6A patent/CN110473183B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| Yong-sheng Zhou et al..Quality analysis for images acquired by a new microwave staring correlation imaging technique.《 IEEE Xplore》.2012,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110473183A (en) | 2019-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596902B (en) | Multi-task full-reference image quality evaluation method based on gating convolutional neural network | |
| CN108090902B (en) | Non-reference image quality objective evaluation method based on multi-scale generation countermeasure network | |
| CN110728656A (en) | Meta-learning-based no-reference image quality data processing method and intelligent terminal | |
| CN110766658B (en) | Non-reference laser interference image quality evaluation method | |
| CN110516716A (en) | Non-reference picture quality appraisement method based on multiple-limb similarity network | |
| CN110766657B (en) | Laser interference image quality evaluation method | |
| CN109788275A (en) | Naturality, structure and binocular asymmetry are without reference stereo image quality evaluation method | |
| CN113269256A (en) | Construction method and application of Misrc-GAN model | |
| CN110473183B (en) | Evaluation method, device, electronic equipment and medium for visible light full-link simulation image | |
| CN115223164A (en) | Melon maturity detection method and system based on artificial intelligence | |
| CN114897858A (en) | Rapid insulator defect detection method and system based on deep learning | |
| Morzelona | Human visual system quality assessment in the images using the IQA model integrated with automated machine learning model | |
| CN105491371A (en) | Tone mapping image quality evaluation method based on gradient magnitude similarity | |
| CN110473169B (en) | Simulation picture confidence evaluation method | |
| CN112818762A (en) | Large-size composite material and rapid nondestructive testing method for sandwich structure thereof | |
| CN107578406A (en) | Based on grid with Wei pool statistical property without with reference to stereo image quality evaluation method | |
| CN116484184A (en) | Method and device for enhancing partial discharge defect sample of power equipment | |
| CN107977967B (en) | No-reference image quality evaluation method for view angle synthesis | |
| CN110796635A (en) | Shear wave transformation-based light field image quality evaluation method | |
| CN109741313A (en) | The non-reference picture quality appraisement method of independent component analysis and convolutional neural networks | |
| CN113610863B (en) | Multi-exposure image fusion quality assessment method | |
| CN111241725B (en) | Structure response reconstruction method for generating countermeasure network based on conditions | |
| CN104915959A (en) | Aerial image quality evaluation method and system | |
| CN113222032B (en) | No-reference image quality evaluation method based on self-attention image coding | |
| Anzhou et al. | Perceptual quality assessment of SAR image compression based on image content partition and neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |