CN117953241A - Interference effect evaluation method, device, equipment and medium based on similarity evaluation - Google Patents
Interference effect evaluation method, device, equipment and medium based on similarity evaluation Download PDFInfo
- Publication number
- CN117953241A CN117953241A CN202410129909.0A CN202410129909A CN117953241A CN 117953241 A CN117953241 A CN 117953241A CN 202410129909 A CN202410129909 A CN 202410129909A CN 117953241 A CN117953241 A CN 117953241A
- Authority
- CN
- China
- Prior art keywords
- interference
- infrared
- similarity
- infrared images
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of infrared image evaluation, in particular to an interference effect evaluation method, device, equipment and medium based on similarity evaluation, wherein the method comprises the following steps: acquiring different infrared images; evaluating the influence degree of the particulate matters on the infrared images by calculating the similarity of infrared interference effects among different infrared images; wherein calculating the infrared interference effect similarity comprises: determining interference caused by particulate matters in the infrared image; determining the overall interference similarity between two infrared images; respectively determining interference matrixes of the two infrared images; obtaining interference distribution similarity between two infrared images; and determining the final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images. The invention can realize the rapid analysis and evaluation of the infrared interference effect caused by the passing of the particle swarm through the detector.
Description
Technical Field
The embodiment of the invention relates to the technical field of infrared image evaluation, in particular to an interference effect evaluation method, device, equipment and medium based on similarity evaluation.
Background
When an aircraft is in flight, the infrared detection system works, some airborne or spatial particles often pass through the field of view of the detector, and the particles can cause infrared interference to the detector, and the interference is closely related to the state and distribution of the particles and the distance from the particles to the detector.
At present, more ways are subjective evaluation for the influence of infrared interference effect caused by the particulate matters on images, and no reliable quantitative evaluation method exists.
Disclosure of Invention
Based on the problem that the influence degree of the infrared interference effect caused by the particles is difficult to accurately evaluate in the prior art, the embodiment of the invention provides an interference effect evaluation method, device, electronic equipment and storage medium based on similarity evaluation, which can calculate the similarity of the infrared interference effect between two infrared images and further realize rapid analysis and evaluation of the influence of the infrared interference effect caused by the particle swarm passing through a detector.
In a first aspect, an embodiment of the present invention provides a method for evaluating interference effects based on similarity evaluation, including:
acquiring different infrared images;
Evaluating the influence degree of the particulate matters on the infrared images by calculating the similarity of infrared interference effects among different infrared images;
the similarity of infrared interference effects between two different infrared images is calculated by adopting the following modes:
preprocessing the two infrared images to determine interference caused by particulate matters in the infrared images;
determining the overall interference similarity between the two infrared images based on the total number, the total scale and the total brightness of the interference of each of the two infrared images;
Respectively determining interference matrixes of the two infrared images based on interference caused by particulate matters in the infrared images and corresponding statistical rules; the interference matrix comprises a classification statistical vector corresponding to interference patterns, view field scales and brightness, and the elements of the classification statistical vector are the number of the interference counted among the partitions according to the corresponding statistical rules;
obtaining interference distribution similarity between two infrared images based on the interference matrixes of the two infrared images;
And determining final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images.
Optionally, the determining the interference caused by the particulate matter in the infrared image includes:
Judging based on the pixel maximum value of the single infrared image; if L min≤0.3Lcut+Lcut and L max≤0.3Lmin+Lmin, judging that the interference quantity in the infrared image is 0, wherein L min represents the minimum value of pixels of the infrared image, L max represents the maximum value of pixels of the infrared image, and L cut represents the detectable threshold of the infrared detector; if L min＞0.3Lcut+Lcut is detected, judging that the whole infrared image is a strong interference; if L min≤0.3Lcut+Lcut and L max＞0.3Lmin+Lmin, executing the following steps;
Adopting DeltaL=0.3L min+Lmin as a threshold value, and carrying out binarization processing on the infrared image to enable an image point with a pixel value exceeding the threshold value DeltaL in the infrared image to be 1 and the rest image points to be 0, so as to obtain a binarization image;
Determining the total number of interference in the infrared image by detecting the connectivity of the graph based on the obtained binarization graph;
Counting the number of image points with pixel values exceeding a threshold value delta L in the infrared image to obtain the total interference scale in the infrared image;
And carrying out pixel value statistics on image points of which the pixel values exceed a threshold value delta L in the infrared image to obtain the total brightness of interference in the infrared image.
Optionally, the determining the overall interference similarity between the two infrared images includes:
Carrying out dimensionless treatment on the total number, the total scale and the total brightness of the interference of each of the two infrared images to obtain two corresponding sets of dimensionless parameters, wherein the expression is as follows:
Wherein N 'g,tol、D′g,tol and L' g,tol represent the total number of disturbances, the total scale and the total brightness, respectively, in the first infrared image and N "g,tol、D″g,tol and L" g,tol represent the total number of disturbances, the total scale and the total brightness, respectively, in the second infrared image; [ n ', d', l '] p1 and [ n', d ', l' ] p2 represent corresponding sets of dimensionless parameters of the first and second infrared images, respectively;
Judging by taking the dimensionless parameter group [ n ', d ', l ' ] p1 corresponding to the first infrared image as a reference, if the dimensionless parameter group [ n ', d ', l ' ] p2 satisfies that n '. Gtoreq.n ', d '. Gtoreq.d ', l '. Gtoreq.l ' or n '. Ltoreq.n ', d '. Ltoreq.d ', l ' -l ' is less than or equal to l ', positive deviation is judged to occur, otherwise negative deviation is judged to occur;
Based on the dimensionless parameter sets [ n ', d', l '] p1 and [ n', d ', l' ] p2, the overall interference similarity between the two infrared images is calculated as:
Wherein, Representing the distance between the corresponding parameter vectors of the two infrared images; σ represents the adjustment factor, σ=0.5 if a positive deviation occurs, and σ=0.8 if a negative deviation occurs.
Optionally, the determining the interference matrix of the two infrared images based on the interference caused by the particulate matters in the infrared images and the corresponding statistical rules includes:
Determining a ratio of each disturbance based on the disturbance caused by the particulate matter in the infrared image, wherein the ratio is used for representing a disturbance pattern; the occupation ratio is determined by the occupation ratio of the interference actual area in the interference circumscribed rectangle;
dividing each statistical interval of the occupation ratio according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the pattern;
determining a field of view scale for each disturbance based on the disturbance caused by the particulate matter in the infrared image;
Dividing each statistical interval of the view field scale according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the view field scale;
determining the brightness of each disturbance based on the disturbance caused by the particulate matter in the infrared image;
dividing each statistical interval of brightness according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain the classification statistical vector corresponding to brightness.
Optionally, the obtaining the interference distribution similarity between the two infrared images based on the interference matrix of the two infrared images includes:
Respectively carrying out normalization processing on the interference matrixes of the two infrared images to obtain two matrixes n p1 and n p2 after normalization processing;
Calculating Euclidean distance d (n p1,np2) based on the two matrices n p1 and n p2 after normalization processing;
Based on the obtained Euclidean distance d (n p1,np2), calculating the interference distribution similarity between two infrared images, wherein the expression is as follows:
optionally, the determining the final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images includes:
The final infrared interference effect similarity expression is eta g＝f(L)sim(np1,np2 obtained through multiplication, wherein f (L) represents the total interference similarity between two infrared images, and sim (n p1,np2) represents the interference distribution similarity between two infrared images.
Optionally, the interference effect evaluation method further includes:
determining a qualitative evaluation result of the overall similarity according to the overall interference similarity between the two infrared images;
If the overall interference similarity f (L) between the two infrared images is more than or equal to 0.9, determining that the two infrared images are overall high in similarity; if f (L) is less than or equal to 0.7 and less than 0.9, determining that the two are similar in total; if f (L) is less than or equal to 0.3 and less than 0.7, determining that the total approach is achieved; if f (L) is less than or equal to 0.1 and less than 0.3, determining that the total dissimilarity is the same; if f (L) < 0.1, then the overall height is determined to be dissimilar.
In a second aspect, an embodiment of the present invention further provides an interference effect evaluation device based on similarity evaluation, including:
The image acquisition module is used for acquiring different infrared images;
the similarity calculation module is used for evaluating the influence degree of the particles on the infrared images by calculating the similarity of the infrared interference effect among different infrared images;
the similarity calculation module calculates the similarity of infrared interference effects between two different infrared images, and adopts the following modes:
preprocessing the two infrared images to determine interference caused by particulate matters in the infrared images;
determining the overall interference similarity between the two infrared images based on the total number, the total scale and the total brightness of the interference of each of the two infrared images;
Respectively determining interference matrixes of the two infrared images based on interference caused by particulate matters in the infrared images and corresponding statistical rules; the interference matrix comprises a classification statistical vector corresponding to interference patterns, view field scales and brightness, and the elements of the classification statistical vector are the number of the interference counted among the partitions according to the corresponding statistical rules;
obtaining interference distribution similarity between two infrared images based on the interference matrixes of the two infrared images;
And determining final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the method for evaluating an interference effect according to any embodiment of the present specification is implemented.
In a fourth aspect, embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, which when executed in a computer, causes the computer to perform the interference effect evaluation method according to any of the embodiments of the present specification.
The embodiment of the invention provides an interference effect evaluation method, device, electronic equipment and storage medium based on similarity evaluation, which are used for evaluating the influence degree of particles on infrared images by calculating the similarity of the infrared interference effects among different infrared images, realizing quantitative evaluation of the influence of the infrared interference effects and filling the blank of the prior art; the invention provides an infrared interference effect similarity calculation mode between two different infrared images, which comprises the steps of firstly determining the overall interference similarity between the two infrared images, then determining the interference distribution similarity, and finally obtaining the infrared interference effect similarity between the two infrared images; the invention can realize the rapid analysis and evaluation of the infrared interference effect caused by the passing of the particle swarm through the detector, and solves the problem that the similarity of the infrared interference caused by the particles cannot be calculated quantitatively.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a step diagram of a method for evaluating interference effect based on similarity evaluation according to an embodiment of the present invention;
FIG. 2 is a step diagram of calculating the similarity of IR interference effects between two different IR images according to an embodiment of the invention;
fig. 3 (a) and 3 (b) show two images affected by the effect of infrared interference;
Fig. 4 (a), 4 (b) and 4 (c) show classification statistics corresponding to the pattern of interference, the field of view scale and the brightness, respectively;
FIG. 5 is a hardware architecture diagram of an electronic device according to an embodiment of the present invention;
Fig. 6 is a block diagram of an interference effect evaluation device based on similarity evaluation according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
Infrared interference formed by analysis space or airborne particles on the detector is studied, and it can be found that when a particle swarm passes through the detector, a near field interference effect is formed on the detector opening, and the near field interference effect generally comprises interference in different forms such as solid circles, spots, circular rings and the like. At different moments, whether the interference effect is strong or similar or not can not be quantitatively evaluated at present. In view of the above, the invention provides a method, a device, an electronic device and a storage medium for evaluating interference effect based on similarity evaluation, which are used for evaluating the influence degree of particles on infrared images by calculating the similarity of infrared interference effects among different infrared images. For example, an infrared image of a particle entering or leaving a field of view of a detector may be used as a reference image, the intensity of influence of the particle on the infrared image at different times is evaluated based on the similarity of the infrared image of the particle passing through the field of view of the detector and the reference image, or an infrared image captured by a certain detector may be used as the reference image, and whether the interference effect caused by different particles is close or not is evaluated based on the similarity of the infrared image captured by another detector and the reference image.
Specific implementations of the above concepts are described below.
Referring to fig. 1 and fig. 2, an embodiment of the present invention provides an interference effect evaluation method based on similarity evaluation, where the method includes:
Step 100, acquiring different infrared images;
Step 200, evaluating the influence degree of particles on the infrared images by calculating the similarity of infrared interference effects among different infrared images;
the similarity of infrared interference effects between two different infrared images is calculated by adopting the following modes:
200-0, preprocessing two infrared images, and determining interference caused by particles in the infrared images;
step 200-2, determining the overall interference similarity between the two infrared images based on the total number, the total scale and the total brightness of the interference of each of the two infrared images;
200-4, respectively determining interference matrixes of two infrared images based on interference caused by particles in the infrared images and corresponding statistical rules;
the interference matrix comprises a classification statistical vector corresponding to interference patterns, view field scales and brightness, and the elements of the classification statistical vector are the number of the interference counted among the partitions according to the corresponding statistical rules;
200-6, obtaining interference distribution similarity between two infrared images based on the interference matrixes of the two infrared images;
Step 200-8, determining a final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images.
The embodiment of the invention provides an interference effect evaluation method based on similarity evaluation, which can calculate the similarity of infrared interference effects between two infrared images, and further realize the rapid analysis and evaluation of the influence of the infrared interference effects caused by the particle swarm passing through a detector. The embodiment also provides a calculation mode of the infrared interference effect similarity, and the image is preprocessed firstly; secondly, calculating the total quantity, the total scale and the total brightness of the interference in each image, and determining the total interference similarity of the two images; determining each statistical interval of pattern classification based on the statistical criterion of the pattern, respectively calculating the number of interference corresponding to each type of pattern, establishing a classification statistical vector for representing the pattern classification result, determining each statistical interval of field scale classification based on the statistical criterion of field scale, respectively calculating the number of interference corresponding to each type of field scale, establishing a classification statistical vector for representing the field scale classification result, determining each statistical interval of brightness classification based on the statistical criterion of brightness, respectively calculating the number of interference corresponding to each type of brightness, and establishing a classification statistical vector for representing the brightness classification result; then calculating the interference distribution similarity between the two images; and finally, obtaining quantitative characterization of the similarity of the infrared interference effect between the two images. The method can solve the problem that the infrared interference similarity caused by the particles cannot be calculated quantitatively, and can evaluate the influence degree of the particles on the infrared image quantitatively according to the obtained infrared interference similarity.
Since the present invention focuses on quantitatively calculating the similarity of the infrared interference caused by the particulate matter, the following describes the steps of quantitatively calculating the similarity of the infrared interference caused by the particulate matter shown in fig. 2.
Optionally, for step 200-0, preprocessing the two infrared images includes:
Checking whether the sizes of the two infrared images are the same; if the two infrared images are different, the two infrared images are the same in size through interpolation processing.
The original two infrared images can be characterized as L 1(i,j)1≤i≤Nx′,1≤j≤Ny′,L2(i,j)1≤i≤Nx″,1≤j≤Ny ", if N x≠Nx" or N y≠Ny ", taking N x＝max{Nx′,Nx″},Ny＝max{Ny′,Ny″},Nx and N y as the standard of uniformity of evaluation, and interpolating one or two infrared images according to N x and N y to obtain two infrared images L 1(i,j)1≤i≤Nx,1≤j≤Ny and L 2(i,j)1≤i≤Nx,1≤j≤Ny with the same size for subsequent processing.
Optionally, the determining the interference caused by the particulate matter in the infrared image includes:
Judging based on the pixel maximum value of a single infrared image (which can be expressed as L (i, j) 1 is not less than i and not more than N x,1≤j≤Ny); if L min≤0.3Lcut+Lcut and L max≤0.3Lmin+Lmin, determining that the interference number in the infrared image is 0, L min represents the minimum pixel value of the single infrared image, L max represents the maximum pixel value of the single infrared image, and L cut represents the detectable threshold of the infrared detector, where the detected signal is equivalent to noise, and the target cannot be resolved, so that the available infrared image cannot be obtained; if L min＞0.3Lcut+Lcut is detected, judging that the infrared image is interfered by strong infrared rays, wherein the whole image is a strong interference; if L min≤0.3Lcut+Lcut and L max＞0.3Lmin+Lmin, executing the following steps;
adopting DeltaL=0.3L min+Lmin as a threshold value, carrying out binarization processing on the single infrared image, so that an image point with a pixel value exceeding the threshold value DeltaL in the infrared image is 1, and the rest image points are 0, thereby obtaining a binarized image, wherein the expression is L (i, j), i is more than or equal to 1 and less than or equal to N x,1≤j≤Nj, and the expression is 1
Based on the obtained binarization graph, determining the total number N g,tol of interference in the infrared image by detecting the connectivity of the graph;
Counting the number of pixels with pixel values exceeding a threshold value delta L in the infrared image, namely the pixels meeting L (i, j) > delta L, to obtain the total interference scale in the infrared image, wherein the expression is that
Carrying out pixel value statistics on pixels with pixel values exceeding a threshold value delta L in the infrared image to obtain the total brightness of interference in the infrared image, wherein the expression is
By adopting the embodiment, the interference caused by the particulate matters in the infrared images can be rapidly determined, and the interference overall parameters [ N 'g,tol,D′g,tol,L′g,tol]p1 and [ N' g,tol,D″g,tol,L″g,tol]p2 of the two infrared images are obtained. If the maximum value in the image is in the range of the threshold value fluctuation, the infrared image fluctuation is caused by the detector signal fluctuation, namely L min≤0.3Lcut+Lcut and L max≤0.3Lmin+Lmin, the infrared interference is not generated at the moment, and the infrared interference quantity in the image is 0; if the minimum value in the image exceeds the fluctuation range of the threshold value, namely L min>0.3Lcut+Lcut, the whole image is subjected to interference effect and is strong interference, and the whole image is strong interference at the moment, and the two conditions are different from the condition that the comprehensive evaluation is carried out by distinguishing each interference, and the similarity calculation of the infrared interference effect can be omitted.
Further, the Two-Pass scanning method (Two-Pass) can be used to detect the connectivity of the pattern, so as to obtain the total number of image disturbances N g,tol, which comprises the following specific steps:
A1, traversing grids in the binarization graph, namely image points, and marking a new label for the current grid if no element exists in the upper, left upper and right upper grids of the grid, namely l (i, j) =0, and adding 1 to the label number;
A2, when one element exists in the upper, left and upper grids of the grid, assigning the element value to the current grid as a label;
A3, when a plurality of elements exist in the upper, left and upper left grids of the grid, taking the lowest value as the label of the current grid;
a4, traversing each non-0 grid, and setting the value of each grid as the value of the corresponding root grid by using a built union method.
The more specific process of detecting the connectivity of the graph by the two-pass scanning method can refer to the prior art, and will not be further described herein. By adopting the mode, the number of independent interference in the binarization graph can be rapidly determined, so that the total number of the interference in the single image can be statistically determined.
Optionally, for step 200-2, the determining the overall interference similarity between the two infrared images includes:
Carrying out dimensionless treatment on the total number, the total scale and the total brightness of the interference of each of the two infrared images to obtain two corresponding sets of dimensionless parameters, wherein the expression is as follows:
Wherein N 'g,tol、D′g,tol and L' g,tol represent the total number of disturbances, the total scale and the total brightness, respectively, in the first infrared image and N "g,tol、D″g,tol and L" g,tol represent the total number of disturbances, the total scale and the total brightness, respectively, in the second infrared image; [ n ', d ', l ' ] p1 and [ n ', d ', l ' ] p2 represent sets of dimensionless parameters corresponding to the first and second infrared images, respectively, the subscripts p1 and p2 are used to distinguish the first and second infrared images, n ' and n ' represent dimensionless parameters corresponding to the total number of interference of the first and second infrared images, respectively, d ' and d ' respectively represent dimensionless parameters corresponding to the total interference scale of the first and second infrared images, and l ' respectively represent dimensionless parameters corresponding to the total interference brightness of the first and second infrared images;
judging by taking the dimensionless parameter group [ n ', d', l '] p1 corresponding to the first infrared image as a reference, if the dimensionless parameter group [ n', d ', l' ] p2 corresponding to the second infrared image meets that n '. Gtoreq.n', d '. Gtoreq.d', l '. Gtoreq.l' or n '. Ltoreq.n', d '. Ltoreq.d', l '. Ltoreq.l', then determining that the second infrared image has a positive deviation from the first infrared image, otherwise determining that a negative deviation has occurred;
Based on the dimensionless parameter sets [ n ', d', l '] p1 and [ n', d ', l' ] p2, the overall interference similarity between the two infrared images is calculated as:
Wherein, Representing the distance between the corresponding parameter vectors of the two infrared images; σ represents the adjustment factor, σ=0.5 if a positive deviation occurs, and σ=0.8 if a negative deviation occurs.
By adopting the embodiment, the conditions of positive deviation or negative deviation can be calculated by different adjustment factors respectively, and the corresponding overall interference similarity is finally determined.
Further, the method further comprises: determining a qualitative evaluation result of the overall similarity according to the overall interference similarity between the two infrared images;
If the overall interference similarity f (L) between the two infrared images is more than or equal to 0.9, determining that the overall similarity qualitative evaluation results are overall high similarity; if f (L) is less than or equal to 0.7 and less than 0.9, determining that the two are similar in total; if f (L) is less than or equal to 0.3 and less than 0.7, determining that the total approach is achieved; if f (L) is less than or equal to 0.1 and less than 0.3, determining that the total dissimilarity is the same; if f (L) < 0.1, then the overall height is determined to be dissimilar.
Through the embodiment, the qualitative representation of the overall interference similarity of the two infrared images can be realized, and the method can be used for rapid analysis and qualitative evaluation of the infrared interference effect caused by the particle swarm passing through the detector.
Optionally, for step 200-4, further comprising:
Determining a ratio of each disturbance based on the disturbance caused by the particulate matter in the infrared image, wherein the ratio is used for representing a disturbance pattern; wherein the duty ratio is determined by the duty ratio of the interference actual area in the interference circumscribed rectangle, and the expression is N zone＝(Imax-Imin)(Jmax-Jmin),Ncell represents the actual area of the disturbance, I max and I min represent the maximum and minimum values of the disturbance's coordinates in the X direction of the infrared image, and J max and J min represent the maximum and minimum values of the disturbance's coordinates in the Y direction of the image;
dividing each statistical interval of the occupation ratio according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the pattern;
based on interference caused by particles in an infrared image, determining the field of view scale of each interference, wherein the expression is Θ x and θ y are field angles in the X-direction and the Y-direction of the infrared image, and N x and N y represent dimensions in the X-direction and the Y-direction of the infrared image;
Dividing each statistical interval of the view field scale according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the view field scale;
Based on interference caused by particulate matters in the infrared image, the brightness of each interference is determined, and the expression is: L k denotes the pixel value of the kth image point of the disturbance in the infrared image;
dividing each statistical interval of brightness according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain the classification statistical vector corresponding to brightness.
Further, in step 200-4, the statistical rule includes dividing the N equally divided statistical intervals according to the corresponding maximum sizes of the two infrared images. N is a positive integer, and the value can be selected from 8 to 12.
By adopting the statistical rule in the embodiment, the range of the classification interval is determined by the corresponding maximum value, so that the method can be better suitable for different images. Too small N may not embody the distribution characteristics of the interference, and too large N may lose the meaning of classification statistics.
In one embodiment, n=10, step 200-4 comprises:
Determining a ratio of each disturbance based on the disturbance caused by the particulate matter in the infrared image, wherein the ratio is used for representing a disturbance pattern; delta g,zone,p1(k),1≤k≤Ng,tol,p1,δg,zone,p2(k),1≤k≤Ng,tol,p2 is available, wherein delta g,zone,p1 (k) and delta g,zone,p2 (k) represent the ratio of the kth interference in the first and second infrared images, respectively, and N g,tol,p1 and N g,tol,p2 represent the total number of interference in the first and second infrared images, respectively;
Dividing each statistical interval of the occupation ratio according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the pattern; the statistical rule of the interference pattern comprises dividing 10 equal-division statistical intervals according to the maximum value of the interference occupation ratio in the two infrared images; that is, the maximum occupation ratio delta max and the minimum occupation ratio delta min of all interference of the two infrared images are taken to determine the range, then the occupation ratio is divided into 10 equal parts, each statistical interval of the occupation ratio is divided, and the occupation ratio range of the m-th interval is obtained Respectively counting the interference quantity of each interval to obtain N form,p1 (i), wherein i is more than or equal to 1 and less than or equal to 10, N form,p2(i),1≤i≤10,Nform,p1 (i) and N form,p2 (i) represent the interference quantity counted in the ith counting interval of the corresponding occupation ratio of the first infrared image and the second infrared image, namely the ith element of the corresponding classification counting vector;
Determining a field of view scale for each disturbance based on the disturbance caused by the particulate matter in the infrared image; the obtainable D g,p1(k),1≤k≤Ng,tol,p1,Dg,p2(k),1≤k≤Ng,tol,p2,Dg,p1 (k) and D g,p2 (k) represent the field of view dimensions of the kth disturbance in the first and second infrared images, respectively;
Dividing each statistical interval of the view field scale according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the view field scale; the statistical rule of the interference view field scale comprises dividing 10 equal-partition statistical intervals according to the maximum value of the interference view field scale in the two infrared images; namely, after the maximum view field scale D max and the minimum view field scale D min in all interferences of two infrared images are taken to determine the range, 10 equally dividing the view field scale, dividing each statistical interval of the view field scale, and obtaining the view field scale range of the mth interval as follows Respectively counting the interference quantity of each interval to obtain N scale,p1 (i), wherein i is more than or equal to 1 and less than or equal to 10, N scale,p2[i),1≤i≤10,Nscale,p1 (i) and N scale,p2 (i) represent the interference quantity counted in the ith counting interval of the corresponding view field scale of the first infrared image and the second infrared image, namely the ith element of the corresponding classification counting vector;
Determining the brightness of each disturbance based on the disturbance caused by the particulate matter in the infrared image; l g,p1(k),1≤k≤Ng,tol,p1,Lg,p2(k),1≤k≤Ng,tol,p2,Lg,p1 (k) and L g,p2 (k) are available to represent the brightness of the kth disturbance in the first and second infrared images, respectively;
Dividing each statistical interval of brightness according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the brightness; the statistical rule of the interference brightness comprises dividing 10 equal-division statistical intervals according to the maximum value of the interference brightness in the two infrared images; namely, after the maximum brightness L max and the minimum brightness L min in all interference of two infrared images are taken to determine the range, the brightness is divided into 10 equal parts, each statistical interval of the brightness is divided, and the interference brightness range of the mth interval is obtained Respectively counting the interference quantity of each interval to obtain N energy,p1 (i), wherein i is more than or equal to 1 and less than or equal to 10, N energy,p2(i),1≤i≤10,Nenergy,p1 (i) and N energy,p2 (i) represent the interference quantity counted in the ith counting interval of the interference brightness corresponding to the first infrared image and the second infrared image, namely the ith element of the corresponding classification counting vector;
finally, the interference matrix of the two images is obtained as And/>
Fig. 3 (a) and 3 (b) show two images affected by the effect of infrared interference; fig. 4 (a), 4 (b) and 4 (c) show classification statistics corresponding to the pattern, field of view and brightness of interference obtained from the two infrared images shown in fig. 3 (a) and 3 (b), respectively, and for convenience of display, the Image shown in fig. 3 (a) is shown in Image1, and the Image shown in fig. 3 (b) is shown in Image2 in fig. 4 (a), 4 (b) and 4 (c).
Optionally, for step 200-6, further comprising:
Respectively carrying out normalization processing on the interference matrixes of the two infrared images to obtain two normalized matrixes n p1 and n p2, wherein the expression is as follows:
Wherein n form,p1(i)、nscale,p1 (i) and n energy,p1 (i) are elements of matrix n p1 and n form,p2(i)、nscale,p2 (i) and n energy,p2 (i) are elements of matrix n p2; i is more than or equal to 1 and less than or equal to N;
Based on the two matrices N p1 and N p2 after normalization processing, the euclidean distance d (N p1,np2) is calculated, when n=10, the corresponding expression is:
Based on the obtained Euclidean distance d (n p1,np2), calculating the interference distribution similarity between two infrared images, wherein the expression is as follows:
by adopting the embodiment, the interference distribution similarity between the infrared images can be quantitatively calculated.
Optionally, for step 200-8, further comprising:
The final infrared interference effect similarity expression is eta g＝f(L)sim(np1,np2 obtained through multiplication, wherein f (L) represents the total interference similarity between two infrared images, and sim (n p1,np2) represents the interference distribution similarity between two infrared images.
The above embodiments provide a way to specifically determine the similarity of ir interference effects. In other embodiments, other ways of coupling the overall interference similarity to the interference distribution similarity may be employed. And the interference similarity quantitative description is utilized to guide the optimal design of the anti-interference performance of the detector.
As shown in fig. 5 and 6, the embodiment of the invention provides an interference effect evaluation device based on similarity evaluation. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. In terms of hardware, as shown in fig. 5, a hardware architecture diagram of an electronic device where an interference effect evaluation device based on similarity evaluation is provided in an embodiment of the present invention, besides a processor, a memory, a network interface, and a nonvolatile memory shown in fig. 5, the electronic device where the device is located in the embodiment may generally include other hardware, such as a forwarding chip responsible for processing a packet, and so on. For example, as shown in fig. 6, the device in a logic sense is formed by reading a corresponding computer program in a nonvolatile memory into a memory by a CPU of an electronic device where the device is located. The interference effect evaluation device based on similarity evaluation provided in this embodiment includes:
An image acquisition module 601, configured to acquire different infrared images;
the similarity calculation module 602 is configured to evaluate a degree of influence of the particulate matter on the infrared image by calculating a similarity of infrared interference effects between different infrared images;
The similarity calculation module 602 calculates the similarity of the infrared interference effect between two different infrared images, and adopts the following manner:
preprocessing the two infrared images to determine interference caused by particulate matters in the infrared images;
determining the overall interference similarity between the two infrared images based on the total number, the total scale and the total brightness of the interference of each of the two infrared images;
Respectively determining interference matrixes of the two infrared images based on interference caused by particulate matters in the infrared images and corresponding statistical rules; the interference matrix comprises a classification statistical vector corresponding to interference patterns, view field scales and brightness, and the elements of the classification statistical vector are the number of the interference counted among the partitions according to the corresponding statistical rules;
obtaining interference distribution similarity between two infrared images based on the interference matrixes of the two infrared images;
And determining final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images.
In an embodiment of the present invention, the image acquisition module 601 may be used to perform the step 100 in the above method embodiment, and the similarity calculation module 602 may be used to perform the step 200 in the above method embodiment.
It will be appreciated that the structure illustrated in the embodiments of the present invention does not constitute a specific limitation on a disturbance effect evaluation device based on similarity evaluation. In other embodiments of the invention, a similarity-based interference effect assessment device may include more or fewer components than shown, or may combine certain components, or split certain components, or may have a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The content of information interaction and execution process between the modules in the device is based on the same conception as the embodiment of the method of the present invention, and specific content can be referred to the description in the embodiment of the method of the present invention, which is not repeated here.
The embodiment of the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the interference effect evaluation method based on similarity evaluation in any embodiment of the invention when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program causes the processor to execute the interference effect evaluation method based on the similarity evaluation in any embodiment of the invention.
Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present invention.
Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs, DVD+RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer by a communication network.
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion module connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion module is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
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. Without further limitation, an element defined by the phrase "comprising one …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: various media in which program code may be stored, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The interference effect evaluation method based on similarity evaluation is characterized by comprising the following steps of:
acquiring different infrared images;
Evaluating the influence degree of the particulate matters on the infrared images by calculating the similarity of infrared interference effects among different infrared images;
the similarity of infrared interference effects between two different infrared images is calculated by adopting the following modes:
preprocessing the two infrared images to determine interference caused by particulate matters in the infrared images;
determining the overall interference similarity between the two infrared images based on the total number, the total scale and the total brightness of the interference of each of the two infrared images;
Respectively determining interference matrixes of the two infrared images based on interference caused by particulate matters in the infrared images and corresponding statistical rules; the interference matrix comprises a classification statistical vector corresponding to interference patterns, view field scales and brightness, and the elements of the classification statistical vector are the number of the interference counted among the partitions according to the corresponding statistical rules;
obtaining interference distribution similarity between two infrared images based on the interference matrixes of the two infrared images;
And determining final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images.
2. The interference effect evaluation method according to claim 1, wherein,
The determining the interference caused by the particulate matters in the infrared image comprises the following steps:
Judging based on the pixel maximum value of the single infrared image; if L min≤0.3Lcut+Lcut and L max≤0.3Lmin+Lmin, judging that the interference quantity in the infrared image is 0, wherein L min represents the minimum value of pixels of the infrared image, L max represents the maximum value of pixels of the infrared image, and L cut represents the detectable threshold of the infrared detector; if L min>0.3Lcut+Lcut is detected, judging that the whole infrared image is a strong interference; if L min≤0.3Lcut+Lcut and L max＞0.3Lmin+Lmin, executing the following steps;
Adopting DeltaL=0.3L min+Lmin as a threshold value, and carrying out binarization processing on the infrared image to enable an image point with a pixel value exceeding the threshold value DeltaL in the infrared image to be 1 and the rest image points to be 0, so as to obtain a binarization image;
Determining the total number of interference in the infrared image by detecting the connectivity of the graph based on the obtained binarization graph;
Counting the number of image points with pixel values exceeding a threshold value delta L in the infrared image to obtain the total interference scale in the infrared image;
And carrying out pixel value statistics on image points of which the pixel values exceed a threshold value delta L in the infrared image to obtain the total brightness of interference in the infrared image.
3. The interference effect evaluation method according to claim 1, wherein,
The determining the overall interference similarity between the two infrared images includes:
Carrying out dimensionless treatment on the total number, the total scale and the total brightness of the interference of each of the two infrared images to obtain two corresponding sets of dimensionless parameters, wherein the expression is as follows:
Wherein N 'g,tol、D′g,tol and L' g,tol represent the total number of disturbances, the total scale and the total brightness, respectively, in the first infrared image and N "g,tol、D″g,tol and L" g,tol represent the total number of disturbances, the total scale and the total brightness, respectively, in the second infrared image; [ n ', d', l '] p1 and [ n', d ', l' ] p2 represent corresponding sets of dimensionless parameters of the first and second infrared images, respectively;
Judging by taking the dimensionless parameter group [ n ', d ', l ' ] p1 corresponding to the first infrared image as a reference, if the dimensionless parameter group [ n ', d ', l ' ] p2 satisfies that n '. Gtoreq.n ', d '. Gtoreq.d ', l '. Gtoreq.l ' or n '. Ltoreq.n ', d '. Ltoreq.d ', l ' -l ' is less than or equal to l ', positive deviation is judged to occur, otherwise negative deviation is judged to occur;
Based on the dimensionless parameter sets [ n ', d', l '] p1 and [ n', d ', l' ] p2, the overall interference similarity between the two infrared images is calculated as:
Wherein, Representing the distance between the corresponding parameter vectors of the two infrared images; σ represents the adjustment factor, σ=0.5 if a positive deviation occurs, and σ=0.8 if a negative deviation occurs.
4. The interference effect evaluation method according to claim 1, wherein,
The method for respectively determining the interference matrixes of the two infrared images based on the interference caused by the particulate matters in the infrared images and the corresponding statistical rules comprises the following steps:
Determining a ratio of each disturbance based on the disturbance caused by the particulate matter in the infrared image, wherein the ratio is used for representing a disturbance pattern; the occupation ratio is determined by the occupation ratio of the interference actual area in the interference circumscribed rectangle;
dividing each statistical interval of the occupation ratio according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the pattern;
determining a field of view scale for each disturbance based on the disturbance caused by the particulate matter in the infrared image;
Dividing each statistical interval of the view field scale according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain a classification statistical vector corresponding to the view field scale;
determining the brightness of each disturbance based on the disturbance caused by the particulate matter in the infrared image;
dividing each statistical interval of brightness according to the corresponding statistical rule, and determining the interference statistical number corresponding to each statistical interval to obtain the classification statistical vector corresponding to brightness.
5. The interference effect evaluation method according to claim 4, wherein,
The interference matrix based on the two infrared images obtains the interference distribution similarity between the two infrared images, and the method comprises the following steps:
Respectively carrying out normalization processing on the interference matrixes of the two infrared images to obtain two matrixes n p1 and n p2 after normalization processing;
Calculating Euclidean distance d (n p1,np2) based on the two matrices n p1 and n p2 after normalization processing;
Based on the obtained Euclidean distance d (n p1,np2), calculating the interference distribution similarity between two infrared images, wherein the expression is as follows:
6. The interference effect evaluation method according to claim 1, wherein,
The determining the final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images comprises:
The final infrared interference effect similarity expression is eta g＝f(L)sim(np1,np2 obtained through multiplication, wherein f (L) represents the total interference similarity between two infrared images, and sim (n p1,np2) represents the interference distribution similarity between two infrared images.
7. The interference effect evaluation method according to claim 3, further comprising:
determining a qualitative evaluation result of the overall similarity according to the overall interference similarity between the two infrared images;
If the overall interference similarity f (L) between the two infrared images is more than or equal to 0.9, determining that the two infrared images are overall high in similarity; if f (L) is less than or equal to 0.7 and less than 0.9, determining that the two are similar in total; if f (L) is less than or equal to 0.3 and less than 0.7, determining that the total approach is achieved; if f (L) is less than or equal to 0.1 and less than 0.3, determining that the total dissimilarity is the same; if f (L) < 0.1, then the overall height is determined to be dissimilar.
8. An interference effect evaluation device based on similarity evaluation, characterized by comprising:
The image acquisition module is used for acquiring different infrared images;
the similarity calculation module is used for evaluating the influence degree of the particles on the infrared images by calculating the similarity of the infrared interference effect among different infrared images;
the similarity calculation module calculates the similarity of infrared interference effects between two different infrared images, and adopts the following modes:
preprocessing the two infrared images to determine interference caused by particulate matters in the infrared images;
determining the overall interference similarity between the two infrared images based on the total number, the total scale and the total brightness of the interference of each of the two infrared images;
Respectively determining interference matrixes of the two infrared images based on interference caused by particulate matters in the infrared images and corresponding statistical rules; the interference matrix comprises a classification statistical vector corresponding to interference patterns, view field scales and brightness, and the elements of the classification statistical vector are the number of the interference counted among the partitions according to the corresponding statistical rules;
obtaining interference distribution similarity between two infrared images based on the interference matrixes of the two infrared images;
And determining final infrared interference effect similarity based on the overall interference similarity and the interference distribution similarity between the two infrared images.
9. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the interference effect evaluation method according to any one of claims 1-7.
10. A storage medium having stored thereon a computer program, characterized in that the computer program, when executed in a computer, causes the computer to perform the interference effect evaluation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410129909.0A CN117953241A (en) | 2024-01-30 | 2024-01-30 | Interference effect evaluation method, device, equipment and medium based on similarity evaluation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410129909.0A CN117953241A (en) | 2024-01-30 | 2024-01-30 | Interference effect evaluation method, device, equipment and medium based on similarity evaluation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117953241A true CN117953241A (en) | 2024-04-30 |
Family
ID=90792077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410129909.0A Pending CN117953241A (en) | 2024-01-30 | 2024-01-30 | Interference effect evaluation method, device, equipment and medium based on similarity evaluation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117953241A (en) |
-
2024
- 2024-01-30 CN CN202410129909.0A patent/CN117953241A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11816579B2 (en) | Method and apparatus for detecting defect pattern on wafer based on unsupervised learning | |
| TWI639824B (en) | Method, apparatus, and non-transitory computer readable storage medium for integration of automatic and manual defect classification | |
| US7084968B2 (en) | Method for analyzing defect data and inspection apparatus and review system | |
| CN107895139B (en) | SAR image target identification method based on multi-feature fusion | |
| JP2018128468A (en) | Optimization of unknown defect removal for automatic defect classification | |
| US20140204238A1 (en) | Feature extraction apparatus, feature extraction program, and image processing apparatus | |
| CN102087790B (en) | Method and system for low-altitude ground vehicle detection and motion analysis | |
| CN116189220A (en) | Building element detection and identification method and device, computer equipment and storage medium | |
| CN110033039A (en) | Hyperspectral real-time classification method based on target constraint detection | |
| CN119206530B (en) | Dynamic target identification method, device, equipment and medium for remote sensing image | |
| Hagwood et al. | Evaluation of segmentation algorithms on cell populations using CDF curves | |
| CN113537253B (en) | Infrared image target detection method, device, computing equipment and storage medium | |
| CN112261402B (en) | Image detection method and system and camera shielding monitoring method and system | |
| Alam et al. | Hyperspectral target detection using Gaussian filter and post-processing | |
| CN117953241A (en) | Interference effect evaluation method, device, equipment and medium based on similarity evaluation | |
| CN108985350B (en) | Method and device for recognizing blurred image based on gradient amplitude sparse characteristic information, computing equipment and storage medium | |
| US10621466B2 (en) | Method for extracting features of a thermal image | |
| CN117541832A (en) | Abnormality detection method, abnormality detection system, electronic device, and storage medium | |
| CN114648683B (en) | Neural network performance improving method and device based on uncertainty analysis | |
| CN114924234B (en) | Radar radiation source target signal detection method based on regional contrast | |
| Promsuk et al. | Numerical Reader System for Digital Measurement Instruments Embedded Industrial Internet of Things. | |
| CN117689614A (en) | Quality detection method and device for insulator infrared image and inspection equipment | |
| CN113673612B (en) | High-field asymmetric ion mobility spectrogram classification and identification method, device and equipment | |
| CN114298137A (en) | Tiny target detection system based on countermeasure generation network | |
| Gupta et al. | A novel unsupervised thresholding technique for landsat image change detection |
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 |