CN118135205A - Hyperspectral image anomaly detection method - Google Patents
Hyperspectral image anomaly detection method Download PDFInfo
- Publication number
- CN118135205A CN118135205A CN202410544586.1A CN202410544586A CN118135205A CN 118135205 A CN118135205 A CN 118135205A CN 202410544586 A CN202410544586 A CN 202410544586A CN 118135205 A CN118135205 A CN 118135205A
- Authority
- CN
- China
- Prior art keywords
- pixel
- matrix
- point
- hyperspectral image
- mahalanobis distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 66
- 239000011159 matrix material Substances 0.000 claims abstract description 79
- 230000002159 abnormal effect Effects 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims description 44
- 239000013598 vector Substances 0.000 claims description 31
- 238000012216 screening Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000001174 ascending effect Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 14
- 230000000052 comparative effect Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 108010035322 rhamnogalacturonan acetylesterase Proteins 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a hyperspectral image anomaly detection method, which comprises the following steps: dividing a hyperspectral image matrix to be detected to obtain a fixed window area and a super-pixel area; converting the hyperspectral image matrix to be detected into a global two-dimensional image matrix; aiming at the global two-dimensional image matrix, the fixed window area and the super-pixel area, anchor point generation model processing and local Markov distance model processing are respectively used to obtain three abnormal detection results; and fusing the three abnormal detection results by considering logical OR operation and AND operation to obtain a final abnormal detection result. The accuracy of hyperspectral image anomaly detection is improved.
Description
Technical Field
The invention relates to a hyperspectral image anomaly detection method, and belongs to the technical field of hyperspectral image processing.
Background
The hyperspectral image contains tens or hundreds of spectral bands, has higher spectral resolution, contains abundant ground feature spectral characteristic information, and can greatly improve the capability of accurately detecting and identifying the ground feature category. In a hyperspectral image, pixels having a large spectral difference from the surrounding background are defined as anomalies.
The RX algorithm is one of the most typical hyperspectral anomaly detection methods. The RX algorithm models the image into a multi-element Gaussian distribution, estimates the mean and covariance matrix of the global image, and then takes the Markov distance between the pixel to be detected and the background as an abnormal decision criterion. However, the RX algorithm still has some drawbacks, and the RX algorithm uses all pixels to calculate the background statistics (mean and covariance matrix) often causes pollution, because abnormal pixels (which are very different from the background) are used in the calculation, so the background statistics are not completely accurate; the RX algorithm is based on gaussian distribution assumptions, but in practical applications, many hyperspectral image data do not conform to gaussian distributions. For some of the drawbacks of the RX algorithm, many improvements have been made to the RX algorithm, such as the Local RX (LRX) algorithm and the Kernel RX (KRX) algorithm. LRX is the most typical window-based method, and LRX algorithm introduces the concept of local information, i.e. only considering data within a certain range around one pixel when calculating covariance matrix, and not considering the whole image. The detection performance of LRX is generally better than RX because the background pixels of the local window are more prone to follow gaussian distribution. However, LRX algorithms have poor capability to process sparse data, and when hyperspectral data are sparse, the performance of the LRX algorithm may be affected.
Disclosure of Invention
The purpose is as follows: in view of at least one of the above technical problems, the present invention provides a hyperspectral image anomaly detection method, which can improve the accuracy of the hyperspectral image anomaly detection result.
The technical scheme is as follows: in order to solve the technical problems, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a hyperspectral image anomaly detection method, including:
Dividing a hyperspectral image matrix to be detected to obtain a fixed window area and a super-pixel area;
Converting the hyperspectral image matrix to be detected into a global two-dimensional image matrix;
Aiming at the global two-dimensional image matrix, the fixed window area and the super-pixel area, anchor point generation model processing and local Markov distance model processing are respectively used to obtain three abnormal detection results;
wherein generating the model process using the anchor points comprises: calculating the mahalanobis distance between each pixel point in the target area and the mean value vector; ascending order sorting is carried out on all the pixel points according to the mahalanobis distance between each pixel point and the mean value vector, and an image matrix is obtained ; Circularly computing the image matrix/>The Markov distance between each pixel point and other pixel points in the array is selected, and the pixel points with the Markov distance smaller than a distance threshold value are screened to obtain a point set/>; Screening out point sets with the number of pixel points being greater than a number threshold value, and analyzing an average value to obtain anchor points and anchor point sets;
Wherein the processing using the local mahalanobis distance model includes: calculating the mahalanobis distance between the pixel point and the nearest anchor point to obtain the abnormal score of the pixel point, thereby obtaining an abnormal detection result;
And fusing the three abnormal detection results by considering logical OR operation and AND operation to obtain a final abnormal detection result.
In some embodiments, a method of obtaining a fixed window region includes: matrix hyperspectral imageDivided into z/>Fixed window area/>, of non-overlapping blocks of; Wherein L, M, B represents the length, width and band number of the hyperspectral image, respectively,/>，/>Representing the length and width of the fixed window area;
in some embodiments, a method of acquiring a region of a superpixel includes:
Matrix of hyperspectral images using principal component analysis PCA Performing dimension reduction, wherein L, M, B respectively represents the length, width and wave band quantity of the hyperspectral image;
dividing the hyperspectral image matrix after dimension reduction into areas of c superpixels by utilizing a superpixel division algorithm SLIC 。
In some embodiments, converting the hyperspectral image matrix to be detected into a global two-dimensional image matrix includes:
Matrix hyperspectral image Conversion to a global two-dimensional image matrixWherein L, M, B respectively represent the length, width and band number of the hyperspectral image, and the global two-dimensional image matrix is composed of K1×B pixel points, wherein K=L×M.
In some embodiments, calculating the mahalanobis distance of each pixel point in the target area from the mean vector includes:
Wherein, Is the mahalanobis distance between the pixel point X and the mean value vector, mu is the mean value vector, T represents the transposition of the matrix,In the form of a covariance matrix,Is the inverse of the covariance matrix; m represents the width of the hyperspectral image; the expression of the mean vector is:
Wherein, Represents the i-th pixel, k=l×m.
In some embodiments, the image matrix is calculatedThe mahalanobis distance between each pixel point and other pixel points comprises:
the calculation formula of the mahalanobis distance between two pixel points is as follows:
Wherein, Is the mahalanobis distance between the pixel point X and the pixel point Y; m represents the width of the hyperspectral image; In the form of a covariance matrix, Is the inverse of the covariance matrix.
In some embodiments, a set of points is obtained by screening pixel points for which the mahalanobis distance is less than a distance thresholdComprising:
Wherein, Representing the set of the g-th point,Representing the image matrixIs selected from the group consisting of the h-th vector,Representing the first of the image matricesThe number of vectors is the number of vectors,Being non-negative, gamma is the distance threshold.
In some embodiments, screening out a point set with the number of pixel points greater than a number threshold value, and analyzing an average value to obtain an anchor point S g and an anchor point set S, including:
Wherein, Represents the number of elements of the g-th point set after the screening by the number threshold,Represents the q-th element in the g-th point set after passing the quantity threshold screening,Representing 1 toIs the sum of all elements of (a);
The set of all anchors is called an anchor set; the expression of the anchor point set S is:
Wherein, Represents the average value of the p-th point set after screening, namely the p-th anchor point.
In some embodiments, calculating the mahalanobis distance between the pixel and the nearest anchor point to obtain the anomaly score for the pixel includes:
wherein K is the total number of pixel points, Is the first pixel pointThe mahalanobis distance from the nearest anchor point,Is the first pixel pointThe mahalanobis distance from the g-th anchor point S g; m represents the width of the hyperspectral image.
In some embodiments, the fusion of the three anomaly detection results with respect to a logical or operation to obtain a final anomaly detection result includes:
Wherein Final represents the Final abnormality detection result, OR represents the logical OR, AND represents the logical AND, R 1、R2、R3 represents the three abnormality detection results, respectively, Representing the weight parameter.
In a second aspect, the present invention provides a hyperspectral image anomaly detection device, including a processor and a storage medium;
The storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the method according to the first aspect.
In a third aspect, the invention provides an apparatus comprising,
A memory;
a processor;
And
A computer program;
Wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of the first aspect described above.
In a fourth aspect, the present invention provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the method of the first aspect.
The beneficial effects are that: according to the hyperspectral image anomaly detection method provided by the invention, an original image is segmented, and an image matrix is divided into two partial areas, namely a fixed window area of a non-overlapping block and an area of a super pixel; acquiring an anchor point set through an anchor point generation algorithm model, firstly averaging spectrum vectors of all pixel points in an area, analyzing the mahalanobis distance between each pixel point and a mean value vector in the area, acquiring the mahalanobis distance between each pixel point and the mean value vector, and carrying out ascending order sequencing on the pixel points according to the mahalanobis distance between each pixel point and the mean value vector to acquire an image matrix; according to the image matrix, circularly analyzing the mahalanobis distance between each pixel point and other pixel points in the area, analyzing whether the mahalanobis distance is smaller than a distance threshold value to obtain a point set, analyzing whether the number of the pixel points in the point set is larger than a number threshold value, and analyzing an average value of the point set if the number of the pixel points in the point set is larger than the number threshold value to obtain an anchor point set; analyzing the mahalanobis distance between each pixel point and the nearest anchor point as the corresponding abnormal score through a local mahalanobis local model, and determining an abnormal detection result; respectively taking pixel points in a global area, pixel points in a fixed window area pixel block and pixel points in an area super pixel block of a super pixel as inputs, and adopting the anchor point generation model and the local Markov distance model to obtain three abnormal detection results; and taking the three abnormal detection results into consideration logic OR and logic AND operations, and then fusing to obtain a final abnormal detection result. Therefore, the method improves the accuracy of detecting the hyperspectral image anomaly through the steps of image segmentation, anchor point generation, local Markov distance analysis, logic fusion and the like.
Drawings
Fig. 1 is a schematic diagram of a hyperspectral image anomaly detection method according to an embodiment of the present invention.
Fig. 2 is an RGB pseudo-color image of an Urban hyperspectral image of an embodiment of the invention.
Fig. 3 is a diagram of the actual ground object position of a hyperspectral image of a comparison example Urban city of the present invention.
FIG. 4 is a diagram of the structure of an anomaly target detection for a hyperspectral image of a comparison example Urman city (Method 1) of the present invention.
FIG. 5 is a graph of the detection result of an abnormal target (Method 2) of a hyperspectral image of a Urban area according to the comparative example Urman of the present invention.
FIG. 6 is a diagram of a structure of detecting an abnormal target of a hyperspectral image of a Urman city according to the comparative example of the present invention (Method 3)
FIG. 7 is a diagram of the structure of an anomaly target detection for a hyperspectral image of a comparison example Urman city of the present invention (Method 4).
FIG. 8 is a diagram of the structure of anomaly target detection for a hyperspectral image of a comparative example Urman city (Method 5) of the present invention.
FIG. 9 is a diagram of the structure of anomaly target detection for a hyperspectral image of a comparative example Urman city (Method 6) of the present invention.
Fig. 10 is a diagram of abnormal target detection results of a Urban city hyperspectral image according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the drawings and examples. The following examples are only for more clearly illustrating the technical aspects of the present invention, and are not intended to limit the scope of the present invention.
In the description of the present invention, the meaning of a number is one or more, the meaning of a number is two or more, and greater than, less than, exceeding, etc. are understood to exclude the present number, and the meaning of a number is understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, the descriptions of the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Example 1
In a first aspect, as shown in fig. 1, the present embodiment provides a hyperspectral image anomaly detection method, including:
S1, dividing a hyperspectral image matrix to be detected to obtain a fixed window area and a super-pixel area;
In some embodiments, a method of obtaining a fixed window region includes: matrix hyperspectral image Divided into zFixed window area of non-overlapping blocks of (a); Wherein L, M, B respectively represent the length, width and band number of the hyperspectral image,，Representing the length and width of the fixed window area;
in some embodiments, a method of acquiring a region of a superpixel includes:
Matrix of hyperspectral images using principal component analysis PCA Performing dimension reduction, wherein L, M, B respectively represents the length, width and wave band quantity of the hyperspectral image;
dividing the hyperspectral image matrix after dimension reduction into areas of c superpixels by utilizing a superpixel division algorithm SLIC 。
S2, converting the hyperspectral image matrix to be detected into a global two-dimensional image matrix;
To facilitate parallel computation, three-dimensional hyperspectral image matrices are required And converting into a global two-dimensional image matrix.
In some embodiments, converting the hyperspectral image matrix to be detected into a global two-dimensional image matrix includes:
Matrix hyperspectral image Conversion to a global two-dimensional image matrixWherein L, M, B respectively represent the length, width and band number of the hyperspectral image, and the global two-dimensional image matrix is composed of K1×B pixel points, wherein K=L×M.
S3, respectively using anchor point generation model processing and local Markov distance model processing for the global two-dimensional image matrix, the fixed window area and the super-pixel area to obtain three abnormal detection results;
in this step, the pixel points in the global two-dimensional image matrix and the pixel blocks in the fixed window area are respectively used In a super pixel block and a super pixel regionThe pixel points in the model are used as input, and three abnormal detection results are obtained by adopting the anchor point generation model and the local Markov distance model;
Wherein, For the ith window region of the fixed window regions,Is the j-th pixel block in the region of the super pixel.
S31, wherein the generating a model process using the anchor point includes: calculating the mahalanobis distance between each pixel point in the target area and the mean value vector; ascending order sorting is carried out on all the pixel points according to the mahalanobis distance between each pixel point and the mean value vector, and an image matrix is obtained; Circularly computing the image matrixThe mahalanobis distance between each pixel point and other pixel points, and the pixel points with the mahalanobis distance smaller than the distance threshold value are screened to obtain a point set; Screening out point sets with the number of pixel points being greater than a number threshold value, and analyzing an average value to obtain anchor points and anchor point sets;
Further, in some embodiments, calculating the mahalanobis distance of each pixel point in the target area from the mean vector includes:
Wherein, Is the mahalanobis distance between the pixel point X and the mean value vector, mu is the mean value vector, T represents the transposition of the matrix,In the form of a covariance matrix,Is the inverse of the covariance matrix; m represents the width of the hyperspectral image; the expression of the mean vector is:
Wherein, Represents the i-th pixel, k=l×m.
In some embodiments, the image matrix is calculatedThe mahalanobis distance between each pixel point and other pixel points comprises:
the calculation formula of the mahalanobis distance between two pixel points is as follows:
Wherein, Is the mahalanobis distance between the pixel point X and the pixel point Y; m represents the width of the hyperspectral image; In the form of a covariance matrix, Is the inverse of the covariance matrix.
Further, the method for calculating the covariance matrix comprises the following steps:
(1) Firstly, analyzing average values of all wave bands of a sample;
(2) Respectively analyzing difference vectors of all wave bands of the two pixel points and the average value of the wave bands;
(3) Solving covariance of all wave bands of the pixel point X and the pixel point Y;
(4) A covariance matrix is formed.
The average value calculation formula of the wave band is as follows:
The covariance calculation formula is as follows:
，
the formula of the covariance matrix is as follows:
，
Wherein, Represents the ith dimension of pixel X,Represents the j-th dimension of pixel Y,Representation ofAndThe covariance between the two is calculated by the method,The desired value is indicated to be the desired value,Represents the average value of all the bands of X,Represents the average value of all bands of Y.
In some embodiments, a set of points is obtained by screening pixel points for which the mahalanobis distance is less than a distance thresholdComprising:
Wherein, Representing the set of the g-th point,Representing the image matrixIs selected from the group consisting of the h-th vector,Representing the first of the image matricesThe number of vectors is the number of vectors,Being non-negative, gamma is the distance threshold.
In some embodiments, screening out a point set with the number of pixel points greater than a number threshold value, and analyzing an average value to obtain an anchor point S g and an anchor point set S, including:
Wherein, Represents the number of elements of the g-th point set after the screening by the number threshold,Represents the q-th element in the g-th point set after passing the quantity threshold screening,Representing 1 toIs the sum of all elements of (a);
The set of all anchors is called an anchor set; the expression of the anchor point set S is:
Wherein, Represents the average value of the p-th point set after screening, namely the p-th anchor point.
S32, wherein the processing using the local mahalanobis distance model includes: calculating the mahalanobis distance between the pixel point and the nearest anchor point to obtain the abnormal score of the pixel point, thereby obtaining an abnormal detection result;
in some embodiments, calculating the mahalanobis distance between the pixel and the nearest anchor point to obtain the anomaly score for the pixel includes:
wherein K is the total number of pixel points, Is the first pixel pointThe mahalanobis distance from the nearest anchor point,Is the first pixel pointThe mahalanobis distance from the g-th anchor point S g; m represents the width of the hyperspectral image.
S4, fusing the three abnormal detection results by considering logical OR operation and AND operation to obtain a final abnormal detection result.
In some embodiments, the fusion of the three anomaly detection results with respect to a logical or operation to obtain a final anomaly detection result includes:
Wherein Final represents the Final abnormality detection result, OR represents the logical OR, AND represents the logical AND, R 1、R2、R3 represents the three abnormality detection results, respectively, Representing the weight parameter.
Specific application examples: an airport hyperspectral image acquired by an onboard visible light/infrared imaging spectrometer (AVIRIS) is adopted, as shown in fig. 2, a pseudo-color image of a Urban city hyperspectral image, which is called a Urban city hyperspectral image for short, has a spatial resolution of 17.2 meters/pixel and contains 204 wave bands for abnormal target detection. The experimental area data size of the Urban city image is 100×100. Fig. 3 shows the actual ground object position of the Urban hyperspectral image of Urban (white spot in fig. 3 is an abnormal target). The abnormal target detection is carried out on the hyperspectral image of the Beach of the Beach according to the embodiment by adopting the existing RX, LRX, CRD, LSMAD, frFE, RGAE and the hyperspectral image abnormal detection method respectively, and the abnormal target detection accuracy is shown in a table 1:
Table 1 hyperspectral anomaly target detection accuracy contrast table
| Abnormal target detection method | RX | LRX | CRD | LSMAD | FrFE | RGAE | The invention is that |
| Abnormal target detection accuracy/% | 99.07 | 99.29 | 98.97 | 98.97 | 98.92 | 98.22 | 99.80 |
As can be seen from Table 1, the method for detecting the anomaly of the hyperspectral image has the anomaly target detection accuracy as high as 99.80%, which is obviously superior to other methods in the prior art. The accuracy AUC score was 0.51% higher than the second high LRX method.
And as can be seen from the clarity degree of the abnormal target and the degree of separability from the background in fig. 4,5,6,7,8,9 and 10, the abnormal target detection effect of the hyperspectral image abnormality detection method of the present application is significantly better than that of the other several methods.
The above proves that the method can effectively improve the detection accuracy of the abnormal target, and is feasible in hyperspectral abnormal target detection.
Example 2
In a second aspect, based on embodiment 1, the present embodiment provides a hyperspectral image anomaly detection apparatus, including a processor and a storage medium;
The storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the method according to embodiment 1.
Example 3
In a third aspect, based on embodiment 1, the present embodiment provides an apparatus, comprising,
A memory;
a processor;
And
A computer program;
Wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of embodiment 1.
Example 4
In a fourth aspect, based on embodiment 1, the present embodiment provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the method described in embodiment 1.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is only a preferred embodiment of the invention, it being noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the invention.
Claims (10)
1. A hyperspectral image anomaly detection method, the method comprising:
Dividing a hyperspectral image matrix to be detected to obtain a fixed window area and a super-pixel area;
Converting the hyperspectral image matrix to be detected into a global two-dimensional image matrix;
Aiming at the global two-dimensional image matrix, the fixed window area and the super-pixel area, anchor point generation model processing and local Markov distance model processing are respectively used to obtain three abnormal detection results;
wherein generating the model process using the anchor points comprises: calculating the mahalanobis distance between each pixel point in the target area and the mean value vector; ascending order sorting is carried out on all the pixel points according to the mahalanobis distance between each pixel point and the mean value vector, and an image matrix is obtained ; Circularly computing the image matrix/>The Markov distance between each pixel point and other pixel points in the array is selected, and the pixel points with the Markov distance smaller than a distance threshold value are screened to obtain a point set/>; Screening out point sets with the number of pixel points being greater than a number threshold value, and analyzing an average value to obtain anchor points and anchor point sets;
Wherein the processing using the local mahalanobis distance model includes: calculating the mahalanobis distance between the pixel point and the nearest anchor point to obtain the abnormal score of the pixel point, thereby obtaining an abnormal detection result;
And fusing the three abnormal detection results by considering logical OR operation and AND operation to obtain a final abnormal detection result.
2. The method of claim 1, wherein the method of acquiring the fixed window area comprises: matrix hyperspectral imageDivided into z/>Fixed window area/>, of non-overlapping blocks of; Wherein L, M, B represents the length, width and band number of the hyperspectral image, respectively,/>，/>Representing the length and width of the fixed window area;
and/or, the method for acquiring the region of the super pixel comprises the following steps:
Matrix of hyperspectral images using principal component analysis PCA Performing dimension reduction, wherein L, M, B respectively represents the length, width and wave band quantity of the hyperspectral image;
dividing the hyperspectral image matrix after dimension reduction into areas of c superpixels by utilizing a superpixel division algorithm SLIC 。
3. The method according to claim 1, wherein converting the hyperspectral image matrix to be detected into a global two-dimensional image matrix comprises:
Matrix hyperspectral image Conversion to a Global two-dimensional image matrix/>Wherein L, M, B respectively represent the length, width and band number of the hyperspectral image, and the global two-dimensional image matrix is composed of K1×B pixel points, wherein K=L×M.
4. The method of claim 1, wherein calculating the mahalanobis distance of each pixel point in the target area from the mean vector comprises:
；
Wherein, The Marshall distance between the pixel point X and the mean vector, mu is the mean vector, T represents the transposition of the matrix,/>Is covariance matrix,/>Is the inverse of the covariance matrix; m represents the width of the hyperspectral image; the expression of the mean vector is:
；
Wherein, Represents the i-th pixel, k=l×m.
5. The method of claim 1, wherein the image matrix is calculatedThe mahalanobis distance between each pixel point and other pixel points comprises:
the calculation formula of the mahalanobis distance between two pixel points is as follows:
；
Wherein, Is the mahalanobis distance between the pixel point X and the pixel point Y; m represents the width of the hyperspectral image; /(I)Is covariance matrix,/>Is the inverse of the covariance matrix.
6. The method of claim 1, wherein the set of points is obtained by filtering pixels whose mahalanobis distance is less than a distance thresholdComprising:
；
Wherein, Represents the g-th set of points,/>Representing the image matrix/>The h-th vector of >/>Representing the/>, in the image matrixVectors,/>Being non-negative, gamma is the distance threshold.
7. The method of claim 1, wherein screening out a set of points with a number of pixels greater than a number threshold for analysis averages to obtain an anchor point S g and an anchor point set S comprises:
；
Wherein, Representing the number of elements of the g-th point set after the screening of the quantity threshold value,/>Represents the q-th element in the g-th point set after passing the quantity threshold screening,/>Represent 1 to/>Is the sum of all elements of (a);
The set of all anchors is called an anchor set; the expression of the anchor point set S is:
；
Wherein, Represents the average value of the p-th point set after screening, namely the p-th anchor point.
8. The method of claim 1, wherein calculating the mahalanobis distance of a pixel point from the nearest anchor point to obtain an outlier score for the pixel point comprises:
；
wherein K is the total number of pixel points, For the first pixel/>Mahalanobis distance from the nearest anchor point,/>For the first pixel/>The mahalanobis distance from the g-th anchor point S g; m represents the width of the hyperspectral image.
9. The method of claim 1, wherein fusing the three anomaly detection results with respect to a logical or and operation to obtain a final anomaly detection result comprises:
；
；
；
Wherein Final represents the Final abnormality detection result, OR represents the logical OR, AND represents the logical AND, R 1、R2、R3 represents the three abnormality detection results, respectively, Representing the weight parameter.
10. A storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410544586.1A CN118135205B (en) | 2024-05-06 | 2024-05-06 | Hyperspectral image anomaly detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410544586.1A CN118135205B (en) | 2024-05-06 | 2024-05-06 | Hyperspectral image anomaly detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118135205A true CN118135205A (en) | 2024-06-04 |
| CN118135205B CN118135205B (en) | 2024-07-16 |
Family
ID=91246799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410544586.1A Active CN118135205B (en) | 2024-05-06 | 2024-05-06 | Hyperspectral image anomaly detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118135205B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118379295A (en) * | 2024-06-25 | 2024-07-23 | 南京信息工程大学 | Hyperspectral anomaly detection method based on registration |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017190542A1 (en) * | 2016-05-04 | 2017-11-09 | 山东大学 | Partition-based vca end-member extraction method |
| WO2021036267A1 (en) * | 2019-08-23 | 2021-03-04 | 华为技术有限公司 | Image detection method and related device |
| CN114202539A (en) * | 2021-12-18 | 2022-03-18 | 南京理工大学 | Hyperspectral image anomaly detection method based on end-to-end RX |
| CN117237618A (en) * | 2023-11-15 | 2023-12-15 | 南京信息工程大学 | Hyperspectral image anomaly detection method |
-
2024
- 2024-05-06 CN CN202410544586.1A patent/CN118135205B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017190542A1 (en) * | 2016-05-04 | 2017-11-09 | 山东大学 | Partition-based vca end-member extraction method |
| WO2021036267A1 (en) * | 2019-08-23 | 2021-03-04 | 华为技术有限公司 | Image detection method and related device |
| CN114202539A (en) * | 2021-12-18 | 2022-03-18 | 南京理工大学 | Hyperspectral image anomaly detection method based on end-to-end RX |
| CN117237618A (en) * | 2023-11-15 | 2023-12-15 | 南京信息工程大学 | Hyperspectral image anomaly detection method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118379295A (en) * | 2024-06-25 | 2024-07-23 | 南京信息工程大学 | Hyperspectral anomaly detection method based on registration |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118135205B (en) | 2024-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110399909B (en) | Hyperspectral image classification method based on label constraint elastic network graph model | |
| CN118135205B (en) | Hyperspectral image anomaly detection method | |
| US10896351B2 (en) | Active machine learning for training an event classification | |
| Dornaika et al. | Building detection from orthophotos using a machine learning approach: An empirical study on image segmentation and descriptors | |
| US7724256B2 (en) | Fast graph cuts: a weak shape assumption provides a fast exact method for graph cuts segmentation | |
| CN107808138B (en) | Communication signal identification method based on FasterR-CNN | |
| Rottmann et al. | Uncertainty measures and prediction quality rating for the semantic segmentation of nested multi resolution street scene images | |
| CN111274964B (en) | Detection method for analyzing water surface pollutants based on visual saliency of unmanned aerial vehicle | |
| CN111401387B (en) | Abnormal sample construction method, device, computer equipment and storage medium | |
| CN111815579A (en) | Image change detection method and device and computer readable storage medium | |
| US20230144724A1 (en) | Method for Finding Image Regions that Significantly Influence Classification in a Tool for Pathology Classification in a Medical Image | |
| CN112561881A (en) | Infrared image self-adaptive data enhancement method based on evaluation model | |
| CN106157330A (en) | A kind of visual tracking method based on target associating display model | |
| CN108447065B (en) | Hyperspectral super-pixel segmentation method | |
| CN117437406A (en) | Multi-target detection method and device | |
| CN105160666B (en) | SAR image change detection based on Non-Stationary Analysis and condition random field | |
| KR101821770B1 (en) | Techniques for feature extraction | |
| CN112989919B (en) | Method and system for extracting target object from image | |
| CN117237618A (en) | Hyperspectral image anomaly detection method | |
| CN116778339A (en) | Method and system for selecting hyperspectral wave bands by aid of local view auxiliary discrimination | |
| Dornaika et al. | A comparative study of image segmentation algorithms and descriptors for building detection | |
| CN110991408A (en) | Method and device for segmenting white matter high signal based on deep learning method | |
| CN115631211A (en) | Hyperspectral image small target detection method based on unsupervised segmentation | |
| CN113947723A (en) | High-resolution remote sensing scene target detection method based on size balance FCOS | |
| Kumar et al. | A symbiosis with panicle-SEG based CNN for count the number of wheat ears |
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 |