CN113159157B - Improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method - Google Patents
Improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method Download PDFInfo
- Publication number
- CN113159157B CN113159157B CN202110407968.6A CN202110407968A CN113159157B CN 113159157 B CN113159157 B CN 113159157B CN 202110407968 A CN202110407968 A CN 202110407968A CN 113159157 B CN113159157 B CN 113159157B
- Authority
- CN
- China
- Prior art keywords
- image
- detection
- target
- value
- detection threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides an improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method, which comprises the steps of firstly preprocessing a detection image and a reference image, and carrying out bidirectional relative radiation correction treatment; secondly, solving a detection quantity image and a detection threshold value based on an image segmentation difference method of the improved clutter distribution model; subtracting the detection image from the reference image to obtain a difference value detection quantity image, estimating clutter distribution of the difference value detection quantity image, setting false alarm probability to obtain a detection threshold value, and obtaining a detection quantity image and a detection threshold value of the first sub-algorithm; then, solving the inspection quantity images and the detection threshold of the one-dimensional edge worth method and the generalized Laguerre polynomial method; and finally, inputting the three inspection quantity images and the corresponding threshold values into an LE-SVDD space for designing a classifier, thereby realizing the change detection of the low-frequency UWB SAR image.
Description
Technical Field
The invention relates to the technical field of radars, in particular to an improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method.
Background
In modern war, the two parties of the fight pay more and more attention to concealing the military targets of the own party, and meanwhile, the detection and reconnaissance capability of the concealed military targets of the enemy is improved. Therefore, the research on the hidden target detection technology can provide important theoretical and technical support for the development of novel battlefield reconnaissance/guided weapon equipment in China, and has important military significance. In addition, the border of China is complex in geographical situation, and a plurality of regional jungles are densely distributed, so that convenience is provided for arrangement of military targets and adjustment of military defence in the vicinity of the border of the adjacent country. Due to the jungle shielding, the conventional radar system cannot penetrate the jungle to effectively detect and reconnaissance the enemy. Therefore, there is an urgent need to develop advanced system radar systems and associated detection systems to improve the ability to detect and detect concealed military targets.
The low-frequency ultra-wideband synthetic aperture radar (UWB SAR) has good leaf cluster penetration detection performance and high-resolution imaging capability, and has become an important means for hidden target detection and reconnaissance. Due to the complex jungle exploration environment and the low frequency UWB system, the obtained UWB SAR image often has many strong scattering points (such as thick trunks) that are not target points. The non-target speckle scattering points enable a plurality of false alarm points to exist in the process of detecting the change of the low-frequency UWB SAR image in different time phases, so that the difficulty of detecting the change of the hidden target of the leaf cluster is increased.
At present, the low-frequency UWB SAR image target detection method mainly comprises three types, wherein the first type is a change detection method based on image pixel level, and whether the pixel point changes is observed through comparison analysis of the same point pixel point in different time phase images, and common methods comprise a difference value method, a ratio method and the like. The image pixel level-based change detection method is simple to realize, but the simple analysis of the pixel gray value is greatly influenced by noise, and the actual detection effect is often poor. The second method is a change detection method based on image feature level, and features are extracted from the surrounding area of the pixels, and the extracted features are comprehensively analyzed to realize detection of change feature points, and common algorithms include an edge worth method and a gray level co-occurrence matrix method. The image feature level-based change detection method adopts the information such as image texture features, edge features and the like when in comparison, has stronger stability and anti-interference capability, and is complex to realize relative to the image pixel level-based change detection method. The third type of method is a change detection method based on image target level, firstly extracting characteristics and classifying images of single-phase images, obtaining attribute information of target points in the images, and then carrying out change detection on the classified images. Compared with the other two algorithms, the image target-level-based change detection method is a higher-level change detection technology, has great difficulty in research and application, and is still in a starting stage at present.
Most of the three methods are used for carrying out change detection on certain change detection information of a target point in the SAR image, the single change detection method is difficult to fully utilize the change detection information in the SAR image, and the condition of missing the detection target point is easy to occur. In recent years, target detection incorporating a plurality of methods has been attracting more and more attention from students. The detection method of the hidden targets of the low-frequency UWB SAR leaf clusters is improved and fused, and a better detection effect can be obtained. At present, fusion change detection methods which are more commonly used in the field of change detection are as follows: a markov model method, a laplacian feature map support vector description (LE-SVDD) method, and the like. The LE-SVDD-based fusion change detection method can fuse a plurality of algorithms, and has better detection performance than a single detection algorithm. However, in the conventional fusion change detection method based on the LE-SVDD, due to the unreasonable setting of the adopted sub-algorithm and the detection threshold, the fusion detection effect is poor, and the high-efficiency high-precision target detection of the low-frequency UWB SAR image is difficult to realize.
Disclosure of Invention
The invention provides an improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method which can effectively inhibit a plurality of non-target strong scattering points existing in a low-frequency UWB SAR image and reduce the occurrence of false alarm points in the change detection process.
In order to achieve the technical effects, the technical scheme of the invention is as follows:
an improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method comprises the following steps:
s1: preprocessing a detection image and a reference image;
s2: obtaining a check quantity image and a detection threshold value based on an image segmentation difference method of an improved clutter distribution model;
s3: obtaining an inspection amount image and a detection threshold value of a one-dimensional edge worth method and a generalized Laguerre polynomial method;
s4: and inputting the three inspection quantity images and the detection threshold value into an LE-SVDD classifier for training, and judging the target and non-target of the test sample, namely the final change detection result.
Further, the process of step S1 includes:
preprocessing the detection image and the reference image, performing bidirectional relative radiation correction processing, removing image gray value variation in the image caused by system response and weather condition non-target variation factors,
the specific process of step S1 is:
for each pixel point of the observation area, 15×15 is adoptedThe pixel neighborhood of (2) calculates the correlation coefficient value of the point between the reference image and the detection image, when the correlation coefficient is larger than 0.5, the point is set as a no-change point, and the no-change point in the whole image in the detection image and the reference image is respectively set as x 1 ,x 2 ...,x t And y 1 ,y 2 ...,y t The method comprises the steps of carrying out a first treatment on the surface of the Performing bidirectional linear estimation by using a least square method to obtain corresponding linear coefficients And->Weighting the unchanged points by using the linear coefficients to perform weighted least square estimation to obtain corresponding linear coefficients +.>And->Then continuing to allocate weights until the linear coefficient is stable, namely k a 、b a 、k o And b o At this time:
in the method, in the process of the invention,and->Respectively is the invariable point x 1 ,x 2 ...,x t And y 1 ,y 2 ...,y t Is the average value of (2);
for all points of the detected image, linear transformation is usedAnd performing transformation to obtain a corrected detection image.
Further, the process of step S2 includes:
the image segmentation difference method based on the improved clutter distribution model is a pixel-level change detection method, a difference check-out image is obtained by subtracting the same point of images in different time phases, then the difference check-out image is segmented, the probability density distribution of a non-target area of the segmented image is estimated, a certain false alarm probability value is set, a corresponding detection threshold value is obtained in the probability density distribution, and if the probability density distribution is larger than the detection threshold value, the detection threshold value is regarded as a change detection point, thereby obtaining the check-out image and the detection threshold value of a first sub-algorithm,
the specific process of the step S2 is as follows:
set S 1 、S 2 Respectively observing the obtained SAR intensity images at different moments S 1 For a reference image without an object, S 2 To detect an image, Z dif Is formed by S 1 And S is 2 The difference value test amount image is formed:
firstly, image segmentation is carried out on a reference image, an OTSU image segmentation algorithm is adopted, the equivalent view number of the reference image is set to be 1, the initial segmentation number of the image is set to be N=2, the reference image is segmented, when the minimum value of the square error divided by the square mean value of each sub-region after the segmentation of the reference image is smaller than the equivalent view number, the segmentation is stopped, otherwise, the image is continuously segmented until the loop is exited;
then, the clutter distribution of each region is estimated, and the clutter distribution of each region of the difference value test amount image is assumed to be F i (z dif ) I epsilon N, the false probability is set to be 10 -8 The detection threshold value corresponding to each region is Image S is subjected to image difference method 2 The mathematical expression for detecting the change of the newly appeared target is as follows:
wherein z is dif 、s 1 、s 2 Respectively, are images Z dif 、S 1 、S 2 Gray value, T of the same pixel point in the pixel array dif Is a detection threshold set according to the false alarm rate.
Further, the process of step S3 includes:
in the one-dimensional edge worth method, each pixel point of an observation area is taken as a center, an estimation based on a Gaussian probability density distribution model is carried out on a pixel gray value probability density function in the neighborhood of the observation area based on an edge worth expansion, and the difference of the probability density functions of each point between multi-time-phase images is analyzed based on a K-L divergence theory, so that a test quantity image related to the probability density difference is obtained; the generalized Laguerre polynomial method is based on a generalized Laguerre polynomial, the probability density function of the pixel gray value in the neighborhood of the generalized Laguerre polynomial is estimated based on a gamma probability density distribution model, and then a check-out image is obtained through K-L divergence; then, carrying out image gray value statistics on the inspection quantity image, finding out the trend of suddenly falling of a statistic curve on the left side, and adopting an inflection point in the suddenly falling curve as an inspection threshold; fitting the density curve by adopting a least square method during detection, taking a horizontal axis value, equal to 0, of a vertical axis in the fitted curve as a detection threshold value to obtain a detection quantity image and a detection threshold value of two sub-algorithms,
the specific process of the step S3 is as follows:
the one-dimensional edge worth method and the generalized Laguerre polynomial method are used for estimating probability density distribution firstly, and then calculating a probability density distribution check quantity image by adopting K-L divergence; for a corresponding point of the detection image and the reference image, calculating the statistical information of the mean value, the variance, the third-order accumulation amount and the fourth-order accumulation amount corresponding to the neighborhood of the point, substituting the statistical information into a related formula deduced by the K-L divergence, and solving a probability distribution difference value;
for the inspection quantity images obtained by the one-dimensional edge worth method and the generalized Laguerre polynomial method, as the number of non-target points in the detection image is far greater than the number of target points, gray statistics are carried out on the inspection quantity images, the fact that the non-target points are concentrated on the left side and the suddenly descending trend occurs is found, the target points are concentrated on the right side, a statistic curve inflection point is adopted as a detection threshold, a method for fitting the statistic curve of the inspection quantity images is adopted on the right side, a y=ax+b fitting curve is obtained, and an x value corresponding to y=0 in the curve is the detection threshold.
Further, the process of step S4 includes:
firstly, marking the detection amount of a change area and the detection amount of a change-free area as a target class sample and an outlier sample by an SVDD classifier, then training the SVDD by utilizing a training sample set formed by pre-extracted target class samples so as to construct a minimum hypersphere containing all training samples in a nuclear feature space, and classifying the detection amount of the change in an observation scene based on the hypersphere; the LE-SVDD sets the detection threshold value and standard deviation that one point of each of three sub-algorithm inspection quantity images is larger than the corresponding inspection quantity image as a training sample on the basis of the SVDD, one or two inspection quantity images corresponding points are larger than the detection threshold value and standard deviation in the three sub-algorithms as test sample, inputs the training sample into the LE-SVDD classifier for training, judges the target and non-target of the test sample, namely the final change detection result,
the specific process of the step S4 is as follows:
for the detection image S 1 And reference image S 2 Let I be the test quantity image based on the image segmentation difference method of the improved clutter distribution model 1 The detection threshold is T 1 The inspection quantity images obtained by adopting a one-dimensional edge worth method and a generalized Laguerre polynomial method are respectively I 2 、I 3 The detection threshold values are respectively T 2 、T 3 ；
Constructing a sample dataset as a = { (i) 1 ,i 2 ,i 3 )|i 1 ∈I 1 ,i 2 ∈I 2 ,i 3 ∈I 3 }，i 1 、i 2 、i 3 Are all inspection volume images I 1 、I 2 、I 3 Corresponding to the point in the first row;
constructing a training dataset of b= { (i) 1 ,i 2 ,i 3 )|i 1 -T 1 ＞σ 1 ,i 2 -T 2 ＞σ 2 ,i 3 -T 3 ＞σ 3 }, wherein sigma 1 、σ 2 、σ 3 Respectively represent the inspection amount images I 1 、I 2 、I 3 Standard deviation of (2);
the test dataset is c= { (i) 1 ,i 2 ,i 3 )||i 1 -T 1 |≤σ 1 Or |i 2 -T 2 |≤σ 2 Or |i 3 -T| 3 ≤σ 3 }；
The non-target region is known as d= { (i) 1 ,i 2 ,i 3 )|i 1 -T 1 ＜σ 1 Or i 2 -T 2 ＜σ 2 Or i 3 -T＜σ 3 }；
Training by using a training data set B through a sequential minimum optimization algorithm, and judging a test data set C through a trained LE-SVDD classifier, so that information of a target point on a detected image is obtained, and further high-efficiency high-precision low-frequency UWB SAR leaf cluster hidden target fusion change detection is realized.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the invention adopts the target fusion change detection technology based on the LE-SVDD, can effectively inhibit a plurality of non-target strong scattering points existing in the low-frequency UWB SAR image, and reduces the occurrence of false alarm points in the change detection process. While maintaining high target detection performance, the target detection efficiency is improved, so that high-efficiency and high-precision detection of the low-frequency UWB SAR is realized, and the position information of the hidden target is obtained. The method is suitable for detecting the change of military targets such as missile launchers, tanks and the like hidden in the forest, and acquiring deployment change information of the leaf cluster hidden targets.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a diagram of the test image and reference image data employed in a simulation experiment in accordance with the present invention;
FIG. 3 shows the detection result of the image segmentation difference method based on the improved clutter distribution model;
FIG. 4 is a graph of detection results and statistical probability distribution of the Edgeworth method and the generalized Laguerre polynomial method;
fig. 5 shows the detection result of the improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
for the purpose of better illustrating the embodiments, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the actual product dimensions;
it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
As shown in fig. 1, an improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method comprises the following steps:
s1: preprocessing a detection image and a reference image;
s2: obtaining a check quantity image and a detection threshold value based on an image segmentation difference method of an improved clutter distribution model;
s3: obtaining an inspection amount image and a detection threshold value of a one-dimensional edge worth method and a generalized Laguerre polynomial method;
s4: and inputting the three inspection quantity images and the detection threshold value into an LE-SVDD classifier for training, and judging the target and non-target of the test sample, namely the final change detection result.
Through simulation experiments, the improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method is verified, and theoretical analysis and simulation experiment results prove the effectiveness of the method.
In the simulation experiment, the test image and the reference image used are shown in fig. 2. The data sets used for the detection image and the reference image are imaging cut-out pictures of the sweden CARABAS-II VHF SAR system under the very high frequency band (20-90 MHz), and the imaging resolution is 2.5m multiplied by 2.5m. 25 vehicle target points can be observed in the detected image, and no target point information is present in the reference image.
As shown in fig. 3, the image segmentation difference method based on the improved clutter distribution model is a pixel-level change detection method, a difference check-out image is obtained by subtracting the same points of images in different time phases, then the difference check-out image is segmented, probability density distribution of a non-target area of the segmented image is estimated, a certain false alarm probability value is set, a corresponding detection threshold value is obtained in the probability density distribution, and if the probability density distribution is larger than the detection threshold value, the detection threshold value is regarded as a change detection point, so that a check-out image and a detection threshold value of a first sub-algorithm are obtained.
The specific process of step S2 is:
set S 1 、S 2 Respectively observing the obtained SAR intensity images at different moments S 1 For a reference image without an object, S 2 To detect an image, Z dif Is formed by S 1 And S is 2 The difference value test amount image is formed:
firstly, image segmentation is carried out on a reference image, an OTSU image segmentation algorithm is adopted, the equivalent view number of the reference image is set to be 1, the initial segmentation number of the image is set to be N=2, the reference image is segmented, when the minimum value of the square error divided by the square mean value of each sub-region after the segmentation of the reference image is smaller than the equivalent view number, the segmentation is stopped, otherwise, the image is continuously segmented until the loop is exited;
then, the clutter distribution of each region is estimated, and the clutter distribution of each region of the difference value test amount image is assumed to be F i (z dif ) I epsilon N, the false probability is set to be 10 -8 The detection threshold value corresponding to each region is Image S is subjected to image difference method 2 The mathematical expression for detecting the change of the newly appeared target is as follows:
wherein z is dif 、s 1 、s 2 Respectively, are images Z dif 、S 1 、S 2 Gray value, T of the same pixel point in the pixel array dif Is a detection threshold set according to the false alarm rate. As can be seen from fig. 3, the image segmentation difference method based on the improved clutter distribution model has a better detection effect on the image, and can identify most of the target points, but some target points are still missing.
In the one-dimensional Edgeworth method, as shown in fig. 4, each pixel point of an observation area is taken as a center, estimation based on a gaussian probability density distribution model is performed on a pixel gray value probability density function in the neighborhood of the pixel point based on the Edgeworth expansion, and on the basis, the difference of the probability density functions of each point between multi-time-phase images is analyzed based on a K-L divergence theory, so that a test quantity image about the probability density difference is obtained; the generalized Laguerre polynomial method is based on a generalized Laguerre polynomial, the probability density function of the pixel gray value in the neighborhood of the generalized Laguerre polynomial is estimated based on a gamma probability density distribution model, and then a check-out image is obtained through K-L divergence; then, carrying out image gray value statistics on the inspection quantity image, finding out the trend of suddenly falling of a statistic curve on the left side, and adopting an inflection point in the suddenly falling curve as an inspection threshold; and during detection, a least square method is adopted to fit a density curve, and a horizontal axis value, equal to 0, of a vertical axis in the fitted curve is taken as a detection threshold value approximately, so that a detection quantity image and a detection threshold value of two sub-algorithms are obtained.
The specific process of step S3 is:
the one-dimensional edge worth method and the generalized Laguerre polynomial method are used for estimating probability density distribution firstly, and then calculating a probability density distribution check quantity image by adopting K-L divergence; for a corresponding point of the detection image and the reference image, calculating the statistical information of the mean value, the variance, the third-order accumulation amount and the fourth-order accumulation amount corresponding to the neighborhood of the point, substituting the statistical information into a related formula deduced by the K-L divergence, and solving a probability distribution difference value;
for the inspection quantity images obtained by the one-dimensional edge worth method and the generalized Laguerre polynomial method, as the number of non-target points in the detection image is far greater than the number of target points, gray statistics are carried out on the inspection quantity images, the fact that the non-target points are concentrated on the left side and the suddenly descending trend occurs is found, the target points are concentrated on the right side, a statistic curve inflection point is adopted as a detection threshold, a method for fitting the statistic curve of the inspection quantity images is adopted on the right side, a y=ax+b fitting curve is obtained, and an x value corresponding to y=0 in the curve is the detection threshold. As can be seen from fig. 4, when the probability distribution curve is fitted and the approximate inflection point in the curve is used as the detection threshold to detect the inspection amount image, almost all the targets can be detected, and the detection performance is good, but some false alarm points exist in the detection result. Unlike the image segmentation difference method based on the improved clutter distribution model, the edge method and the generalized Laguerre polynomial method are used for carrying out difference analysis on the statistical distribution characteristics of the image, but the change detection of a single detection object is difficult to achieve both good detection probability and false alarm rate.
As shown in fig. 5, the SVDD classifier firstly marks the detection amounts of the change areas and the change-free areas as target class samples and outlier samples, and then trains the SVDD by using a training sample set formed by pre-extracted target class samples, so as to construct a minimum hypersphere containing all training samples in a nuclear feature space, and classifies the detection amounts of the change in an observation scene based on the hypersphere; the LE-SVDD sets the detection threshold value and standard deviation that one point of each of three sub-algorithm inspection quantity images is larger than the corresponding inspection quantity image as a training sample on the basis of the SVDD, one or two inspection quantity images corresponding points are larger than the detection threshold value and standard deviation in the three sub-algorithms as test sample, inputs the training sample into the LE-SVDD classifier for training, judges the target and non-target of the test sample, namely the final change detection result,
the specific process of step S4 is:
for the detection image S 1 And reference image S 2 Let I be the test quantity image based on the image segmentation difference method of the improved clutter distribution model 1 The detection threshold is T 1 The inspection quantity images obtained by adopting a one-dimensional edge worth method and a generalized Laguerre polynomial method are respectively I 2 、I 3 The detection threshold values are respectively T 2 、T 3 ；
Constructing a sample dataset as a = { (i) 1 ,i 2 ,i 3 )|i 1 ∈I 1 ,i 2 ∈I 2 ,i 3 ∈I 3 }，i 1 、i 2 、i 3 Are all inspection volume images I 1 、I 2 、I 3 Corresponding to the point in the first row;
constructing a training dataset of b= { (i) 1 ,i 2 ,i 3 )|i 1 -T 1 ＞σ 1 ,i 2 -T 2 ＞σ 2 ,i 3 -T 3 ＞σ 3 }, wherein sigma 1 、σ 2 、σ 3 Respectively represent the inspection amount images I 1 、I 2 、I 3 Standard deviation of (2);
the test dataset is c= { (i) 1 ,i 2 ,i 3 )||i 1 -T 1 |≤σ 1 Or |i 2 -T 2 |≤σ 2 Or |i 3 -T| 3 ≤σ 3 }；
The non-target region is known as d= { (i) 1 ,i 2 ,i 3 )|i 1 -T 1 ＜σ 1 Or i 2 -T 2 ＜σ 2 Or i 3 -T＜σ 3 }；
Training by using a training data set B through a sequential minimum optimization algorithm, and judging a test data set C through a trained LE-SVDD classifier, so that information of a target point on a detected image is obtained, and further high-efficiency high-precision low-frequency UWB SAR leaf cluster hidden target fusion change detection is realized. As can be seen from fig. 5, the method has a good detection effect on the low-frequency UWB SAR image, can detect the change information of different time-phase SAR images, reduces the false alarm rate while maintaining a certain detection probability, and has a detection speed faster than that of the traditional detection method for the leaf cluster hidden target fusion change based on the LE-SVDD. Therefore, the method is an efficient high-precision change detection method for the low-frequency UWB SAR image.
The same or similar reference numerals correspond to the same or similar components;
the positional relationship depicted in the drawings is for illustrative purposes only and is not to be construed as limiting the present patent;
it is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (6)
1. An improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method is characterized by comprising the following steps:
s1: preprocessing a detection image and a reference image;
s2: obtaining a check quantity image and a detection threshold value based on an image segmentation difference method of an improved clutter distribution model;
the image segmentation difference method based on the improved clutter distribution model is a pixel-level change detection method, a difference value inspection amount image is obtained by subtracting the same point of images in different time phases, then the difference value inspection amount image is segmented, probability density distribution of a non-target area of the segmented image is estimated, a certain false alarm probability value is set, a corresponding detection threshold value is obtained in the probability density distribution, and if the probability density distribution is larger than the detection threshold value, the detection threshold value is regarded as a change detection point, so that the inspection amount image and the detection threshold value of a first sub-algorithm are obtained;
s3: obtaining an inspection amount image and a detection threshold value of a one-dimensional edge worth method and a generalized Laguerre polynomial method;
in the one-dimensional edge worth method, each pixel point of an observation area is taken as a center, an estimation based on a Gaussian probability density distribution model is carried out on a pixel gray value probability density function in the neighborhood of the observation area based on an edge worth expansion, and the difference of the probability density functions of each point between multi-time-phase images is analyzed based on a K-L divergence theory, so that a test quantity image related to the probability density difference is obtained; the generalized Laguerre polynomial method is based on a generalized Laguerre polynomial, the probability density function of the pixel gray value in the neighborhood of the generalized Laguerre polynomial is estimated based on a gamma probability density distribution model, and then a check-out image is obtained through K-L divergence; then, carrying out image gray value statistics on the inspection quantity image, finding out the trend of suddenly falling of a statistic curve on the left side, and adopting an inflection point in the suddenly falling curve as an inspection threshold; fitting a density curve by adopting a least square method during detection, and taking a horizontal axis value, equal to 0, of a vertical axis in the fitted curve as a detection threshold value to obtain a detection quantity image and a detection threshold value of two sub-algorithms;
s4: inputting three inspection quantity images and detection threshold values into an LE-SVDD classifier for training, and judging the target and non-target of a test sample, namely a final change detection result;
firstly, marking the detection amount of a change area and the detection amount of a change-free area as a target class sample and an outlier sample by an SVDD classifier, then training the SVDD by utilizing a training sample set formed by pre-extracted target class samples so as to construct a minimum hypersphere containing all training samples in a nuclear feature space, and classifying the detection amount of the change in an observation scene based on the hypersphere; based on SVDD, LE-SVDD sets detection threshold values and standard deviations, which are larger than corresponding detection quantity images, of all three sub-algorithm detection quantity images as training samples, wherein one or two detection quantity images corresponding to the detection threshold values and the standard deviations are larger than the detection threshold values and the standard deviations are test samples in the three sub-algorithms, inputs the training samples into an LE-SVDD classifier for training, and judges the target and the non-target of the test samples, namely the final change detection result.
2. The improved low frequency UWB SAR leaf cluster hidden target fusion change detection method of claim 1, wherein the process of step S1 comprises:
preprocessing the detection image and the reference image, carrying out bidirectional relative radiation correction processing, and removing image gray value change in the image caused by system response and weather condition non-target change factors.
3. The improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method according to claim 2, wherein the specific process of step S1 is:
for each pixel point of the observation area, adoptsThe pixel neighborhood of (2) calculates the correlation coefficient value of the point between the reference image and the detection image, when the correlation coefficient is larger than 0.5, the point is set as a no-change point, and the no-change point in the whole image in the detection image and the reference image is respectively set as ++>And->The method comprises the steps of carrying out a first treatment on the surface of the Carrying out bidirectional linear estimation by adopting a least square method to obtain a corresponding linear coefficient +.>、/>、/>And->The method comprises the steps of carrying out a first treatment on the surface of the Weighting the unchanged points by using the linear coefficients to perform weighted least square estimation to obtain corresponding linear coefficients +.>、/>、/>And->Continuing to assign weights until the linear coefficient is stable, namely +.>、/>、/>And->At this time:
，/>
in the method, in the process of the invention,and->Respectively is a constant point->And->Is the average value of (2);
for all points of the detected image, linear transformation is usedAnd performing transformation to obtain a corrected detection image.
4. The improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method according to claim 3, wherein the specific process of step S2 is:
is provided with、/>Observing the intensity images of the obtained SAR at different moments, respectively,/->For a reference image without target, +.>For detecting images +.>Is made of->And->The difference value test amount image is formed:
firstImage segmentation is carried out on the reference image, an OTSU image segmentation algorithm is adopted, the equivalent vision number of the reference image is set to be 1, and the initial segmentation number of the image is set to beDividing the reference image, stopping dividing when the minimum value of the square error divided by the square mean value of each sub-region after dividing the reference image is smaller than the equivalent vision number, otherwise +.>Continuing to segment the image until the loop is exited;
then, the clutter distribution of each region is estimated, and the clutter distribution of each region of the difference value test amount image is assumed to be，/>Setting the false probability as +.>The detection threshold value of each corresponding region is +.>，/>Image difference method is used for image->The mathematical expression for detecting the change of the newly appeared target is as follows:
in the method, in the process of the invention,、/>、/>respectively is image +.>、/>、/>Gray value of the same pixel point, +.>Is a detection threshold set according to the false alarm rate.
5. The improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method according to claim 4, wherein the specific process of step S3 is:
the one-dimensional edge worth method and the generalized Laguerre polynomial method are used for estimating probability density distribution firstly, and then calculating a probability density distribution check quantity image by adopting K-L divergence; for a corresponding point of the detection image and the reference image, calculating the statistical information of the mean value, the variance, the third-order accumulation amount and the fourth-order accumulation amount corresponding to the neighborhood of the point, substituting the statistical information into a related formula deduced by the K-L divergence, and solving a probability distribution difference value;
for the inspection quantity images obtained by a one-dimensional edge worth method and a generalized Laguerre polynomial method, as the number of non-target points in the detected image is far greater than the number of target points, the inspection quantity images are subjected to gray statistics, the non-target points are found to be concentrated on the left side and have a suddenly descending trend, the target points are concentrated on the right side, a statistic curve inflection point is adopted as a detection threshold, and the right side is fitted with the inspection quantity imagesIs to obtain the statistics curveFitting a curve, in which +.>Corresponding->The value is the detection threshold.
6. The improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method according to claim 5, wherein the specific process of step S4 is:
for detected imagesAnd reference image->Let the test quantity image based on the image segmentation difference method of the improved clutter distribution model be +.>The detection threshold is->The inspection quantity images obtained by adopting a one-dimensional edge worth method and a generalized Laguerre polynomial method are respectively ++>、/>The detection threshold values are respectively->、/>；
Constructing a sample dataset as，/>、/>、/>Are all inspection volume images +.>、/>、/>Corresponding to the point in the first row;
constructing a training dataset asWherein->、/>、Respectively represent inspection quantity image +.>、/>、/>Standard deviation of (2);
the test data set is；
The non-target area is known as；
Utilization of training data sets using sequential minimum optimization algorithmsTraining and then using the trained LE-SVDD classifier to test data set +.>And judging to obtain information of a target point on the detected image, and further realizing high-efficiency high-precision low-frequency UWB SAR leaf cluster hidden target fusion change detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110407968.6A CN113159157B (en) | 2021-04-15 | 2021-04-15 | Improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110407968.6A CN113159157B (en) | 2021-04-15 | 2021-04-15 | Improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113159157A CN113159157A (en) | 2021-07-23 |
| CN113159157B true CN113159157B (en) | 2023-07-25 |
Family
ID=76868045
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110407968.6A Active CN113159157B (en) | 2021-04-15 | 2021-04-15 | Improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113159157B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102005049A (en) * | 2010-11-16 | 2011-04-06 | 西安电子科技大学 | Unilateral generalized gaussian model-based threshold method for SAR (Source Address Register) image change detection |
| CN102968790A (en) * | 2012-10-25 | 2013-03-13 | 西安电子科技大学 | Remote sensing image change detection method based on image fusion |
| CN105005983A (en) * | 2015-04-13 | 2015-10-28 | 西南科技大学 | SAR image background clutter modeling and target detection method |
| CN106023229A (en) * | 2016-06-02 | 2016-10-12 | 中国矿业大学 | SAR image change detection method by combining half Gauss model and Gauss model |
| CN109919910A (en) * | 2019-01-25 | 2019-06-21 | 合肥工业大学 | The SAR image change detection of level set is merged and improved based on disparity map |
-
2021
- 2021-04-15 CN CN202110407968.6A patent/CN113159157B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102005049A (en) * | 2010-11-16 | 2011-04-06 | 西安电子科技大学 | Unilateral generalized gaussian model-based threshold method for SAR (Source Address Register) image change detection |
| CN102968790A (en) * | 2012-10-25 | 2013-03-13 | 西安电子科技大学 | Remote sensing image change detection method based on image fusion |
| CN105005983A (en) * | 2015-04-13 | 2015-10-28 | 西南科技大学 | SAR image background clutter modeling and target detection method |
| CN106023229A (en) * | 2016-06-02 | 2016-10-12 | 中国矿业大学 | SAR image change detection method by combining half Gauss model and Gauss model |
| CN109919910A (en) * | 2019-01-25 | 2019-06-21 | 合肥工业大学 | The SAR image change detection of level set is merged and improved based on disparity map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113159157A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109581378B (en) | Moving object detection method, electronic device, and storage medium | |
| CN107358258B (en) | SAR image target classification based on NSCT double CNN channels and selective attention mechanism | |
| CN107886498B (en) | Space target detection tracking method based on satellite-borne image sequence | |
| Akbari et al. | A textural–contextual model for unsupervised segmentation of multipolarization synthetic aperture radar images | |
| Xiang et al. | Adaptive superpixel generation for SAR images with linear feature clustering and edge constraint | |
| CN110400294B (en) | Infrared target detection system and detection method | |
| CN108038856B (en) | Infrared small target detection method based on improved multi-scale fractal enhancement | |
| CN110827262B (en) | Weak and small target detection method based on continuous limited frame infrared image | |
| CN113256667B (en) | SAR image ship target detection method based on Otsu and joint distribution | |
| CN111080674A (en) | Multi-target ISAR key point extraction method based on Gaussian mixture model | |
| CN112598708A (en) | Hyperspectral target tracking method based on four-feature fusion and weight coefficient | |
| CN110310263B (en) | SAR image residential area detection method based on significance analysis and background prior | |
| CN111861905A (en) | SAR image speckle noise suppression method based on Gamma-Lee filtering | |
| CN108665420A (en) | Infrared DIM-small Target Image background suppression method based on variation Bayesian model | |
| CN107194896A (en) | A kind of background suppression method and system based on neighbour structure | |
| Zhang et al. | Infrared small target detection based on morphology and wavelet transform | |
| CN106097292B (en) | Space-time neighborhood Gaussian weighted median filtering method for remote sensing image processing | |
| CN109461127B (en) | SAR image sparse regularization feature enhancement method with interpretation as purpose | |
| CN110751671B (en) | Target tracking method based on kernel correlation filtering and motion estimation | |
| CN107479052B (en) | Ground concealed target detection method based on Generalized Gaussian Distribution Model | |
| CN107729903A (en) | SAR image object detection method based on area probability statistics and significance analysis | |
| CN113159157B (en) | Improved low-frequency UWB SAR leaf cluster hidden target fusion change detection method | |
| CN110363105B (en) | Method for inhibiting speckle of fully-polarized SAR image | |
| Ning et al. | Background Modeling and Fuzzy Clustering for Motion Detection from Video. | |
| CN111461999A (en) | SAR image speckle suppression method based on super-pixel similarity measurement |
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 |