A method, device, equipment and storage medium for target detection based on local area feature differences

Abstract

The present invention discloses a target detection method, device, equipment and storage medium based on local area feature differences, belonging to the field of target detection technology. The target detection method includes: reconstructing an image based on background cancellation of a sensor; fitting the brightness temperature distribution of the reconstructed image using a Gaussian mixture model to calculate the multi-order statistical characteristic parameters of each Gaussian component; calculating the Fisher vector of the superpixel using the multi-order statistical characteristic parameters and constructing the Fisher vector contrast; constructing a reference superpixel set in the local area based on the slow variation of the background superpixel; constructing the suppression feature of the background superpixel using extreme value suppression based on the brightness temperature characteristic; in the local area, multiplying the Fisher vector contrast and the suppression feature of the background superpixel to obtain the heterogeneous feature of the local area difference; using a dual-parameter method to binarize the difference feature, obtain the target area pixels, and obtain the target detection result. It can improve the intersection-over-union ratio and quality factor performance of target detection.

Description

Technical Field

[0001] The present invention belongs to the field of target detection technology, and more specifically, relates to a target detection method, device, equipment and storage medium based on local area feature differences. Background Art

[0002] Synthetic aperture radiometer imaging systems, with their sensitivity to metal and heat sources, excellent concealment, inherent forward-looking observation capabilities, and instantaneous imaging, have been widely used in target detection for Earth remote sensing, radio astronomy, military reconnaissance, and human security screening. Under airborne observation conditions, the observed target has a certain texture structure, its brightness temperature distribution is non-uniform, the background area is complex, and the reconstructed image is affected by noise, making it difficult to detect the entire target area. Consequently, numerous studies have been devoted to solving the problem of target detection based on synthetic aperture radiometer imaging.

[0003] Existing target detection technologies based on synthetic aperture radiometer imaging primarily rely on differential features and can be divided into two categories: one is based on trajectory features from continuous frame images, detecting targets by extracting continuous target positioning points; the other is based on features from single frame images, exploiting pixel brightness temperature differences or frequency characteristics under noise suppression for target detection. However, both of these methods suffer from false detection and missed target pixels due to their single-feature nature. Summary of the Invention

[0004] In response to the defects of the related art, the purpose of the present invention is to provide a target detection method, device, equipment and storage medium based on local area feature differences, aiming to solve the problems of missed detection and false detection of target pixels caused by only using a single feature in the existing methods.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a target detection method based on local area feature differences, comprising:

[0006] S1. Perform background cancellation processing on an image acquired by a sensor to obtain a reconstructed image; perform superpixel segmentation on the reconstructed image, use a Gaussian mixture model to fit the brightness temperature distribution of the reconstructed image, and calculate multi-order statistical characteristic parameters of each Gaussian component;

[0007] S2. Calculating the Fisher vector of the superpixel according to the multi-order statistical characteristic parameters; constructing a local region of a preset size and a reference superpixel set based on the gradual variation of the background superpixels near the target area in the reconstructed image; calculating the feature difference between each superpixel to be tested in the target area and each reference superpixel in the local area according to the Fisher vector of each superpixel, and constructing a Fisher vector contrast;

[0008] S3. Based on the brightness temperature characteristics of the target, a suppression feature of the background superpixel is constructed by using extreme value suppression; within the local area, a difference feature of the local area is obtained by multiplying the Fisher vector contrast and the suppression feature of the background superpixel;

[0009] S4. Use a dual-parameter method to perform binarization processing on the difference features of the local area, obtain target area pixels, and obtain target detection results.

[0010] Optionally, S1 specifically includes:

[0011] S11, acquiring a detection scene brightness temperature image and a background brightness temperature image based on the sensor, subtracting the background brightness temperature image from the detection scene brightness temperature image to perform background cancellation, and obtaining a reconstructed image;

[0012] S12. Perform superpixel segmentation on the reconstructed image, and use a Gaussian mixture model to fit the brightness temperature distribution of the reconstructed image to obtain multi-order statistical characteristic parameters of each Gaussian component:

[0013]

[0014] Among them, x represents the brightness temperature of the pixel corresponding to the background cancellation reconstructed image, θ Q =[ω1,ω2,…,ω Q ,μ1,μ2,…,μ Q ,σ1,σ2,…,σ Q ] T Represents the multi-order statistical characteristic parameters corresponding to the Gaussian mixture model, Q represents the number of components, ω q is the clustering weight of the component, μ q is the cluster center, σ q is the cluster width, is the Gaussian density function.

[0015] Optionally, S2 specifically includes:

[0016] S21. Calculate the Fisher vector of the superpixel according to the multi-order statistical characteristic parameters:

[0017]

[0018] Among them, P l represents the number of pixels contained in the lth superpixel, is the Cholesky decomposition of the inverse matrix of Fisher information, l∈{1,2,…,L} represents the superpixel index, L represents the number of superpixels divided, Represents about θ Q The gradient operator, x l,p Indicates the brightness temperature corresponding to the p-th pixel in the l-th superpixel;

[0019] S22, constructing a local area of ​​a preset size and a reference superpixel set C based on the gradual variation of the background superpixels near the target area in the reconstructed image l ;

[0020] Among them, C l It represents the geometric center of the first superpixel as the center and the w The set of superpixels covered by a rectangular box with a side length of d w =ρ·S represents the side length of the rectangular frame, ρ represents the magnification of the rectangular frame, represents the average superpixel size;

[0021] S23. Calculate the feature difference between each superpixel point to be tested in the target area and each reference superpixel point in the local area based on the Fisher vector of each superpixel, and construct the Fisher vector contrast using the power-normalized Fisher vector and the Euclidean distance:

[0022]

[0023] in, represents the power normalized Fisher vector, ||·||2 represents the 2-norm of the vector, sgn(·) represents the element-wise sign function, represents the element-wise arithmetic square root, and l and l′ represent different superpixel indices.

[0024] Optionally, S3 specifically includes:

[0025] S31. For low brightness temperature target observation scenes, the suppression feature of background superpixels is constructed as follows:

[0026]

[0027] Among them, min{·,0} means taking the minimum value compared with 0. Indicates the median brightness temperature of pixels in the superpixel, l and l′ represent different superpixel indices;

[0028] For high-brightness temperature target observation scenes, the suppression feature of background superpixels is constructed as follows:

[0029]

[0030] Among them, max{·,0} means taking the maximum value compared with 0;

[0031] S32, in the local area, combining the Fisher vector contrast by multiplication and the suppression feature δ(x l ,x l′ ), construct the difference features of local areas:

[0032]

[0033] Optionally, S4 specifically includes:

[0034] S41. Use the dual parameter method to set the detection threshold as: in, Represents the mean of the local regional difference characteristics, represents the standard deviation of local regional difference characteristics, and α represents the threshold adjustment factor;

[0035] S42. Binarize the difference features of the local areas of all superpixels, obtain the target area pixels, and obtain the target detection result.

[0036] In a second aspect, the present invention further provides a target detection device based on local area feature differences, comprising:

[0037] A segmentation module is used to perform background cancellation processing on the image acquired by the sensor to obtain a reconstructed image; perform superpixel segmentation on the reconstructed image, use a Gaussian mixture model to fit the brightness temperature distribution of the reconstructed image, and calculate the multi-order statistical characteristic parameters of each Gaussian component;

[0038] A calculation module is configured to calculate the Fisher vector of the superpixel based on the multi-order statistical characteristic parameters; construct a local region of a preset size and a reference superpixel set based on the gradual variation of the background superpixels near the target area in the reconstructed image; calculate the feature difference between each superpixel to be tested in the target area and each reference superpixel in the local area based on the Fisher vector of each superpixel, and construct a Fisher vector contrast;

[0039] A construction module is used to construct a suppression feature of the background superpixel based on the brightness temperature characteristics of the target by using an extreme value suppression method; in the local area, a difference feature of the local area is obtained by multiplying the Fisher vector contrast and the suppression feature of the background superpixel;

[0040] The detection module is used to perform binarization processing on the difference features of the local area using a dual-parameter method, obtain pixels of the target area, and obtain target detection results.

[0041] In a third aspect, the present invention further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method as described in any one of the first aspects when executing the computer program.

[0042] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method as described in any one of the first aspects.

[0043] Compared with the prior art, the above technical solutions conceived by the present invention can achieve the following beneficial effects:

[0044] The present invention provides a target detection method based on local area feature differences. First, an image is reconstructed based on background cancellation of a sensor, multi-order statistical characteristic parameters of components are obtained using a Gaussian mixture model, Fisher vectors are calculated based on the description of superpixels using multi-order statistical characteristics, Fisher vector contrast is constructed, and false alarm pixels are avoided and the signal-to-noise ratio is improved through superpixel-level processing. The local brightness temperature characteristics of the target and the slow variation of the background near the target are considered, and the background superpixels are suppressed by extreme value suppression to reduce the background superpixel intensity. The local area difference feature is constructed in combination with the Fisher vector contrast to improve the superpixel intensity of the target area. Based on the local area difference feature, the feature is binarized using a two-parameter method to achieve target detection, and the target area pixels are obtained. In this scheme, multi-order statistical characteristics are used to describe superpixels, and the differences in feature vectors (Fisher vectors) composed of zero-order, first-order and second-order statistical information are considered for target detection. Compared with the traditional method that only relies on brightness temperature differences for target detection, multi-order statistical information is used to improve the difference compared with a single feature / single statistical information; it solves the problems of high false detection rate and missed target pixel detection based on single feature target detection, and can improve the target detection intersection-over-union ratio and quality factor performance, and effectively detect extended source targets under the influence of noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a flow chart of a target detection method based on local area feature differences in an embodiment of the present invention;

[0046] Figure 2 is an array configuration diagram of a data acquisition system used in an embodiment of the present invention;

[0047] Figure 3a is an optical image of a selected target in an embodiment of the present invention;

[0048] Figure 3b is the brightness temperature image reconstructed by background cancellation of the 15th frame of scene data in an embodiment of the present invention;

[0049] Figure 4 15 is a density function and component function diagram of the Gaussian mixture model fitting of the scene data frame in an embodiment of the present invention;

[0050] Figure 5 is a local area difference feature map of the 15th frame of scene data in an embodiment of the present invention;

[0051] Figure 6The dual parameter method of the 15th frame of the scene data in the embodiment of the present invention is used to calculate the local area difference feature. Figure 2 The valued test result graph;

[0052] Figure 7a 15 is a detection result diagram of the scene data frame 15 based on the windowed background cancellation binarization method in an embodiment of the present invention;

[0053] Figure 7b is a graph showing how the overall IoU of all 29 frames of scene data changes with the normalization threshold adjustment factor in an embodiment of the present invention;

[0054] Figure 7c 3 is a graph showing how the overall quality factor of all 29 frames of scene data changes with the normalized threshold adjustment factor in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0056] The contents involved in the above embodiment are described below in conjunction with a preferred embodiment.

[0057] Example 1

[0058] The present invention provides a target detection method based on local area feature differences, comprising:

[0059] S1. Perform background cancellation processing on an image acquired by a sensor to obtain a reconstructed image; perform superpixel segmentation on the reconstructed image, use a Gaussian mixture model to fit the brightness temperature distribution of the reconstructed image, and calculate multi-order statistical characteristic parameters of each Gaussian component;

[0060] S2. Calculating the Fisher vector of the superpixel according to the multi-order statistical characteristic parameters; constructing a local region of a preset size and a reference superpixel set based on the gradual variation of the background superpixels near the target area in the reconstructed image; calculating the feature difference between each superpixel to be tested in the target area and each reference superpixel in the local area according to the Fisher vector of each superpixel, and constructing a Fisher vector contrast;

[0061] S3. Based on the brightness temperature characteristics of the target, a suppression feature of the background superpixel is constructed by using extreme value suppression; within the local area, a difference feature of the local area is obtained by multiplying the Fisher vector contrast and the suppression feature of the background superpixel;

[0062] S4. Use a dual-parameter method to perform binarization processing on the difference features of the local area, obtain target area pixels, and obtain target detection results.

[0063] Background cancellation is performed on the image acquired by the sensor to obtain a reconstructed image. The brightness temperature distribution of the background-cancelled reconstructed image is fitted using a Gaussian mixture model to obtain multi-order statistical characteristic parameters for each Gaussian component. The Fisher vector of the superpixel is calculated based on these parameters, and the Fisher vector contrast is constructed using power-normalized Fisher vectors and Euclidean distance. Superpixel-level processing is used to avoid false alarm pixels and improve the signal-to-noise ratio. Considering the differences between the local differences between different background superpixels and the local differences between target superpixels, extreme value suppression is used to suppress background superpixels with local differences in brightness temperature distribution, reducing the intensity of background superpixels. The superpixels covered by the local rectangular box are used as reference units to suppress background superpixels near the target area, increasing the intensity of the target superpixels, constructing local region difference features, and improving the signal-to-noise ratio. The local region difference features are used to obtain a detection threshold using a two-parameter method, and the target region pixels are detected to achieve target detection.

[0064] Optionally, S1 specifically includes:

[0065] S11, acquiring a detection scene brightness temperature image and a background brightness temperature image based on the sensor, subtracting the background brightness temperature image from the detection scene brightness temperature image to perform background cancellation, and obtaining a reconstructed image;

[0066] S12. Perform superpixel segmentation on the reconstructed image, and use a Gaussian mixture model to fit the brightness temperature distribution of the reconstructed image to obtain multi-order statistical characteristic parameters of each Gaussian component:

[0067]

[0068] Among them, x represents the brightness temperature of the pixel corresponding to the background cancellation reconstructed image, θ Q =[ω1,ω2,…,ω Q ,μ1,μ2,…,μ Q ,σ1,σ2,…,σ Q ] T Represents the multi-order statistical characteristic parameters corresponding to the Gaussian mixture model, Q represents the number of components, ω q is the clustering weight of the component, μ q is the cluster center, σ q is the cluster width, is the Gaussian density function.

[0069] The specific steps are as follows:

[0070] (1) Using the expectation maximization algorithm, the multi-order statistical characteristic parameters corresponding to the Gaussian mixture model of the background cancellation image are estimated to obtain the density function of the fitting brightness temperature distribution;

[0071] (2) Establish the relationship between the density function of the brightness temperature distribution of the reconstructed image after fitting background cancellation and each Gaussian component. The expression is as follows:

[0072]

[0073] Where x represents the brightness temperature of the pixel in the background cancellation reconstructed image, and the value of this variable is the brightness temperature value in the image. Q Represents the multi-order statistical characteristic parameters corresponding to the Gaussian mixture model. The parameter vector is a column vector composed of the cluster weights, cluster centers, and cluster widths of each component in sequence. Q is equal to the number of components.

[0074] For the multi-order statistical characteristic parameters corresponding to the Gaussian mixture model:

[0075] θ Q =[ω1,ω2,…,ω Q ,μ1,μ2,…,μ Q ,σ1,σ2,…,σ Q ] T , where ω q 、μ q and σ q are the cluster weights, cluster centers, and cluster widths of the components, respectively.

[0076] p(x|μ q ,σ q ) represents the Gaussian density function corresponding to each component, which is expressed as:

[0077]

[0078] Optionally, S2 specifically includes:

[0079] S21. Calculate the Fisher vector of the superpixel according to the multi-order statistical characteristic parameters:

[0080]

[0081] Among them, P l represents the number of pixels contained in the lth superpixel, is the Cholesky decomposition of the inverse matrix of Fisher information, l∈{1,2,…,L} represents the superpixel index, L represents the number of superpixels divided, Represents about θ Q The gradient operator, x l,pIndicates the brightness temperature corresponding to the p-th pixel in the l-th superpixel;

[0082] S22, constructing a local area of ​​a preset size and a reference superpixel set C based on the gradual variation of the background superpixels near the target area in the reconstructed image l ;

[0083] Among them, C l It represents the geometric center of the first superpixel as the center and the w The set of superpixels covered by a rectangular box with a side length of d w =ρ·S represents the side length of the rectangular frame, ρ represents the magnification of the rectangular frame, represents the average superpixel size;

[0084] S23. Calculate the feature difference between each superpixel point to be tested in the target area and each reference superpixel point in the local area based on the Fisher vector of each superpixel, and construct the Fisher vector contrast using the power-normalized Fisher vector and the Euclidean distance:

[0085]

[0086] in, represents the power normalized Fisher vector, ||·||2 represents the 2-norm of the vector, sgn(·) represents the element-wise sign function, represents the element-wise arithmetic square root, and l and l′ represent different superpixel indices.

[0087] Optionally, S3 specifically includes:

[0088] S31. For low brightness temperature target observation scenes, the suppression feature of background superpixels is constructed as follows:

[0089]

[0090] Among them, min{·,0} means taking the minimum value compared with 0. Indicates the median brightness temperature of pixels in the superpixel, l and l′ represent different superpixel indices;

[0091] For high-brightness temperature target observation scenes, the suppression feature of background superpixels is constructed as follows:

[0092]

[0093] Among them, max{·,0} means taking the maximum value compared with 0;

[0094] S32. Combine Fisher vector contrast by multiplication and the suppression feature δ(x l ,x l′), construct the difference features of local areas:

[0095]

[0096] Optionally, S4 specifically includes:

[0097] S41. Use the dual parameter method to set the detection threshold as: in, Represents the mean of the local regional difference characteristics, represents the standard deviation of local regional difference characteristics, and α represents the threshold adjustment factor;

[0098] S42. Binarize the difference features of the local areas of all superpixels, obtain the target area pixels, and obtain the target detection result.

[0099] In a specific embodiment, the background cancellation and reconstructed brightness temperature image data collected by the synthetic aperture radiometer system can be selected as the original data. Figure 2 Indicates the array configuration of the system used.

[0100] In this embodiment, a civilian ship in Qinhuangdao waters is selected as the detection target. The optical image corresponding to the scene target is as follows: Figure 3a As shown, the scene data consists of 29 frames of continuous frame data, of which the background cancellation and reconstruction brightness temperature image of the 15th frame is as follows Figure 3b shown.

[0101] (1) The brightness temperature distribution of the background cancellation reconstructed image is fitted according to the Gaussian mixture model to obtain the multi-order statistical characteristic parameters of each Gaussian component. The Fisher vector of the superpixel is calculated based on these parameters, and the Fisher vector contrast is constructed using the sparsity and Euclidean distance of the Fisher vector.

[0102] The expectation maximization algorithm is used to estimate the multi-order statistical characteristic parameters corresponding to the Gaussian mixture model, and the density function and component functions of the brightness temperature distribution of the fitted background cancellation reconstructed image are obtained. There are Q component functions in total, among which the component function of the 15th frame is as follows Figure 4 shown.

[0103] A Fisher vector is calculated to represent each superpixel, where the dimension of the Fisher vector is 3Q × 1. The sparse Fisher vector is power-normalized by the signed square root, and then the Fisher vector contrast between each pair of superpixels is calculated using the Euclidean distance.

[0104] (2) Considering the difference between the local differences of different background superpixels and the local differences of target superpixels, the superpixels covered by the local rectangular box are used as reference units, and the extreme value suppression method is used to suppress the background superpixels with local differences in brightness temperature distribution, thereby constructing local area difference features.

[0105] According to the slow variation of the background superpixels near the target area and the local high brightness temperature properties of the background superpixels to be suppressed, the reference superpixels in the local area are selected by setting a rectangular box.

[0106] The brightness temperature distribution of superpixels in the local area is determined by median operation, and extreme value suppression is used to suppress background superpixels in the local area that appear to have high brightness temperature distribution.

[0107] The Fisher vector contrast is multiplied by the background suppression feature to suppress the background superpixel. The eigenvalues ​​corresponding to the low brightness temperature superpixels in the local area are converted into high intensity values ​​by squaring. The local area difference features are obtained based on the contrast and brightness temperature distribution differences of the selected reference superpixels.

[0108] In this embodiment, the target area is characterized by low brightness temperature in the local area. The background superpixel suppression feature mainly suppresses the background superpixels with high brightness temperature distribution in the local area. The local area difference feature map of the 15th frame is shown as follows: Figure 5 shown.

[0109] (3) Based on the local area difference features obtained in step (2), a dual-parameter method is used to obtain a detection threshold and detect pixels in the target area.

[0110] The mean and standard deviation of the local area difference features are calculated to obtain the detection threshold.

[0111] The local area difference features of all superpixels are binarized to obtain the pixels contained in the target area.

[0112] In this embodiment, the local area difference characteristics are analyzed by the dual parameter method. Figure 2 The detection results of the 15th frame obtained by quantization are as follows Figure 6 shown.

[0113] Furthermore, other methods may be used to determine the detection threshold during specific implementation.

[0114] For further explanation, a comparison of the overall intersection-over-union ratio and overall quality factor between the present invention and other target detection methods for synthetic aperture radiometers is set up.

[0115] All 29 frames of data in this embodiment are uniformly used to detect targets in all frames using the dual parameter method. In addition to the detection method of the present invention (LRC), the detection results based on the windowed background cancellation binarization (BWDFT) method are also considered. The detection results of the 15th frame are as follows: Figure 7a As shown. The overall intersection-over-union (IoU) and the overall quality factor (FoM) are given in the normalized threshold adjustment factor α0 = (α-α min ) / (α max -αmin ) changes, where the overall intersection-over-union ratio and overall quality factor of the BWDFT ​​method and the present method under all 29 frames of data change with the normalized threshold adjustment factor are shown as follows: Figure 7b and Figure 7c As shown in the figure, a larger overall IoU indicates more accurate pixel-level detection across all frames, while a larger overall quality factor indicates fewer false detections and more true target detections across all frames. Table 1 compares the average IoU and average quality factor across the entire normalized threshold adjustment factor range.

[0116] Table 1

[0117] Detection method BWDFT LRC Average Intersection-Union Ratio 0.1691 0.5099 Average quality factor 0.5517 0.6858

[0118] In the embodiment provided by the present invention, the detection results obtained show that the above-mentioned target detection method based on local area feature differences has high intersection-over-union ratio and quality factor performance, and can detect the complete target area in continuous frames, effectively solving the problems of false detection and missed detection of target pixels.

[0119] In the embodiment of the present invention, the image is reconstructed by canceling the background of the sensor, the multi-order statistical characteristic parameters of the components are obtained by using a Gaussian mixture model, the Fisher vector is calculated based on the multi-order statistical characteristic parameters, the Fisher vector contrast is constructed, the background superpixels are suppressed by using extreme value suppression, the local area difference feature is constructed in combination with the Fisher vector contrast, and finally the feature is binarized using a two-parameter method to achieve target detection. The technical problem of missed detection and false detection of target pixels caused by using only a single feature in the existing method is solved. The beneficial effect of improving the intersection-over-union ratio and quality factor performance of target detection and effectively detecting the extended source target under the influence of noise is achieved.

[0120] Example 2

[0121] The present invention also provides a target detection device based on local area feature differences, comprising:

[0122] A segmentation module is used to perform background cancellation processing on the image acquired by the sensor to obtain a reconstructed image; perform superpixel segmentation on the reconstructed image, use a Gaussian mixture model to fit the brightness temperature distribution of the reconstructed image, and calculate the multi-order statistical characteristic parameters of each Gaussian component;

[0123] A calculation module is configured to calculate the Fisher vector of the superpixel based on the multi-order statistical characteristic parameters; construct a local region of a preset size and a reference superpixel set based on the gradual variation of the background superpixels near the target area in the reconstructed image; calculate the feature difference between each superpixel to be tested in the target area and each reference superpixel in the local area based on the Fisher vector of each superpixel, and construct a Fisher vector contrast;

[0124] A construction module is used to construct a suppression feature of the background superpixel based on the brightness temperature characteristics of the target by using an extreme value suppression method; in the local area, a difference feature of the local area is obtained by multiplying the Fisher vector contrast and the suppression feature of the background superpixel;

[0125] The detection module is used to perform binarization processing on the difference features of the local area using a dual-parameter method, obtain pixels of the target area, and obtain target detection results.

[0126] An object detection device based on local area feature differences provided by an embodiment of the present invention is used to execute an object detection method based on local area feature differences provided by any embodiment of the present invention, and has corresponding beneficial effects.

[0127] Example 3

[0128] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method as described in any one of the embodiments are implemented.

[0129] Example 4

[0130] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method as described in any one of the embodiments are implemented.

[0131] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A target detection method based on local area feature differences, characterized in that: include: S1, performing background cancellation processing on the image acquired by the sensor to obtain a reconstructed image; Performing superpixel segmentation on the reconstructed image, fitting the brightness temperature distribution of the reconstructed image using a Gaussian mixture model, and calculating multi-order statistical characteristic parameters of each Gaussian component; S2. Calculating the Fisher vector of the superpixel according to the multi-order statistical characteristic parameters; constructing a local region of a preset size and a reference superpixel set based on the gradual variation of the background superpixels near the target area in the reconstructed image; calculating the feature difference between each superpixel to be tested in the target area and each reference superpixel in the local area according to the Fisher vector of each superpixel, and constructing a Fisher vector contrast; S3. Based on the brightness temperature characteristics of the target, a suppression feature of the background superpixel is constructed by using extreme value suppression; within the local area, a difference feature of the local area is obtained by multiplying the Fisher vector contrast and the suppression feature of the background superpixel; S4. Use a dual-parameter method to perform binarization processing on the difference features of the local area, obtain target area pixels, and obtain target detection results.

2. The method according to claim 1, wherein S1 specifically includes: S11, acquiring a detection scene brightness temperature image and a background brightness temperature image based on the sensor, subtracting the background brightness temperature image from the detection scene brightness temperature image to perform background cancellation, and obtaining a reconstructed image; S12. Perform superpixel segmentation on the reconstructed image, and use a Gaussian mixture model to fit the brightness temperature distribution of the reconstructed image to obtain multi-order statistical characteristic parameters of each Gaussian component: Among them, x represents the brightness temperature of the pixel corresponding to the background cancellation reconstructed image, θ Q =[ω1,ω2,…,ω Q ,μ1,μ2,…,μ Q ,σ1,σ2,…,σ Q ] T Represents the multi-order statistical characteristic parameters corresponding to the Gaussian mixture model, Q represents the number of components, ω q is the clustering weight of the component, μ q is the cluster center, σ q is the cluster width, is the Gaussian density function.

3. The method according to claim 1, wherein S2 specifically includes: S21. Calculate the Fisher vector of the superpixel according to the multi-order statistical characteristic parameters: Among them, P l represents the number of pixels contained in the lth superpixel, is the Cholesky decomposition of the inverse matrix of Fisher information, l∈{1,2,…,L} represents the superpixel index, L represents the number of superpixels divided, Represents about θ Q The gradient operator, x l,p Indicates the brightness temperature corresponding to the p-th pixel in the l-th superpixel; S22, constructing a local area of ​​a preset size and a reference superpixel set C based on the gradual variation of the background superpixels near the target area in the reconstructed image l ; Among them, C l It represents the geometric center of the first superpixel as the center and the w The set of superpixels covered by a rectangular box with a side length of d w =ρ·S represents the side length of the rectangular frame, ρ represents the magnification of the rectangular frame, represents the average superpixel size; S23. Calculate the feature difference between each superpixel to be tested in the target area and each reference superpixel in the local area based on the Fisher vector of each superpixel, and construct the Fisher vector contrast using the power-normalized Fisher vector and the Euclidean distance: in, represents the power normalized Fisher vector, ||·||2 represents the 2-norm of the vector, sgn(·) represents the element-wise sign function, represents the element-wise arithmetic square root, and l and l′ represent different superpixel indices.

4. The method according to claim 1, wherein S3 specifically includes: S31. For low brightness temperature target observation scenes, the suppression feature of background superpixels is constructed as follows: Among them, min{·,0} means taking the minimum value compared with 0. Indicates the median brightness temperature of pixels in the superpixel, l and l′ represent different superpixel indices; For high-brightness temperature target observation scenes, the suppression feature of background superpixels is constructed as follows: Among them, max{·,0} means taking the maximum value compared with 0; S32, in the local area, combining the Fisher vector contrast by multiplication and the suppression feature δ(x l ,x l′ ), construct the difference features of local areas:

5. The method according to claim 1, wherein S4 specifically includes: S41. Use the dual parameter method to set the detection threshold as: in, Represents the mean of the local regional difference characteristics, represents the standard deviation of local regional difference characteristics, and α represents the threshold adjustment factor; S42. Binarize the difference features of the local areas of all superpixels, obtain the target area pixels, and obtain the target detection result.

6. A target detection device based on local area feature differences, characterized in that: include: A segmentation module is used to perform background cancellation processing based on the image acquired by the sensor to obtain a reconstructed image; Performing superpixel segmentation on the reconstructed image, and using a Gaussian mixture model to fit the brightness temperature distribution of the reconstructed image to calculate the multi-order statistical characteristic parameters of each Gaussian component; A calculation module is configured to calculate the Fisher vector of the superpixel based on the multi-order statistical characteristic parameters; construct a local region of a preset size and a reference superpixel set based on the gradual variation of the background superpixels near the target area in the reconstructed image; calculate the feature difference between each superpixel to be tested in the target area and each reference superpixel in the local area based on the Fisher vector of each superpixel, and construct a Fisher vector contrast; A construction module is used to construct a suppression feature of the background superpixel based on the brightness temperature characteristics of the target by using an extreme value suppression method; in the local area, a difference feature of the local area is obtained by multiplying the Fisher vector contrast and the suppression feature of the background superpixel; The detection module is used to perform binarization processing on the difference features of the local area using a dual-parameter method, obtain the pixels of the target area, and obtain the target detection result.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images