A polarization spectral image fusion method based on non-subsampled contourlet transform

Abstract

The present application belongs to the field of image fusion, and particularly discloses a polarization spectrum image fusion method based on non-subsampled contourlet transform. The method comprises the following steps: S1, acquiring four spectral images and intensity images I of different linear polarization angles (0°, 45°, 90° and 135°) through a polarization spectrum imaging system; S2, calculating the corresponding Stokes parameters of the images to obtain corresponding Q, U and DoLP images; S3, decomposing the Q and I images by using non-subsampled contourlet transform, taking the mean value of the low-pass subbands, and preliminarily fusing the high-pass subbands by using the maximum amplitude rule to obtain a polarization characteristic S; and finally, decomposing the S image and the intensity image by using non-subsampled contourlet transform, fusing the low-pass subbands obtained by using an improved pulse-coupled neural network method, and fusing the high-pass subbands by using a weighted fusion rule based on local mode spectrum characteristics.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image fusion, in particular to a polarization spectrum image fusion method based on non-subsampled contourlet transform. BACKGROUND

[0002] In modern military operations, with the continuous progress of camouflage technology, soldiers, weapons and ammunition and other military supplies are highly similar to the environment, making it difficult for traditional optical target recognition technology to effectively identify camouflaged targets. Polarization imaging technology captures the polarization characteristics of light on the surface of objects, enhances the contrast between objects and backgrounds, and provides additional image information. Fusing polarization information and spectral information can more comprehensively describe the characteristics of target objects. Such multi-dimensional information helps to more accurately identify and distinguish different types of objects, especially in complex backgrounds. A polarization spectrum image fusion method is proposed as a technology for identifying target information in complex backgrounds.

[0003] Previous polarization spectrum image fusion methods, due to differences in light source, polarization and spectrum between the front and rear images, are prone to spectral distortion, especially the fused image has too much redundant information and obvious loss of image edge information. Therefore, a polarization spectrum image fusion method based on non-subsampled contourlet transform is proposed to solve the above problems. SUMMARY

[0004] Technical problems solved

[0005] To overcome the deficiencies of the prior art, the present application provides a polarization spectrum image fusion method based on non-subsampled contourlet transform, which solves the problems raised in the background art.

[0006] (II) Technical solutions

[0007] The present application specifically adopts the following technical solutions to achieve the above purposes:

[0008] A polarization spectrum image fusion method based on non-subsampled contourlet transform, comprising the following steps:

[0009] S1, preparing polarization spectrum images: acquiring polarization spectrum images and light intensity images I of four different linear polarization angles (0°, 45°, 90° and 135°) through a polarization spectrum imaging system;

[0010] S2, data preprocessing: calculating the corresponding Stokes parameters of the images to obtain the corresponding Q, U and DoLP images;

[0011] S3, preliminary fusion: The polarization spectrum image and visible light image with the same edge information are decomposed using non-subsampled contourlet transform, the low-pass sub-band is averaged, and the high-pass sub-band is preliminarily fused using the maximum amplitude rule to obtain the polarization feature S;

[0012] S4, image fusion: The polarization features, intensity images, and polarization degree are decomposed by non-subsampled contourlet transform. The low-pass subbands obtained by the decomposition are fused using an improved pulse coupled neural network method, and the high-pass subbands are fused using a weighted fusion rule based on local pattern spectrum characteristics;

[0013] S5, image reconstruction: the image fused in S4 is reconstructed using non-subsampled contourlet transform to obtain the final fused image;

[0014] S6, image evaluation: Evaluate the fusion effect of the image using subjective and objective indicators. The objective indicators include standard deviation, information entropy, and average gradient.

[0015] Furthermore, the method for the four directional parameters and linear polarization degree image in the image preprocessing in S2 is to calculate the Stokes vector of the polarization images in the four directions (0°, 45°, 90°, 135°) in the polarization data set and to quantitatively describe the intensity image S0 and the polarization degree image DoLP using the Stokes vector as shown in the following formula:

[0016]

[0017] Where I is the sum of the polarization component intensities of the two coordinate axis directions; Q represents the intensity difference image of linear polarization in the 0° and 90° directions; and U represents the intensity difference image of linear polarization in the 45° and 135° directions.

[0018] Furthermore, in the S3 preliminary fusion, the non-subsampled contourlet transform is an improved multi-scale and multi-directional image transformation method, which avoids the information loss problem in the traditional contourlet transform by using a non-subsampled pyramid and a non-subsampled directional filter bank;

[0019] The non-subsampled contourlet transform decomposes an image into sub-bands of multiple scales and directions, effectively capturing image details and directional features while maintaining the image's translation invariance, thereby providing high-quality processing results in image fusion applications. The non-subsampled contourlet transform consists of two main steps:

[0020] First, a non-subsampled pyramid is used to perform multi-scale decomposition of the image to generate high-pass subbands and low-pass subbands. Then, a non-subsampled directional filter bank is used to directional decompose the high-pass subbands, dividing the frequency domain into multiple subbands, and organizing these subbands through a layered binary tree structure.

[0021] The non-subsampled contourlet transform is mainly divided into the following two steps. First, a non-subsampled pyramid is used to perform multi-scale decomposition into two parts: a high-pass subband and a low-pass subband. Then, a non-subsampled directional filter bank is used to perform directional decomposition on the high-pass subband, and a layered binary tree is used to divide the frequency domain into multiple subbands. The number of decomposition layers of the non-subsampled contourlet transform is 2. The first layer performs 4-directional decomposition, and the second layer performs 8-directional decomposition.

[0022] Furthermore, in the S4 image fusion, the local spectrum pattern is characterized by converting each local region in the image into the frequency domain and extracting texture features therefrom;

[0023] First, for each pixel of the image, a small window around it is selected as the local area. Second, the Fourier transform is applied to convert these local areas from their original spatial domain to the frequency domain. In the frequency domain, various frequency components can be detected, which reveal the texture information of the local area. Then, the amplitude features are extracted from these frequency components and encoded to obtain the representation of the local texture.

[0024] The high-pass subband focuses on image details such as edges, textures, and fine structures, emphasizing image details and helping to determine image boundaries and structures. The weights are calculated through the local pattern spectrum. The steps are as follows:

[0025] (5) Calculate the LSP of each pixel p of S, Q1 and DoLP images respectively s (p), and LSP DoLP (p); (6) For each local mode spectrum feature, calculate E S (p), and E DoLP (p);

[0026] (7) Energy normalization processing:

[0027]

[0028] In the above formula, E S (p), and E DoLP (p) are the local pattern spectrum features of the same pixel point in image S, Q1, and DOLP image, respectively, and W S (P) is related to E S (p) The related normalized weight represents the ratio of the polarization component S at the pixel point p to that at the pixel point s; is with The related normalized weight represents the ratio of the polarization component Q1 at the pixel point p to that at the pixel point q; W DOLP (P) is related to E DOLP(p) The normalized weight associated with it represents the ratio of the polarization component DOLP at the pixel point p to that at the pixel point p.

[0029] (8) The high frequency sub-band fusion formula is:

[0030]

[0031] In the above formula, H S (p), H DoLP (p) represent high-pass subbands at different scales in the same direction, H f (p) is the fused high-pass subband.

[0032] Furthermore, in the S4 image fusion, the high-pass sub-band fusion of the local pattern spectrum features may have a large difference in magnitude. In order to make the weight more stable and easier to compare, the local pattern spectrum features are normalized. The local pattern spectrum weights of the same position in different images are calculated as follows, and then the high-pass sub-bands are fused. The fusion rule is as follows:

[0033]

[0034] H f (p)=W1(p)·H1(p)+W2(p)·H2(p)

[0035] In the above formula, E1(p) and E2(p) are calculated energies for each local mode spectrum feature; In the above formula, H f (p) is the fused high-frequency sub-band pixel quality, and W1(p) and W2(p) are the weights calculated based on the local pattern spectrum features.

[0036] Furthermore, the low-pass subband in the S4 image fusion is fused by combining the improved pulse coupled neural network method. The low-pass subband represents the part of the original image with relatively uniform grayscale value changes. The low-pass subband is the area with relatively uniform grayscale distribution in the original image, which mainly shows the global features and overall structure of the image, including global information and lower-frequency details in the image. The specific steps of the low-pass subband fusion combined with the pulse coupled neural network are as follows:

[0037] (8) Calculate the j-th layer coefficient C of S, Q1 and DoLP images respectively A,j(x,y) , C B,j(x,y) ;

[0038] (9) C A,j(x,y) , C B,j(x,y) Perform normalization processing and input F channel to activate the pulse coupled neural network;

[0039] (10) Initialize, so that Lj (x,y,0)=U j (x,y,0)=0,θ j (x,y,0)=1, after initialization, the pixel will not be excited, so Y j (x,y,0)=0, the number of pulses generated is T j (x,y,0)=0;

[0040] (11) According to formula (2), L j (x,y,n),U j (x,y,n)θ j (x,y,n), Y j (x,y,n);

[0041] (12) Calculate the number of pulses T j (x,y,n)=T j (x,y,n-1)+Y j (x,y,n);

[0042] (13) In order to achieve better fusion effect, the matching parameter is introduced. The matching degree of two images is defined as follows:

[0043]

[0044] T in the above formula A,j (x,y,n) and T B,j (x,y,n) is in N max The excitation time of the two images in the j-th layer decomposition after iterations; the threshold T in fusion th It can be calculated by the following formula

[0045]

[0046] In the above formula

[0047] (14) The low-frequency sub-band coefficients can be fused according to the following rules:

[0048] d) When M j ≤T th And T A,j (x,y,N max )≥T B,j (x,y,N max ), so that C F,j (x,y)=C A,j (x,y);

[0049] e) When M j ≤T th And T A,j (x,y,N max)<T B,j (x,y,N max ), so that C F,j (x,y)=C B,j (x,y);

[0050] f) When M j >T th , so that C F,j (x,y)=αC A,j (x,y)+βC B,j (x,y), where

[0051]

[0052] Using C F,j (x,y) is used as the low-pass subband coefficient, and the fused image is obtained after reconstruction.

[0053] (3) Beneficial effects

[0054] Compared with the existing technology, the present invention provides a polarization spectrum image fusion method based on non-subsampled contourlet transform, which has the following beneficial effects:

[0055] The present invention addresses the problem that traditional polarization image fusion methods are insufficient in processing details, nonlinear information, noise and directional information in images; proposes a more complex multi-scale and multi-directional transformation fusion algorithm, which is a multi-scale fusion algorithm based on non-subsampled contourlet transform, combined with the characteristics of local pattern spectrum for maintaining local similarity, adaptive weight distribution, good noise resistance and robustness, and an improved pulse coupled neural network algorithm is used in the low-frequency part; the algorithm of the present invention and traditional fusion algorithms such as LRD and PCA are evaluated from subjective and objective perspectives on the fusion results. The subjective observation of the comparison between the fused image and the original image shows that the algorithm of the present invention is superior to other algorithms. In terms of objective data, the algorithm of the present invention improves the four evaluation indicators of EN, AG, SNR and SF by 5.18%, 7.69%, 30.82% and 10.29% respectively compared with the experimental optimal fusion algorithm other than the present method. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is the overall flow chart of the present invention;

[0057] Figure 2 This is the algorithm fusion flow chart of the present invention;

[0058] Figure 3 Schematic diagram of the decomposition of the non-subsampled contourlet transform of the present invention;

[0059] Figure 4Middle (a): original image; (b): LRD fusion effect; (c): non-subsampled contourlet transform fusion effect; (d): PCA fusion effect; (e): wavelet transform fusion effect; (f): fusion effect of the method in this paper. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0061] like Figure 1-4 As shown, one embodiment of the present invention proposes a polarization spectrum image fusion method based on non-subsampled contourlet transform, comprising the following steps:

[0062] S1, prepare polarization spectrum image: collect polarization spectrum image through polarization spectrum imaging system, obtain polarization spectrum images and light intensity image I at four different linear polarization angles (0°, 45°, 90° and 135°).

[0063] S2, data preprocessing: calculate the corresponding Stokes parameters of the image and obtain the corresponding Q, U and DoLP images.

[0064] Use I 0° , I 45° , I 90° , I 135° The polarization hyperspectral images obtained at four angles of 0°, 45°, 90°, and 135° are represented respectively; where I represents the sum of the light intensities of the polarization components in the two coordinate axis directions; Q represents the intensity difference of linear polarization in the 0° and 90° directions; U represents the intensity difference of linear polarization in the 45° and 135° directions. The Stokes vector is calculated as follows:

[0065]

[0066] The value of the degree of linear polarization (DoLP) indicates the proportion of linearly polarized light in the light wave to the total light intensity, which can be expressed as follows:

[0067]

[0068] S3, preliminary fusion: The polarization spectrum image and visible light image with the same edge information are decomposed using non-subsampled contourlet transform, the low-pass sub-band is averaged, and the high-pass sub-band is preliminarily fused using the maximum amplitude rule to obtain the polarization feature S.

[0069] First, the image is decomposed at multiple scales using the non-subsampled pyramid (NSP) to generate high-pass and low-pass subbands. Then, the high-pass subband is directional-decomposed using the non-subsampled directional filter bank (NSDFB), which divides the frequency domain into multiple subbands. These subbands are then organized into a layered binary tree structure. Figure 2 The decomposition process of non-subsampled contourlet transform is demonstrated.

[0070] The non-subsampled contourlet transform is divided into two main steps. First, the NSP is used to perform multi-scale decomposition into high-pass and low-pass subbands. Then, the high-pass subband is directional decomposed using NSDFB, and the frequency domain is divided into subbands using a layered binary tree. The non-subsampled contourlet transform has two decomposition levels, with the first level performing a four-directional decomposition and the second level performing an eight-directional decomposition.

[0071] S4, image fusion: The polarization features, intensity images, and polarization degree are decomposed by non-subsampled contourlet transform. The low-pass subbands obtained by the decomposition are fused using an improved pulse coupled neural network method, and the high-pass subbands are fused using a weighted fusion rule based on local pattern spectrum characteristics;

[0072] The principle of local pattern spectrum is based on converting each local region in the image to the frequency domain and extracting texture features from it. For each pixel in the image, a small window around it is selected as the local region. Fourier transform or other spectral transformation methods are applied to convert these local regions from their original spatial domain to the frequency domain. Various frequency components are detected in the frequency domain, which reveal the texture information of the local region. In the local pattern spectrum, each channel represents the relationship between the center point and one of its neighboring points. Its formula is:

[0073]

[0074] in, represents the kth channel of the local mode spectrum of point (x, y), f C is a convolution feature with multiple channels, and (δx k ,δy k ) represents the offset of the kth adjacent point; Φ(·,·) is a function that measures the similarity between two vectors and outputs a scalar; cosine similarity is chosen for its numerical stability. Next, features are extracted from these frequency components, such as amplitude, energy, or phase statistics, and these features are encoded to obtain a representation of the local texture; finally, these encoded features are mapped back to the central pixel corresponding to each local area in the image, thereby constructing a complete feature image; this feature image retains the local texture distribution and detail information in the original image;

[0075] A pulse coupled neural network is a feedback network composed of a certain number of neurons. Each neuron consists of three parts: a branch tree, a link field, and a pulse generator. It can be described as a mathematical model as follows:

[0076]

[0077] In formula (11), I j and J j is the input of the neuron, Y j is the output of the neuron, U j The branch tree has two parts, the feed input F j and link input L j . M kj and W kj are the synaptic gain coefficients of the branch tree and connection field between neuron j and neuron k, respectively, and is the time decay constant, β j is the joint strength, and are the amplification factor and time constant of the threshold integrator, θ j is the dynamic threshold.

[0078] S5, image reconstruction: The image fused in S4 is reconstructed using non-subsampled contourlet transform to obtain the final fused image.

[0079] S6, image evaluation: Evaluate the fusion effect of the image using subjective and objective indicators. Objective indicators include standard deviation, information entropy, average gradient, etc.

[0080] To verify the effectiveness of the proposed method, it is compared with several common polarization fusion methods, including wavelet transform, principal component analysis (PCA), Laplace reconstruction decomposition (LRD) and non-subsampled contourlet transform. Among them, the non-subsampled contourlet transform takes the coefficient with the largest absolute value as the fusion rule for the high-pass subband and the mean value for the low-frequency subband.

[0081] Information entropy (EN), standard deviation (STD), average gradient (AG), peak signal-to-noise ratio (PSNR), and spatial frequency (SF) are used as objective metrics to evaluate fusion performance. The information entropy value measures the amount of image information; higher information entropy generally indicates greater detail preservation. It is based on the image's grayscale value distribution and reflects the randomness and uncertainty of different grayscale levels within the image. The standard deviation reflects the dispersion of the image's grayscale values; higher values ​​indicate higher image contrast and a more dispersed grayscale value distribution. The standard deviation characterizes the overall contrast and brightness variation of the image. The average gradient quantifies image sharpness. Higher gradient values ​​indicate greater image sharpness and more pronounced edges and textures. PSNR is a measure of image quality; higher values ​​indicate closer alignment between the processed image and the original, meaning better signal fidelity. Spatial frequency indicates the rate of change in grayscale values ​​within an image and reflects the richness of image detail and texture complexity. A higher frequency indicates that the image contains more detail and texture. Different image fusion metrics are shown in Table 1.

[0082] Table 1 Different image fusion indicators

[0083] EN STD AG PSNR SF This method 7.5567 58.7277 74.8020 17.5765 97.8477 LRD fusion 5.9975 28.7237 48.3215 6.6726 59.0037 NSCT fusion 7.1652 35.5965 69.0479 10.4781 88.0135 PCA fusion 6.3314 59.4546 66.2833 12.1589 87.7759 Wavelet transform fusion 6.0505 30.2075 42.2925 8.1540 50.2012

[0084] exist Figure 3 The data in Table 1 also confirm that the contrast between LRD and wavelet transform fusions is relatively low. The data in Table 1 also confirm that their STD values ​​are significantly lower than those of the other methods. PCA fusion suffers from a weak ability to preserve detail in the fused image, resulting in reduced effective information. However, this fusion method achieves excellent contrast. Conventional non-subsampled contourlet transform fusion yields relatively balanced evaluation metrics, but the resulting image differs significantly from the original image, resulting in poor signal fidelity.

[0085] In the objective evaluation metrics listed in Table 1, our method outperforms the other four fusion methods in all but STD. Contrast is 1.24% lower than the PCA fusion method. EN, AG, SNR, and SF improve by 5.18%, 7.69%, 30.82%, and 10.29%, respectively, compared to the optimal fusion method other than our method. Subjectively, our fusion image contains more edge information and texture features, is closer to the original image, and retains more effective information. In summary, our proposed local pattern spectrum feature fusion algorithm based on the non-subsampled contourlet transform outperforms the other four image fusion algorithms.

[0086] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A polarization spectrum image fusion method based on non-subsampled contourlet transform, characterized by: The following steps are included: S1, prepare polarization spectrum image: collect polarization spectrum image through polarization spectrum imaging system, obtain polarization spectrum images and light intensity image I at four different linear polarization angles of 0°, 45°, 90° and 135°; S2, data preprocessing: calculate the corresponding Stokes parameters of the image and obtain the corresponding Q, U and DoLP images; S3, preliminary fusion: The polarization spectrum image and visible light image with the same edge information are decomposed using non-subsampled contourlet transform, the low-pass sub-band is averaged, and the high-pass sub-band is preliminarily fused using the maximum amplitude rule to obtain the polarization feature S; S4, image fusion: The polarization features, intensity images, and polarization degree are decomposed by non-subsampled contourlet transform. The low-pass subbands obtained by the decomposition are fused using an improved pulse coupled neural network method, and the high-pass subbands are fused using a weighted fusion rule based on local pattern spectrum characteristics; S5, image reconstruction: the image fused in S4 is reconstructed using non-subsampled contourlet transform to obtain the final fused image; S6, image evaluation: Evaluate the fusion effect of the image using subjective and objective indicators. The objective indicators include standard deviation, information entropy, and average gradient.

2. The polarization spectrum image fusion method based on non-subsampled contourlet transform according to claim 1, characterized in that: The method for the four directional parameters and linear polarization degree image in the image preprocessing in S2 is to calculate the Stokes vector of the polarization images of the four directions of 0°, 45°, 90°, and 135° in the polarization data set and to quantitatively describe the intensity image S0 and the polarization degree image DoLP using the Stokes vector as shown in the following formula: Where I is the sum of the polarization component intensities of the two coordinate axis directions; Q represents the intensity difference image of linear polarization in the 0° and 90° directions; and U represents the intensity difference image of linear polarization in the 45° and 135° directions.

3. The polarization spectrum image fusion method based on non-subsampled contourlet transform according to claim 1, characterized in that: In the S3 preliminary fusion, the non-subsampled contourlet transform is an improved multi-scale and multi-directional image transformation method that avoids the information loss problem in the traditional contourlet transform by using a non-subsampled pyramid and a non-subsampled directional filter bank; The non-subsampled contourlet transform decomposes an image into sub-bands of multiple scales and directions, effectively capturing image details and directional features while maintaining the image's translation invariance, thereby providing high-quality processing results in image fusion applications. The non-subsampled contourlet transform consists of two main steps: First, a non-subsampled pyramid is used to perform multi-scale decomposition of the image to generate high-pass subbands and low-pass subbands. Then, a non-subsampled directional filter bank is used to directional decompose the high-pass subbands, dividing the frequency domain into multiple subbands, and organizing these subbands through a layered binary tree structure. The non-subsampled contourlet transform is mainly divided into the following two steps. First, a non-subsampled pyramid is used to perform multi-scale decomposition into two parts: a high-pass subband and a low-pass subband. Then, a non-subsampled directional filter bank is used to perform directional decomposition on the high-pass subband, and a layered binary tree is used to divide the frequency domain into multiple subbands. The number of decomposition layers of the non-subsampled contourlet transform is 2. The first layer performs 4-directional decomposition, and the second layer performs 8-directional decomposition.

4. The polarization spectrum image fusion method based on non-subsampled contourlet transform according to claim 1, characterized in that: In the S4 image fusion, the local spectrum pattern is characterized by converting each local area in the image into the frequency domain and extracting texture features from it; First, for each pixel of the image, a small window around it is selected as the local area. Second, the Fourier transform is applied to convert these local areas from their original spatial domain to the frequency domain. In the frequency domain, various frequency components can be detected, which reveal the texture information of the local area. Then, the amplitude features are extracted from these frequency components and encoded to obtain the representation of the local texture. The high-pass subband focuses on image details such as edges, textures, and fine structures, emphasizing image details and helping to determine image boundaries and structures. The weights are calculated through the local pattern spectrum. The steps are as follows: (1) Calculate the LSP of each pixel p of S, Q1 and DoLP images respectively s (p), and LSP DoLP (p); (2) For each local mode spectrum feature, calculate E S (p), and E DoLP (p); (3) Energy normalization processing: In the above formula, E S (p), and E DoLP (p) are the local pattern spectrum features of the same pixel point in image S, Q1, and DOLP image, respectively, and W S (P) is related to E S (p) The related normalized weight represents the ratio of the polarization component S at the pixel point p to that at the pixel point s; is with The related normalized weight represents the ratio of the polarization component Q1 at the pixel point p to that at the pixel point q; W DOLP (P) is related to E DOLP (p) The normalized weight associated with it represents the ratio of the polarization component DOLP at the pixel point p to that at the pixel point p. (4) The high frequency sub-band fusion formula is: In the above formula, H S (p), H DoLP (p) represent high-pass subbands at different scales in the same direction, H f (p) is the fused high-pass subband.

5. The polarization spectrum image fusion method based on non-subsampled contourlet transform according to claim 1, characterized in that: In the S4 image fusion, the high-pass sub-band fusion of local pattern spectrum features may have large differences in magnitude. In order to make the weight more stable and easier to compare, the local pattern spectrum features are normalized. The local pattern spectrum weights of the same position in different images are calculated as follows. Then, the high-pass sub-bands are fused. The fusion rule is as follows: H f (p)=W1(p)·H1(p)+W2(p)·H2(p) In the above formula, E1(p) and E2(p) are calculated energies for each local mode spectrum feature; In the above formula, H f (p) is the fused high-frequency sub-band pixel quality, and W1(p) and W2(p) are the weights calculated based on the local pattern spectrum features.

6. The polarization spectrum image fusion method based on non-subsampled contourlet transform according to claim 1, characterized in that: The low-pass subband in the S4 image fusion is fused by combining the improved pulse coupled neural network method. The low-pass subband represents the part of the original image with relatively uniform grayscale value changes. The low-pass subband is the area with relatively uniform grayscale distribution in the original image, which mainly shows the global features and overall structure of the image, including global information and lower-frequency details in the image. The specific steps of the low-pass subband fusion combined with the pulse coupled neural network are as follows: (1) Calculate the j-th layer coefficient C of S, Q1 and DoLP images respectively A,j(x,y) , C B,j(x,y) ; (2) C A,j(x,y) , C B,j(x,y) Perform normalization processing and input F channel to activate the pulse coupled neural network; (3) Initialize, so that L j (x,y,0)=U j (x,y,0)=0,θ j (x,y,0)=1, after initialization, the pixel will not be excited, so Y j (x,y,0)=0, the number of pulses generated is T j (x,y,0)=0; (4) According to formula (2), calculate L j (x,y,n),U j (x,y,n)θ j (x,y,n), Y j (x,y,n); (5) Calculate the number of pulses T j (x,y,n)=T j (x,y,n-1)+Y j (x,y,n); (6) In order to achieve better fusion effect, the matching parameter is introduced. The matching degree of two images is defined as follows: T in the above formula A,j (x,y,n) and T B,j (x,y,n) is in N max The excitation time of the two images in the j-th layer decomposition after iterations; the threshold T in fusion th It can be calculated by the following formula In the above formula (7) The low-frequency sub-band coefficients can be fused according to the following rules: a) When M j ≤T th And T A,j (x,y,N max )≥T B,j (x,y,N max ), so that C F,j (x,y)=C A,j (x,y); b) When M j ≤T th And T A,j (x,y,N max )<T B,j (x,y,N max ), so that C F,j (x,y)=C B,j (x,y); c) When M j >T th , so that C F,j (x,y)=αC A,j (x,y)+βC B,j (x,y), where Using C F,j (x,y) is used as the low-pass subband coefficient, and the fused image is obtained after reconstruction.

Images