Multi-dimensional imaging detection device and method under strong light background

Abstract

The invention discloses a multi-dimensional imaging detection device and method under a strong light background, and relates to the field of target detection, and the device comprises a light splitting unit, an LC-SLM unit and a visible light polarization CCD unit which are sequentially arranged on the same light path; the infrared imaging system is arranged on the other light path; the infrared imaging system and the visible light polarization CCD unit are respectively connected with the image processing system; the light splitting unit is used for splitting the measured light into first light and second light and changing the polarization degree of the first light to obtain first modulated light; the infrared imaging system is used for converting the second light into short-wave infrared images with different polarization degrees; the LC-SLM unit is used for weakening strong background light in the first modulated light to obtain strong light weakening light; and the visible light polarization CCD unit is used for converting the strong light weakening light into visible light images with different polarization degrees. According to the invention, high-efficiency suppression of strong background light and accurate highlighting of target features are realized.

Description

Technical Field

[0001] The present application relates to the field of target detection technology, and in particular to a multi-dimensional imaging detection device and method under a strong light background. Background Art

[0002] In the field of target detection, target detection under strong light background (environment) has always been a challenging problem, especially in areas involving space surveillance, military defense, night vision assistance and infrared photography.

[0003] Traditional detection devices are easily affected by strong background light. In strong background light, they often suffer from pixel overexposure, signals drowned in noise, and difficulty in identifying target features. This greatly limits the effectiveness and reliability of the detection system, resulting in its low detection and recognition capabilities in strong background light. At the same time, the images ultimately generated by the detection system also have problems such as loss of details, limited dynamic range, and complex post-processing. Summary of the Invention

[0004] The purpose of this application is to provide a multi-dimensional imaging detection device and method under strong light background, which improves the detection and recognition capabilities of target objects under strong light background, achieves efficient suppression of strong background light and accurate highlighting of target features.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In the first aspect, the present application provides a multi-dimensional imaging detection device under a strong light background, wherein the multi-dimensional imaging detection device under a strong light background includes: a visible light imaging system, an infrared imaging system and an image processing system; the visible light imaging system includes: a spectroscopic unit, an LC-SLM unit and a visible light polarization CCD unit; the spectroscopic unit, the LC-SLM unit and the visible light polarization CCD unit are arranged in sequence on the same optical path; the infrared imaging system is arranged on another optical path; the infrared imaging system and the visible light polarization CCD unit are respectively connected to the image processing system.

[0007] The spectroscopic unit is used to split the measured light into a first light and a second light, and change the polarization degree of the first light to obtain a first modulated light; the measured light is the light generated by the target object under a strong light background; the second light is turned and projected onto the infrared imaging system; the infrared imaging system is used to convert the second light into a short-wave infrared image with different polarization degrees; the LC-SLM unit is used to weaken the strong background light in the first modulated light to obtain a strong light weakened light; the visible light polarization CCD unit is used to convert the strong light weakened light into a visible light image with different polarization degrees; the image processing system is used to: obtain visible light images and short-wave infrared images with different polarization degrees, and perform the following steps on the visible light image and short-wave infrared image with each polarization degree: perform multi-scale Retinex decomposition on the original image to obtain an initial illumination component and an initial reflection component. component; perform NSCT transformation on the initial illumination component, perform DT-CWT transformation on the initial reflection component, and obtain high-frequency components and low-frequency components under different transformations; based on the U-Net network, the ResNet network and the regional energy weighted method, the high-frequency components and low-frequency components under different transformations are fused and enhanced, and the illumination component and reflection component are reconstructed through NSCT inverse transformation and DT-CWT inverse transformation; based on the reconstructed illumination component and reflection component, a multi-scale Retinex is used to reconstruct the image, and the reconstructed visible light image and short-wave infrared image are input into a dual-channel PCNN network for fusion to obtain a fused image; determine the performance evaluation index of the fused image, and calculate the information value of the fused image based on the performance evaluation index; compare the information values ​​of the fused images with different polarization degrees, and output the fused image whose information value is greater than a set threshold.

[0008] In a second aspect, the present application also provides a multi-dimensional imaging detection method under a strong light background, and the multi-dimensional imaging detection method under a strong light background is as follows.

[0009] Obtain visible light images and shortwave infrared images with different polarization degrees, and perform the following steps on the visible light image and shortwave infrared image with each polarization degree: perform multi-scale Retinex decomposition on the original image to obtain an initial illumination component and an initial reflection component; perform NSCT transformation on the initial illumination component, perform DT-CWT transformation on the initial reflection component, and obtain high-frequency components and low-frequency components under different transformations; based on a U-Net network, a ResNet network and a regional energy weighted method, fuse and enhance the high-frequency components and low-frequency components under different transformations, and reconstruct the illumination component and reflection component through inverse NSCT transformation and inverse DT-CWT transformation; reconstruct the image based on the reconstructed illumination component and reflection component using multi-scale Retinex, and input the reconstructed visible light image and shortwave infrared image into a dual-channel PCNN network for fusion to obtain a fused image; determine a performance evaluation index of the fused image, and calculate the information value of the fused image based on the performance evaluation index; compare the information values ​​of the fused images with different polarization degrees, and output a fused image whose information value is greater than a set threshold.

[0010] According to the specific embodiments provided in this application, this application discloses the following technical effects.

[0011] This application innovatively constructs a light field detection device that combines multi-dimensional collaborative detection with intelligent fusion. This device effectively divides the measured light into two optical paths by fully utilizing the spectroscopic unit. It also collaborates with other components in the infrared imaging system and the visible light imaging system to construct a multi-spectral collaborative mechanism. This application combines the dynamic control technology of the Liquid Crystal Spatial Light Modulator (LC_SLM) to achieve the simultaneous capture of light intensity, polarization, and spectral information. This device can suppress 90% of background noise under strong light interference and improve the target signal-to-noise ratio by 3-5 times. In addition, the image processing system of the present application also effectively decomposes and reconstructs visible light images and short-wave infrared images, and fuses and enhances the reconstructed visible light images and short-wave infrared images. The image processing system integrates adaptive light field optimization with non-subsampled contourlet transform (NSCT), dual-tree complex wavelet transform (DT-CWT), and dual-channel pulse coupled neural network (PCNN) to perform multi-scale image fusion. By enhancing high-frequency details and weighted fusion of low-frequency energy, the target recognition rate is significantly improved. Based on the above features, the present application improves the detection and recognition capabilities of target objects in strong light backgrounds, achieving efficient suppression of strong background light and precise highlighting of target features. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0013] Figure 1 Schematic diagram of the structure of the multi-dimensional imaging detection device under strong light background in an embodiment of the present application.

[0014] Figure 2 This is a module schematic diagram of a multi-dimensional imaging detection device under a strong light background in an embodiment of the present application.

[0015] Figure 3 This is a flowchart of the execution of the multi-dimensional imaging detection method under a strong light background in an embodiment of the present application.

[0016] Figure numerals: visible light imaging system-1, spectroscopic unit-11, dual telecentric lens unit-111, spectroscopic prism unit-112, dual polarizer unit-113, LC-SLM unit-12, visible light polarization CCD unit-13, infrared imaging system-2, short-wave infrared polarizer unit-21, short-wave infrared polarization CCD unit-22, image processing system-3, electric wheel unit-4. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] Since traditional visual imaging devices have problems such as loss of details, limited dynamic range and complex post-processing under strong backgrounds, polarized target detection can realize imaging detection in complex environments, significantly improving the effective range and imaging quality of visual imaging devices under strong interference conditions. The advantages of liquid crystal spatial light modulators in strong light background detection lie in precise light beam control, high dynamic range and flexibility. Therefore, polarized target detection and liquid crystal spatial light modulators can be applied to the technical solutions of this application.

[0019] The purpose of this application is to provide a multi-dimensional imaging detection device and method under strong light background, which improves the detection and recognition capabilities of target objects under strong light background, achieves efficient suppression of strong background light and accurate highlighting of target features.

[0020] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0021] In an exemplary embodiment, Figure 1 and Figure 2 As shown, a multi-dimensional imaging detection device under a strong light background is provided, which includes: a visible light imaging system 1, an infrared imaging system 2 and an image processing system 3; the visible light imaging system 1 includes: a spectrometer unit 11, an LC-SLM unit 12 and a visible light polarization charge coupled device (CCD) unit 13.

[0022] The spectrometer 11 , the LC-SLM unit 12 and the visible light polarization CCD unit 13 are sequentially arranged on the same optical path; the infrared imaging system 2 is arranged on another optical path; the infrared imaging system 2 and the visible light polarization CCD unit 13 are respectively connected to the image processing system 3 .

[0023] The spectroscopic unit 11 is used to split the measured light into a first light and a second light, and change the polarization degree of the first light to obtain a first modulated light; the measured light is the light generated by the target object under the background of strong light (strong light generally includes at least one of coherent light and incoherent light); the second light is turned and projected onto the infrared imaging system 2; the infrared imaging system 2 is used to convert the second light into a short-wave infrared image with different polarization degrees; the LC-SLM unit 12 is used to weaken the strong background light in the first modulated light to obtain a strong-light-weakened light; the visible light polarization CCD unit 13 is used to convert the strong-light-weakened light into a visible light image with different polarization degrees; the image processing system 3 is used to: obtain visible light images and short-wave infrared images with different polarization degrees, and perform the following steps on the visible light image and short-wave infrared image of each polarization degree: perform multi-scale Retinex decomposition on the original image to obtain an initial Initial illumination component and initial reflection component; perform NSCT transformation on the initial illumination component, perform DT-CWT transformation on the initial reflection component, and obtain high-frequency components and low-frequency components under different transformations; based on the U-Net network, ResNet network and regional energy weighted method, the high-frequency components and low-frequency components under different transformations are fused and enhanced, and the illumination component and reflection component are reconstructed through NSCT inverse transformation and DT-CWT inverse transformation; based on the reconstructed illumination component and reflection component, multi-scale Retinex is used to reconstruct the image, and the reconstructed visible light image and short-wave infrared image are input into the dual-channel PCNN network for fusion to obtain a fused image; determine the performance evaluation index of the fused image, and calculate the information value of the fused image based on the performance evaluation index; compare the information values ​​of the fused images with different polarization degrees, and output the fused image with an information value greater than the set threshold.

[0024] As a preferred embodiment, the angle between the first light and the second light is set to 90 degrees.

[0025] Furthermore, the spectroscopic unit 11 specifically includes: a double telecentric lens unit 111, a spectroscopic prism unit 112 and a double polarizer unit 113; the double telecentric lens unit 111, the spectroscopic prism unit 112, the double polarizer unit 113, the LC-SLM unit 12 and the visible light polarization CCD unit 13 are arranged in sequence on the same optical path (or the same straight line).

[0026] The bi-telecentric lens unit 111 is used to collimate and control the cross-section of the measured light and ensure that the measured light completely covers the effective aperture of the beam splitter prism unit 112; the beam splitter prism unit 112 is used to split the measured light into a first light and a second light; the first light is projected onto the bi-polarizer unit 113 through the beam splitter prism unit 112; the bi-polarizer unit 113 is used to change the polarization degree of the first light to obtain a first modulated light.

[0027] Furthermore, the infrared imaging system 2 includes: a short-wave infrared polarizer unit 21 and a short-wave infrared polarization CCD unit 22; the short-wave infrared polarizer unit 21 and the short-wave infrared polarization CCD unit 22 are sequentially arranged on the optical path where the second light is located; the short-wave infrared polarization CCD unit 22 is connected to the image processing system 3.

[0028] The short-wave infrared polarizer unit 21 is used to change the polarization degree of the second light to obtain a second modulated light; the short-wave infrared polarization CCD unit 22 is used to convert the second modulated light into a short-wave infrared image with different polarization degrees.

[0029] Furthermore, the multi-dimensional imaging detection device under strong light background also includes multiple electric wheel units 4; the dual polarizer unit 113 and the short-wave infrared polarizer unit 21 are respectively installed on different electric wheel units 4; the electric wheel unit 4 is used to drive the dual polarizer unit 113 and the short-wave infrared polarizer unit 21 to rotate; the electric wheel unit 4 steps according to a step size of "1°".

[0030] As a preferred embodiment, the dual telecentric lens unit 111 is located in front of the beam splitter prism unit 112, the beam splitter prism unit 112 is located in front of the dual polarizer unit 113, the dual polarizer unit 113 is located in front of the LC-SLM unit 12, the dual polarizer unit 113 is installed on the electric wheel unit 4, the LC-SLM unit 12 is located in front of the visible light polarization CCD unit 13, the visible light polarization CCD unit 13 is connected to the image processing system 3 so that the target object is imaged at the center of the imaging target surface of the visible light polarization CCD unit 13, the short-wave infrared polarizer unit 21 is located in front of the short-wave infrared polarization CCD unit 22 and is installed on the electric wheel unit 4, and the short-wave infrared polarization CCD unit 22 is used to receive the light separated by the beam splitter prism unit 112. Among them, the double telecentric lens unit 111 uses XF-PTL15235-F from Canrui Optics, the beam splitter prism unit 112 uses BSC0125-4 from Youguang Technology, the electric wheel unit 4 uses K10CR2 / M from THORLABS, the dual polarizer unit 113 uses LPVISC050 from THORLABS, the LC-SLM unit 12 uses TSLM14U-A from Zhongke Weixing, the visible light polarization CCD unit 13 uses MER2-301-125U3C-HS from Daheng Imaging, the short-wave infrared polarizer unit 21 uses GCL-051002 from Daheng Optoelectronics, and the short-wave infrared polarization CCD unit 22 uses MER3-138-136G3M-P-SWIR F02 from Daheng Imaging.

[0031] In addition, the specific steps for using the above-mentioned multi-dimensional imaging detection device under strong light background are as follows.

[0032] Step 1: Align the large aperture of the bi-telecentric lens unit 111 with the target object under a strong light background, and align the small aperture with the beam splitter prism unit 112 , so that the measured light completely passes through the beam splitter prism unit 112 .

[0033] Step 2: Install the two polarizers in the dual polarizer unit 113 on the two electric wheel units 4 respectively, and control the rotation angles of the two polarizers (rotate in different directions) by a computer to transmit different light signals to the LC-SLM unit 12.

[0034] Step 3: The lattice of the liquid crystal layer in the LC-SLM unit 12 can distinguish the target signal from the strong background signal based on the obtained light signal, and reduce the background light signal intensity by changing the lattice transmittance.

[0035] Step 4: The optical signal is converted into a visible light image by the visible light polarization CCD unit 13, and a total of 360 visible light images of various polarization degrees are obtained.

[0036] Step 5: Place the short-wave infrared polarizer unit 21 on the other light beam separated by the beam splitting prism unit 112 and install it on the electric wheel unit 4. The rotation angle of the short-wave infrared polarizer unit 21 is controlled by a computer. The short-wave infrared polarization CCD unit 22 obtains a total of 360 short-wave infrared images of various polarization degrees.

[0037] Step 6: All images obtained from the short-wave infrared polarization CCD unit 22 and the visible light polarization CCD unit 13 are input into the image processing system 3 for processing, and finally a high-definition image containing the target object is output.

[0038] In another exemplary embodiment, Figure 3 As shown, a multi-dimensional imaging detection method under strong light background is provided. The multi-dimensional imaging detection method under strong light background is applied to the above-mentioned multi-dimensional imaging detection device under strong light background. The multi-dimensional imaging detection method under strong light background is as follows.

[0039] First, visible light images and shortwave infrared images with different polarization degrees are acquired, and the following steps are performed on the visible light image and shortwave infrared image with each polarization degree.

[0040] In a preferred embodiment, visible light images are named and stored as "rotation angle of the first polarizer in the dual polarizer unit; rotation angle of the second polarizer in the dual polarizer unit; visible light image name," for example, a set of images is named "15°; 30°; Vis." Shortwave infrared images are named and stored as "shortwave infrared polarizer rotation angle; shortwave infrared image name," for example, a set of images is named "30°; IR." Once storage is complete, a computer can send a control signal to the motorized wheel unit to acquire visible light and shortwave infrared images with different polarization degrees in steps of 1°. The stored visible light and shortwave infrared images should correspond one to one with the corresponding polarization degrees.

[0041] (1) Perform multi-scale Retinex decomposition on the original image to obtain the initial illumination component and the initial reflection component; the original image refers to a set of visible light images and short-wave infrared images under polarization.

[0042] Among them, the multi-scale Retinex decomposition method is as follows.

[0043] .

[0044] Where, represents the original image, The standard deviation is Gaussian filter, Indicates the n The weight of each scale must satisfy , NGenerally choose 3.

[0045] The initial lighting component is expressed as: .

[0046] The initial reflection component is expressed as: .

[0047] (2) Perform NSCT transformation on the initial illumination component and DT-CWT transformation on the initial reflection component, and obtain the high-frequency component and low-frequency component under different transformations.

[0048] Specifically, the initial illumination component is subjected to NSCT transformation to obtain the first initial high-frequency component and the first initial low-frequency component. Among them, the NSCT transformation consists of non-subsampled pyramid decomposition (NSP) and non-subsampled directional filter bank (NSDFB). The image is decomposed into multi-scale subbands through the non-subsampled pyramid, and each level generates a low-pass subband and a band-pass subband. Suppose the image to be decomposed is I , then k The level decomposition process is as follows.

[0049] Low-pass filtering: .

[0050] Where, is the low-pass subband, For the k The low-pass filter of the stage, represents the convolution operation, .

[0051] Bandpass sub-band: .

[0052] Bandpass subbands at each level The detailed information of the current scale is retained, and the input directional filter group is subsequently decomposed into directions. Each bandpass subband It is further decomposed into Directional sub-bands ( is the directional decomposition level), the directional filter is constructed as follows.

[0053] Assume the prototype directional filter is , multiple directional filters are generated through frequency domain modulation.

[0054] .

[0055] Where, for j Directional filter for directions, is the frequency domain coordinate, j is the direction index, j=0,1, 2,......, - 1.

[0056] Directional subband generation: .

[0057] In the formula, each directional subband The corresponding image is at scale k and direction j The coefficient on .

[0058] Then, a DT-CWT transformation is performed on the initial reflection component to obtain a second initial high-frequency component and a second initial low-frequency component.

[0059] (3) Based on the U-Net network, ResNet network and regional energy weighted method, the high-frequency components and low-frequency components under different transformations are fused and enhanced, and the illumination component and reflection component are reconstructed through the NSCT inverse transform and the DT-CWT inverse transform.

[0060] Specifically, the first initial high-frequency component is input into the U-Net network to obtain a first fused enhanced high-frequency component.

[0061] The second initial high-frequency component is input into the ResNet network to obtain the second fused enhanced high-frequency component.

[0062] The first initial low-frequency component and the second initial low-frequency component are fused using a regional energy weighting method to obtain a first fused enhanced low-frequency component and a second fused enhanced low-frequency component. Specific steps of the regional energy weighting method are as follows.

[0063] The first step is to calculate the neighborhood energy of the shortwave infrared image and the visible light image.

[0064] .

[0065] Where, M 、 N Represent the length and width of the neighborhood window, Indicates that the image is at position The neighborhood energy at MN represents the size of the neighborhood window, Indicates that the image is at an offset position The pixel value of .

[0066] In the second step, the corresponding neighborhood energy matrix is ​​divided into several non-overlapping sub-regions, and the regional eigenvalue calculation formula is as follows.

[0067] .

[0068] Where, Indicates the image iThe regional characteristic value of a sub-region is the mean sum of squares of all pixel values ​​in the sub-region.

[0069] The third step is to calculate the shortwave infrared image and visible light image i The fusion weight of the sub-blocks.

[0070] .

[0071] .

[0072] Where, and are the fusion weights of visible light image and shortwave infrared image respectively, and Represents the visible light image and shortwave infrared image i The energy of a sub-block.

[0073] The fourth step is to find the low-frequency coefficient.

[0074] .

[0075] Where, represents the low-frequency coefficient, Represents the data of visible light image input, Represents the data of low-frequency infrared image input, and Indicates the corresponding sub-block weight.

[0076] Perform NSCT inverse transform on the first fusion enhanced high-frequency component and the first fusion enhanced low-frequency component to obtain the reconstructed illumination component.

[0077] Perform DT-CWT inverse transform on the second fusion enhanced high-frequency component and the second fusion enhanced low-frequency component to obtain a reconstructed reflection component.

[0078] (4) Based on the reconstructed illumination component and reflection component, the multi-scale Retinex is used to reconstruct the image, and the reconstructed visible light image and short-wave infrared image are input into the dual-channel PCNN network for fusion to obtain the fused image.

[0079] Specifically, a multi-scale Retinex reconstruction is performed on the reconstructed illumination component and the reconstructed reflection component to obtain a reconstructed image; the reconstructed image includes a reconstructed visible light image and a reconstructed short-wave infrared image.

[0080] The reconstructed visible light image and the reconstructed shortwave infrared image are input into a dual-channel PCNN network for image fusion to obtain a fused image. The mathematical model of the dual-channel PCNN network is as follows.

[0081] .

[0082] .

[0083] .

[0084] .

[0085] .

[0086] .

[0087] Where, i and j Represent the coordinates of the pixels in the image, n represents the number of iterations, represents the gain coefficient, is the weight matrix, representing the node ( i , j )and( a , b ), represents binary input from other locations, Indicates the k The energy input of the layer, Feed the neuron's dual-channel input, is the link input of the neuron, for The corresponding link strength, is the internal state of the neuron, is the firing pulse output of the neuron, and The neuron link inputs are and Dynamic attenuation coefficient, represents an adaptive threshold that decays over time and is modulated by the input, Indicates the adjustment parameter.

[0088] (5) Determine the performance evaluation index of the fused image and calculate the information value of the fused image based on the performance evaluation index.

[0089] Specifically, the performance evaluation indicators include: information entropy IE , average gradient AG , standard deviation SD and peak signal-to-noise ratio PSNR Among them, information entropy The calculation formula is as follows.

[0090] .

[0091] .

[0092] Where, L Indicates the grayscale level of the image, Represents grayscale value k The probability of appearing in the image.

[0093] Furthermore, the average gradient AG The calculation formula is as follows.

[0094] .

[0095] .

[0096] .

[0097] Where, M and N Represent the number of rows and columns of the image, and Representative pixel The gradient values ​​in the horizontal and vertical directions.

[0098] Furthermore, the standard deviation SD The calculation formula is as follows.

[0099] .

[0100] .

[0101] Where, Expressed as the mean value of the image pixels, Indicates that the image is at position The pixel value at .

[0102] Furthermore, the peak signal-to-noise ratio PSNR The calculation formula is as follows.

[0103] .

[0104] .

[0105] Where, MAX Indicates the maximum value of the image pixel value, MSE Represents the mean square error between the original image and the distorted image.

[0106] Finally, the information value is calculated as follows.

[0107] .

[0108] Where, is the information value, 、 、 and are weight coefficients, is the maximum value of the peak signal-to-noise ratio, is the maximum value of information entropy, is the maximum average gradient, is the maximum standard deviation.

[0109] (6) Compare the information values ​​of the fused images with different polarization degrees and output the fused image whose information value is greater than the set threshold.

[0110] As a preferred implementation, the weight distribution of each performance evaluation index is: =0.4, =0.3, =0.2, =0.1, and when MIQI When >0.75, the current fused image is determined to be the optimal fused image.

[0111] In summary, this application mainly has the following advantages.

[0112] This application leverages the multispectral synergy of visible and infrared imaging systems, combined with the dynamic control technology of LC-SLM (response time <2ms), to achieve the simultaneous capture of light intensity, polarization, and spectral information. This technology suppresses background noise by 90% and improves the target signal-to-noise ratio by 3-5 times even under strong light interference. Furthermore, the image processing system integrates adaptive light field optimization with the DT-CWT / NSCT dual-channel PCNN multi-scale fusion algorithm. By enhancing high-frequency detail (increasing PSNR by 8-12dB) and integrating low-frequency energy-weighted fusion, it significantly improves target recognition by 65%.

[0113] This application adopts a full-link anti-interference design and modular scalable architecture with strong environmental adaptability. By synergizing the dual telecentric lens unit, LC-SLM unit, and multi-scale Retinex algorithm, it eliminates 99% of stray light, improving the detection range and reducing the false alarm rate in scenarios such as military reconnaissance and space observation, achieving both high precision and engineering practicality.

[0114] All actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0115] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0116] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A multi-dimensional imaging detection device under strong light background, characterized in that: The multi-dimensional imaging detection device under strong light background includes: a visible light imaging system, an infrared imaging system and an image processing system; the visible light imaging system includes: a spectroscopic unit, an LC-SLM unit and a visible light polarization CCD unit; The spectroscopic unit, the LC-SLM unit and the visible light polarization CCD unit are sequentially arranged on the same optical path; the infrared imaging system is arranged on another optical path; the infrared imaging system and the visible light polarization CCD unit are respectively connected to the image processing system; The spectroscopic unit is used to split the measured light into a first light and a second light, and change the polarization degree of the first light to obtain a first modulated light; the measured light is light generated by the target object under a strong light background; the second light is deflected and projected onto the infrared imaging system; the infrared imaging system is used to convert the second light into a short-wave infrared image with different polarization degrees; the LC-SLM unit is used to attenuate the strong background light in the first modulated light to obtain a strong light-attenuated light; the visible light polarization CCD unit is used to convert the strong light-attenuated light into a visible light image with different polarization degrees; and the image processing system is used to: Obtain visible light images and shortwave infrared images with different polarization degrees, and perform the following steps on the visible light image and shortwave infrared image with each polarization degree: perform multi-scale Retinex decomposition on the original image to obtain an initial illumination component and an initial reflection component; perform NSCT transformation on the initial illumination component, perform DT-CWT transformation on the initial reflection component, and obtain high-frequency components and low-frequency components under different transformations; based on a U-Net network, a ResNet network and a regional energy weighted method, fuse and enhance the high-frequency components and low-frequency components under different transformations, and reconstruct the illumination component and reflection component through inverse NSCT transformation and inverse DT-CWT transformation; reconstruct the image based on the reconstructed illumination component and reflection component using multi-scale Retinex, and input the reconstructed visible light image and shortwave infrared image into a dual-channel PCNN network for fusion to obtain a fused image; determine a performance evaluation index of the fused image, and calculate the information value of the fused image based on the performance evaluation index; compare the information values ​​of the fused images with different polarization degrees, and output a fused image whose information value is greater than a set threshold.

2. The multi-dimensional imaging detection device under strong light background according to claim 1, characterized in that: The light splitting unit specifically includes: a double telecentric lens unit, a light splitting prism unit and a double polarizer unit; The bi-telecentric lens unit, the beam splitter prism unit, the dual polarizer unit, the LC-SLM unit and the visible light polarization CCD unit are sequentially arranged on the same optical path; The bi-telecentric lens unit is used for collimating and cross-section control of the measured light, and ensuring that the measured light completely covers the effective aperture of the beam splitter prism; the beam splitter prism unit is used for splitting the measured light into a first light and a second light; the first light is projected onto the bi-polarizer unit through the beam splitter prism unit; the bi-polarizer unit is used for changing the polarization degree of the first light to obtain a first modulated light.

3. The multi-dimensional imaging detection device under strong light background according to claim 2, characterized in that: The infrared imaging system comprises: a short-wave infrared polarizer unit and a short-wave infrared polarization CCD unit; The short-wave infrared polarizer unit and the short-wave infrared polarization CCD unit are sequentially arranged on the optical path where the second light is located; the short-wave infrared polarization CCD unit is connected to the image processing system; The short-wave infrared polarizer unit is used to change the polarization degree of the second light to obtain a second modulated light; the short-wave infrared polarization CCD unit is used to convert the second modulated light into a short-wave infrared image with different polarization degrees.

4. The multi-dimensional imaging detection device under strong light background according to claim 3, characterized in that: The multi-dimensional imaging detection device under strong light background further includes a plurality of electric rotating wheel units; The dual polarizer unit and the short-wave infrared polarizer unit are respectively mounted on different electric wheel units; the electric wheel unit is used to drive the dual polarizer unit and the short-wave infrared polarizer unit to rotate.

5. The multi-dimensional imaging detection device under strong light background according to claim 1, characterized in that: The included angle between the first light and the second light is 90 degrees.

6. A multi-dimensional imaging detection method under strong light background, characterized in that: The multi-dimensional imaging detection method under strong light background includes: Obtain visible light images and shortwave infrared images at different polarization degrees, and perform the following steps for each visible light image and shortwave infrared image at each polarization degree: Perform multi-scale Retinex decomposition on the original image to obtain the initial illumination component and the initial reflection component; Performing NSCT transformation on the initial illumination component and performing DT-CWT transformation on the initial reflection component, and obtaining high-frequency components and low-frequency components under different transformations; Based on the U-Net network, ResNet network and regional energy weighting method, the high-frequency components and low-frequency components under different transformations are fused and enhanced, and the illumination component and reflection component are reconstructed through the inverse NSCT transform and the inverse DT-CWT transform. Based on the reconstructed illumination component and reflection component, the multi-scale Retinex is used to reconstruct the image, and the reconstructed visible light image and short-wave infrared image are input into the dual-channel PCNN network for fusion to obtain the fused image. determining a performance evaluation index of the fused image, and calculating an information value of the fused image based on the performance evaluation index; The information values ​​of the fused images of different polarization degrees are compared, and a fused image having an information value greater than a set threshold is output.

7. The multi-dimensional imaging detection method under strong light background according to claim 6, characterized in that: Performing NSCT transformation on the initial illumination component and performing DT-CWT transformation on the initial reflection component, and obtaining high-frequency components and low-frequency components under different transformations, specifically including: Performing NSCT transformation on the initial illumination component to obtain a first initial high-frequency component and a first initial low-frequency component; Performing DT-CWT transformation on the initial reflection component to obtain a second initial high-frequency component and a second initial low-frequency component.

8. The multi-dimensional imaging detection method under strong light background according to claim 7, characterized in that: Based on the U-Net network, ResNet network and regional energy weighted method, the high-frequency components and low-frequency components under different transformations are fused and enhanced, and the illumination component and reflection component are reconstructed through the NSCT inverse transform and the DT-CWT inverse transform. Specifically, Inputting the first initial high-frequency component into a U-Net network to obtain a first fused enhanced high-frequency component; Inputting the second initial high-frequency component into the ResNet network to obtain a second fused enhanced high-frequency component; fusing the first initial low-frequency component and the second initial low-frequency component using a regional energy weighted method to obtain a first fused enhanced low-frequency component and a second fused enhanced low-frequency component; Performing an inverse NSCT transform on the first fused enhanced high-frequency component and the first fused enhanced low-frequency component to obtain a reconstructed illumination component; Perform a DT-CWT inverse transform on the second fused enhanced high-frequency component and the second fused enhanced low-frequency component to obtain a reconstructed reflection component.

9. The multi-dimensional imaging detection method under strong light background according to claim 8, characterized in that: Based on the reconstructed illumination component and reflection component, multi-scale Retinex is used to reconstruct the image. The reconstructed visible light image and short-wave infrared image are input into the dual-channel PCNN network for fusion to obtain the fused image. Specifically, the following steps are performed: Performing multi-scale Retinex reconstruction on the reconstructed illumination component and the reconstructed reflection component to obtain a reconstructed image; the reconstructed image includes a reconstructed visible light image and a reconstructed short-wave infrared image; The reconstructed visible light image and the reconstructed shortwave infrared image are input into a dual-channel PCNN network for image fusion to obtain a fused image.

10. The multi-dimensional imaging detection method under strong light background according to claim 6, characterized in that: The performance evaluation indicators include: information entropy, average gradient, standard deviation and peak signal-to-noise ratio; the calculation formula of the information value is: ； Where, is the information value, 、 、 and are weight coefficients, is the peak signal-to-noise ratio, is the information entropy, is the average gradient, is the standard deviation, is the maximum value of the peak signal-to-noise ratio, is the maximum value of information entropy, is the maximum average gradient, is the maximum standard deviation.

Images