A method and system for enhancing the brightness of an S0 image based on a polarization imaging mechanism

Abstract

The application belongs to the technical field of photoelectric imaging and image processing, and discloses a kind of S0 image brightness enhancement method and system based on polarization imaging mechanism.The method obtains polarization intensity image by polarization demosaicking and intensity denoising of the selected polarization image through preprocessing module;The polarization intensity image is input into the parameter optimization weighted enhancement module to obtain the S0 result image after brightness enhancement by weight parameter optimization and weighted summation enhancement fusion.The application effectively solves the problem of weak S0 image caused by polarization imaging mechanism while maintaining the integrity of polarization information in S0 image.By improving the brightness of S0 image, the recognition of target object and the overall clarity of image are improved, providing more intuitive and accurate visual information for users, overcoming the problem of insufficient S0 image brightness caused by the limitation of existing polarization camera imaging mechanism.

Description

Technical Field

[0001] This invention belongs to the field of optoelectronic imaging and image processing technology, and particularly relates to a method and system for enhancing the brightness of SO images based on polarization imaging mechanism. Background Technology

[0002] Polarization imaging, as a special imaging technique, has demonstrated unique advantages in various fields such as environmental monitoring, medical diagnosis, and materials analysis. It can provide information about the polarization state of light in a scene, which is crucial for tasks such as identifying surface properties of objects and detecting hidden features. However, due to the influence of the polarization imaging mechanism, polarization images often suffer from low brightness, severely affecting the information extraction effect.

[0003] Traditional methods for enhancing the brightness of polarized images include, but are not limited to, histogram equalization, contrast stretching, and gamma correction. While these methods can improve image visibility and contrast in some cases, their effectiveness is less than ideal for dim images caused by polarization imaging mechanisms. On the one hand, these traditional methods struggle to accurately assign appropriate weights to polarized images at different angles; on the other hand, they may introduce additional computational complexity and longer processing times, making them particularly inadequate for real-time applications.

[0004] In recent years, with the development of artificial intelligence technology, swarm intelligence optimization algorithms (such as ant colony optimization and particle swarm optimization) have received increasing attention in the field of image processing due to their global optimization capabilities and high adaptability. These algorithms mimic the collective behavior patterns in nature, effectively searching the solution space and automatically discovering optimal or near-optimal solutions. However, in the field of polarization imaging, how to utilize swarm intelligence algorithms to solve the problem of insufficient brightness in polarization images remains a topic that urgently needs in-depth research.

[0005] Given the limitations of existing technologies, there is an urgent need to develop new methods and technologies to address the problem of insufficient image brightness caused by polarization imaging mechanisms. This invention proposes a method and system for enhancing the brightness of SO images based on polarization imaging mechanisms. It aims to improve the brightness level of polarized images through an intelligent weight selection strategy, thereby improving image quality and information extraction efficiency. Through this method, this invention hopes to overcome the challenges faced by traditional technologies and provide a more efficient and accurate solution for enhancing the brightness of polarized images. Summary of the Invention

[0006] To overcome the shortcomings of existing technologies, this invention discloses a method and system for enhancing the brightness of SO images based on a polarization imaging mechanism. Specifically, it relates to a method for enhancing the brightness of SO images under a polarization imaging mechanism combined with an improved horned lizard optimization algorithm. This invention aims to solve the problems existing in current SO image brightness enhancement techniques under polarization imaging mechanisms. By integrating polarization de-mosaicing, intensity denoising, swarm intelligence optimization algorithms, and neural network technology, this invention can effectively address the problem of weak SO images caused by the polarization imaging mechanism without losing polarization information, significantly improving the recognition of targets and overall clarity in SO images, thereby providing users with more intuitive and accurate image information. Furthermore, the method of this invention has been tested and verified on the publicly available dataset RCPI, and the results demonstrate its effectiveness.

[0007] The technical solution is as follows: A method for enhancing the brightness of an S0 image based on a polarization imaging mechanism, comprising:

[0008] S1: The selected polarization image is processed by the preprocessing module (1) to perform polarization de-mosaicing and intensity denoising to obtain a polarization intensity image;

[0009] S2: Input the polarization intensity image into the parameter optimization and weighted enhancement module (2) to perform weight parameter optimization and weighted summation enhancement fusion to obtain the brightness-enhanced S0 result image.

[0010] In step S1, the acquired polarization intensity image includes intensity images of any polarization direction from 0° to 360°, and the intensity images of any polarization direction are collectively referred to as... .

[0011] The polarization intensity image includes:

[0012] S101: Polarization image The image is input to the polarization demosaic module (101) for polarization image demosaicing, generating an intensity image containing arbitrary polarization directions. ;

[0013] S102: Intensity image of arbitrary polarization direction The image is input to the intensity denoising module (102) for initial denoising to obtain the polarization intensity image. .

[0014] In step S2, obtaining the brightness-enhanced result image S0 includes:

[0015] S201: Optimize the weighted summation enhancement fusion module (202) using the improved horned lizard optimization algorithm module (201) and output the optimal parameter intensity weight coefficients w1, w2, w3, w4;

[0016] S202: Based on the optimal parameter intensity weighting coefficients w1, w2, w3, w4, the polarization intensity image is set. The input is fed into the optimal weighted summation enhancement fusion module (202) to achieve the S0 result image after brightness enhancement. .

[0017] Furthermore, in step S201, the improved horned lizard optimization algorithm module (201) finds the optimal combination of weight coefficients in the complex search space through iterative search and continuous adjustment of weight coefficients, thereby significantly improving the brightness and clarity of the S0 image; the weighted summation enhancement fusion module (202) takes the polarization intensity image as input, integrates the intensity information in multiple polarization directions, and performs weighted summation according to the optimized weight coefficients to generate the brightness-enhanced S0 result image. ;

[0018] The specific steps of the improved horned lizard optimization algorithm module (201) are as follows:

[0019] S2011: Algorithm Parameter Initialization: This invention utilizes the Logistic Tent chaotic mapping to initialize the initial parameters of the HLOA optimization algorithm, including: population size N, maximum number of iterations T. max , specify the number of search agents K.

[0020] In the HLOA algorithm, the initial velocity population is randomly generated in the search space, just like most intelligent algorithms. This random generation mode leads to a decrease in population diversity in the later stages of iteration and makes it prone to getting trapped in local optima, which has an adverse effect on global extremum search. Therefore, this invention introduces Logistic Tent chaotic mapping to improve the initialization of the HLOA algorithm. Using Logistic Tent chaotic mapping instead of random parameters enables the algorithm to obtain a good diversity of initial solutions in the search space, effectively improving the convergence speed and solution accuracy of the HLOA algorithm. Its formula is shown in (1):

[0021] (1)

[0022] in, The range of chaotic orbital state values ​​is (0, 1).

[0023] S2012: Construct the objective function to calculate the fitness value. The objective function is:

[0024] (2)

[0025] Where J is the objective function, The calculated brightness value of the S0 image. It is the brightness value of the visible light image at the corresponding pixel position.

[0026] S2013: The search agent's location is updated by simulating the horned lizard's defense strategy, which includes three strategies:

[0027] Strategy 1: Stealth Behavior Strategy. When the horned lizard is attacked and in a camouflaged state, it adopts a stealth behavior strategy to update the location of the horned lizard search agent. The update formula is shown in (3):

[0028] (3)

[0029] in, This indicates the proxy position of the i-th horned lizard in the (t+1)-th generation search space; This represents the optimal solution with the highest fitness at the t-th iteration; It is a constant, with a value of 2; This represents the maximum number of iterations for the population. , , and It is a random integer, and its value ranges from [1, population size N]; , , and Representing the first The position vector of the search agent in generation t; Represents binary numbers, and This represents a random number obtained from the standard color palette, and .

[0030] Strategy 2: Movement and Escape Strategy. When the horned lizard is under attack and is not in a camouflage state, if it chooses to escape, it will use random and rapid movement to avoid the predator. The movement and escape strategy is adopted to update the horned lizard's search agent position. The update formula is shown in (4):

[0031] (4)

[0032] in, This indicates the proxy position of the i-th horned lizard in the (t+1)-th generation search space; This represents the optimal solution with the highest fitness at the t-th iteration; This represents a random number whose value is in the range [-1, 1]. This represents a random number generated from a Cauchy distribution with a mean of 0 and a variance of 1.

[0033] Strategy 3: Improved Blood-Spitting Strategy. When the horned lizard is attacked and not in camouflage, if it does not choose to flee, it will adopt an aggressive strategy, defending itself by shooting blood from its eyes.

[0034] This invention addresses the drawback of the fixed initial velocity of blood spray in the original blood-spraying strategy of horned lizards by designing an optimized inertia weighting approach. The improved blood-spraying strategy can adjust the initial velocity of the spray based on the iteration number of the horned lizard optimization algorithm and the individual's fitness. The improved blood-spraying formula is shown in (5):

[0035] (5)

[0036] in, This indicates the proxy position of the i-th horned lizard in the (t+1)-th generation search space; Indicates the initial velocity; The angle at which the horned lizard sprays blood, with a value of ; This represents the maximum number of iterations for the population. Take 1E-6; Let represent the optimal solution with the highest fitness at the t-th iteration; g represents Earth's gravity, with a value of 0.009807 km / s. 2 ; Let represent the proxy position of the i-th horned lizard in the t-th generation search space.

[0037] The formula for V0 is shown in (6):

[0038] (6)

[0039] in, Indicates the initial velocity; This indicates the weight of the current search agent; Indicates the current search agent speed; and These represent the initial weights and the final weights, respectively. This represents the maximum number of iterations for the population. Indicates the current iteration number; and Table of control coefficients; and These represent the worst-case fitness value and the best-case fitness value, respectively. This represents the fitness value of the current agent.

[0040] S2014: The worst position of the search agent is updated by simulating the adjustment strategy of the horned lizard's skin becoming brighter or darker. That is, if the horned lizard's skin becomes brighter, Equation (7) can be used for update and replacement; if the horned lizard's skin becomes darker, Equation (8) can be used for update and replacement.

[0041] (7)

[0042] (8)

[0043] in, This represents the worst-fit solution in the t-th iteration; This represents the optimal solution with the highest fitness at the t-th iteration; , , and Representing the first The position vector of the search agent in generation t; L1 and L2 are random numbers in binary; L1 and L2 are random numbers with a value range of [0, 0.4046661]; D1 and D2 are random numbers with a value range of [0.5440510, 1].

[0044] S2015: By observing the effect of the α-melanocyte rate value of the horned lizard on the color brightness of the horned lizard skin in S504, if the α-melanocyte rate value of the horned lizard is lower than 0.3, the search agent with a low value needs to be replaced, and the best search agent value is selected, as shown in Equation (9):

[0045] (9)

[0046] in, This represents the proxy position of the i-th horned lizard in the t-th generation search space; This represents the optimal solution with the highest fitness at the t-th iteration; and Representing the first The position vector of the search agent in generation t; Represents a binary number.

[0047] S2016: Determine if the maximum number of iterations has been reached. If so, output the optimal parameter strength weight coefficient; otherwise, return to S502 to continue the optimization operation.

[0048] Furthermore, the weighted summation enhancement fusion module (202) uses optimized weight coefficients to perform weighted summation on the input polarization intensity image. Specifically, it multiplies the image by the corresponding weight coefficient in each polarization direction, and then adds all the weighted intensity values ​​to obtain the brightness-enhanced S0 result image. The formula is as follows:

[0049] (10)

[0050] in, , , and An intensity image representing an arbitrary polarization direction; , , and This represents the weight value of each intensity image; different weight values ​​represent different levels of importance.

[0051] Another object of the present invention is to provide an S0 image brightness enhancement system based on a polarization imaging mechanism, the system implementing the aforementioned S0 image brightness enhancement method based on a polarization imaging mechanism, the system comprising:

[0052] The preprocessing module is used to perform polarization demosaicing and intensity denoising on the selected polarization image to obtain a polarization intensity image;

[0053] Furthermore, the polarization demosaic module is used to convert polarization images... Perform polarization image de-mosaic processing to generate intensity images containing arbitrary polarization directions. ;

[0054] The intensity denoising module is used to denoise intensity images in any polarization direction. Perform initial denoising to obtain the polarization intensity image. .

[0055] The parameter optimization and weighted enhancement module employs an improved horned lizard optimization algorithm. This algorithm iteratively searches and continuously adjusts the weight coefficients to find the optimal combination of weight coefficients within a complex search space. The polarization intensity image is provided as input to this module, integrating intensity information from multiple polarization directions. Based on the optimized weight coefficients, the module performs a weighted summation operation to generate a brightness-enhanced S0 result image. This process, known as weighted summation fusion, aims to significantly improve the brightness and quality of the image without sacrificing polarization information.

[0056] Furthermore, the improved horned lizard optimization module (201) is used to generate the optimal parameter intensity weight coefficients w1, w2, w3, w4 of the optimized weighted summation enhancement fusion module;

[0057] The weighted summation enhancement fusion module (202) is used to perform polarization intensity image fusion according to the above-mentioned optimal parameter intensity weight coefficients w1, w2, w3, w4. A weighted summation process is performed to generate the brightness-enhanced S0 result image. .

[0058] Furthermore, the low-light color polarization image enhancement system is based on a polarization imaging mechanism and is deployed on a computer device. This device includes at least one processor, a memory, and a dedicated computer program stored in the memory and running on the processor. When the processor executes these programs, it is able to realize the various functions of the low-light color polarization image enhancement system.

[0059] The S0 image enhancement system based on polarization imaging mechanism is mounted on a computer device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, it implements the functions of the S0 image brightness enhancement system based on polarization imaging mechanism.

[0060] Combining all the above technical solutions, the beneficial effects of this invention are as follows: This invention provides a method and system for enhancing the brightness of S0 images based on a polarization imaging mechanism. This method preprocesses the selected polarization image, including polarization de-mosaicing and intensity denoising, to obtain a polarization intensity image. Then, it optimizes the weighted summation enhancement fusion module using an improved horned lizard optimization algorithm module, outputting optimal intensity weight coefficients. These coefficients are then used to perform a weighted summation of the polarization intensity image, ultimately achieving a brightness-enhanced S0 result image. This invention not only effectively solves the problem of weak S0 images caused by the polarization imaging mechanism without losing polarization information in the S0 image, but also significantly improves the object recognition and overall clarity of the image, providing observers with more intuitive and accurate image information. Compared to existing polarization image brightness enhancement methods, this invention significantly improves image brightness levels and image quality through an intelligent weight selection strategy, thereby improving information extraction efficiency. It is particularly suitable for multiple fields such as environmental monitoring, remote sensing imagery, medical imaging, machine vision and autonomous driving, and agricultural monitoring, providing strong technical support for applications in these fields.

[0061] Compared to existing technologies, the advantages of this invention further include: First, by employing advanced preprocessing techniques such as polarization de-mosaicing and intensity denoising, this invention can effectively remove various interfering factors in the original polarization image, such as mosaic effects and random noise, thereby obtaining a cleaner and higher-quality polarization intensity image, which lays a solid foundation for subsequent image enhancement work. Second, this invention innovatively proposes an improved horned lizard optimization algorithm and applies it to the parameter optimization weighted enhancement module. This algorithm can not only automatically find the optimal weight parameter configuration, but also flexibly adjust the optimization strategy according to the characteristics of different images, ensuring that each enhancement achieves the desired effect. Finally, the weighted summation enhancement fusion module of this invention can fully utilize the optimized weight parameters to perform meticulous enhancement processing on the polarization intensity image. It can not only significantly improve the overall brightness of the image, but also highlight the contour and texture details of the target object without affecting the original polarization information, making the image more visually appealing and practical.

[0062] In summary, the ultimate goal of this invention is to enhance the brightness of polarized images while preserving the polarization information in the original image to the greatest extent possible, thus preventing information loss. Furthermore, this invention utilizes an improved optimization algorithm to flexibly adjust weighting coefficients to adapt to different types of polarized images. Attached Figure Description

[0063] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure;

[0064] Figure 1 This is a flowchart of the S0 image brightness enhancement method under the polarization imaging mechanism provided in the embodiments of the present invention;

[0065] Figure 2 This is a schematic diagram of the S0 image brightness enhancement system under the polarization imaging mechanism provided in this embodiment of the invention;

[0066] Figure 3 This is a schematic diagram of the structure and principle of the improved horned lizard optimization algorithm module provided in an embodiment of the present invention.

[0067] In the diagram: 1. Preprocessing module; 101. Polarization de-mosaic module; 102. Intensity denoising module; 2. Parameter optimization and weighted enhancement module; 201. Improved horned lizard optimization algorithm module; 202. Weighted summation enhancement fusion module. Detailed Implementation

[0068] To make the objectives, features, and advantages of the present invention clearer and more understandable, specific embodiments will be described in detail below with reference to the accompanying drawings. Numerous specific details are provided in the following description to aid in a comprehensive understanding of the invention. However, the present invention can be implemented in many ways different from those described herein, and those skilled in the art can make similar modifications without departing from the core principles of the invention. Therefore, the scope of the present invention is not limited to the following specific embodiments.

[0069] The innovation of this invention lies in addressing the insufficient brightness problem in current brightness enhancement methods for S0 images based on polarization imaging mechanisms. A new brightness enhancement method for S0 images based on polarization imaging mechanisms is proposed, combining a preprocessing module 1 and a parameter optimization weighted enhancement module 2. The preprocessing module 1 uses a polarization de-mosaic module 101 to de-mosaic the polarization image and an intensity denoising module 102 for initial denoising. The parameter optimization weighted enhancement module 2 uses an improved optimized angular lizard optimization algorithm 201 to optimize the weighted summation enhancement fusion module to obtain the optimal parameter intensity weight coefficients. The weighted summation enhancement fusion module 202 then uses these optimal parameter weight coefficients to achieve the brightness enhancement of the S0 image.

[0070] Example 1, such as Figure 1 As shown in the figure, an embodiment of the present invention provides a method for enhancing the brightness of an S0 image based on a polarization imaging mechanism. This method comprises de-mosaicing and denoising, and a swarm intelligence optimization algorithm. The method includes a preprocessing module 1 and a parameter optimization weighted enhancement module 2. The method includes the following steps:

[0071] S1: The selected polarization image is processed by the preprocessing module (1) to perform polarization de-mosaicing and intensity denoising to obtain a polarization intensity image;

[0072] S2: Input the polarization intensity image into the parameter optimization and weighted enhancement module (2) to perform weight parameter optimization and weighted summation enhancement fusion to obtain the brightness-enhanced S0 result image.

[0073] In step S1, the acquired polarization intensity image includes intensity images of any polarization direction from 0° to 360°, and the intensity images of any polarization direction are collectively referred to as... .

[0074] In a preferred embodiment, the intensity image of any polarization direction includes polarization states in four directions: 0°, 45°, 90°, and 135°, collectively referred to as... .

[0075] The polarization intensity image includes the following steps:

[0076] S101: Polarization image The image is input to the polarization demosaic module (101) for polarization image demosaicing, generating an intensity image containing arbitrary polarization directions. ;

[0077] In the embodiments, as a preferred method, the polarization demosaicing module of the present invention employs the EARI algorithm, which currently has superior demosaicing quality.

[0078] S102: Intensity image of arbitrary polarization direction The image is input to the intensity denoising module (102) for initial denoising to obtain the polarization intensity image. .

[0079] In this embodiment, as a preferred method, the present invention utilizes median filtering to denoise polarization intensity images;

[0080] This invention employs de-mosaicing and intensity denoising techniques to more effectively address the brightness enhancement issue in S0 images under polarization imaging mechanisms, thereby improving the brightness of S0 images. Through polarization de-mosaicing, an intensity image containing arbitrary polarization directions is generated. By intensity denoising, the intensity image in any polarization direction is initially denoised to obtain a polarization intensity image.

[0081] In step S2 of this embodiment of the invention, as follows Figure 2 As shown, the parameter optimization weighted enhancement module 2 specifically includes an improved horned lizard optimization algorithm module 201 and a weighted summation enhancement fusion module 202;

[0082] The improved horned lizard optimization module (201) is used to generate the optimal parameter intensity weight coefficients w1, w2, w3, w4 of the optimized weighted summation enhancement fusion module;

[0083] The weighted summation enhancement fusion module (202) is used to perform polarization intensity image fusion according to the above-mentioned optimal parameter intensity weight coefficients w1, w2, w3, w4. A weighted summation process is performed to generate the brightness-enhanced S0 result image. .

[0084] The polarization intensity image is input into the parameter optimization and weighted enhancement module 2 for weighted enhancement and fusion to obtain the brightness-enhanced S0 result image. The specific steps are as follows:

[0085] S201: Optimize the weighted summation enhancement fusion module 202 using the improved horned lizard optimization algorithm module 201, and output the optimal parameter strength weight coefficients w1, w2, w3, w4;

[0086] It is understood that the improved horned lizard optimization algorithm module 201 used in this invention finds the optimal combination of weight coefficients in the complex search space through iterative search and continuous adjustment of weight coefficients, thereby significantly improving the brightness and clarity of the S0 image.

[0087] S202: Based on the optimal parameter intensity weighting coefficients w1, w2, w3, w4, the polarization intensity image is set. The input is fed into the optimal weighted summation enhancement fusion module 202 to achieve the S0 result image after brightness enhancement. .

[0088] It is understood that the weighted summation enhancement fusion module 202 used in this invention takes the polarization intensity image as input, integrates the intensity information in multiple polarization directions, performs weighted summation according to the optimized weight coefficients, and generates the brightness-enhanced S0 result image. ;

[0089] Example 2, exemplary, as one implementation method, step S2 in this embodiment of the invention includes:

[0090] like Figure 3 The diagram shown illustrates the structure of the improved horned lizard optimization algorithm module. The specific steps of this process are as follows:

[0091] This invention utilizes the Logistic Tent chaotic mapping to initialize the initial parameters of the HLOA optimization algorithm, including: population size N, maximum number of iterations T. max The algorithm specifies the number of search agents, K; constructs an objective function to calculate the fitness value; updates the search agent positions by simulating the horned lizard's defense strategy; updates the worst-case search agent positions by simulating the horned lizard's skin brightening or darkening adjustment strategy; observes the effect of the horned lizard's α-melanocyte rate on the skin's brightness and darkness; if the α-melanocyte rate is below 0.3, the search agent with the low value needs to be replaced, and the best search agent value is selected; it determines whether it is at the maximum iteration count; if so, it outputs the optimal parameter strength weight coefficient; otherwise, it returns to continue the optimization operation. In this embodiment, the population size N=50, and the maximum iteration count T max =200, specifying the number of search agents K=10;

[0092] In step S2 of this embodiment, the parameter optimization and weighted enhancement module 202 of the present invention also includes a weighted summation enhancement fusion module 202. The input polarization intensity image is weighted and summed using the optimized weight coefficients. Specifically, the corresponding weight coefficient is multiplied in each polarization direction, and then all weighted intensity values ​​are summed to obtain the brightness-enhanced result image S0.

[0093] As can be seen from the above embodiments, the present invention also has the following advantages:

[0094] Environmental monitoring: Polarization imaging can be used to monitor environmental parameters such as air quality, water pollution, and vegetation health. By optimizing weights, polarization information related to these parameters can be extracted, providing strong support for environmental protection and disaster early warning.

[0095] Remote sensing imagery: In the field of remote sensing, polarization information can be used to improve the accuracy of tasks such as land cover classification, vegetation monitoring, and water body detection. By optimizing weights, useful information in polarization images acquired from satellites or drones can be enhanced.

[0096] Medical Imaging: In medical imaging, polarization imaging technology can be used to detect abnormal structural or functional changes in tissues, extracting clearer pathological features from optimized polarization images, thereby assisting in diagnosis and treatment.

[0097] Machine vision and autonomous driving: Polarization information helps enhance image contrast, reduce glare, and improve target detection capabilities. Optimized polarized images can be applied to camera systems in autonomous vehicles to improve the accuracy of road and obstacle recognition.

[0098] Agricultural monitoring: Optimized polarization images can be used for crop pest and disease monitoring, crop growth status assessment, etc., and can highlight abnormal changes in crop leaves, providing technical support for precision agriculture.

[0099] This invention is the first to combine polarization de-mosaicing, intensity denoising, and parameter optimization weighted enhancement techniques to enhance the brightness of S0 images under polarization imaging mechanisms. It employs a novel algorithm that overcomes the shortcomings of current methods for polarized optical images like S0 images under polarization imaging mechanisms. The algorithm effectively solves the problem of weak images under polarization imaging mechanisms and fills the technological gap in image brightness enhancement under polarization imaging mechanisms.

[0100] This invention employs a rich dataset covering various scenarios and environments for training and evaluation. This helps ensure that the algorithm possesses good generalization ability, rather than just performing well under specific conditions. During the training process, we eliminated factors that could cause technical bias, such as insufficient ambient light intensity (lux). For the above embodiments, each example has a different focus; if any part is not described or recorded in detail in a certain embodiment, it can be found in the relevant descriptions of other embodiments.

[0101] The information interaction and execution process between the above-mentioned devices are based on the same concept as the method embodiments of the present invention. For details on their specific functions and technical effects, please refer to the method implementation section, and they will not be repeated here.

[0102] Those skilled in the art will understand that, for ease of description and simplification, this explanation uses only specific examples of the division of functional units and modules. In practical applications, the aforementioned functions can be allocated to different functional units or modules as needed; that is, the internal structure of the device can be divided into different units or modules according to functional requirements to complete all or part of the stated functions. These functional units or modules can be integrated in a single processing unit, exist as independent physical entities, or integrate the functions of two or more units / modules into one unit. Such integrated units can be implemented in hardware or software functional units. Furthermore, the specific naming of each functional unit and module is only for distinguishing them and does not limit the scope of protection of this invention. The specific operation process of each unit and module in the system can be referred to the corresponding process in the foregoing method embodiments.

[0103] This invention also introduces a computer device comprising at least one processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor runs these computer programs, it performs the steps described in the various method embodiments above.

[0104] This invention also provides an information data processing terminal that can operate on various electronic devices and provides users with an input interface to execute the steps in the above-described method embodiments. The application of this information data processing terminal is not limited to devices such as mobile phones, computers, and switches.

[0105] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments in this application can be implemented by a computer program guiding related hardware. This computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program referred to herein includes computer program code, which can be source code, object code, executable files, or some intermediate form. A computer-readable medium can include any entity or device capable of carrying computer program code to a target device (such as a camera or terminal), such as a recording medium, computer memory, ROM (Read-Only Memory), RAM (Random Access Memory), electrical signals, software distribution media, etc. Specific examples include USB flash drives, portable hard drives, magnetic disks, optical disks, etc.

[0106] To further illustrate the effects of the embodiments of the present invention, the following experiments were conducted: The present invention selected the publicly available RCPI dataset from 2024. The polarization de-mosaicing and intensity denoising modules were used to better de-mosaic and denoise the polarization image. The improved horned lizard optimization algorithm module was used to generate the optimal parameter intensity weight coefficients w1, w2, w3, w4 for the optimized weighted summation enhancement fusion module. The weighted summation enhancement fusion module was used to perform weighted summation processing with the obtained optimal parameter intensity weight coefficients w1, w2, w3, w4 and the polarization intensity image to generate the brightness-enhanced S0 result image.

[0107] Table 1 Comparison Results of Different Optimization Algorithms

[0108]

[0109] The foregoing describes specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Those skilled in the art should understand that all modifications, equivalent substitutions, and improvements made within the spirit and basic principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for enhancing the brightness of SO images based on polarization imaging mechanism, characterized in that, The method includes: S1: The selected polarization image is processed by the preprocessing module (1) to perform polarization de-mosaicing and intensity denoising to obtain a polarization intensity image; S2: Input the polarization intensity image into the parameter optimization and weighted enhancement module (2) to perform weight parameter optimization and weighted summation enhancement fusion to obtain the brightness-enhanced S0 result image; In step S1, the acquired polarization intensity image includes intensity images of any polarization direction from 0° to 360°, and the intensity images of any polarization direction are collectively referred to as... ; The polarization intensity image includes: S101: Polarization image The image is input to the polarization demosaic module (101) for polarization image demosaicing, generating an intensity image containing arbitrary polarization directions. ; S102: Intensity image of arbitrary polarization direction The image is input to the intensity denoising module (102) for initial denoising to obtain the polarization intensity image. ; In step S2, obtaining the brightness-enhanced result image S0 includes: S201: Optimize the weighted summation enhancement fusion module (202) using the improved horned lizard optimization algorithm module (201) and output the optimal parameter intensity weight coefficients w1, w2, w3, w4; S202: Based on the optimal parameter intensity weighting coefficients w1, w2, w3, w4, the polarization intensity image is set. The input is fed into the optimal weighted summation enhancement fusion module (202) to achieve the S0 result image after brightness enhancement. ; In step S201, the improved horned lizard optimization algorithm module (201) finds the optimal combination of weight coefficients in a complex search space through iterative search and continuous adjustment of weight coefficients, thereby significantly improving the brightness and clarity of the S0 image; the weighted summation enhancement fusion module (202) takes the polarization intensity image as input, integrates the intensity information in multiple polarization directions, performs weighted summation according to the optimized weight coefficients, and generates the brightness-enhanced S0 result image. .

2. The method for enhancing the brightness of SO images based on polarization imaging mechanism according to claim 1, characterized in that, In step S201, the specific steps of the improved horned lizard optimization algorithm module (201) are as follows: S2011: Algorithm Parameter Initialization: Initialize the initial parameters of the HLOA optimization algorithm using the Logistic Tent chaotic mapping, including: population size N, maximum number of iterations T. max Specify the number of search agents, K; As the horned lizard optimization algorithm is like most intelligent algorithms, its initial velocity population is randomly generated in the search space. This random generation mode will lead to a decrease in the diversity of the population in the later stages of the algorithm's iteration, and it is easy to get trapped in local optima, which will have an adverse effect on the global extreme value search. Therefore, the Logistic Tent chaotic mapping is introduced to improve the initialization of the HLOA algorithm. The Logistic Tent chaotic mapping is used to replace the random parameters so that the algorithm can obtain a good diversity of initial solutions in the search space, which can effectively improve the convergence speed and solution accuracy of the HLOA algorithm. Its formula is shown in (1): （1）; in, The range of chaotic orbital state values ​​is (0, 1); S2012: Construct the objective function to calculate the fitness value. The objective function is: （2）; Where J is the objective function, The calculated brightness value of the S0 image. It is the brightness value of the visible light image at the corresponding pixel location; S2013: The search agent's location is updated by simulating the horned lizard's defense strategy, which includes three strategies: Strategy 1: Stealth Behavior Strategy. When the horned lizard is attacked and in a camouflaged state, it adopts a stealth behavior strategy to update the horned lizard search agent location. The update formula is shown in (3): （3）; in, This indicates the proxy position of the i-th horned lizard in the (t+1)-th generation search space; This represents the optimal solution with the highest fitness at the t-th iteration; It is a constant, with a value of 2; This represents the maximum number of iterations for the population. , , and It is a random integer, and its value ranges from [1, population size N]; , , and Representing the first The position vector of the search agent in generation t; Represents binary numbers, and This represents a random number obtained from the standard color palette, and ; Strategy 2: Movement and escape strategy. When the horned lizard is under attack and is not in a camouflage state, if it chooses to escape, it will move quickly and randomly to avoid the predator. The movement and escape strategy is adopted to update the horned lizard's search agent position. The update formula is shown in (4): （4）; in, This indicates the proxy position of the i-th horned lizard in the (t+1)-th generation search space; This represents the optimal solution with the highest fitness at the t-th iteration; This represents a random number whose value is in the range [-1, 1]. This represents a random number generated from a Cauchy distribution with a mean of 0 and a variance of 1. Strategy 3: Improved blood-spurting strategy. When the horned lizard is attacked and is not in a camouflage state, if it does not choose to run away, the horned lizard will adopt an aggressive strategy and defend itself by spurting blood from its eyes. To address the drawback of the fixed initial velocity of blood spray in the original blood-spraying strategy of the horned lizard, an optimized inertia weight was introduced into the blood-spraying strategy. The improved blood-spraying strategy can adjust the initial velocity of the spray based on the number of iterations of the horned lizard optimization algorithm and the individual's fitness. The improved blood-spraying formula is shown in (5): （5）; in, This indicates the proxy position of the i-th horned lizard in the (t+1)-th generation search space; Indicates the initial velocity; The angle at which the horned lizard sprays blood, with a value of ; This represents the maximum number of iterations for the population. Take 1E-6; Let represent the optimal solution with the highest fitness at the t-th iteration; g represents Earth's gravity, with a value of 0.009807 km / s. 2 ; This represents the proxy position of the i-th horned lizard in the t-th generation search space; The formula for V0 is shown in (6): （6）; in, Indicates the initial velocity; This indicates the weight of the current search agent; Indicates the current search agent speed; and These represent the initial weights and the final weights, respectively. This represents the maximum number of iterations for the population. Indicates the current iteration number; and Table of control coefficients; and These represent the worst-case fitness value and the best-case fitness value, respectively. This represents the fitness value of the current agent; S2014: The worst position of the search agent is updated by simulating the adjustment strategy of the horned lizard's skin becoming brighter or darker. That is, if the horned lizard's skin becomes brighter, Equation (7) can be used for update and replacement; if the horned lizard's skin becomes darker, Equation (8) can be used for update and replacement. （7）; （8）; in, This represents the worst-fit solution in the t-th iteration; This represents the optimal solution with the highest fitness at the t-th iteration; , , and Representing the first The position vector of the search agent in generation t; L1 and L2 are random numbers in binary; L1 and L2 are random numbers with values ​​ranging from [0, 0.4046661]; D1 and D2 are random numbers with values ​​ranging from [0.5440510, 1]; S2015: By observing the effect of the α-melanocyte rate value of the horned lizard on the color brightness of the horned lizard skin in S504, if the α-melanocyte rate value of the horned lizard is lower than 0.3, the search agent with a low value needs to be replaced, and the best search agent value is selected, as shown in Equation (9): （9）; in, This represents the proxy position of the i-th horned lizard in the t-th generation search space; This represents the optimal solution with the highest fitness at the t-th iteration; and Representing the first The position vector of the search agent in generation t; Represents binary numbers; S2016: Determine if the maximum number of iterations has been reached. If so, output the optimal parameter strength weight coefficient; otherwise, return to S502 to continue the optimization operation.

3. The method for enhancing the brightness of SO images based on polarization imaging mechanism according to claim 1, characterized in that, In step S202, the weighted summation enhancement fusion module (202) uses the optimized weight coefficients to perform weighted summation on the input polarization intensity image; specifically, it multiplies by the corresponding weight coefficient in each polarization direction, and then adds all the weighted intensity values ​​to obtain the brightness-enhanced S0 result image. ; The formula is as follows: （10）; in, , , and An intensity image representing an arbitrary polarization direction; , , and This represents the weight value of each intensity image; different weight values ​​represent different levels of importance.

4. A brightness enhancement system for SO images based on polarization imaging mechanism, characterized in that, The system implements the S0 image brightness enhancement method based on polarization imaging mechanism as described in any one of claims 1-3, and the system includes: The preprocessing module (1) is used to perform polarization demosaicing and intensity denoising on the selected polarization image to obtain a polarization intensity image; The parameter optimization and weighted enhancement module (2) is used to optimize the polarization intensity image by weight parameters and perform weighted summation enhancement and fusion to obtain the brightness-enhanced S0 result image.

5. The SO image brightness enhancement system based on polarization imaging mechanism according to claim 4, characterized in that, The preprocessing module (1) includes: a polarization desacrifice module (101) for desacrifice polarization images and an intensity denoising module (102) for denoising intensity images. The polarization demosaic module (101) is used to polarize the image. Perform polarization image de-mosaic processing to generate intensity images containing arbitrary polarization directions. ; The intensity denoising module (102) is used to denoise intensity images with arbitrary polarization directions. Perform initial denoising to obtain the polarization intensity image. .

6. The SO image brightness enhancement system based on polarization imaging mechanism according to claim 4, characterized in that, The parameter optimization and weighted enhancement module (2) includes: an improved horn lizard optimization algorithm module (201) that finds the optimal combination of weight coefficients in a complex search space through iterative search and continuous adjustment of weight coefficients; and a module that takes the polarization intensity image as input, integrates intensity information from multiple polarization directions, and performs weighted summation based on the optimized weight coefficients to generate a brightness-enhanced S0 result image. The weighted summation enhancement fusion module (202); The improved horned lizard optimization algorithm module (201) is used to generate the optimal parameter intensity weight coefficients w1, w2, w3, w4 of the optimized weighted summation enhancement fusion module; The weighted summation enhancement fusion module (202) is used to perform polarization intensity image fusion according to the above-mentioned optimal parameter intensity weight coefficients w1, w2, w3, w4. A weighted summation process is performed to generate the brightness-enhanced S0 result image. .

Images