A method and system for enhancing the brightness of low-light space target images

Abstract

A method and system for enhancing the brightness of low-light space target images relates to the field of on-orbit image processing. The present invention is intended to solve the problem that in low-light environments, which are common in space environments, and in unique space environments with extremely unstable lighting conditions, the brightness of acquired images is often insufficient due to the obstruction of sunlight or the lack of cosmic background light, thereby affecting the quality of the image and subsequent image analysis and application. Technical highlights: A low-light image is produced as input using a simulation engine, and a lightweight convolutional neural network is used to estimate the lighting components of the low-light image based on a neural network combining unsupervised deep learning and a Retinex algorithm. An unsupervised learning strategy is adopted in the network, and the network is trained by means of non-reference loss functions such as exposure loss, spatial loss, and lighting smoothing loss, thereby avoiding dependence on paired training data. After obtaining the image with enhanced lighting conditions through the neural network, it is fused with the original image. The present invention is used to improve the quality of images captured under low-light conditions.

Description

Technical Field

[0001] The present invention belongs to the field of on-orbit image processing, and in particular relates to a method and system for enhancing the brightness of low-light space target images. Background Art

[0002] Images captured under low-light conditions often suffer from numerous problems, such as increased noise, reduced contrast, and loss of detail. These problems are particularly prominent in space environments, where the lighting conditions are not only low but also highly variable. Coupled with the particularity of space targets, such as satellites and space stations, improving image quality is particularly important and challenging. Currently, common image brightness enhancement techniques include histogram equalization, local enhancement algorithms, and deep learning-based methods. Although these methods can generally effectively enhance image brightness and contrast, they often introduce over-enhancement problems, such as noise amplification and detail distortion, when processing extreme low-light space images. In addition, these technologies are often not optimized for the special properties of space targets (such as material, shape, and reflective properties).

[0003] For example, the prior art document CN114862722A discloses a method and processing terminal for image brightness enhancement. The method includes: exposing an original image to obtain N exposed images; converting each exposed image from RGB to YUV to obtain a YUV exposed image; extracting a color scale distribution map from the YUV exposed image, wherein the color scale distribution map is divided into dark, mid-tone, and highlight regions in ascending order of brightness; assigning a weight value to each pixel in the YUV exposed image, and assigning successively increasing weight values to pixels in the dark, mid-tone, and highlight regions; taking the weighted average of pixels at the same position according to their respective weights to obtain a target pixel value; and reconstructing a target image based on the target pixel value, which serves as the brightness-enhanced image. This prior art method can improve the brightness of dark areas without affecting the normally exposed areas of the original image, thereby restoring the original color. The prior art document CN115861101A discloses a low-light image enhancement method based on depthwise separable convolution. The method includes: Step S1: capturing surveillance video of tunnel construction during day and night and segmenting it into frames for low-light image enhancement; Step S2: building a self-calibrated low-light image enhancement model based on depthwise separable convolution, determining model parameters and the neural network loss function, and optimizing model performance; Step S3: applying the trained low-light image enhancement network to dim day and night frame images to enhance image brightness, resulting in an enhanced image. This method maintains smoothness in the estimated illumination and achieves superior performance in both image quality and inference speed, enabling rapid improvement of image quality in complex tunnel environments.

[0004] It can be seen that in the existing technology, no one has proposed and provided a solution for how to enhance the brightness of low-light space target images, which usually have complex geometric shapes and material properties. These properties behave completely differently from those of objects on the ground under low-light conditions.

[0005] Therefore, when enhancing such images, it is necessary to consider their unique reflective characteristics and the influence of background illumination, as well as how to retain important spatial target information while enhancing image brightness.

[0006] Given the shortcomings of existing technologies, it is crucial to develop a brightness enhancement method specifically for low-light space target images. Such a method should effectively address image noise, improve the image's dynamic range, and preserve important target details. Furthermore, given the real-time demands of space missions, the method should also be computationally efficient and adaptable, enabling rapid adaptation and application to varying observation conditions and mission requirements. Summary of the Invention

[0007] The technical problems to be solved by the present invention are:

[0008] The purpose of the present invention is to provide a method and system for enhancing the brightness of low-light space target images to solve the problem that in low-light conditions common in space environments and in unique space environments with extremely unstable lighting conditions, the acquired images are often insufficiently bright due to obstruction of sunlight or lack of cosmic background light, thereby affecting the image quality and subsequent image analysis and application.

[0009] The technical solution adopted by the present invention to solve the above technical problems is:

[0010] A method for enhancing the brightness of a low-light space target image, the method comprising:

[0011] Step 1: Acquire low-light images

[0012] The definition of low-light images is as follows: Low-light images are images acquired under extremely low light conditions, characterized by an average brightness below 30 luminance units, a signal-to-noise ratio below 20 dB, a contrast ratio below 0.1, a color fidelity CIEDE2000 color difference exceeding 5, and a dynamic range below 40 dB. Furthermore, these images must meet on-orbit requirements, including complex lighting conditions, special target characteristics, and environmental adaptability. This definition can provide clear standards and guidance for the application of image brightness enhancement methods.

[0013] Step 2: Build a brightness enhancement network

[0014] A lightweight convolutional neural network based on unsupervised deep learning and the Retinex algorithm is constructed as a brightness enhancement network, and a lightweight convolutional neural network (CNN) is used to estimate the lighting components of low-light images.

[0015] The network receives a low-light image as input, decomposes the input image into an illumination layer and a reflection layer, and then outputs the reflection layer as the result of image brightness enhancement;

[0016] Step 3: Brightness Enhancement Network Model Training

[0017] During network training, the network is trained using no-reference loss functions such as exposure loss, spatial loss, and illumination smoothness loss to avoid dependence on paired training data. This no-reference loss function can effectively train the network to achieve image enhancement without real-world labels. The exposure loss is used to brighten underexposed areas in the image, the spatial loss ensures spatial consistency after image enhancement, and the illumination smoothness loss encourages smooth changes in the illumination layer to match the natural variations in lighting in the real world.

[0018] Step 4: Fusion processing

[0019] After obtaining the image enhanced by the neural network, it is fused with the original image. The pixel values corresponding to the two images are weighted averaged, and the fusion effect is determined by calculating the peak signal-to-noise ratio. If it does not meet the requirements, return to step 3 for network training.

[0020] Step 5: Verify the data enhancement effect after brightness enhancement network training:

[0021] After obtaining the fused image, the network model is tested and optimized. According to the training effect and performance of the network model, the parameters are adjusted and continuously tuned until the enhanced low-light spatial target image quality assessment requirements are met.

[0022] Furthermore, in step 1, the low-light image refers to a low-light image taken by a satellite or space detection equipment in a space environment, or produced using a simulation engine as input.

[0023] Furthermore, in step 2, the lightweight convolutional neural network (CNN) is based on the U-Net architecture and is used for illumination estimation in low-light images. The network consists of seven layers, each using a 3×3 convolution kernel. The first six layers have 8 output channels, and the last layer has 1 output channel. The network structure includes skip connections to preserve image details and reduce information loss during training.

[0024] The brightness enhancement network estimates the illumination and reflection components separately. The illumination estimation uses the deep features extracted by the encoder to estimate the illumination component of the image. The reflection estimation divides the original input image by the estimated illumination component to obtain the reflection component of the image. The established Retinex model is as follows:

[0025] I=R×L

[0026] In the formula, the image I can be modeled as the element-by-element product of the illumination component L and the reflection component R, where L represents the illumination of the object by the light source, which usually changes slowly and is evenly distributed; R represents the color and properties of the object itself, which is related to the inherent properties of the object and is not affected by the light intensity.

[0027] Furthermore, the specific steps in step three are:

[0028] (1) Initialize the brightness enhancement network model: Based on the pre-defined lightweight convolutional neural network architecture, use the Xavier initialization method to initialize all weights of the brightness enhancement network model; Xavier initialization can ensure that the network weights have a reasonable distribution in the early stage of training, which helps to improve the stability and convergence speed of model training;

[0029] (2) Define the loss function: Construct a composite loss function including exposure loss, spatial loss, illumination loss, and smoothness loss to optimize the training process of the low-light image brightness enhancement network; the content loss part of the composite loss function is used to ensure that the enhanced image is semantically consistent with the original low-light image and maintain the original information and details of the image; the spatial loss is intended to adjust the overall style of the enhanced image to meet specific visual standards; the regularization term added to the composite loss function helps prevent the network from overfitting and promotes the generalization ability of the model under different low-light conditions; (In this way, the composite loss function provides a strong training basis for the effective enhancement of low-light images, thereby achieving high-quality image output);

[0030] (3) Training and Monitoring: After training is completed, the trained model is used to perform brightness enhancement on actual low-light images. By comparing the enhanced images with the original images, not only the visual effects of the images are evaluated, but also the quality of the generated data, the convergence speed of the model, and the accuracy of style transfer are comprehensively examined to comprehensively evaluate the performance and practicality of the model.

[0031] (4) Brightness enhancement effect and performance verification: The trained brightness enhancement network model is used to perform brightness enhancement processing on the in-orbit target image; by comparing the brightness enhanced image with the original image, the brightness improvement effect is judged, and the image improvement quality, the speed of model convergence and the noise resistance of the network are considered to comprehensively evaluate the performance of the network model.

[0032] Furthermore, the brightness network model for high-level enhancement of low-light images is implemented through unsupervised learning training. The core lies in the design of a no-reference loss function. The loss function includes four components: exposure loss, spatial loss, and lighting and smoothness loss:

[0033] Exposure loss is defined as follows:

[0034]

[0035] Where M is the number of non-overlapping local regions where the image is segmented, R k is the average intensity of the kth region in the reflectance image, and E is the preset desired exposure level, which is set to 0.6 here. This loss function improves the overall brightness by enhancing the underexposed areas in the image to achieve the ideal exposure level, which helps to obtain consistent image quality under different brightness conditions.

[0036] The spatial loss function is defined as follows:

[0037]

[0038] Where K is the number of local regions considered in the image, Ω(i) represents the four neighboring regions (upper, lower, left, and right) surrounding region i, R and I represent the average local brightness of the enhanced and original images, respectively; this loss maintains the similarity in spatial consistency between the enhanced image and the original low-light image, thereby maintaining the integrity of the image structure.

[0039] The lighting loss function is defined as follows:

[0040]

[0041] In the formula, here and are the gradient operations in the horizontal and vertical directions, representing the smoothness of the lighting component L in these two directions;

[0042] Image smoothing loss function definition:

[0043]

[0044] Where: I represents the image, I[i,j] represents the pixel value of the image at position (i,j). This formula calculates the gradient values between all adjacent pixels of the image, sums them up and takes the square root, thereby quantifying the overall smoothness of the image; the loss function represents the sum of the intensity differences between adjacent pixels in the image, which represents a measure of the local smoothness of the image; are the differences between adjacent pixels in the horizontal and vertical directions of the image, respectively, and these differences represent the gradients of the image in these directions; I[i,j+1]-I[i,j] and |I[i+1,j]-I[i,j] are the differences between adjacent pixels in the horizontal and vertical directions of the image, respectively, and the differences represent the gradients of the image in these directions;

[0045] The total loss function is set as:

[0046] L total =λ1L exp +λ2L spa +λ3L smo +λ4L TV

[0047] Where λ1λ2λ3λ4 represent the weight coefficients for balancing the importance of each loss term, and these weight coefficients can be adjusted according to specific task requirements.

[0048] Furthermore, in step three, the network training is based on the Pytorch deep learning framework on the Ubuntu 20.04 system, and the training uses the NVIDIA 3060 GPU; the initial learning rate is set to 0.0001; the batch size is set to 8; the training cycle is 40 cycles; and L2 regularization is used.

[0049] Furthermore, the specific steps of the fusion process in step 4 are as follows:

[0050] After obtaining the image with enhanced lighting conditions through the neural network, it is fused with the original image; the pixel values corresponding to the two images are weighted averaged, and the formula is:

[0051]

[0052] Among them I fused (x,y) is the pixel value of the fused image at (x,y), I i (x,y) is the pixel value of the original image and the image after illumination enhancement at (x,y), w i is the corresponding weighting coefficient, which is dynamically adjusted according to the enhancement effect. The enhancement effect is determined by calculating the peak signal-to-noise ratio. The calculation formula for the peak signal-to-noise ratio is:

[0053]

[0054] Where, MAXI is the maximum possible pixel value of the image (such as 255 for an 8-bit image); where MSE is the mean squared error, calculated as follows:

[0055]

[0056] Where I is the original image, K is the fused image, m and n are the number of rows and columns of the image, respectively. After obtaining the peak signal ratio, the weighting coefficient is dynamically adjusted and optimized.

[0057] Furthermore, the specific process in step five includes the following steps:

[0058] 1) Data preprocessing and preparation

[0059] The collected low-light image dataset undergoes a series of preprocessing operations. These include normalizing the pixel values in the images to ensure they are within the range of 0 to 1, thereby ensuring consistency during data processing. Furthermore, the images are resized to 256×256 pixels, as required by the brightness enhancement model. Data augmentation techniques that do not alter the semantic content of the images are also applied to increase the diversity of the dataset, including random rotation and flipping.

[0060] 2) Quality assessment before enhancement

[0061] Establish quality assessment metrics for brightness enhancement: image brightness level, detail visibility, and noise level. Then, perform a preliminary evaluation of the images in the dataset using these metrics and record their initial quality status to provide a reference standard for subsequent comparison of enhancement effects.

[0062] 3) Enhanced quality assessment

[0063] Use non-reference image quality evaluation metrics (such as NIQE and BRISQUE) to evaluate or measure the enhancement quality of the enhanced image; compare the quality scores before and after enhancement to measure the degree of image brightness improvement, and adjust and optimize the network parameters based on the evaluation results;

[0064] The quality assessment indicators of non-reference images include NIQE and / or BRISQUE.

[0065] NIQE is a scoring system based on the statistical properties of natural scenes and does not rely on specific image content or any type of reference image;

[0066] BRISQUE is also a reference-free image quality assessment algorithm that predicts image quality by analyzing the spatial domain features of the image. BRISQUE focuses on the natural properties of the image (especially the local spatial features of the image, such as image texture and edges).

[0067] 4) Domain adaptability evaluation and generalization ability test

[0068] By quantitatively analyzing performance indicators such as accuracy and recall, the model's domain adaptability and generalization ability are evaluated; based on the test results, the network model and data processing flow are optimized.

[0069] A low-light space target image brightness enhancement system has a program module corresponding to the steps of the low-light space target image brightness enhancement method, and executes the steps of the low-light space target image brightness enhancement method when running.

[0070] A computer-readable storage medium stores a computer program, wherein the computer program is configured to implement the steps of the method for enhancing the brightness of a target image in a low-light space when called by a processor.

[0071] A low-light space target image processing device, the low-light space target image processing device includes at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the low-light space target image brightness enhancement method.

[0072] The present invention has the following beneficial technical effects:

[0073] This invention is a method for enhancing the image brightness of effective space targets in low-light conditions, based on an image brightness enhancement network. It is specifically designed for enhancing the brightness of low-light space target images. The space environment is unique and the lighting conditions are extremely unstable. Obstruction of sunlight or the absence of cosmic background light often results in insufficient brightness in acquired images, which affects image quality and subsequent image analysis and application. This invention significantly improves the brightness and visibility of images captured in low-light environments in space, thereby enhancing the efficiency and accuracy of space exploration, monitoring, and research.

[0074] The present invention specifically considers the unique reflective characteristics and the influence of background lighting when performing brightness enhancement on low-light space target images, as well as how to retain important space target information while enhancing image brightness. The method of the present invention can effectively process image noise, improve the dynamic range of the image, and retain important target details. In addition, the present invention takes into account the real-time needs of space missions and has high computational efficiency and adaptability so that it can be quickly adjusted and applied under different observation conditions and mission requirements. The efficient space target image brightness enhancement method and system provided by the present invention solves the low-light problem often encountered in space environments and significantly improves the quality of images captured under low-light conditions. The brightness enhancement effect is as follows: Figure 6 、 Figure 7 and Figure 8 As shown, the following are the specific effects of the present invention in enhancing image brightness:

[0075] (1) Image brightness improvement

[0076] This paper combines deep learning technology with Retinex theory to effectively improve the brightness of space target images captured under extreme low-light conditions. This makes low-quality images captured under conditions of sunlight obstruction or insufficient cosmic background light much brighter and clearer.

[0077] (2) Improved image quality

[0078] In addition to the brightness improvement, the system also optimizes the contrast and detail of the image, which significantly improves the visual quality of the image. This quality improvement makes the image more suitable for detailed analysis and processing.

[0079] (3) Adaptive lighting changes

[0080] The system is designed to adapt to different lighting conditions and can automatically adjust processing parameters according to different ambient lighting conditions to ensure optimal image enhancement effects under various lighting conditions.

[0081] (4) Improved space detection and monitoring efficiency:

[0082] By providing clearer images, the present invention significantly improves the efficiency and accuracy of space exploration, monitoring, and research, which is particularly important for applications such as satellite remote sensing, celestial observation, and space station monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 This is a flow chart of the spatial target image data enhancement method based on deep learning. Figure 2 is the first original image of a low-light space target, Figure 3 is the second low-light space target original image, Figure 4is the third low-light space target original image, Figure 5 This is the network structure diagram for image brightness enhancement;

[0084] Figure 6 The first brightness enhancement corresponding target image, Figure 7 This is the second target image corresponding to the brightness enhancement. Figure 8 This is the third target image corresponding to brightness enhancement. DETAILED DESCRIPTION

[0085] The following is based on the attached Figure 1-8 The present invention will be described in detail.

[0086] Specific embodiment 1: This embodiment provides a method for enhancing the brightness of a low-light space target image, the method steps comprising:

[0087] Step 1: Acquire low-light images

[0088] Images of on-orbit space targets are captured under complex and variable lighting conditions. These images are typically captured by satellites or other space exploration equipment in a space environment. Due to the limited angle of sunlight and obstruction by other celestial bodies, the images are subjected to low-light conditions. In this paper, a simulation engine was used to generate low-light images as input to simulate the low-brightness environment of real-world on-orbit space.

[0089] Step 2: Build a brightness enhancement network

[0090] The present invention proposes a neural network based on the combination of unsupervised deep learning and Retinex theory, and uses a lightweight convolutional neural network (CNN) to estimate the illumination components of low-light images. The network receives a low-light image as input, estimates the illumination layer of the image, and then decomposes the input image into an illumination layer and a reflection layer according to the Retinex theory. Finally, the reflection layer is the result of image brightness enhancement. The network in the present invention is based on the U-Net architecture, which is a lightweight convolutional neural network designed specifically for illumination estimation of low-light images. The network consists of seven layers, each layer uses a 3×3 convolution kernel, the number of output channels of the first six layers is 8, and the number of output channels of the last layer is 1, which is specifically used for illumination estimation. In addition, the network structure contains skip connections to maintain image details and reduce information loss during training.

[0091] Step 3: Brightness Enhancement Network Model Training

[0092] This network employs an unsupervised learning strategy, training the network using no-reference loss functions such as exposure loss, spatial loss, and illumination smoothness loss, thus avoiding the need for paired training data. This no-reference loss function effectively trains the network for image enhancement without ground-truth labels. The exposure loss brightens underexposed areas in the image, the spatial loss ensures spatial consistency after enhancement, and the illumination smoothness loss encourages smooth variations in illumination layers to match the natural variations in lighting in the real world.

[0093] Specific steps:

[0094] (1) Initialize the brightness enhancement network model: Based on the predefined lightweight convolutional neural network architecture, all weights of the brightness enhancement network model are initialized using the Xavier initialization method. Xavier initialization ensures that the network weights are reasonably distributed in the early stages of training, which helps improve the stability and convergence speed of model training.

[0095] (2) Define the loss function: Construct a training network for exposure loss, spatial loss, and illumination flatness loss. In the present invention, a composite loss function is designed to optimize the training process of the low-light image brightness enhancement network. This loss function combines content loss to ensure that the enhanced image is semantically consistent with the original low-light image, thereby maintaining the original information and details of the image. Spatial loss aims to adjust the overall style of the enhanced image to meet specific visual standards. The added regularization term helps prevent the network from overfitting and promotes the generalization ability of the model under different low-light conditions. In this way, the composite loss function provides a strong training basis for the effective enhancement of low-light images, thereby achieving high-quality image output.

[0096] (3) Training and Monitoring: After training, the trained model is used to perform brightness enhancement on actual low-light images. By comparing the enhanced images with the original images, not only the visual effects of the images are evaluated, but also the quality of the generated data, the convergence speed of the model, and the accuracy of style transfer are comprehensively examined to comprehensively evaluate the performance and practicality of the model.

[0097] (4) Brightness enhancement effect and performance verification: The trained brightness enhancement network model is used to perform brightness enhancement processing on the in-orbit target image. By comparing the brightness enhanced image with the original image, not only the brightness improvement effect is judged, but also the image improvement quality, the speed of model convergence, and the noise resistance of the network are comprehensively considered to comprehensively evaluate the performance of the network model.

[0098] Step 4: Fusion processing

[0099] After obtaining the image enhanced by the neural network, it is fused with the original image. The pixel values corresponding to the two images are weighted averaged, and the enhancement effect is determined by calculating the peak signal-to-noise ratio.

[0100] Step 5: Verify the data enhancement effect after brightness enhancement network training

[0101] After obtaining the fused image, the network model is tested and optimized. According to the training effect and performance of the network model, the parameters are adjusted and continuously tuned. The specific process includes the following steps:

[0102] 1. Data preprocessing and preparation

[0103] The collected low-light image dataset undergoes a series of preprocessing operations. This includes normalizing the pixel values in the images to ensure they are within the range of 0 to 1, thereby ensuring consistency during data processing. Furthermore, the images are resized to 256×256 pixels, as required by the brightness enhancement model. To enhance the diversity of the dataset, data augmentation techniques that do not alter the semantic content of the images are also applied, such as random rotation and flipping.

[0104] 2. Quality Assessment Before Enhancement

[0105] In this step, the present invention establishes a series of quality assessment metrics for brightness enhancement, such as image brightness level, detail visibility, and noise level. The images in the dataset are then preliminarily evaluated using these metrics, and their initial quality status is recorded to provide a reference standard for subsequent comparison of enhancement effects.

[0106] 3. Enhanced Quality Assessment

[0107] The quality of the enhanced image will be evaluated. In order to objectively evaluate the enhancement effect, the present invention will use non-reference image quality evaluation indicators, such as NIQE and BRISQUE, to measure the enhanced quality of the image. The present invention will compare the quality scores before and after enhancement to measure the degree of improvement in image brightness, and adjust and optimize the network parameters based on the evaluation results. NIQE is a scoring system based on the statistical characteristics of natural scenes. It does not depend on specific image content or any type of reference image. BRISQUE is also a non-reference image quality assessment algorithm that predicts image quality by analyzing the spatial domain characteristics of the image. BRISQUE focuses on the natural properties of the image, especially the local spatial features of the image, such as the texture and edges of the image.

[0108] 4. Domain Adaptability Evaluation and Generalization Ability Test

[0109] This paper proposes to analyze performance indicators through quantitative indicators, such as accuracy and recall, to evaluate the domain adaptability and generalization ability of the model. Based on the test results, this paper further optimizes the network model or data processing flow.

[0110] Specific embodiment 2: The present invention can obtain a low-light image by enhancing the image brightness through the system to obtain an enhanced image. The low-light space target image brightness enhancement method and system are as follows: Figure 1 shown.

[0111] Step 1: Acquire low-light images

[0112] First, an advanced graphics simulation platform is used to create a detailed three-dimensional space scene and build an accurately simulated space target model. By carefully simulating the lighting effects of sunlight and other celestial bodies, including sunrise, sunset, and scenes where the sun is blocked, complex and varied low-light conditions are generated. In these scenes, multiple virtual cameras are set at different positions and angles, and these cameras are controlled by writing automated scripts to follow preset trajectories or dynamically adjust the shooting path according to the light intensity to capture a wide range of low-light images. The collected images are then annotated in detail, including lighting conditions and camera settings, to form a comprehensive image dataset, providing high-quality basic data for the training and verification of image brightness enhancement models. This method not only avoids costly experiments in actual space environments, but also provides a controllable, efficient and repeatable method of acquiring data, greatly improving the research and development efficiency and accuracy of space target image brightness enhancement systems. Among them Figure 2 Figure 3 Figure 4 Some images of the dataset.

[0113] Step 2: Build a brightness enhancement network

[0114] The brightness enhancement network uses a lightweight convolutional neural network (CNN). Figure 5As shown in the figure, the network contains multiple convolutional layers, each of which uses a 3x3 convolution kernel and skip connections to retain image details and reduce information loss during training. The 3x3 convolution kernel helps capture image details while reducing the computational complexity of the model. The number of output channels of the first six layers of the network is set to 8, and the number of output channels of the last layer is set to 1, which is specifically used for lighting estimation. The skip connection used by the network is to directly connect the encoder part of the network to the corresponding decoder part, so as to retain more detailed information during the image enhancement process and prevent information loss in the convolution layer. The network architecture maintains the same network architecture as U-net, with a symmetrical encoder and decoder structure. Then, using the Retinex theory, the brightness enhancement network restores the true reflective properties of the image by estimating and adjusting the lighting component.

[0115] The brightness enhancement network estimates the illumination and reflection components separately. Illumination estimation uses deep features extracted by the encoder to estimate the illumination component of the image. Reflection estimation divides the original input image by the estimated illumination component to obtain the reflection component of the image. This operation is based on the Retinex theory. The Retinex model established in this invention is as follows:

[0116] I=R×L

[0117] In the formula, the image I can be modeled as the element-by-element product of the illumination component L and the reflection component R, where L represents the illumination of the object by the light source, which usually changes slowly and is evenly distributed; R represents the color and properties of the object itself, which is related to the inherent properties of the object and is not affected by the light intensity.

[0118] Step 3: Brightness network model training

[0119] The low-light image enhancement method proposed in this paper is implemented through unsupervised learning training. The core lies in its unique no-reference loss function design. This loss function includes four components: exposure loss, spatial loss, illumination loss, and smoothness loss.

[0120] Exposure loss is defined as follows:

[0121]

[0122] Where M is the number of non-overlapping local regions where the image is segmented, R k is the average intensity of the kth region in the reflectance image, and E is the preset desired exposure level, set to 0.6 here. This loss function improves the overall brightness by enhancing underexposed areas in the image to achieve the ideal exposure level. This helps achieve consistent image quality under different brightness conditions.

[0123] The spatial loss function is defined as follows:

[0124]

[0125] Where K is the number of local regions considered in the image, Ω(i) represents the four neighboring regions (above, below, left, and right) surrounding region i, and R and I represent the average local brightness of the enhanced and original images, respectively. This loss maintains the spatial consistency of the enhanced image and the original low-light image, thereby preserving the integrity of the image structure.

[0126] The lighting loss function is defined as follows:

[0127]

[0128] In the formula, here and are the gradient operations in the horizontal and vertical directions, respectively, representing the smoothness of the lighting component L in these two directions.

[0129] Image smoothing loss function definition:

[0130]

[0131] Where: I represents the image, and I[i,j] represents the pixel value of the image at position (i,j). This formula calculates the gradient values between all adjacent pixels of the image, sums them up and takes the square root, thereby quantifying the overall smoothness of the image. This loss function represents the sum of the intensity differences between adjacent pixels in the image and represents a measure of the local smoothness of the image. |I[i,j+1]-I[i,j] and |I[i+1,j]-I[i,j] are the differences between adjacent pixels in the horizontal and vertical directions of the image, respectively. These differences represent the gradient of the image in these directions. I[i,j+1]-I[i,j] and |I[i+1,j]-I[i,j] are the differences between adjacent pixels in the horizontal and vertical directions of the image, respectively. These differences represent the gradient of the image in these directions.

[0132] The total loss function is set as:

[0133] L total =λ1L exp +λ2L spa +λ3L smo +λ4L TV

[0134] Where λ1λ2λ3λ4 represent the weight coefficients for balancing the importance of each loss term, and these weight coefficients can be adjusted according to specific task requirements.

[0135] Combined with the comprehensive expression of the above loss functions, the network in this paper not only enhances the brightness of the image, but also maintains the spatial structure and smooth lighting transition of the image, which is crucial to achieving natural and realistic image enhancement effects.

[0136] The specific steps are:

[0137] (1) Training set preparation

[0138] The brightness enhancement network uses a dataset of images captured in a variety of low-light environments, ensuring that the dataset encompasses a variety of lighting conditions and scenarios to enhance the model's generalization capabilities. The present invention preprocesses the image data before inputting it into the network, including standardizing the image size (e.g., 256×256 pixels) and normalizing the pixel values.

[0139] (2) Optimizer settings

[0140] When training the brightness enhancement network model, the Adam optimizer was used. For image enhancement tasks, the learning rate of each parameter was adaptively adjusted by calculating the first-order and second-order moment estimates of the gradient to achieve the optimal image brightness enhancement results.

[0141] (3) Hyperparameter setting

[0142] The specific hyperparameter settings in the network model are: Initial learning rate: set to 0.0001. This is a relatively common starting value, suitable for most cases, and small enough to avoid excessive weight updates in the early stages of training, thereby avoiding potential instability; Batch size: set to 8. It can run effectively on most GPUs while maintaining memory efficiency and sufficient data diversity during training. Smaller batches can provide more frequent model updates, which helps to converge faster; Training cycle (Epochs): set to 40 cycles. This value is determined based on experimental observations and is sufficient to enable the network to converge on a given dataset without overfitting. Regularization technology: L2 regularization is used to prevent model overfitting and improve the generalization ability of the model.

[0143] Step 4: Fusion processing

[0144] After obtaining the image enhanced by the neural network, it is fused with the original image. The weighted average of the pixel values corresponding to the two images is calculated as follows:

[0145]

[0146] Among them I fused (x,y) is the pixel value of the fused image at (x,y), I i (x,y) is the pixel value of the original image and the image after illumination enhancement at (x,y), wi is the corresponding weighting coefficient, which is dynamically adjusted according to the enhancement effect. The enhancement effect is determined by calculating the peak signal-to-noise ratio. The calculation formula for the peak signal-to-noise ratio is:

[0147]

[0148] Where, MAX I is the maximum possible pixel value of the image (such as 255 for an 8-bit image). Where MSE is the mean squared error, calculated as follows:

[0149]

[0150] Here, I is the original image, K is the fused image, and m and n are the number of rows and columns of the image, respectively. After obtaining the peak signal ratio, the weighting coefficient is dynamically adjusted and optimized.

[0151] Step 5: Verify the data enhancement effect after brightness enhancement network training

[0152] After obtaining the fused image, the network model is tested and optimized. According to the training effect and performance of the network model, the parameters are adjusted and continuously tuned. The specific process includes the following steps:

[0153] 1. Data preprocessing and preparation

[0154] The collected low-light image dataset undergoes a series of preprocessing operations. This includes normalizing the pixel values in the images to ensure they are within the range of 0 to 1, thereby ensuring consistency during data processing. Furthermore, the images are resized to 256×256 pixels, as required by the brightness enhancement model. To enhance the diversity of the dataset, data augmentation techniques that do not alter the semantic content of the images are also applied, such as random rotation and flipping.

[0155] 2. Quality Assessment Before Enhancement

[0156] In this step, the present invention establishes a series of quality assessment metrics for brightness enhancement, such as image brightness level, detail visibility, and noise level. The images in the dataset are then preliminarily evaluated using these metrics, and their initial quality status is recorded to provide a reference standard for subsequent comparison of enhancement effects.

[0157] 3. Enhanced Quality Assessment

[0158] The enhanced image quality will be evaluated. To objectively assess the enhancement effect, this paper uses non-reference image quality assessment metrics, such as NIQE and BRISQUE, to measure the image enhancement quality. This paper compares the quality scores before and after enhancement to measure the degree of image brightness improvement and adjusts and optimizes network parameters based on the evaluation results.

[0159] NIQE is a scoring system based on the statistical properties of natural scenes. It does not rely on specific image content or any type of reference image. NIQE works by first learning a statistical model from a set of undistorted images that captures the normal visual quality characteristics of images. This model is then used to evaluate the quality of test images, generating a quality score by comparing the statistical properties of the test image with the learned model. Lower NIQE scores indicate higher image quality, closer to natural perception.

[0160] BRISQUE is also a reference-free image quality assessment algorithm that predicts image quality by analyzing the spatial domain features of the image. BRISQUE focuses on the natural properties of the image, especially the local spatial features of the image, such as the texture and edges of the image. It uses machine learning methods to predict the visual quality of the image and does not require prior knowledge of the distortion type during training. It models some common characteristics of natural images (for example, the edge distribution of the image should conform to specific statistical laws), and then uses this model to evaluate the quality of the test image. The lower the BRISQUE score, the better, indicating that the image quality is closer to the natural state observed by the human eye.

[0161] 4. Domain Adaptability Evaluation and Generalization Ability Test

[0162] The present invention proposes to analyze performance indicators such as accuracy and recall with reference to Table 2 to evaluate the domain adaptability and generalization ability of the model. Based on the test results, the present invention further optimizes the network model or data processing flow.

[0163] Table 2 Performance indicators of brightness enhancement network evaluation

[0164] Performance indicators describe importance Accuracy The proportion of correctly classified samples to the total samples Reflects the overall performance of the model Recall The proportion of correctly identified positive classes Measures the model's ability to identify positive samples Precision The proportion of positive classes that are identified as positive Measures the model's ability to exclude negative samples F1 Score Harmonic mean of precision and recall An indicator that comprehensively considers precision and recall, suitable for unbalanced data sets AUC value (Area Under Curve) The area under the ROC curve measures the overall performance of the classifier Comprehensively evaluate model performance without being affected by decision thresholds

[0165] In summary, the method proposed in the present invention solves the practical technical problem of the present invention. The method of the present invention has been verified through simulation experiments and actual applications, and the technical effects and practicality claimed by the present invention have been verified.

[0166] The algorithm (method) proposed in the present invention is the underlying technical core of the present invention, and various products can be derived based on the algorithm.

[0167] Based on the algorithm (method) proposed in the present invention, a low-light space target image brightness enhancement system is developed using a programming language. The system has program modules corresponding to the steps of the above-mentioned technical solution, and executes the steps of the above-mentioned low-light space target image brightness enhancement method during operation.

[0168] The developed system (software) computer program is stored on a computer-readable storage medium. The computer program is configured to implement the steps of the above-mentioned low-light spatial target image brightness enhancement method when called by a processor. This materializes the present invention on a carrier, becoming a computer program product.

[0169] The present invention also provides a low-light space target image processing device, comprising at least one processor and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the aforementioned low-light space target image brightness enhancement method. The low-light space target image processing device serves as a terminal intelligent product applied by the present invention and is used for oil and gas pipeline network fault diagnosis.

[0170] Various implementations of the systems and techniques described herein can be realized in digital electronic circuitry, integrated circuitry, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0171] The computer programs (also referred to as programs, software, software applications, or code) of the present invention include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0172] It should be understood that the various forms of the above-described processes may be used, and steps may be reordered, added, or deleted. For example, the steps described in this application may be performed in parallel, sequentially, or in a different order. As long as the desired results of the technical solutions disclosed in this application can be achieved, they are all within the scope of protection of the present invention.

Claims

1. A method for enhancing the brightness of a low-light space target image, characterized in that: The method comprises: Step 1: Acquire low-light images Low-light images are defined as those acquired under extremely dim lighting conditions, characterized by an average brightness below 30 luminance units, a signal-to-noise ratio below 20 dB, a contrast ratio below 0.1, a color fidelity CIEDE2000 color difference exceeding 5, and a dynamic range below 40 dB. Furthermore, these images must meet on-orbit requirements, including complex lighting conditions, special target characteristics, and environmental adaptability. Step 2: Build a brightness enhancement network A lightweight convolutional neural network based on unsupervised deep learning and the Retinex algorithm is constructed as a brightness enhancement network, and a lightweight convolutional neural network (CNN) is used to estimate the lighting components of low-light images. The network receives a low-light image as input, decomposes the input image into an illumination layer and a reflection layer, and then outputs the reflection layer as the result of image brightness enhancement; Step 3: Brightness Enhancement Network Model Training During network training, the network is trained using no-reference loss functions such as exposure loss, spatial loss, and illumination smoothness loss to avoid dependence on paired training data. This no-reference loss function can effectively train the network to achieve image enhancement without real-world labels. The exposure loss is used to brighten underexposed areas in the image, the spatial loss ensures spatial consistency after image enhancement, and the illumination smoothness loss encourages smooth changes in the illumination layer to match the natural variations in lighting in the real world. Step 4: Fusion processing After obtaining the image enhanced by the neural network, it is fused with the original image. The pixel values corresponding to the two images are weighted averaged, and the fusion effect is determined by calculating the peak signal-to-noise ratio. If it does not meet the requirements, return to step 3 for network training. Step 5: Verify the data enhancement effect after brightness enhancement network training: After obtaining the fused image, the network model is tested and optimized. Based on the training effect and performance of the network model, the parameters are adjusted and continuously tuned until the enhanced low-light spatial target image quality assessment requirements are met; In step 2, The lightweight convolutional neural network (CNN) is based on the U-Net architecture and is used for illumination estimation in low-light images. The network consists of seven layers, each using a 3×3 convolution kernel. The first six layers have 8 output channels, and the last layer has 1 output channel. The network structure includes skip connections to preserve image details and reduce information loss during training. The brightness enhancement network estimates the illumination and reflection components separately. The illumination estimation uses the deep features extracted by the encoder to estimate the illumination component of the image. The reflection estimation divides the original input image by the estimated illumination component to obtain the reflection component of the image. The established Retinex model is as follows: I=R×L In the formula, the image I is modeled as the element-by-element product of the illumination component L and the reflection component R, where L represents the illumination of the object by the light source, which changes slowly and is evenly distributed; R represents the color and properties of the object itself, which is related to the inherent properties of the object and is not affected by the light intensity. The specific steps in step three are: (1) Initialize the brightness enhancement network model: Based on the pre-defined lightweight convolutional neural network architecture, use the Xavier initialization method to initialize all weights of the brightness enhancement network model; Xavier initialization can ensure that the network weights have a reasonable distribution in the early stage of training, which helps to improve the stability and convergence speed of model training; (2) Define the loss function: Construct a composite loss function including exposure loss, spatial loss, illumination loss, and smoothness loss to optimize the training process of the low-light image brightness enhancement network; the content loss part of the composite loss function is used to ensure that the enhanced image is semantically consistent with the original low-light image and maintain the original information and details of the image; the spatial loss is intended to adjust the overall style of the enhanced image to meet specific visual standards; the regularization term added to the composite loss function helps prevent the network from overfitting and promotes the generalization ability of the model under different low-light conditions; in this way, the composite loss function provides a strong training basis for the effective enhancement of low-light images, thereby achieving high-quality image output; (3) Training and Monitoring: After training is completed, the trained model is used to perform brightness enhancement on actual low-light images. By comparing the enhanced images with the original images, not only the visual effects of the images are evaluated, but also the quality of the generated data, the convergence speed of the model, and the accuracy of style transfer are comprehensively examined to comprehensively evaluate the performance and practicality of the model. (4) Brightness enhancement effect and performance verification: Use the trained brightness enhancement network model to perform brightness enhancement processing on the image of the space target on orbit; by comparing the brightness enhancement image with the original image, the brightness improvement effect is judged, and the image improvement quality, model convergence speed and network noise resistance are considered to comprehensively evaluate the performance of the network model; The brightness network model for high-level enhancement of low-light images is implemented through unsupervised learning training. The core lies in the design of a no-reference loss function. The loss function includes four components: exposure loss, spatial loss, and lighting and smoothing loss: Exposure loss is defined as follows: Where M is the number of non-overlapping local regions where the image is segmented, R k is the average intensity of the kth region in the reflectance image, and E is the preset desired exposure level, set to 0.

6. This loss function improves the overall brightness by enhancing the underexposed areas in the image to achieve the ideal exposure level, which helps to obtain consistent image quality under different brightness conditions. The spatial loss function is defined as follows: Where K is the number of local regions considered in the image, Ω(i) represents the four neighboring regions above, below, left, and right around region i, R and I represent the average local brightness of the enhanced and original images, respectively. This loss maintains the spatial consistency of the enhanced image and the original low-light image, thereby maintaining the integrity of the image structure. The lighting loss function is defined as follows: Where, and are the gradient operations in the horizontal and vertical directions, representing the smoothness of the lighting component L in these two directions; Image smoothing loss function definition: Where: I represents the image, I[i,j] represents the pixel value of the image at position (i,j); this formula calculates the gradient values between all adjacent pixels of the image, sums them and takes the square root, thereby quantifying the overall smoothness of the image; the loss function represents the sum of the intensity differences between adjacent pixels in the image, which represents a measure of the local smoothness of the image; |I[i,j+1]-I[i,j] and |I[i+1,j]-I[i,j] are the differences between adjacent pixels in the horizontal and vertical directions of the image, respectively, and these differences represent the gradients of the image in these directions; I[i,j+1]-I[i,j] and |I[i+1,j]-I[i,j] are the differences between adjacent pixels in the horizontal and vertical directions of the image, respectively, and the differences represent the gradients of the image in these directions; The total loss function is set as: L total =λ1L exp +λ2L spa +λ3L smo +λ4L TV Where λ1λ2λ3λ4 represents the weight coefficients for balancing the importance of each loss term, and these weight coefficients are adjusted according to the specific task requirements; In step 3, the network training was performed on an Ubuntu 20.04 system using the Pytorch deep learning framework and an NVIDIA 3060 GPU. The initial learning rate was set to 0.0001, the batch size was set to 8, the training epoch was 40, and L2 regularization was used. The specific steps of the fusion processing in step 4 are: After obtaining the image with enhanced lighting conditions through the neural network, it is fused with the original image; the pixel values corresponding to the two images are weighted averaged, and the formula is: Among them I fused (x,y) is the pixel value of the fused image at (x,y), I i (x,y) is the pixel value of the original image and the image after illumination enhancement at (x,y), w i is the corresponding weighting coefficient, which is dynamically adjusted according to the enhancement effect. The enhancement effect is determined by calculating the peak signal-to-noise ratio. The calculation formula for the peak signal-to-noise ratio is: Where, MAX I is the maximum pixel value of the image; where MSE is the mean square error, calculated as follows: Where I is the original image, K is the fused image, m and n are the number of rows and columns of the image respectively; after obtaining the peak signal ratio, the weighting coefficient is dynamically adjusted and optimized; The specific process of step five includes the following steps: 1) Data preprocessing and preparation The collected low-light image dataset undergoes a series of preprocessing operations. These include normalizing the pixel values in the images to ensure they are within the range of 0 to 1, thereby ensuring consistency during data processing. Furthermore, the images are resized to 256×256 pixels, as required by the brightness enhancement model. Data augmentation techniques that do not alter the semantic content of the images are also applied to increase the diversity of the dataset, including random rotation and flipping. 2) Quality assessment before enhancement Establish quality assessment metrics for brightness enhancement: image brightness level, detail visibility, and noise level. Then, perform a preliminary evaluation of the images in the dataset using these metrics and record their initial quality status to provide a reference standard for subsequent comparison of enhancement effects. 3) Enhanced quality assessment Use the image quality evaluation index without reference to evaluate or measure the enhanced quality of the enhanced image; compare the quality scores before and after enhancement to measure the degree of image brightness improvement, and adjust and optimize the network parameters based on the evaluation results; The quality assessment indicators of non-reference images include NIQE and / or BRISQUE. NIQE is a scoring system based on the statistical properties of natural scenes and does not rely on specific image content or any type of reference image; BRISQUE is also a reference-free image quality assessment algorithm that predicts image quality by analyzing the spatial domain characteristics of the image; BRISQUE focuses on the natural properties of the image; 4) Domain adaptability evaluation and generalization ability test By quantitatively analyzing performance indicators such as accuracy and recall, the model's domain adaptability and generalization ability are evaluated; based on the test results, the network model and data processing flow are optimized.

2. A low-light space target image brightness enhancement system, characterized by: The system has a program module corresponding to the steps of any one of claim 1, and executes the steps of the low-light space target image brightness enhancement method when running.

3. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is configured to implement the steps of the low-light space target image brightness enhancement method according to any one of claims 1 when called by a processor.

4. A low-light space target image processing device, characterized by: The low-light space target image processing device includes at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the low-light space target image brightness enhancement method described in any one of claim 1.

Images