Spatial target image enhancement method, program product and medium under low light intensity

Abstract

The present invention relates to an image enhancement method, and more specifically to a method, program product, and medium for enhancing images of space targets under low light intensity. To address the shortcomings of prior art in the difficulty of identifying space targets under low light conditions, the method comprises: reading an original image, converting the color space, generating a binary image, performing contour extraction on the binary image, selecting the outer contour connected region with the largest area as the initial target region; performing adaptive gamma correction on the initial target region to obtain a corrected color component image; generating a composite mask, and performing image fusion using the composite mask, the original image, and the corrected color component image to achieve secondary enhancement effect optimization, and merging channels to obtain an enhanced image of the space target. Also provided are a computer program product and a readable storage medium capable of implementing the above method.

Description

Technical Field

[0001] The present invention relates to an image enhancement method, and in particular to a method, a program product and a medium for enhancing a space target image under low light intensity. Background Art

[0002] Humans use cameras to capture objects in space, providing a more intuitive understanding of space through images. However, during image acquisition, space lighting conditions are complex, including backlighting and sidelighting, as well as insufficient illumination due to obstruction by meteorites. These factors degrade the quality of captured images, making the outlines of space objects unclear. Therefore, image object outline enhancement is crucial to support subsequent low-light tasks, such as target tracking and non-cooperative target pose estimation in space applications.

[0003] To improve the imaging quality of space environments under low illumination, practical low-light, high-quality imaging solutions are essential. Traditional image enhancement algorithms, such as histogram equalization, image sharpening, and gamma correction, typically adopt global brightness and contrast enhancement strategies, but do not fully consider the unevenness of illumination distribution. This results in poor target area restoration and low universality, making spatial target recognition difficult under low-light conditions. In recent years, significant progress has been made in deep learning-based image enhancement methods, such as super-resolution convolutional neural networks (SRCNN), feedforward denoising neural networks (DnCNN), and unsupervised generative adversarial networks (EnlightenGAN). However, these methods still face certain challenges in practical applications, and their maturity and practicality need to be further improved. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art in that space targets are difficult to identify under low light conditions, and to provide a method, program product and medium for enhancing space target images under low light intensity, so as to improve the accuracy of target contour recognition under low light intensity and when the space target and the background color are similar.

[0005] To achieve the above objectives, the present invention provides the following technical solutions:

[0006] A method for enhancing a space target image under low light intensity is characterized in that it comprises the following steps:

[0007] Step 1, read in the original image;

[0008] Step 2: Convert the original image into YCbCr color space, perform threshold segmentation, and generate a binary image;

[0009] Step 3: Perform edge detection on the binary image to obtain an edge detection result image, merge the edge detection result image with the binary image to obtain a binary result image, and filter out isolated noise points in the binary result image;

[0010] Step 4: perform closing and opening morphological operations on the binary result image after filtering out noise points.

[0011] Step 5: extract all contours in the binary result image processed in step 4, calculate the area of the connected region enclosed by each contour, and select the connected region with the largest area as the initial target region;

[0012] Step 6: Fill the small holes in the initial target area to obtain a complete binary image of the target area. ,in, is the pixel position index;

[0013] Step 7: The R, G, and B color component images of the original image Perform adaptive gamma correction separately to obtain the corrected color component images ,in, Represents the color component, ;

[0014] Step 8: Based on the complete target area binary map Get the synthetic mask ;

[0015] Step 9: Using the synthetic mask , the R, G, and B color component images of the original image And the corrected color component images Perform image fusion to obtain a fused image , merge color channels and complete spatial target image enhancement.

[0016] Furthermore, step 7 is specifically as follows:

[0017] Decompose the original image into three color components R, G, and B to obtain the corresponding color component images , and adaptively derive the parameters based on the average grayscale value of each color component , as shown below:

[0018]

[0019] in, are the height and width of the original image respectively;

[0020] Then through the adaptive gamma correction function For color component images Perform correction to obtain the corrected color component image , as shown below:

[0021]

[0022] .

[0023] Furthermore, step 8 is specifically as follows:

[0024] Step 8.1. Detect the complete target area binary image The boundary of the target area is processed by Gaussian blur to obtain the blurred boundary image of the complete target area. ;

[0025] Step 8.2. Obtain the synthetic mask by the following formula :

[0026] .

[0027] Furthermore, in step 9, using 、 as well as Perform image fusion to obtain a fused image , specifically:

[0028] .

[0029] Furthermore, in step 2, the threshold segmentation is specifically as follows: Luminance component map, according to The mean value of the brightness component image is used for threshold segmentation;

[0030] In step 3, the edge detection adopts Canny edge detection; the isolated noise points in the binary result image are filtered out by median filtering;

[0031] Step 4 is as follows: create an ellipse kernel with a radius of 19-22 pixels as a structural element; and then use the ellipse kernel to perform closing and opening morphological operations on the binary result image after filtering out noise points.

[0032] Furthermore, in step 3, the merging method is phase OR;

[0033] In step 4, an ellipse kernel with a radius of 20 pixels is created as a structural element.

[0034] At the same time, the present invention also provides a computer program product, including a computer program, which is special in that when the program is executed by a processor, it implements the steps of the above-mentioned method for enhancing the image of a space target under low light intensity.

[0035] The present invention also provides a computer-readable storage medium having a computer program stored thereon, the special feature of which is that when the program is executed by a processor, the steps of the above-mentioned method for enhancing the image of a space target under low light intensity are implemented.

[0036] Beneficial effects of the present invention:

[0037] 1. The present invention comprehensively applies threshold segmentation, contour extraction, adaptive gamma correction and image fusion technologies to effectively preserve texture details while enhancing spatial targets, restore colors more naturally, and has a simple process with high computational efficiency and significant enhancement effect.

[0038] 2. The present invention adopts an adaptive gamma correction function to enhance the brightness of the target area, and combines it with a synthetic mask for image fusion to further optimize the correction results, thereby effectively restoring more detailed texture and contour information, improving the recognizability of the target area, and thus improving the accuracy of space target detection, pose estimation and other tasks in subsequent applications.

[0039] 3. The present invention performs image fusion on the synthetic mask, the R, G, and B color component images of the original image, and the corrected color component image, which can effectively smooth the color transition at the edge of the target area, and ultimately obtain a more natural low-illumination spatial target image enhancement effect.

[0040] 4. The present invention also provides a computer program product and a computer-readable storage medium capable of executing the above-mentioned method steps, which can promote and apply the method of the present invention to achieve space target image enhancement on corresponding hardware devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Schematic diagram of a flow chart of an embodiment of a method for enhancing a space target image under low light intensity according to the present invention;

[0042] Figure 2 The space target contour image obtained in the embodiment of the space target image enhancement method under low light intensity of the present invention;

[0043] Figure 3 Schematic diagram of the synthetic mask obtained in step 10 of the embodiment of the method for enhancing the image of a space target under low light intensity of the present invention;

[0044] Figure 4 1 is a comparison diagram of the space target image before and after enhancement in an embodiment of the space target image enhancement method under low light intensity of the present invention, wherein (a) is before enhancement and (b) is after enhancement. DETAILED DESCRIPTION

[0045] The method for enhancing space target images under low light intensity in this invention realizes the fully automatic contour extraction of space targets and the adaptive enhancement of target areas. It first converts the image from RGB color space to YCbCr color space, extracts the Y brightness component image, and then sets a threshold based on the mean value of the brightness component to generate a binary image and extract the target contour. The specific process is as follows Figure 1 As shown, the following steps are included:

[0046] Step 1: Read the original image.

[0047] Step 2: Convert the original image from RGB to YCbCr color space. Luminance component map.

[0048] Step 3: Calculation The mean of the brightness component image is used as the threshold for threshold segmentation to generate a binary image.

[0049] Step 4: Use Canny edge detection to process the binary image and obtain the spatial target contour in a low light intensity environment, such as Figure 2 As shown, the result of edge detection is obtained.

[0050] In this embodiment, the effect of using Canny edge detection is better, with a higher signal-to-noise ratio, high positioning accuracy, and strong single-edge response capability. In other embodiments, other edge detection methods such as Sobel edge detection, Roberts edge detection, Marr-Hildreth edge detection, Gaussian Laplace edge detection, and Transformer-based edge detection may also be used.

[0051] Step 5: Merge the edge detection result image with the binary image obtained in step 3 to obtain the final binary result image. Then, apply median filtering to it to remove isolated noise points.

[0052] The way to merge the edge detection result image with the binary image obtained in step 3 is phase OR. Specifically, the binary image consists of 0 and 1, and the edge detection result is also a binary image. Phase OR represents a bitwise OR operation on the pixel values at the corresponding positions. If at least one of the two is 1, the result is 1. If both are 0, the result is 0, that is, 0 or 0 is 0, 0 or 1 is 1, and 1 or 1 is 1.

[0053] Median filtering is a nonlinear smoothing technique that sets the grayscale value of a central pixel to the median of the grayscale values of all pixels within its neighborhood window. It is effective for filtering out "salt and pepper noise" and isolated noise points. In this embodiment, the neighborhood window size is 20×20 pixels, and the default value of padded pixels at the image boundary is 0. Specifically, median filtering selects the central pixel of a digital image and the pixels within its neighborhood window, sorts these pixels by pixel value, and then uses the value of the pixel in the middle as the pixel value of the current central pixel, thereby eliminating isolated noise points.

[0054] Step 6: Perform closing and opening morphological operations on the resulting binary image after filtering out noise. Specifically, create a structuring element. In this embodiment, the structuring element is an elliptical kernel with a radius of 20 pixels. Then, use the elliptical kernel to perform closing and opening morphological operations on the resulting binary image after filtering out noise. In other embodiments of the present invention, elliptical kernels of other sizes with a radius between 19 and 22 pixels may also be used.

[0055] The closing operation first performs a dilation operation on the binary result image, followed by an erosion operation. This is mainly used to fill small holes within the region and connect disconnected parts between objects. The opening operation is the opposite of the closing operation, performing an erosion operation first and then a dilation operation. It is mainly used to remove small objects or noise in the image, smooth the boundaries of the object, and remove small protrusions at the edge. This operation sequence effectively ensures the integrity of the target area.

[0056] Step 7: Extract all contours in the binary result image processed in step 6, calculate the area of the connected region enclosed by each contour, and select the connected region with the largest area in pixels as the initial target region.

[0057] Step 8: Fill the small holes in the initial target area to achieve complete recognition of the target area and obtain a complete binary image of the target area .

[0058] Step 9: Use the adaptive gamma correction function to correct the R, G, and B color components of the original image. Perform correction to obtain the corrected color component image ,in, , representing the three color channels R, G, and B respectively. The adaptive gamma correction function of the present invention is defined as , where the parameters set The average gray value of each color component is adaptively derived, and the three color component images of R, G, and B are Associated with the adaptive gamma correction function to improve the correction effect. The details are as follows:

[0059]

[0060]

[0061]

[0062] in, are the height and width of the original image respectively.

[0063] Step 10: Due to the limited target segmentation accuracy, after adaptive gamma correction, the edge processing effect of the target area is not ideal. To this end, the present invention proposes a method for generating a synthetic mask. The method is as follows: the complete target area binary map obtained in step eight , perform Canny edge detection, use Gaussian function for filtering, that is, perform Gaussian blur processing to smooth edge transition, and obtain a fuzzy boundary image of the complete target area , reuse Get the synthetic mask ,like Figure 3 As shown, the expression is as follows:

[0064]

[0065] in, is the pixel position index.

[0066] Step 11: Optimize the enhancement effect of the spatial target area, and use the synthetic mask, the R, G, B three color component images of the original image and the corrected color component image to perform image fusion to obtain the fused image , expressed as:

[0067]

[0068] Then, the color channels are merged to complete the space target image enhancement and obtain the enhanced space target image, such as Figure 4 As shown in (b), Figure 4 By comparison with (a), it can be seen that the enhancement effect of the present invention is significant.

[0069] The method for enhancing space target images under low light intensity of the present invention can also be formed into a computer program product, comprising a computer program that, when executed by a processor, implements the steps of the method for enhancing space target images under low light intensity. Furthermore, the method for enhancing space target images under low light intensity of the present invention can be implemented in a computer-readable storage medium having a computer program stored therein. The method for enhancing space target images under low light intensity can be stored as a computer program in the computer-readable storage medium. When executed by a processor, the computer program implements the steps of the method for enhancing space target images under low light intensity.

Claims

1. A method for enhancing space target images under low light intensity, characterized in that: The following steps are involved: Step 1, read in the original image; Step 2: Convert the original image into YCbCr color space, perform threshold segmentation, and generate a binary image; Step 3: Perform edge detection on the binary image to obtain an edge detection result image, merge the edge detection result image with the binary image to obtain a binary result image, and filter out isolated noise points in the binary result image; Step 4: perform closing and opening morphological operations on the binary result image after filtering out noise points. Step 5: extract all contours in the binary result image processed in step 4, calculate the area of the connected region enclosed by each contour, and select the connected region with the largest area as the initial target region; Step 6: Fill the small holes in the initial target area to obtain a complete target area binary map T(x,y), where x and y are pixel position indices. Step 7: Decompose the original image into three color components R, G, and B to obtain the corresponding color component image I i (x, y), where i represents the color component, i∈{R,G,B}, and the parameter α is adaptively derived according to the average grayscale value of each color component. i , as shown below: Among them, m and n are the height and width of the original image respectively; Then through the adaptive gamma correction function γ i (x,y) color component image I i (x, y) is corrected to obtain the corrected color component image IG i (x,y), as shown below: Step 8: Obtain a synthetic mask M(x, y) based on the complete target area binary image T(x, y); Step 9: Use the composite mask M(x,y) and the original image's R, G, and B color component images I i (x, y) and the corrected color component image IG i (x,y) performs image fusion to obtain the fused image IE i (x,y), merge color channels and complete spatial target image enhancement.

2. The method for enhancing space target images under low light intensity according to claim 1, characterized in that: Step 8 is as follows: Step 8.

1. Detect the boundary of the complete target region binary image T(x,y) and perform Gaussian blur processing on it to obtain the blurred boundary image B(x,y) of the complete target region; Step 8.

2. Obtain the synthetic mask M(x,y) by the following formula: M(x,y)=[T(x,y)×(1-B(x,y))]+B(x,y).

3. The method for enhancing space target images under low light intensity according to claim 1 or 2, characterized in that: In step 9, using M(x,y), I i (x,y) and IG i (x,y) performs image fusion to obtain the fused image IE i (x,y), specifically: IE i (x,y)=I i (x,y)×(1-M(x,y))+IG i (x,y)×M(x,y).

4. The method for enhancing space target images under low light intensity according to claim 3, characterized in that: In step 2, the threshold segmentation is specifically as follows: taking the Y brightness component image, and performing threshold segmentation according to the mean value of the Y brightness component image; In step 3, the edge detection adopts Canny edge detection; the isolated noise points in the binary result image are filtered out by median filtering; Step 4 is as follows: create an ellipse kernel with a radius of 19-22 pixels as a structural element; and then use the ellipse kernel to perform closing and opening morphological operations on the binary result image after filtering out noise points.

5. The method for enhancing space target images under low light intensity according to claim 4, characterized in that: In step 3, the merging method is phase OR; In step 4, an ellipse kernel with a radius of 20 pixels is created as a structural element.

6. A computer program product comprising a computer program, characterized in that: When the program is executed by a processor, the steps of the method for enhancing the image of a space target under low light intensity described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for enhancing a space target image under low light intensity as claimed in any one of claims 1 to 5 are implemented.

Images