Low-illumination image enhancement method based on color space transformation

Abstract

The invention discloses a low-illumination image enhancement method based on color space transformation. The method comprises the following steps: acquiring an initial low-illumination image, and preprocessing the initial low-illumination image to obtain an intensity graph of the initial low-illumination image; generating a saturation map according to the intensity map of the initial low-illumination image; generating a hue map based on the saturation map, the intensity map of the initial low-illumination image and the initial low-illumination image; processing the hue image to obtain a horizontal axis set and a vertical axis set of the hue image; and setting an adaptive intensity collapse function of the intensity graph of the initial low-illumination image. According to the invention, the technical problem of low conversion accuracy of converting a low-illumination image into a normal-illumination image in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a low-illumination image enhancement method based on color space transformation. Background Art

[0002] In low-light conditions, imaging sensors usually capture weak light signals with severe noise, resulting in poor visual quality of low-light images. To obtain high-quality images from such poor-quality images, low-light image enhancement (LLIE) is necessary, which aims to increase image brightness while reducing the impact of noise and color deviation. Most existing LLIE methods focus on finding the right image brightness, usually by adopting deep neural networks to learn the mapping between low-brightness images and normal-brightness images in the standard RGB (sRGB) color space; however, in these LLIE methods, image brightness and colors from the three sRGB channels show strong coupling, i.e., high color sensitivity (proposed in the book "Color Computer Vision: Fundamentals and Applications" by Theo Gawels et al.), which leads to obvious color distortion in the restored images; Inspired by the Kubelka-Munk theory, some recent methods attempt to convert images from the sRGB color space to the hue, saturation, and value (HSV) color space; these methods help to achieve brightness enhancement more accurately, but amplify local color space noise, thereby introducing severe artifacts in the results; Specifically, the conversion from sRGB to HSV destroys the continuity of red (red discontinuous noise) and black (black plane noise), resulting in an increase in the Euclidean distance of similar colors and introducing artifacts in the final image; these two types of noise can cause severe artifacts when enhancing images that are mainly red or extremely dark. Summary of the invention

[0003] The embodiment of the present invention provides a low illumination image enhancement method based on color space transformation, so as to at least solve the technical problem of low conversion accuracy of converting low illumination images into normal illumination images in the prior art.

[0004] According to one aspect of an embodiment of the present invention, a method for low-light image enhancement based on color space transformation is provided. The method may include: obtaining an initial low-light image, preprocessing the initial low-light image, and obtaining an intensity map of the initial low-light image; generating a saturation map based on the intensity map of the initial low-light image; generating a tone map based on the saturation map, the intensity map of the initial low-light image, and the initial low-light image; processing the tone map to obtain a horizontal axis set and a vertical axis set of the tone map; setting an adaptive intensity collapse function of the intensity map of the initial low-light image; obtaining a horizontal map and a vertical map based on the adaptive intensity collapse function, the saturation map, the horizontal axis set, and the vertical axis set; splicing the horizontal map and the vertical map to obtain an HV map; constructing a CIDNet convolutional neural network, wherein the CIDNet convolutional neural network includes I- branch, HV-branch and feature fusion layer; input the intensity map of the initial low-illuminance image into the I-branch to obtain a first feature map; input the HV map and the intensity map of the initial low-illuminance image into the HV-branch to obtain a second feature map; input the first feature map, the second feature map, the HV map and the intensity map of the initial low-illuminance image into the feature fusion layer to obtain a first low-illuminance image; perform an inverse HVI transform on the first low-illuminance image to obtain an enhanced map of the initial low-illuminance image; set a first intermediate variable and a second intermediate variable based on the enhanced map of the initial low-illuminance image and an adaptive intensity collapse function; obtain a target normal-lighting image based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhanced map of the initial low-illuminance image.

[0005] Optionally, generating a saturation map based on the intensity map of the initial low-light image includes: determining the pixel value of each pixel of the saturation map based on the maximum pixel value and the minimum pixel value of each pixel in the intensity map of the initial low-light image; and splicing the pixel values ​​of each pixel of the saturation map to obtain the saturation map.

[0006] Optionally, the saturation map, the intensity map of the initial low-light image and the initial low-light image are used to generate a tone map, including: obtaining the pixel value of each pixel in the tone map based on the pixel value of each pixel in the saturation map, the maximum pixel value and the minimum pixel value of each pixel in the intensity map of the initial low-light image, and the R value, G value and B value of each pixel in the initial low-light image; and splicing the pixel values ​​of each pixel in the tone map to obtain the tone map.

[0007] Optionally, the processing of the tone map to obtain a horizontal axis set and a vertical axis set of the tone map includes: converting the hue axis of each pixel in the tone map into polar coordinates to obtain a horizontal axis and a vertical axis of each pixel in the tone map; splicing the horizontal axis of each pixel to obtain a horizontal axis set of the tone map; splicing the vertical axis of each pixel to obtain a vertical axis set of the tone map.

[0008] Optionally, the target normal-light image is obtained based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhancement map of the initial low-light image, including: converting the enhancement map of the initial low-light image into a target HSV image based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhancement map of the initial low-light image; and inversely transforming the target HSV image to obtain the target normal-light image.

[0009] Beneficial effects of the present invention: (1) The initial low-illuminance image is enhanced to obtain an intensity map of the initial low-illuminance image; the intensity map of the initial low-illuminance image is converted into a saturation map and a hue map, so that the low-illuminance image is converted into a normal-illuminance image without being constrained by illumination; (2) When the low-light image is converted to a normal-light image, with red discontinuity and black plane noise in the color space, the hue axis of each pixel of the tone map is processed to obtain the horizontal and vertical maps of the tone map, and the adaptive intensity collapse function of the intensity map of the initial low-light image is introduced to obtain the horizontal and vertical maps; (3) When the low-illumination image is converted to a normal-illumination image and the chromaticity and brightness in the HVI space are low, a CIDNet convolutional neural network is constructed. The intensity map and HV map of the initial low-illumination image and the intensity map of the initial low-illumination image are input into the CIDNet convolutional neural network to obtain an enhanced map of the initial low-illumination image, which more effectively utilizes the chromaticity and brightness information in the HVI space and reduces global color cast and color noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 is a flow chart of a low illumination image enhancement method based on color space transformation according to an embodiment of the present invention; Figure 2 is a schematic diagram of an initial low-light image according to an embodiment of the present invention; Figure 3 sRGB-based transformation schematic diagram of HVI color space according to an embodiment of the present invention; Figure 4 is a schematic diagram of a CIDNet convolutional neural network according to an embodiment of the present invention; Figure 5 is a schematic diagram of a target normal illumination image according to an embodiment of the present invention. DETAILED DESCRIPTION

[0011] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0012] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] Example 1 According to an embodiment of the present invention, a low-light image enhancement method based on color space transformation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system comprising at least one set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0014] Figure 1 is a flow chart of a low illumination image enhancement method based on color space transformation according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps: Step S101: acquiring an initial low-illumination image, and preprocessing the initial low-illumination image to obtain an intensity map of the initial low-illumination image.

[0015] In the technical solution provided in the above step S101 of the present invention, Figure 2 is a schematic diagram of an initial low-illuminance image according to an embodiment of the present invention. The pixel value of each pixel point of the initial low-illuminance image is processed to obtain an expression of the pixel value of each pixel point of the intensity map of the initial low-illuminance image:

[0016] in, is the pixel value of each pixel of the initial low-light image, are the R value, G value and B value of each pixel in the initial low-light image, is the maximum pixel value of each pixel in the intensity map of the initial low-light image, is the maximum value among the R value, G value and B value of each pixel in the initial low-light image.

[0017] Step S102: generating a saturation map according to the intensity map of the initial low-illumination image.

[0018] In the technical solution provided in the above step S102 of the present invention, Figure 3 : is a schematic diagram of sRGB conversion based on the HVI color space according to an embodiment of the present invention, such as Figure 3 (a) in is the intensity map of the initial low-light image, such as Figure 3 (b) in FIG. 1 is an HSV color space image corresponding to the intensity image of the initial low-light image. Each pixel point of the intensity image of the initial low-light image is processed to generate a saturation image.

[0019] Step S103 : generating a tone map based on the saturation map, the intensity map of the initial low-light image, and the initial low-light image.

[0020] In the technical solution provided in the above step S103 of the present invention, each pixel point of the saturation map, each pixel point of the intensity map of the initial low-light image, and each pixel point of the initial low-light image are processed to generate a tone map.

[0021] Step S104, processing the tone map to obtain a horizontal axis set and a vertical axis set of the tone map.

[0022] In the technical solution provided in step S104 of the present invention, if Figure 3 As shown, the hue axis of each pixel point in the tone map is converted into polar coordinates to obtain a horizontal axis set and a vertical axis set of the tone map.

[0023] Step S105: setting an adaptive intensity collapse function of the intensity map of the initial low-illumination image.

[0024] In the technical solution provided in step S105 of the present invention, if Figure 3 As shown in the figure, for the black plane noise problem, the goal is to collapse the area with lower light intensity while retaining the area with higher light intensity; however, the optimal degree of collapse is different in different data sets and networks; therefore, it is very important to adaptively collapse the area through the learning process; for this purpose, an adaptive intensity collapse function of the intensity map of the initial low-light image is introduced to obtain the HVI color space, where the expression of the adaptive intensity collapse function of the intensity map of the initial low-light image is:

[0025] in, is the adaptive intensity collapse function for each pixel of the intensity map of the initial low-light image, is a rational number, .

[0026] Step S106, obtaining a horizontal map and a vertical map based on the adaptive intensity collapse function, the saturation map, the horizontal axis set and the vertical axis set.

[0027] In the technical solution provided in the above step S106 of the present invention, the adaptive intensity collapse function of each pixel point of the intensity map of the initial low-light image, the pixel value of each pixel point in the saturation map, and the horizontal axis of each pixel point in the hue map are calculated, and the expression of the pixel value of each pixel point in the horizontal map is obtained as follows:

[0028] in, represents element-wise multiplication, is the pixel value of each pixel in the horizontal image; The pixel values ​​of each pixel point of the horizontal image are spliced ​​to obtain a horizontal image; The adaptive intensity collapse function of each pixel point of the intensity map of the initial low-light image, the pixel value of each pixel point in the saturation map, and the vertical axis of each pixel point in the hue map are calculated, and the expression of the pixel value of each pixel point in the vertical map is obtained as follows:

[0029] in, is the pixel value of each pixel in the vertical image; The pixel values ​​of each pixel point of the vertical image are spliced ​​to obtain a vertical image.

[0030] Step S107, splicing the horizontal image and the vertical image to obtain an HV image.

[0031] In the technical solution provided in the above step S107 of the present invention, the horizontal graph and the vertical graph are connected through a channel to obtain an HV graph.

[0032] Step S108, constructing a CIDNet convolutional neural network, wherein the CIDNet convolutional neural network includes an I-branch, an HV-branch and a feature fusion layer.

[0033] In the technical solution provided in the above step S108 of the present invention, Figure 4 is a schematic diagram of a CIDNet convolutional neural network according to an embodiment of the present invention, Figure 4 The first line in the figure is the I-branch, the second line is the HV-branch, and the last plus sign indicates the feature fusion layer.

[0034] Step S109: input the intensity map of the initial low-light image into the I-branch to obtain a first feature map.

[0035] In the technical solution provided in step S109 of the present invention, if Figure 4 As shown, the intensity map of the initial low-light image ( Figure 4 The light intensity map in ( ) is input to the I-branch to obtain the first feature map ( Figure 4 in I).

[0036] Step S110 , inputting the HV map and the intensity map of the initial low-light image into the HV-branch to obtain a second feature map.

[0037] In the technical solution provided in step S110 of the present invention, if Figure 4 As shown, the HV diagram ( Figure 4 The HV color map in ( ) and the intensity map of the initial low-light image are input to the HV-branch to obtain the second feature map ( Figure 4 in HV).

[0038] Step S111, inputting the first feature map, the second feature map, the HV map and the intensity map of the initial low-light image into a feature fusion layer to obtain a first low-light image.

[0039] In the technical solution provided in step S111 of the present invention, the first feature map, the second feature map, the HV map and the intensity map of the initial low-light image are input to the feature fusion layer ( Figure 4 ), and obtain the first low-light image.

[0040] Step S112, performing an HVI inverse transform on the first low-illumination image to obtain an enhanced image of the initial low-illumination image.

[0041] In the technical solution provided in step S112 of the present invention, if Figure 4 As shown, the first low-light image is subjected to HVI inverse transformation to obtain an enhanced image of the initial low-light image ( Figure 4 ).

[0042] Step S113, setting a first intermediate variable and a second intermediate variable based on the enhancement map of the initial low-illuminance image and the adaptive intensity collapse function.

[0043] In the technical solution provided in the above step S113 of the present invention, the first intermediate variable and the second intermediate variable are set according to the enhancement map of the initial low-light image and the adaptive intensity collapse function, and the expressions of the first intermediate variable and the second intermediate variable are respectively:

[0044]

[0045] in, is the first intermediate variable, is the second intermediate variable, is the h value of each pixel in the enhanced image of the initial low-light image, is the v value of each pixel in the enhanced image of the initial low-light image, .

[0046] Step S114, obtaining a target normal illumination image based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhancement map of the initial low illumination image.

[0047] In the technical solution provided in the above step S114 of the present invention, the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhancement map of the initial low-light image are processed to obtain a target normal-light image. Figure 5 is a schematic diagram of a target normal illumination image according to an embodiment of the present invention.

[0048] The above method of this embodiment is further introduced below.

[0049] As an optional implementation method, step S102, generating a saturation map based on the intensity map of the initial low-light image, includes: determining the pixel value of each pixel of the saturation map based on the maximum pixel value and the minimum pixel value of each pixel in the intensity map of the initial low-light image; and splicing the pixel values ​​of each pixel of the saturation map to obtain the saturation map.

[0050] In this embodiment, based on the maximum pixel value and the minimum pixel value of each pixel in the intensity map of the initial low-light image, the expression for determining the pixel value of each pixel in the saturation map is:

[0051] in, , is the pixel value of each pixel in the saturation map, is the minimum pixel value of each pixel in the intensity map of the initial low-light image.

[0052] As an optional implementation method, step S103, the tone map is generated based on the saturation map, the intensity map of the initial low-light image and the initial low-light image, including: obtaining the pixel value of each pixel in the tone map based on the pixel value of each pixel in the saturation map, the maximum pixel value and the minimum pixel value of each pixel in the intensity map of the initial low-light image, and the R value, G value and B value of each pixel in the initial low-light image; splicing the pixel values ​​of each pixel in the tone map to obtain the tone map.

[0053] In this embodiment, based on the pixel value of each pixel in the saturation map, the maximum pixel value and the minimum pixel value of each pixel in the intensity map of the initial low-light image, and the R value, G value, and B value of each pixel in the initial low-light image, the expression for the pixel value of each pixel in the tone map is obtained as follows:

[0054] in, is the pixel value of each pixel in the tone map, is the R value of each pixel in the initial low-light image, is the G value of each pixel in the initial low-light image, The B value of each pixel in the initial low-light image, To find the remainder, the result is 6.

[0055] As an optional implementation method, step S104, the processing of the tone map to obtain a horizontal axis set and a vertical axis set of the tone map, includes: performing polar coordinate conversion on the hue axis of each pixel in the tone map to obtain a horizontal axis and a vertical axis of each pixel in the tone map; splicing the horizontal axis of each pixel to obtain a horizontal axis set of the tone map; splicing the vertical axis of each pixel to obtain a vertical axis set of the tone map.

[0056] In this embodiment, the hue axis of each pixel in the hue map is Perform polar coordinate conversion to obtain the horizontal axis of each pixel in the tone map and vertical axis ,in, , .

[0057] As an optional implementation method, step S104, the target normal lighting image is obtained based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhancement map of the initial low-light image, including: based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhancement map of the initial low-light image, converting the enhancement map of the initial low-light image into a target HSV image; inversely transforming the target HSV image to obtain the target normal lighting image.

[0058] In this embodiment, based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the h value of each pixel of the enhanced image of the initial low-light image, the expressions of the H value, S value and V value of each pixel of the target HSV image are obtained:

[0059] in, is the H value of each pixel of the target HSV image, is the S value of each pixel of the target HSV image, is the V value of each pixel of the target HSV image, and It is a custom parameter used to adjust the saturation and brightness of the target HSV image. To find the remainder, remainder 1, concatenate the H value, S value and V value of each pixel of the target HSV image to obtain the target HSV image, and inversely transform the target HSV image to obtain the target normal illumination image, that is, Figure 5 .

[0060] In an embodiment of the present invention, an initial low-illuminance image is obtained, and the initial low-illuminance image is preprocessed to obtain an intensity map of the initial low-illuminance image; a saturation map is generated according to the intensity map of the initial low-illuminance image; a tone map is generated based on the saturation map, the intensity map of the initial low-illuminance image and the initial low-illuminance image; the tone map is processed to obtain a horizontal axis set and a vertical axis set of the tone map; an adaptive intensity collapse function of the intensity map of the initial low-illuminance image is set; a horizontal map and a vertical map are obtained based on the adaptive intensity collapse function, the saturation map, the horizontal axis set and the vertical axis set; the horizontal map and the vertical map are spliced ​​to obtain an HV map; a CIDNet convolutional neural network is constructed, wherein the CIDNet convolutional neural network includes an I-branch, an HV-branch and a feature fusion layer; the intensity map of the initial low-illuminance image is input into the I - branch to obtain a first feature map; input the HV map and the intensity map of the initial low-illuminance image into the HV- branch to obtain a second feature map; input the first feature map, the second feature map, the HV map and the intensity map of the initial low-illuminance image into the feature fusion layer to obtain a first low-illuminance image; perform an HVI inverse transform on the first low-illuminance image to obtain an enhanced map of the initial low-illuminance image; based on the enhanced map of the initial low-illuminance image and an adaptive intensity collapse function, set a first intermediate variable and a second intermediate variable; based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhanced map of the initial low-illuminance image, obtain a target normal-illuminance image, thereby solving the technical problem of low conversion accuracy of converting a low-illuminance image into a normal-illuminance image in the prior art and achieving the technical effect of improving the conversion accuracy of a low-illuminance image into a normal-illuminance image.

[0061] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0062] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0063] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0064] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0065] In addition, each functional unit in each embodiment of the present invention may be integrated into a first processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0066] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A low-light image enhancement method based on color space transformation, characterized in that: include: Acquire an initial low-illumination image, and preprocess the initial low-illumination image to obtain an intensity map of the initial low-illumination image; Generate a saturation map according to the intensity map of the initial low-light image; generating a tone map based on the saturation map, the intensity map of the initial low-light image, and the initial low-light image; Processing the tone map to obtain a horizontal axis set and a vertical axis set of the tone map; Setting an adaptive intensity collapse function of the intensity map of the initial low-light image; A horizontal map and a vertical map are obtained based on the adaptive intensity collapse function, the saturation map, the horizontal axis set and the vertical axis set; The horizontal graph and the vertical graph are spliced ​​together to obtain the HV graph; Construct a CIDNet convolutional neural network, where the CIDNet convolutional neural network includes an I-branch, an HV-branch and a feature fusion layer; Input the intensity map of the initial low-light image into the I-branch to obtain the first feature map; Inputting the HV map and the intensity map of the initial low-light image into the HV-branch to obtain a second feature map; Inputting the first feature map, the second feature map, the HV map, and the intensity map of the initial low-light image into the feature fusion layer to obtain a first low-light image; Performing an HVI inverse transform on the first low-light image to obtain an enhanced image of the initial low-light image; Based on the enhancement map of the initial low-light image and the adaptive intensity collapse function, setting a first intermediate variable and a second intermediate variable; A target normal illumination image is obtained based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhancement map of the initial low illumination image.

2. The method according to claim 1, characterized in that The step of generating a saturation map according to the intensity map of the initial low-light image comprises: Determine the pixel value of each pixel in the saturation map based on the maximum pixel value and the minimum pixel value of each pixel in the intensity map of the initial low-light image; The pixel values ​​of each pixel point of the saturation map are spliced ​​to obtain the saturation map.

3. The method according to claim 2, characterized in that The step of generating a tone map based on the saturation map, the intensity map of the initial low-light image, and the initial low-light image includes: Based on the pixel value of each pixel in the saturation map, the maximum pixel value and the minimum pixel value of each pixel in the intensity map of the initial low-light image, and the R value, G value, and B value of each pixel in the initial low-light image, the pixel value of each pixel in the tone map is obtained; The pixel values ​​of each pixel in the tone map are concatenated to obtain the tone map.

4. The method according to claim 3, characterized in that The tone map is processed to obtain a horizontal axis set and a vertical axis set of the tone map, including: Convert the hue axis of each pixel in the tone map to polar coordinates to obtain the horizontal axis and vertical axis of each pixel in the tone map; The horizontal axes of each pixel are spliced ​​to obtain a set of horizontal axes of the tone map; The vertical axes of each pixel are spliced ​​to obtain the vertical axis set of the tone map.

5. The method according to claim 4, characterized in that The step of obtaining a target normal illumination image based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter and the enhancement map of the initial low illumination image comprises: Based on the first intermediate variable, the second intermediate variable, the first parameter, the second parameter, and the enhancement map of the initial low-light image, converting the enhancement map of the initial low-light image into a target HSV image; The target HSV image is inversely transformed to obtain the target normal lighting image.

6. A computer system, characterized in that include: One or more processors, and a computer-readable storage medium for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method of claim 1.

7. A computer-readable storage medium, characterized in that Computer executable instructions are stored, and when the instructions are executed, they are used to implement the method of claim 1.

8. A computer program product, characterized in that The invention comprises computer executable instructions, which are used to implement the method of claim 1 when being executed.

Images