CN110570384A - A method, device, computer equipment, and computer storage medium for performing illumination equalization processing on scene images - Google Patents

Abstract

the invention relates to the technical field of image processing, and discloses a method and a device for performing illumination equalization processing on a scene image, computer equipment and a computer storage medium. The invention provides a scheme for carrying out self-adaptive correction and improvement on pixel point brightness on the basis of a classical Gamma correction method, can carry out self-adaptive equalization processing on illumination of a scene image on the whole situation and the local situation, namely can self-adaptively improve the contrast of the image according to the contrast relation between the local situation and the whole situation, can realize the purposes of effectively solving the problems of uneven illumination, shadow and the like in the image, and is convenient for practical application and popularization.

Description

A method, device, and computer equipment for performing illumination equalization processing on scene images and computer storage media

technical field

The invention belongs to the technical field of image processing, and in particular relates to a method, a device, a computer device and a computer storage medium for performing illumination equalization processing on a scene image.

Background technique

At present, the application fields of mobile robots are very wide, and most of the application fields are located in outdoor scenes. Therefore, for the scene images obtained by the imaging system carried by the mobile robot and containing the target, there are usually defects due to factors such as backlight, backlight, side light, and optical path occlusion. The resulting images are overall too bright, overall too dark, partly too bright and too dark, and local unevenness, etc., which have adverse effects on the extraction of feature points, target representation, and subsequent target recognition and tracking. Therefore, before performing target recognition and tracking on the scene image, it is first necessary to perform illumination equalization processing on the scene image.

Although there are many ways to improve the light balance and contrast of an image, the most commonly used and effective method is Gamma correction. This method has low computational complexity and obvious improvement in contrast, but at the same time, it also has problems such as poor local adjustment effect and difficult elimination of shadows.

Contents of the invention

In order to solve the problems of poor local adjustment effect and difficult to eliminate shadows existing in current image illumination equalization methods, the purpose of the present invention is to provide a method, device, computer equipment and computer storage medium for performing illumination equalization processing on scene images.

The technical scheme adopted in the present invention is:

A method for performing light equalization processing on a scene image, comprising the following steps:

S101. Obtain a scene image to be processed;

S102. Calculate the brightness average μ of the scene image according to the following formula:

In the formula, M is the total number of horizontal pixels of the scene image, N is the total number of vertical pixels of the scene image, I(x, y) is the input brightness value of the pixel point (x, y), and x is the pixel point The abscissa of (x, y), y is the ordinate of the pixel (x, y);

S103. For each pixel point (x, y) of the scene image, calculate the corresponding correction coefficient γ(x, y) according to the following formula:

In the formula, ε=(μ/k) is the normalization coefficient, and k is a natural number between 120 and 136;

S104. For each pixel point (x, y) of the scene image, correct the corresponding brightness value according to the following formula:

In the formula, O(x, y) is the output brightness value of the pixel point (x, y), and c is a scale factor used to control the global brightness change and is a positive real number not greater than 1;

S105. Outputting the corrected scene image.

Optimally, when the color description mode of the scene image is the RGB color space, before the step S102, the scene image is also converted from the RGB color space to the Lab color space, and then for the L of the scene image For the channel component, light balance correction is realized by performing steps S102-S104, and finally for the scene image, the corrected L channel component is converted to the RGB color space together with the original color component a and color component b.

Further optimized, the scene image is converted from the RGB color space to the Lab color space in the following manner: first from the RGB color space to the XYZ color space, and then from the XYZ color space to the Lab color space;

And convert the scene image from the Lab color space to the RGB color space in the following manner: first convert from the Lab color space to the XYZ color space, and then convert from the XYZ color space to the RGB color space.

Further optimized, after the scene image is converted from the RGB color space to the Lab color space and before step S102 is performed, for each pixel point (x, y) of the scene image, the corresponding input brightness value is according to 255: A scale of 100 is mapped to a value range between 0 and 255;

And after step S104 is executed and before the scene image is converted from the Lab color space to the RGB color space, for each pixel point (x, y) of the scene image, the corresponding input brightness value is converted according to the ratio of 100:255 The scale scale maps to a numerical range between 0 and 100.

Further optimized, after the scene image is converted from the RGB color space to the Lab color space and before step S102 is performed or after the step S104 is performed and before the scene image is converted from the Lab color space to the RGB color space, the The scene image is subjected to histogram equalization processing.

Optimally, in the step S103, the value of k is 128.

Optimally, before the step S104, the scale factor c is calculated according to the following formula:

Another kind of technical scheme that the present invention adopts is:

A device for performing illumination equalization processing on a scene image, comprising an image acquisition module, a brightness average calculation module, a correction coefficient calculation module, a brightness correction processing module, and an image output module connected sequentially through communication;

The image acquisition module is used to acquire scene images to be processed;

The brightness average calculation module is used to calculate the brightness average μ of the scene image according to the following formula:

In the formula, M is the total number of horizontal pixels of the scene image, N is the total number of vertical pixels of the scene image, I(x, y) is the input brightness value of the pixel point (x, y), and x is the pixel point The abscissa of (x, y), y is the ordinate of the pixel (x, y);

The correction coefficient calculation module is used to calculate the corresponding correction coefficient γ(x, y) according to the following formula for each pixel point (x, y) of the scene image:

In the formula, ε=(μ/k) is the normalization coefficient, and k is a natural number between 120 and 136;

The brightness correction processing module is configured to, for each pixel (x, y) of the scene image, correct the corresponding brightness value according to the following formula:

In the formula, O(x, y) is the output brightness value of the pixel point (x, y), and c is a scale factor used to control the global brightness change and is a positive real number not greater than 1;

The image output module is used to output corrected scene images.

Another kind of technical scheme that the present invention adopts is:

A computer device, comprising a communication-connected memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the method steps of performing illumination equalization processing on a scene image as described above .

Another kind of technical scheme that the present invention adopts is:

A computer storage medium. A computer program is stored on the computer storage medium. When the computer program is executed by a processor, the method steps of performing illumination equalization processing on a scene image as described above are implemented.

The beneficial effects of the present invention are:

(1) The present invention provides an adaptive correction and improvement scheme for pixel brightness on the basis of the classic Gamma correction method, which can perform adaptive equalization processing on the illumination of the scene image globally and locally, that is, it can be based on The local and global contrast relationship can adaptively improve the contrast of the image, which can effectively solve the purpose of uneven illumination and shadows in the image, and is convenient for practical application and promotion.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic flowchart of a method for performing illumination equalization processing on a scene image provided by the present invention.

Fig. 2 is a schematic diagram of Gamma responses of different correction coefficients provided by the present invention.

FIG. 3 is a schematic structural diagram of a device for performing illumination equalization processing on a scene image provided by the present invention.

Fig. 4 is a schematic structural diagram of a computer device provided by the present invention.

Detailed ways

The present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments. It should be noted here that the descriptions of these embodiments are used to help understand the present invention, but are not intended to limit the present invention. Specific structural and functional details disclosed herein are for purposes of describing example embodiments of the invention only. However, the invention may be embodied in many alternative forms and should not be construed as limited to the embodiments set forth herein.

It should be understood that in some processes described herein, multiple operations appearing in a specific order are included, but these operations may not be performed in the order they appear in this document or executed in parallel, and the sequence numbers of the operations are S101, S102, etc., It is only used to distinguish different operations, and the sequence number itself does not represent any execution order. Additionally, these flows may include more or fewer operations, and these operations are also performed sequentially or in parallel.

It will be understood that, although the terms first, second etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments of the present invention.

It should be understood that the term "and/or" in this article is only an association relationship describing associated objects, indicating that there may be three relationships, for example, A and/or B may mean: A exists alone, B exists alone, and at the same time There are three situations of A and B. The term "/and" in this article describes another associated object relationship, which means that there can be two relationships, for example, A/ and B, which can mean: A exists alone, and A and B exist alone In both cases, in addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.

It will be understood that when an element is referred to as being "connected," "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. In contrast, when an element is referred to as being "directly connected" or "directly coupled" to another element, there are no intervening elements present. Other words used to describe the relationship between elements should be interpreted in a similar fashion (eg, "between" versus "directly between," "adjacent" versus "directly adjacent," etc.).

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly dictates otherwise. It should also be understood that the terms "comprises", "comprises", "comprises" and/or "comprises" when used herein designate the existence of stated features, integers, steps, operations, elements and/or components, And it does not exclude the existence or addition of one or more other features, numbers, steps, operations, units, components and/or their combinations.

It should also be noted that in some alternative implementations, the functions/acts may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently or may sometimes be executed in the reverse order, depending upon the functions/acts involved.

In the following description specific details are provided to facilitate a thorough understanding of example embodiments. However, it would be understood by those of ordinary skill in the art that example embodiments may be practiced without these specific details. For example, systems may be shown in block diagrams in order not to obscure the examples in unnecessary detail. In other instances, well-known procedures, structures and techniques may not be shown in unnecessary detail in order not to obscure the example embodiments.

Embodiment one

As shown in FIGS. 1-2 , the method for performing illumination equalization processing on a scene image provided in this embodiment may, but is not limited to, include the following steps S101-S105.

S101. Acquire a scene image to be processed.

In the step S101, the scene image may be, but not limited to, an on-site image including a target obtained by an imaging system, and the acquisition method may be but not limited to a conventional method such as importing.

S102. Calculate the brightness average μ of the scene image according to the following formula:

In the formula, M is the total number of horizontal pixels of the scene image, N is the total number of vertical pixels of the scene image, I(x, y) is the input brightness value of the pixel point (x, y), and x is the pixel point The abscissa of (x, y), y is the ordinate of the pixel (x, y).

In the step S102, the input brightness value is the brightness parameter value before processing, and each pixel has a corresponding brightness parameter.

S103. For each pixel point (x, y) of the scene image, calculate the corresponding correction coefficient γ(x, y) according to the following formula:

In the formula, ε=(μ/k) is the normalization coefficient, and k is a natural number between 120 and 136.

In the step S103, the correction coefficient γ is a key parameter in the classical Gamma correction method: when γ>1, the Gamma correction method has a stretching effect on the brightness histogram in the image (even if the brightness is extended to a high brightness value) ; Conversely, when γ<1, the Gamma correction method has a contraction effect on the brightness histogram in the image (that is, the brightness shrinks to a low brightness value). As shown in FIG. 2 , the effect of different correction coefficients on the correction of the scene image is illustrated. Therefore, the core of Gamma correction is to enhance the details of the lower or higher part of the image by selecting an appropriate correction coefficient γ. Usually the correction coefficient γ is an ideal value artificially selected after multiple test comparisons.

However, for the scene image obtained by imaging the movement of the target in the real world, there are different lighting conditions in different images, and in the same image, there are also different lighting distributions such as partial lighting unevenness and shadows. The ideal correction coefficient can be obtained by artificial setting. Therefore, in the step S103, the correction coefficient γ can be changed and adapted according to the brightness information of different pixels through a specific formula, so as to realize the subsequent adaptive Gamma correction: when the illumination is relatively low, γ tends to 0, low light The contrast of some parts can be greatly improved; on the contrary, when the light is relatively high, the contrast improvement effect of the high-light part will be obvious. In addition, after studying the relationship between the average value of the image and the visual characteristics, the inventors found that when the average value of brightness μ>128, it means that the image is brighter as a whole, while the average value of brightness μ≤128 means that the image is brighter on the whole. It is dark, so when the average value is around 128, the visual characteristics of the image with uniform brightness distribution are the best, that is, the preferred value of k is 128.

S104. For each pixel point (x, y) of the scene image, correct the corresponding brightness value according to the following formula:

In the formula, O(x, y) is the output brightness value of the pixel point (x, y), and c is a scale factor used to control the global brightness change and is a positive real number not greater than 1.

In the step S104, since the adaptive correction and improvement of pixel brightness is performed on the basis of the classic Gamma correction method, adaptive equalization processing can be performed on the illumination of the scene image globally and locally, that is, according to the local and local The global contrast relationship adaptively improves the contrast of the image, which can effectively solve the purpose of uneven illumination and shadows in the image. In addition, considering that the overall very dark or particularly bright scene images, such localized adjustments are not perfect for improving the visual characteristics of the scene images, so before the step S104, the scale factor c can also be calculated according to the following formula : That is, when the average brightness μ is smaller, that is, the overall brightness of the scene image is darker, and the scale factor c is larger, the image brightness is improved more obviously; on the contrary, when the average brightness μ is larger, that is, the overall brightness of the scene image is brighter, and the scale factor c is larger. Smaller, the more obvious the suppression of image brightness.

Optimized, considering that the target image collected by the imaging system is usually an RGB (Red, Green, Blue, red, green, blue) three-color image, although the brightness information is contained in the three color spaces, if it is directly compared to The processing will not only increase the computational complexity, but also cause the color distortion of the scene image due to the difference in the color component size of the same pixel point undergoing adaptive equalization of different scales. Therefore, when the color description method of the scene image is RGB color space , then before the step S102, the scene image is also converted from the RGB color space to the Lab color space (i.e. the color has nothing to do with brightness CIE Lab color space, Commission Internationaled'Eclairage Lab color space, International Commission on Illumination color-opposite Space), and then for the L channel component of the scene image, realize illumination balance correction by performing steps S102 to S104, and finally for the scene image, combine the corrected L channel component together with the original color component a and color component b Convert to RGB color space to get the scene image after lighting balance. Since the L channel in the Lab color space is an independent brightness channel, the a channel represents the color range from green to red, and the b channel represents the color range from blue to yellow, so there is no color information in the L channel, and It closely matches the brightness perception in human visual characteristics, so by performing adaptive equalization on the L channel component alone, it can achieve excellent color fidelity while completing the lighting balance of the scene image.

For further optimization, consider that images with RGB color space cannot be directly converted to Lab color space, and images in Lab color space cannot be directly converted to RGB color space, so the scene image is converted from RGB color space in the following manner To Lab color space: first convert from RGB color space to XYZ color space, and then convert from XYZ color space to Lab color space; Color space conversion to XYZ color space, and then conversion from XYZ color space to RGB color space. The XYZ color space is also called SML (Short, Middle, Length, short, medium, and long) color space, which is based on human eyes' perception of short-wave (420-440nm wavelength), medium-wave (530-540nm wavelength) and long-wave ( 560-580nm wavelength) color description method derived from photosensitive stimulation.

Specifically, the RGB color space has the following conventional mapping relationship with the XYZ color space:

Specifically, from the XYZ color space to the Lab color space and from the Lab color space to the XYZ color space, can be calculated by the following conventional formulas:

In the formula, X _n =0.950456, Y _n =1.0, and Z _n =1.088754 are correction coefficients, so that the XYZ color space converted by the above formula has the same range of mapping as the Lab color space.

In addition, considering that the value range of the L channel in the Lab space is 0-100, so after the scene image is converted from the RGB color space to the Lab color space and before step S102 is performed, for each pixel point of the scene image ( x, y), mapping the corresponding input brightness value to a numerical range between 0 and 255 according to the ratio scale of 255:100; and after step S104 will be executed and the scene image will be converted from the Lab color space Before entering the RGB color space, for each pixel point (x, y) of the scene image, the corresponding input brightness value is mapped to a value range between 0 and 100 according to a scale of 100:255. In addition, since the adaptive light equalization is to adjust all the pixels of the scene image one by one, the sudden changes in light and the highlighted parts in the scene usually cause severe responses, resulting in an overshoot phenomenon. After the RGB color space is converted to the Lab color space and before step S102 is performed or after step S104 is performed and the scene image is converted from the Lab color space to the RGB color space, the scene image can also be subjected to histogram equalization processing , in order to make the adjustment result smoother and more natural.

S105. Outputting the corrected scene image.

To sum up, adopting the method for performing illumination equalization processing on scene images provided by this embodiment has the following technical effects:

(1) This embodiment provides an adaptive correction and improvement scheme for pixel brightness on the basis of the classic Gamma correction method, which can perform adaptive equalization processing on the illumination of the scene image globally and locally, that is, it can be based on The local and global contrast relationship can adaptively improve the contrast of the image, which can effectively solve the purpose of uneven illumination and shadows in the image, and is convenient for practical application and promotion.

Embodiment two

As shown in Figure 3, this embodiment provides a device for realizing the illumination equalization processing of scene images described in Embodiment 1, including an image acquisition module, a brightness average calculation module, a correction coefficient calculation module, a brightness correction module, and a sequential communication connection. processing module and image output module;

The image acquisition module is used to acquire scene images to be processed;

The brightness average calculation module is used to calculate the brightness average μ of the scene image according to the following formula:

In the formula, M is the total number of horizontal pixels of the scene image, N is the total number of vertical pixels of the scene image, I(x, y) is the input brightness value of the pixel point (x, y), and x is the pixel point The abscissa of (x, y), y is the ordinate of the pixel (x, y);

The correction coefficient calculation module is used to calculate the corresponding correction coefficient γ(x, y) according to the following formula for each pixel point (x, y) of the scene image:

In the formula, ε=(μ/k) is the normalization coefficient, and k is a natural number between 120 and 136;

The brightness correction processing module is configured to, for each pixel (x, y) of the scene image, correct the corresponding brightness value according to the following formula:

In the formula, O(x, y) is the output brightness value of the pixel point (x, y), and c is a scale factor used to control the global brightness change and is a positive real number not greater than 1;

The image output module is used to output corrected scene images.

For the working process, working details and technical effects of the device provided in this embodiment, please refer to Embodiment 1, which will not be repeated here.

Embodiment three

As shown in Figure 4, this embodiment provides a computer device that applies the method for performing illumination equalization processing on scene images described in Embodiment 1, including a memory and a processor that are connected in communication, wherein the memory is used to store the program, the processor is configured to execute the computer program to implement the method steps of performing illumination equalization processing on the scene image as described in the first embodiment.

The working process, working details and technical effects of the computer device provided in this embodiment can be referred to Embodiment 1, and will not be repeated here.

Embodiment four

This embodiment provides a computer storage medium that stores a computer program including the method for performing illumination balance processing on a scene image described in Embodiment 1, that is, a computer program is stored on the computer storage medium, and the computer program is processed When the device is executed, the method steps of performing illumination equalization processing on the scene image as described in the first embodiment are realized. Wherein, the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices, and may also be a mobile smart device (such as a smart phone, a PAD, or an ipad, etc.).

For the working process, working details and technical effects of the computer storage medium provided in this embodiment, reference may be made to Embodiment 1, which will not be repeated here.

The multiple embodiments described above are only illustrative, and 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 Located in one place, or can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative efforts.

Through the above description of the implementations, those skilled in the art can clearly understand that each implementation can be implemented by means of software plus a necessary general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device execute the methods described in various embodiments or some parts of the embodiments.

The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be described in the foregoing embodiments Modifications to the technical solutions recorded, or equivalent replacements for some of the technical features. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Finally, it should be noted that the present invention is not limited to the above optional embodiments, and anyone can obtain other various forms of products under the enlightenment of the present invention. The above specific implementation methods should not be construed as limiting the protection scope of the present invention. The protection scope of the present invention should be defined in the claims, and the description can be used to interpret the claims.

Claims (10)

1. A method for performing illumination equalization processing on a scene image, comprising the steps of: S101. Obtain a scene image to be processed; S102. Calculate the brightness average μ of the scene image according to the following formula: In the formula, M is the total number of horizontal pixels of the scene image, N is the total number of vertical pixels of the scene image, I(x, y) is the input brightness value of the pixel point (x, y), and x is the pixel point The abscissa of (x, y), y is the ordinate of the pixel (x, y); S103. For each pixel point (x, y) of the scene image, calculate the corresponding correction coefficient γ(x, y) according to the following formula: In the formula, ε=(μ/k) is the normalization coefficient, and k is a natural number between 120 and 136; S104. For each pixel point (x, y) of the scene image, correct the corresponding brightness value according to the following formula: In the formula, O(x, y) is the output brightness value of the pixel point (x, y), and c is a scale factor used to control the global brightness change and is a positive real number not greater than 1; S105. Outputting the corrected scene image. 2. A method for performing illumination equalization processing on a scene image according to claim 1, wherein when the color description method of the scene image is RGB color space, before the step S102, also The scene image is converted from the RGB color space to the Lab color space, and then for the L channel component of the scene image, the illumination balance correction is realized by performing steps S102 to S104, and finally for the scene image, the corrected L channel component Convert to the RGB color space together with the original color component a and color component b. 3. a kind of method that scene image is carried out illumination balance processing as claimed in claim 2, is characterized in that, described scene image is converted to Lab color space by RGB color space as follows: first convert from RGB color space to XYZ color space, and then convert from XYZ color space to Lab color space; And convert the scene image from the Lab color space to the RGB color space in the following manner: first convert from the Lab color space to the XYZ color space, and then convert from the XYZ color space to the RGB color space. 4. A method for performing illumination equalization processing on a scene image as claimed in claim 2, characterized in that, after converting the scene image from the RGB color space to the Lab color space and before performing step S102, for the For each pixel point (x, y) of the scene image, the corresponding input brightness value is mapped to a value range between 0 and 255 according to the scale of 255:100; And after step S104 is executed and before the scene image is converted from the Lab color space to the RGB color space, for each pixel point (x, y) of the scene image, the corresponding input brightness value is converted according to the ratio of 100:255 The scale scale maps to a numerical range between 0 and 100. 5. A method for performing illumination equalization processing on a scene image as claimed in claim 2, characterized in that, after the scene image is converted from the RGB color space to the Lab color space and before step S102 is executed or after the step S102 is executed After step S104 and before converting the scene image from the Lab color space to the RGB color space, perform histogram equalization processing on the scene image. 6. A method for performing illumination equalization processing on a scene image according to claim 1, characterized in that, in the step S103, the value of k is 128. 7. A method for performing illumination equalization processing on a scene image according to claim 1, wherein, before the step S104, the scale factor c is calculated according to the following formula: 8. A device for performing illumination equalization processing on a scene image, characterized in that it includes an image acquisition module, a brightness mean calculation module, a correction coefficient calculation module, a brightness correction processing module, and an image output module that are sequentially connected by communication; The image acquisition module is used to acquire scene images to be processed; The brightness average calculation module is used to calculate the brightness average μ of the scene image according to the following formula: In the formula, M is the total number of horizontal pixels of the scene image, N is the total number of vertical pixels of the scene image, I(x, y) is the input brightness value of the pixel point (x, y), and x is the pixel point The abscissa of (x, y), y is the ordinate of the pixel (x, y); The correction coefficient calculation module is used to calculate the corresponding correction coefficient γ(x, y) according to the following formula for each pixel point (x, y) of the scene image: In the formula, ε=(μ/k) is the normalization coefficient, and k is a natural number between 120 and 136; The brightness correction processing module is configured to, for each pixel (x, y) of the scene image, correct the corresponding brightness value according to the following formula: In the formula, O(x, y) is the output brightness value of the pixel point (x, y), and c is a scale factor used to control the global brightness change and is a positive real number not greater than 1; The image output module is used to output corrected scene images. 9. A computer device, characterized in that it includes a memory and a processor connected by communication, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement any one of claims 1 to 7. The method steps of performing illumination equalization processing on the scene image described in the item. 10. A computer storage medium, characterized in that, a computer program is stored on the computer storage medium, and when the computer program is executed by a processor, the illumination balance of the scene image according to any one of claims 1 to 7 is realized Processed method steps.