Image processing method, image processing device, electronic device, and storage medium

Abstract

This disclosure provides an image processing method, an image processing apparatus, an electronic device, and a storage medium. The image processing method includes: determining a dark channel image of an input image; determining atmospheric luminance based on the grayscale histogram of the dark channel image; and determining a dehazed image of the input image based on the atmospheric luminance.

Description

Technical Field

[0001] This disclosure relates to the field of image processing, and more specifically, to an image processing method, an image processing apparatus, an electronic device, and a storage medium. Background Technology

[0002] Images taken in hazy weather are often degraded due to atmospheric light. Because images taken in hazy weather are grayish-white and have less edge information, their detectability is significantly reduced. Therefore, research on image dehazing is of significant practical importance. In related image dehazing processes, when a hazy image contains near-white areas (such as white objects) or sky areas, problems such as image oversaturation, blurred boundary areas, color distortion in the sky area, and over-dehazing may occur.

[0003] The above information is presented as background technical information only to aid in understanding this disclosure. No decision or assertion has been made regarding whether any of the above content can be considered as prior art applicable to this disclosure. Summary of the Invention

[0004] Some exemplary embodiments of this disclosure provide an image processing method, image processing apparatus, electronic device, and storage medium to at least solve the above-mentioned problems and / or disadvantages.

[0005] According to some aspects of exemplary embodiments of the present disclosure, an image processing method is provided, comprising: determining a dark channel image of an input image; determining atmospheric luminance based on a grayscale histogram of the dark channel image; and determining a dehazed image of the input image based on the atmospheric luminance.

[0006] In some example embodiments, the step of determining atmospheric luminance based on the grayscale histogram of the dark channel image includes: obtaining a grayscale histogram of the dark channel image based on the statistics of the pixels of the dark channel image; and determining the atmospheric luminance by performing grayscale traversal on the grayscale histogram.

[0007] In some example embodiments, the step of determining the atmospheric luminance by performing grayscale traversal on the grayscale histogram includes: filtering the grayscale histogram; obtaining a first point satisfying a first condition along a first direction by traversing the filtered grayscale histogram along a first direction, wherein the first direction is the direction of decreasing grayscale; determining whether there is a second point corresponding to a trough by continuing to traverse the filtered grayscale histogram along the first direction from the first point, wherein the second point also satisfies a second condition; determining the grayscale value corresponding to the first point as the atmospheric luminance based on the determination that there is no second point, or determining the grayscale value corresponding to the second point as the atmospheric luminance based on the determination that there is a second point.

[0008] In some example embodiments, the steps of determining the gray value corresponding to the first point as the atmospheric luminance based on the determination that there is no second point, or determining the gray value corresponding to the second point as the atmospheric luminance based on the determination that there is a second point, include: determining the gray value corresponding to the second point as the atmospheric luminance based on the existence of a second point corresponding to a trough and satisfying a second condition, wherein the second point is the initial second point in the first direction; and determining the gray value corresponding to the first point as the atmospheric luminance based on the determination that there is no second point corresponding to a trough and satisfying the second condition.

[0009] In some example embodiments, the first condition is that the number of pixels corresponding to the first point is greater than or equal to a first threshold, and the second condition is that the number of pixels corresponding to the second point is less than or equal to a second threshold and the grayscale value corresponding to the second point is greater than or equal to a third threshold.

[0010] In some example embodiments, the step of determining a dehazed image of an input image based on the atmospheric photometric value includes: determining transmittance based on a luminance image of the input image and the atmospheric photometric value; determining transmittance mapping weights based on the transmittance; determining a dehazed luminance image based on the luminance image, the atmospheric photometric value, and the transmittance mapping weights; and determining a dehazed image based at least on a chrominance image of the input image and the dehazed luminance image.

[0011] In some example embodiments, the step of determining transmittance based on the brightness image of the input image and the atmospheric photometric value includes: determining a base transmittance based on the brightness image and the atmospheric photometric value; obtaining a refined transmittance based on the base transmittance; and obtaining the transmittance based on the refined transmittance.

[0012] In some example embodiments, the step of determining transmittance based on the brightness image of the input image and the atmospheric photometric information further includes: determining a fourth threshold for transmittance updating based on the atmospheric photometric information, wherein the fourth threshold is a value greater than 0 and less than or equal to 1; and determining the larger of the transmittance and the fourth threshold as the updated transmittance.

[0013] In some example embodiments, the step of determining a dehazed image based at least on the chroma image of the input image and the dehazed luminance image includes: determining a fusion weight based on the atmospheric luminance and the luminance image; and obtaining the dehazed image by applying an enhanced saturation value and the fusion weight to the chroma image and the dehazed luminance image.

[0014] According to some aspects of some exemplary embodiments of this disclosure, an image processing apparatus is provided, including: a dark channel image determination unit configured to determine a dark channel image of an input image; an atmospheric luminance determination unit configured to determine atmospheric luminance based on a grayscale histogram of the dark channel image; and a dehazing processing unit configured to determine a dehazed image of the input image based on the atmospheric luminance.

[0015] In some example embodiments, the atmospheric luminance determination unit is configured to determine atmospheric luminance based on a grayscale histogram of a dark channel image by: obtaining a grayscale histogram of the dark channel image by statistically analyzing the pixels of the dark channel image; and determining the atmospheric luminance by performing grayscale traversal on the grayscale histogram.

[0016] In some example embodiments, the atmospheric photometric determination unit is configured to determine the atmospheric photometric value based on grayscale traversal of the grayscale histogram by the following operations: filtering the grayscale histogram; obtaining a first point satisfying a first condition in the first direction by traversing the filtered grayscale histogram along a first direction, wherein the first direction is the direction of decreasing grayscale; determining whether there is a second point corresponding to a trough by continuing to traverse the filtered grayscale histogram along the first direction from the first point, wherein the second point also satisfies a second condition; and determining the grayscale value corresponding to the first point as the atmospheric photometric value based on the determination that there is no second point, or determining the grayscale value corresponding to the second point as the atmospheric photometric value based on the determination that there is a second point.

[0017] In some example embodiments, the atmospheric photometric determination unit is configured to determine the gray value corresponding to the first point as the atmospheric photometric value based on the following operations: determining the gray value corresponding to the second point as the atmospheric photometric value based on the determination that a second point does not exist; or determining the gray value corresponding to the second point as the atmospheric photometric value based on the determination that a second point exists: determining the gray value corresponding to the second point as the atmospheric photometric value based on the existence of a second point corresponding to a trough and satisfying a second condition, wherein the second point is the initial second point in a first direction; and determining the gray value corresponding to the first point as the atmospheric photometric value based on the absence of a second point corresponding to a trough and satisfying a second condition.

[0018] In some example embodiments, the first condition is that the number of pixels corresponding to the first point is greater than or equal to a first threshold, and the second condition is that the number of pixels corresponding to the second point is less than or equal to a second threshold and the grayscale value corresponding to the second point is greater than or equal to a third threshold.

[0019] In some example embodiments, the dehazing processing unit is configured to determine a dehazed image of an input image based on the atmospheric photometric by: determining transmittance based on a luminance image of the input image and the atmospheric photometric; determining transmittance mapping weights based on the transmittance; determining a dehazed luminance image based on the luminance image, the atmospheric photometric, and the transmittance mapping weights; and determining the dehazed image based at least on a chrominance image of the input image and the dehazed luminance image.

[0020] In some example embodiments, the dehazing unit is configured to determine transmittance based on a brightness image of an input image and the atmospheric photometric value by: determining a base transmittance based on the brightness image and the atmospheric photometric value; obtaining a refined transmittance based on the base transmittance; and obtaining the transmittance based on the refined transmittance.

[0021] In some example embodiments, the dehazing unit is also configured to determine transmittance based on the brightness image of the input image and the atmospheric photometric based on the following operations: determining a fourth threshold for transmittance updating based on the atmospheric photometric, wherein the fourth threshold is a value greater than 0 and less than or equal to 1; and determining the larger of the transmittance and the fourth threshold as the updated transmittance.

[0022] In some example embodiments, the dehazing processing unit is configured to determine a dehazed image based at least on a chroma image of the input image and a luminance image of the dehazed image by: determining a fusion weight based on the atmospheric luminance and the luminance image; and obtaining the dehazed image by applying an enhanced saturation value and the fusion weight to the chroma image and the luminance image of the dehazed image.

[0023] According to some aspects of some exemplary embodiments of the present disclosure, an electronic device is provided, comprising: at least one processor; and at least one non-volatile memory configured to store computer-executable instructions, wherein the computer-executable instructions, when executed by the at least one processor, cause the at least one processor to perform the image processing method as described above.

[0024] According to some aspects of some exemplary embodiments of the present disclosure, a computer-readable storage medium is provided, wherein instructions in the computer-readable storage medium are executed by at least one processor to cause the at least one processor to perform the image processing method as described above.

[0025] Image processing methods, apparatuses, electronic devices, and storage media according to some example embodiments of this disclosure can determine atmospheric photometric values ​​considering whether an image contains a sky region, providing highly accurate data for subsequent image processing. Furthermore, the processing is simple and does not add excessive additional computation, thus effectively optimizing image processing results while saving computational costs (e.g., in processing time, processing resources, power consumption, component degradation, etc.). Image processing methods, apparatuses, electronic devices, and storage media according to some example embodiments of this disclosure can achieve improved dehazing effects through dark spectral dehazing without introducing color anomalies in the sky region. Image processing methods, apparatuses, electronic devices, and storage media according to some example embodiments of this disclosure can improve the dehazing intensity of the boundary transition regions of the sky region, resulting in a more natural overall effect for the processed image. Image processing methods, apparatuses, electronic devices, and storage media according to some example embodiments of this disclosure can be applied to or are well-suited for many image processing scenarios, such as applications with large sky regions.

[0026] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0027] The above and other aspects, features and advantages of certain embodiments of this disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings, wherein:

[0028] Figure 1 This is a flowchart illustrating an image processing method according to some example embodiments of the present disclosure;

[0029] Figure 2 This is a flowchart illustrating a grayscale traversal process according to some example embodiments of the present disclosure;

[0030] Figure 3 This is a flowchart illustrating the process of determining a dehazed image based on atmospheric photometry according to some example embodiments of the present disclosure;

[0031] Figure 4 This is a block diagram illustrating an image processing apparatus according to some example embodiments of the present disclosure; and

[0032] Figure 5 This is a block diagram illustrating an electronic device according to some example embodiments of the present disclosure. Detailed Implementation

[0033] To enable those skilled in the art to better understand the technical concept of this disclosure, the technical concept of the exemplary embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0034] The example embodiments and the terminology used with respect to some example embodiments are not intended to limit the technology described herein to the specific embodiments, and should be understood to include various modifications, equivalents, and / or alternatives to some example embodiments. As used herein, each of the descriptions such as “A or B,” “at least one of A or B,” “at least one of A and B,” “A, B, or C,” “at least one of A, B, and C,” and “at least one of A, B, or C” may include all possible combinations of the items enumerated together with the corresponding description in the plurality of descriptions. As used herein, terms such as “first” and “second” may be used to simply distinguish one item from another and do not limit the items in other respects (e.g., importance or order).

[0035] Traditional image dehazing methods typically rely on dark channel prior dehazing. However, statistical analysis of tens of thousands of haze-free natural images reveals that for clear, haze-free natural images of non-sky / non-white scenes, any local region always contains one or more pixels with a very low grayscale value, for example, close to zero, in at least one of the RGB color channels. The channel with the lowest grayscale value among the RGB color channels can be termed the dark channel. Although some example embodiments involve the RGB color channel, this disclosure is not limited to this, and other color channels can be used. Traditional dark channel prior dehazing methods may include atmospheric photometric estimation, transmittance calculation, and image restoration processing, as detailed below:

[0036] First, the defogging model used for defogging is shown in equation (1):

[0037]

[0038] Where I(x) represents the observed foggy image; J(x) represents the fog-free image, i.e., the target image; and A represents the atmospheric photometric value (also known as the atmospheric light value). represents transmittance; x represents a pixel.

[0039] The goal of traditional dehazing methods is to recover a hazy image J(x) from a hazy image I(x). In traditional dark channel prior dehazing methods, the dark channel image J is calculated from the original image using equation (2). dark (x):

[0040]

[0041] Where Ω(x) represents a square window centered at pixel x; J C(y) represents any color channel of the hazy image J. That is, c represents a channel among the three RGB color channels, where y represents a pixel within the range of Ω(x).

[0042] The typical atmospheric photometric estimation process includes: acquiring the top 0.1% of pixels in the dark channel image based on their brightness; finding the corresponding point in the original hazy image; and determining the brightness value of the highest-brightness point among the found points as the atmospheric photometric value A. Typically, the atmospheric photometric value is set to 255.

[0043] After determining the atmospheric photometric value, the transmittance is calculated using equation (3):

[0044]

[0045] The parameter ω is used to adjust the degree of defogging. It is a value that is greater than or equal to 0 and less than or equal to 1. When ω is 0, it means no defogging; when ω is 1, it means full defogging.

[0046] Finally, the foggy image is restored to a fog-free image using equation (4):

[0047]

[0048] To avoid overexposure of the haze-free image J, a constant value t0 is introduced, which is usually 0.1.

[0049] Traditional dark channel prior dehazing methods can achieve dehazing, but because they are statistically based and rely on statistical results from a large number of hazy images, their application is limited. For example, in images containing areas similar to atmospheric lighting (e.g., large areas of near-white patterns) or sky regions, traditional dark channel prior dehazing methods do not address these types of hazy images. Therefore, using traditional dark channel prior dehazing methods on such hazy images will not yield satisfactory results. For instance, in the case of the aforementioned hazy images, the dark channel priority rule may fail, resulting in image oversaturation, blurred boundaries, and noticeable color distortion in the sky.

[0050] In summary, given the significant risk of dehazing failure and the limited application of dehazing processing in existing image processing methods, dehazing image processing for foggy images with scenes similar to atmospheric lighting is particularly important. This disclosure addresses the aforementioned problems in related technologies by proposing an image processing method, image processing apparatus, electronic device, and storage medium based on the histogram of dark channel images to determine atmospheric luminosity. The following will refer to… Figures 1 to 4Image processing methods, image processing apparatuses, electronic devices, and storage media according to some example embodiments of the present disclosure will be described in detail.

[0051] It should be understood that the above application scenarios are merely examples, and the application scenarios described are not limited to those described in the example embodiments of this disclosure. In the following description, although image processing considering sky regions is described according to some example embodiments of this disclosure, those skilled in the art will understand that this description is merely exemplary, and sky regions may include, but are not limited to, any other image regions. Furthermore, in the following description, a luminance image may represent an image in the luminance domain or the luminance component (Y) of a corresponding image, and a chrominance image may represent an image in the chrominance domain or the chrominance component (UV) of a corresponding image.

[0052] First, refer to Figures 1 to 3 This document describes image processing methods according to some example embodiments of the present disclosure.

[0053] Figure 1 This is a flowchart illustrating an image processing method according to some example embodiments of the present disclosure.

[0054] Reference Figure 1 In operation S101, the dark channel image of the input image is determined. Here, the input image according to some example embodiments of this disclosure may include a hazy image to be processed, such as, but not limited to, the original image I in RGB format. For example, the dark channel image J of the input image I in RGB format can be calculated by the above equation (2). dark This will not be described again here.

[0055] In operation S102, atmospheric luminosity is determined based on the grayscale histogram of the dark channel image. According to some example embodiments of this disclosure, atmospheric luminosity may include the grayscale value of the brightest point in a non-sky region. Since the grayscale histograms of different dark channel images may differ significantly, atmospheric luminosity according to some example embodiments of this disclosure can be determined based on the grayscale histogram of the dark channel image.

[0056] According to some example embodiments of this disclosure, the step of determining atmospheric luminance based on the grayscale histogram of the dark channel image may include: obtaining a grayscale histogram of the dark channel image by statistically analyzing the pixels of the dark channel image based on the grayscale (or grayscale value) of each pixel; and determining the atmospheric luminance by performing grayscale traversal on the grayscale histogram.

[0057] For example, a grayscale histogram of a dark channel image can be used to represent the relationship between the frequency of each gray level and the grayscale value in the dark channel image. The horizontal axis of the grayscale histogram represents the grayscale value, which is between 1 and 255; the higher the grayscale value, the brighter the image. The vertical axis of the grayscale histogram represents the number of pixels and reflects the frequency of pixels with the same grayscale value; the more pixels corresponding to a certain grayscale value, the higher the frequency of pixels corresponding to that grayscale value.

[0058] Having obtained the grayscale histogram of the dark channel image, the atmospheric luminosity used for subsequent image processing can be determined by performing grayscale traversal on the grayscale histogram. The following will refer to... Figure 2 The steps for determining the atmospheric luminosity by performing grayscale traversal on the grayscale histogram are described in detail.

[0059] Figure 2 This is a flowchart illustrating a grayscale traversal process according to some example embodiments of the present disclosure. Figure 2 Show Figure 1 Description of operation S102.

[0060] Reference Figure 2 According to some exemplary embodiments of this disclosure, from Figure 1 Starting from operation S101, in step S201, the grayscale histogram is filtered. For example, firstly, the grayscale histogram of the obtained dark channel image can be filtered to obtain a smooth curve. For example, the filtering method includes, but is not limited to, Gaussian filtering. By using Gaussian filtering, which is a relatively simple filtering process, to filter the grayscale histogram, a filtered grayscale histogram that retains more of the original shape can be obtained.

[0061] Then, having obtained the filtered grayscale histogram, the filtered grayscale histogram can be traversed along a first direction of decreasing grayscale, that is, traversing the grayscale histogram along the horizontal axis from the brightest value to the lowest value (e.g., the direction of decreasing grayscale) to find candidate points for determining atmospheric luminosity. According to some example embodiments of this disclosure, candidate points for determining atmospheric luminosity can be defined as the brightest points in non-sky regions, which may include, but are not limited to, the brightest points in non-sky regions when there are sky regions in the image and / or the brightest points in the overall image when there are no sky regions in the image.

[0062] In operation S202, by traversing the filtered grayscale histogram along the first direction, the first point that satisfies the first condition in the first direction is obtained, where the first direction is the direction of grayscale decrease.

[0063] For example, according to some exemplary embodiments of this disclosure, the first point in the traversal process with a number of pixels greater than or equal to a first threshold (e.g., the first point with a ordinate greater than or equal to the first threshold in the opposite direction of the horizontal axis) can be determined as the first point. This first point can be considered as the brightest point in the overall image when there is no sky region in the image (e.g., including but not limited to cases where there is no sky region in the image, or the influence of the sky region in the image on image processing can be ignored). According to some exemplary embodiments of this disclosure, the first condition can be, but is not limited to, the number of pixels corresponding to the first point being greater than or equal to the first threshold. Here, the first threshold can be a value preset based on experience, or optionally, a desired or selected value, for example, the first threshold is 10, 12, etc.

[0064] Having determined the first point, the traversal process continues from the first point along the first direction of decreasing grayscale. In operation S203, by continuing to traverse the filtered grayscale histogram from the first point along the first direction, it is determined whether there exists a second point corresponding to the trough that satisfies the second condition.

[0065] For example, according to some exemplary embodiments of this disclosure, it can be determined whether there is a second point satisfying the second condition among one or more points corresponding to one or more troughs in the continued traversal process (e.g., one or more troughs in the opposite direction of the horizontal axis from the first point), wherein the one or more points can be considered as one or more bright spots in the non-sky region when there is a sky region in the image (e.g., including but not limited to, the presence of a sky region in the image, or the need to consider the influence of the sky region in the image on image processing), that is, it is determined whether there is a second point satisfying the second condition among one or more bright spots in the above situation.

[0066] Using a second point that takes the sky region into account to determine atmospheric photometric accuracy is generally more accurate than using a first point that does not consider the sky region. However, in image processing, the original image does not always include the sky region; in such cases, using a second point to determine atmospheric photometric accuracy may not be highly accurate. Furthermore, multiple bright spots corresponding to troughs may be identified, but only one of these bright spots can be used as a reference bright spot for atmospheric photometric accuracy. Therefore, by using a second condition, it can be determined whether a second point exists among the one or more points corresponding to one or more troughs that satisfies the second condition. Based on the determination of the existence of the second point, the gray value corresponding to either the first or second point can be determined as the atmospheric photometric accuracy with higher precision.

[0067] In operation S204, based on the result of the judgment on whether the second point exists in operation S203, the gray value corresponding to the first point or the second point is determined as the atmospheric photometric value.

[0068] According to some example embodiments of this disclosure, the step of determining the gray value corresponding to the first point or the second point as the atmospheric luminance based on the determination result may include: if there exists a second point corresponding to a trough that satisfies a second condition, then the gray value corresponding to the first second point in the first direction is determined as the atmospheric luminance; and if there is no second point corresponding to a trough that satisfies the second condition, then the gray value corresponding to the first point is determined as the atmospheric luminance. According to some example embodiments of this disclosure, the second condition may be, but is not limited to, the number of pixels corresponding to the second point being less than or equal to a second threshold and the gray value corresponding to the second point being greater than or equal to a third threshold. In some example embodiments, the second threshold and the third threshold may be values ​​preset based on experience, or optionally, expected or selected values; for example, the second threshold may be 160 and the third threshold may be 128.

[0069] For example, the existence of a second point corresponding to a trough that satisfies the second condition can indicate the presence of a brightest point in a qualified non-sky region. For instance, the brightest point in a non-sky region suitable for determining atmospheric luminance could be the grayscale value corresponding to the first second point in a first direction of grayscale reduction. Therefore, in some example embodiments, the second point can be used to determine atmospheric luminance. The absence of a second point corresponding to a trough that satisfies the second condition can indicate the absence of a non-sky region or the failure to find a brightest point in a non-sky region. Therefore, in some example embodiments, it can be assumed that there is no brightest point in a sky region, and the grayscale value corresponding to the first point can be used to determine atmospheric luminance. In this way, the estimation of atmospheric luminance by traversal processing (e.g., by improving the selection criteria for atmospheric luminance as described in some example embodiments) improves upon the conventional atmospheric luminance estimation method that selects the top 0.1% of pixels.

[0070] Image processing methods according to some example embodiments of this disclosure can determine atmospheric photometric values ​​taking into account whether an image contains sky regions, providing highly accurate data for subsequent image processing. Furthermore, the processing methods are simple and do not add excessive additional computation, thereby saving computational costs while effectively optimizing and / or improving the image processing results. For example, the processing methods described in this disclosure can be used to improve the power consumption, processing time, and / or lifetime efficiency of electrical components.

[0071] After operations S103 and S204, a dehazed image of the input image is determined based on the atmospheric photometric values. The following will refer to... Figure 3 The steps for determining the dehazed image of the input image based on the atmospheric photometric information are described in detail.

[0072] Figure 3This is a flowchart illustrating the processing of a dehazed image based on atmospheric photometry according to some example embodiments of the present disclosure. Figure 3 Show Figure 1 Description of operation S103.

[0073] Reference Figure 3 According to some example embodiments of this disclosure, starting from operation S102, in step S301, transmittance is determined based on the luminance image of the input image and the atmospheric photometric value. In some example embodiments, when the input image is an RGB image, the RGB image can be converted into a luminance image and a chrominance image of the input image. Dehazing is performed based on the luminance image of the input image, and finally, the chrominance image of the input image is combined with the dehazed luminance image to determine the final dehazed image. In addition to the meaning as will be understood by those skilled in the art, an RGB image may also refer to an image including image data related to red (R), green (G), and blue (B) color levels. In addition to the meaning as will be understood by those skilled in the art, a luminance image may also refer to an image including image data related to luminance, or black and white, or achromatic levels. In addition to the meaning as will be understood by those skilled in the art, a chrominance image may also refer to an image including image data related to color levels.

[0074] According to some example embodiments of this disclosure, the step of determining transmittance based on a brightness image of an input image and the atmospheric photometric value may include: determining a base transmittance based on the brightness image and the atmospheric photometric value; obtaining a refined transmittance based on the base transmittance; and obtaining the transmittance based on the refined transmittance.

[0075] For example, in some exemplary embodiments, the basic transmittance t is determined based on the brightness image and the atmospheric photometric using equation (5). base :

[0076] t base =1-ω×Y / A (5)

[0077] Wherein, ω is a parameter used to adjust the degree of dehazing, which is a value preset based on experience, or optionally, a desired or selected value, and can be a value less than or equal to 1 and greater than or equal to 0. For example, ω can be 0.9; Y is the brightness image of the input image; A is the atmospheric luminosity determined in operation S102.

[0078] Then, refined transmittance is obtained by filtering the base transmittance. For example, filtering methods include, but are not limited to, directed filtering.

[0079] Then, the transmittance used for image processing is determined by taking the absolute value of the refined transmittance.

[0080] Furthermore, if the transmittance is too low, the resulting haze-free image may be overexposed, and noise will be more noticeable. Therefore, a fourth threshold can be used to avoid calculating the transmittance to be too low, and a fourth threshold is set to determine an appropriate or minimum transmittance. According to some example embodiments of this disclosure, the step of determining the transmittance based on the brightness image of the input image and the atmospheric photometric value may further include: determining a fourth threshold for transmittance updating based on the atmospheric photometric value, wherein the fourth threshold is a value greater than 0 and less than or equal to 1; and determining the larger value of the transmittance and the fourth threshold as the updated transmittance.

[0081] For example, the fourth threshold T4 can be determined by the following equation (6):

[0082] T4= min(1-A / 256+T_p,1) (6)

[0083] Where T_p is a constant value preset based on experience, or optionally, a desired or selected value; and A is the atmospheric luminosity determined in operation S102.

[0084] In this way, by taking into account the degree of dehazing and the lower limit of transmittance, a more appropriate transmittance can be determined and (e.g., adjusted in a timely or rapid manner) to improve the accuracy of image processing, avoid excessive dehazing of the recovered haze-free image due to excessively low transmittance, and improve resource allocation, such as the resource allocation of the processing circuitry configured to perform transmittance determination. The transmittance determination described above according to some example embodiments of this disclosure is merely illustrative, and those skilled in the art can determine transmittance in any other suitable manner.

[0085] In operation S302, the transmittance mapping weight is determined based on the transmittance. For example, the transmittance mapping weight w_t can be determined based on the transmittance determined in operation S301 using equation (7):

[0086] w_t=1-a×log(t) (7)

[0087] Where t is the transmittance determined as described above; a is a constant value preset based on experience, for example, a can be 1.5.

[0088] In operation S303, a dehazed brightness image is determined based on the brightness image, the atmospheric photometric value, and the transmittance mapping weights. For example, the dehazed brightness image is obtained by calculating the photometric image based on the atmospheric photometric value and transmittance mapping weights determined according to the method described above. According to some example embodiments of this disclosure, the dehazed brightness image Y_d can be determined by equation (8):

[0089] Y_d=(YA)×w_t+A (8)

[0090] Where A is the atmospheric photometric value determined / updated in operation S102; and Y is the brightness image of the input image.

[0091] Then, in operation S304, a dehazed image is determined based at least on the chroma image of the input image and the dehazed luminance image. In other words, given the dehazed luminance image, the final dehazed image is determined based on the chroma image and the dehazed luminance image.

[0092] According to some example embodiments of this disclosure, the step of determining a dehazed image based at least on the chroma image of the input image and the dehazed luminance image includes: determining a fusion weight based on the atmospheric luminance and the luminance image; and obtaining the dehazed image by applying an enhanced saturation value and the fusion weight to the chroma image and the dehazed luminance image.

[0093] For example, according to some example embodiments of this disclosure, the fusion weight can be a value used to measure the degree of fusion of a dehazed brightness image. As an example, the fusion weight w can be determined by equation (9). a :

[0094]

[0095] Where A is the atmospheric luminosity determined in operation S102; Y is the luminance image of the input image; and deta is a constant value preset based on experience, or optionally, a desired or selected constant value.

[0096] Then, the luminance image J_Y and chrominance images J_U and J_V of the dehazed image are determined by equation (10):

[0097]

[0098] Wherein, U is the U component of the chroma image, V is the V component of the chroma image, and sat is the enhancement saturation value used to enhance the saturation of the chroma image. It can be a value preset based on experience, or optionally, a desired or selected value, and for example, it can be a value between 0.5 and 1.

[0099] By considering fusion weights and saturation enhancement to determine the final dehazed image, the restoration of hazy images can be improved, and the impact of image processing on the original image can be reduced.

[0100] In summary, according to some exemplary embodiments of this disclosure, atmospheric photometric intensity can first be determined by processing the RGB image of the input image, and then, for example, the chromaticity image and the dehazed brightness image can be determined by processing the YUV image of the input image based on the atmospheric photometric intensity, thus finally obtaining the dehazed image.

[0101] Image processing methods according to some example embodiments of this disclosure can achieve improved dehazing effects through dark primary color dehazing while maintaining a consistent sky color (e.g., without introducing color anomalies in sky areas). Image processing methods according to some example embodiments of this disclosure can increase the dehazing intensity in the boundary transition regions of the sky area, resulting in a more natural overall effect for the processed image. Image processing methods according to some example embodiments of this disclosure can be applied to and / or are well-suited to many image processing scenarios, such as image processing scenarios with large areas of sky.

[0102] Figure 4 This is a block diagram illustrating an image processing apparatus according to some example embodiments of the present disclosure.

[0103] Reference Figure 4 The image processing apparatus 400 according to some example embodiments of the present disclosure may include a dark channel image determination unit 401, an atmospheric photometric determination unit 402, and a dehazing processing unit 403.

[0104] The dark channel image determination unit 401, according to some exemplary embodiments of the present disclosure, can be configured to determine the dark channel image of an input image. The atmospheric photometric determination unit 402, according to some exemplary embodiments of the present disclosure, can be configured to determine atmospheric photometric values ​​based on the grayscale histogram of the dark channel image. The dehazing processing unit 403, according to some exemplary embodiments of the present disclosure, can be configured to determine a dehazed image of the input image based on the atmospheric photometric values.

[0105] In other words, the dark channel image determination unit 401 can perform the same operation as described above. Figure 1 The image processing method operation S101 corresponds to the operation performed by the atmospheric photometric determination unit 402, as described above. Figure 1 and Figure 2 The image processing method operation S102 corresponds to the operation performed by the dehazing unit 403 as described above. Figure 1 and Figure 3 The image processing method described in step S103 involves corresponding operations.

[0106] According to some example embodiments, the dark channel image determination unit 401 and / or the image processing device 400 can receive input image data of an input image. The input image data may include image data related to the hazy image. The input image data may include or be accompanied by instructions for the image processing device 400 and / or the dark channel image determination unit 401 to perform operations related to... Figure 1 The signals, commands, data, or other features of the processing described in the other example embodiments above. In other words, the image processing apparatus 400 can perform the disclosed operations on the received image data.

[0107] In some example embodiments, the dark channel image determination unit 401 can perform the same actions as described above. Figure 1 The image processing method operates accordingly in S101, and can send a determined dark channel image (for example, to the atmospheric brightness determination unit 402).

[0108] According to some example embodiments of this disclosure, the atmospheric photometric determination unit 402 can receive a determined dark channel image sent by the dark channel image determination unit.

[0109] In some example embodiments, the atmospheric luminance determination unit 402 is configured to determine atmospheric luminance based on the grayscale histogram of the dark channel image by: statistically analyzing the pixels of the dark channel image based on the grayscale values ​​of each pixel to obtain the grayscale histogram of the dark channel image; and determining the atmospheric luminance by performing grayscale traversal on the grayscale histogram.

[0110] According to some example embodiments of this disclosure, the atmospheric photometric determination unit 402 is configured to determine the atmospheric photometric value by performing grayscale traversal on the grayscale histogram through the following operations: filtering the grayscale histogram; obtaining a first point satisfying a first condition in the first direction by traversing the filtered grayscale histogram along a first direction, wherein the first direction is the direction of decreasing grayscale; determining whether there exists a second point corresponding to a trough that satisfies a second condition by continuing to traverse the filtered grayscale histogram along the first direction from the first point; and determining the grayscale value corresponding to the first point or the second point as the atmospheric photometric value based on the result of the determination. In some example embodiments, the atmospheric photometric determination unit 402 may (e.g., send the determined atmospheric photometric value to the defogging processing unit 403).

[0111] According to some example embodiments of this disclosure, the atmospheric photometric determination unit 402 is configured to determine the gray value corresponding to the first point or the second point as the atmospheric photometric value based on the result of the determination by the following operations: if there exists a second point corresponding to a trough that satisfies a second condition, then the gray value corresponding to the first second point in the first direction is determined as the atmospheric photometric value; and if there is no second point corresponding to a trough that satisfies the second condition, then the gray value corresponding to the first point is determined as the atmospheric photometric value. In some example embodiments, the atmospheric photometric determination unit 402 may (e.g., send the determined atmospheric photometric value to the defogging processing unit 403).

[0112] According to some example embodiments of this disclosure, the first condition is that the number of pixels corresponding to the first point is greater than or equal to a first threshold, and the second condition is that the number of pixels corresponding to the second point is less than or equal to a second threshold and the gray value corresponding to the second point is greater than or equal to a third threshold.

[0113] According to some exemplary embodiments of this disclosure, the dehazing processing unit 403 may receive (e.g., from the atmospheric photometric determination unit 402) transmitted, determined atmospheric photometric values. According to some exemplary embodiments of this disclosure, the dehazing processing unit 403 is configured to determine a dehazed image of an input image based on the atmospheric photometric values ​​by: determining transmittance based on a luminance image of the input image and the atmospheric photometric values; determining transmittance mapping weights based on the transmittance; determining a dehazed luminance image based on the luminance image, the atmospheric photometric values, and the transmittance mapping weights; and determining the dehazed image based at least on a chrominance image of the input image and the dehazed luminance image. According to some exemplary embodiments of this disclosure, the dehazing processing unit 403 is configured to output the dehazed image and / or dehazed image data of the input image to an external device (e.g., a processor and / or display of an electronic device not shown herein). In some exemplary embodiments, the dehazing processing unit 403 may send the dehazed image data of the dehazed image to an external device (e.g., a processor and / or display of an electronic device not shown herein).

[0114] According to some example embodiments of this disclosure, the dehazing unit 403 is configured to determine transmittance based on a brightness image of an input image and the atmospheric photometric value by: determining a base transmittance based on the brightness image and the atmospheric photometric value; obtaining a refined transmittance based on the base transmittance; and obtaining the transmittance based on the refined transmittance.

[0115] According to some example embodiments of this disclosure, the dehazing unit 403 is also configured to determine transmittance based on a brightness image of an input image and the atmospheric photometric by: determining a fourth threshold for transmittance updating based on the atmospheric photometric, wherein the fourth threshold is a value greater than 0 and less than or equal to 1; and determining the larger of the transmittance and the fourth threshold as the updated transmittance.

[0116] According to some example embodiments of this disclosure, the dehazing processing unit 403 is configured to determine a dehazed image based at least on a chroma image of an input image and a luminance image of the dehazed image by: determining a fusion weight based on the atmospheric luminance and the luminance image; and obtaining the dehazed image by applying an enhanced saturation value and the fusion weight to the chroma image and the luminance image of the dehazed image.

[0117] Regarding the image processing apparatus 400 in the above embodiments, the specific manner in which each unit performs its operations has been described in detail in some example embodiments of related image processing methods, and will not be elaborated upon here.

[0118] Furthermore, it should be understood that the various units in the image processing apparatus 400 according to some example embodiments of this disclosure may be implemented as hardware components and / or software components. Those skilled in the art, based on the processing performed by the defined various units, may implement the various units, for example, using a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). In some example embodiments, the dark channel image determination unit 401, the atmospheric photometric determination unit 402, and the dehazing processing unit 403 may be implemented as separate components or may be combined with each other. In some example embodiments, one of the dark channel image determination unit 401, the atmospheric photometric determination unit 402, and the dehazing processing unit 403 may perform some or all of the functions of the other three units as disclosed above.

[0119] Figure 5 This is a block diagram illustrating an electronic device according to some example embodiments of the present disclosure.

[0120] Reference Figure 5 Furthermore, an electronic device 10 is also provided. The electronic device 10 includes at least one processor 200 and at least one memory 300, wherein the at least one memory 300 includes at least one non-volatile memory storing computer-executable instructions, wherein the computer-executable instructions, when executed by the at least one processor 200, cause the at least one processor 200 to perform the image processing method described above. That is, the processor 200 may include... Figure 4The image processing apparatus 400 has a corresponding image processing unit 410, which can perform its functions, or alternatively, the processor 200 can instruct the image processing apparatus 400 to perform the image processing method as described above.

[0121] According to some example embodiments of this disclosure, the electronic device may be a PC computer, a tablet device, a personal digital assistant, a smartphone, and / or other devices capable of executing the aforementioned set of instructions. Here, the electronic device is not necessarily a single electronic device, but may be any collection of devices or circuits capable of executing the aforementioned instructions (or instruction sets) individually or in combination. The electronic device may also be part of an integrated control system or system manager, or may be configured to interconnect with a portable electronic device locally or remotely (e.g., via wireless transmission) through an interface.

[0122] In an electronic device, processor 200 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, and / or a microprocessor. By way of example and not limitation, processor 200 may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, etc.

[0123] The processor 200 can execute instructions or code stored in the memory 300, which can also store data. Instructions and data can also be sent and received over a network via a network interface device, which can employ any known transmission protocol.

[0124] Memory 300 may include non-volatile memory and be integrated with the processor, for example, by placing RAM or flash memory within an integrated circuit microprocessor. Alternatively, memory 300 may include a separate device, such as an external disk drive, a storage array, or other storage device that can be used by any database system. Memory 300 and processor 200 may be operatively coupled or may communicate with each other, for example, via I / O ports, network connections, etc., enabling the processor to read files stored in the memory.

[0125] In addition, the electronic device 10 may also include a video display (such as a liquid crystal display) 500 and a user interaction interface 600 (such as one or more of a keyboard, mouse, touch input device, etc.). All components of the electronic device may be connected to each other via a bus (not shown) and / or a network (not shown).

[0126] Furthermore, in some example embodiments, the electronic device 10 may include an image capturing device 700, wherein the image capturing device 700 is capable of collecting or otherwise generating image data corresponding to an image. The image may correspond to a foggy image discussed above, and the image data may correspond to the image data discussed above. In some example embodiments, the electronic device 10 does not have an image capturing device 700 and may receive image data from an external source.

[0127] In some example embodiments, some or all of the video display 500, user interface 600, and / or image capture device 700 may be excluded from the electronic device 10.

[0128] According to some example embodiments of this disclosure, a computer-readable storage medium (corresponding to memory 300) may also be provided, wherein when instructions in the computer-readable storage medium are executed by at least one processor 200, the at least one processor 200 causes the at least one processor 200 to perform the image processing method as described above.

[0129] According to some exemplary embodiments of this disclosure, examples of computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage, hard disk drive (HDD), solid-state drive (SSD), card storage (such as multimedia cards, secure digital (SD) cards, or ultra-fast digital (XD) cards), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, and any other device configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and to provide the computer program and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the aforementioned computer-readable storage medium can run in an environment deployed in electronic devices such as clients, hosts, agent devices, servers, etc. Furthermore, in some example embodiments, the computer program and any associated data, data files, and data structures are distributed across a networked computer system, such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner through one or more processors or computers.

[0130] Those skilled in the art, upon consideration of the specification and practice of the invention disclosed herein, will be able to identify other embodiments of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and exemplary embodiments are to be considered as examples only, and the true scope and spirit of this disclosure are indicated by the claims.

[0131] The first and second conditions, as well as the saturation value, can be selected, determined, predetermined, or desired in various ways. For example, the various conditions can be predetermined in the image processing apparatus, or determined based on the image generation hardware, or otherwise selected based on this disclosure and as understood by those skilled in the art.

[0132] When the terms “approximately” or “substantially” are used in conjunction with numerical values ​​in this specification, it is intended that the relevant numerical value includes manufacturing or operational tolerances (e.g., ±10%) around the stated value. Furthermore, when the words “generally” and “substantially” are used in conjunction with geometry, it is intended not to require precision of the geometry, but rather a degree of freedom of shape within the scope of this disclosure. Moreover, regardless of whether a numerical value or shape is modified to “approximately” or “substantially”, it should be understood that these numerical values ​​and shapes should include manufacturing or operational tolerances (e.g., ±10%) around the stated value or shape.

[0133] As described herein, any electronic device and / or component thereof according to any example embodiment may include one or more instances of processing circuitry (such as hardware including logic circuitry; a hardware / software combination, e.g., a processor executing software; or any combination of hardware and hardware / software combination), may be included in one or more instances of said processing circuitry, and / or may be implemented by one or more instances of said processing circuitry. For example, the processing circuitry may more specifically include, but is not limited to, a central processing unit (CPU), an arithmetic logic unit (ALU), a graphics processing unit (GPU), an application processor (AP), a digital signal processor (DSP), a microcomputer, a field-programmable gate array (FPGA) and programmable logic unit, a microprocessor, an application-specific integrated circuit (ASIC), a neural network processing unit (NPU), an electronic control unit (ECU), an image signal processor (ISP), etc. In some example embodiments, the processing circuitry may include: a non-transitory computer-readable storage device (e.g., a memory), such as a DRAM device, storing an instruction program; and a processor (e.g., a CPU) configured to execute the instruction program to implement some or all of any of any device, system, module, unit, controller, circuit, architecture, and / or portions thereof, performed by any part of any device, system, module, unit, controller, circuit, architecture, and / or any portion thereof, according to any example embodiment.

[0134] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the claims.

Claims

1. An image processing method, comprising: Determine the dark channel image of the input image; Atmospheric luminosity is determined based on the grayscale histogram of the dark channel image; and The dehazed image of the input image is determined based on the atmospheric photometric data. The steps for determining atmospheric luminosity based on the grayscale histogram of the dark channel image include: Filter the grayscale histogram; By traversing the filtered grayscale histogram along the first direction, the first point satisfying the first condition in the first direction is obtained, where the first direction is the direction of grayscale decrease; By traversing the filtered grayscale histogram along the first direction from the first point, it is determined whether there exists a second point corresponding to the trough that satisfies the second condition; and The atmospheric luminance is determined based on the determination that there is no second point, or the atmospheric luminance is determined based on the determination that there is a second point, or the atmospheric luminance is determined based on the determination that there is a second point.

2. The image processing method according to claim 1, further comprising: The grayscale histogram of the dark channel image is obtained by statistically analyzing the pixels of the dark channel image.

3. The image processing method according to claim 1 or 2, wherein, The steps of determining the atmospheric photometric value based on the absence of a second point and the corresponding gray value of the first point, or determining the atmospheric photometric value based on the presence of a second point, include: Based on the existence of a second point corresponding to the trough and satisfying the second condition, the gray value corresponding to the second point is determined as the atmospheric luminosity, wherein the second point is the initial second point in the first direction; and If there is no second point that corresponds to the trough and satisfies the second condition, then the gray value corresponding to the first point is determined as the atmospheric photometric value.

4. The image processing method according to claim 1 or 2, wherein, The first condition is that the number of pixels corresponding to the first point is greater than or equal to the first threshold, and the second condition is that the number of pixels corresponding to the second point is less than or equal to the second threshold and the gray value corresponding to the second point is greater than or equal to the third threshold.

5. The image processing method according to claim 1, wherein, The steps for determining the dehazed image of the input image based on the atmospheric photometric information include: Transmittance is determined based on the brightness image of the input image and the atmospheric photometric data. The transmittance mapping weights are determined based on the transmittance. The dehazing brightness image is determined based on the brightness image, the atmospheric photometric value, and the transmittance mapping weight; and The dehazed image is determined based at least on the chroma image of the input image and the luminance image of the dehazed image.

6. The image processing method according to claim 5, wherein, The step of determining transmittance based on the brightness image of the input image and the atmospheric photometric data includes: The basic transmittance is determined based on the brightness image and the atmospheric photometric data. Based on the aforementioned basic transmittance, a refined transmittance is obtained; and The transmittance is obtained based on the refined transmittance.

7. The image processing method according to claim 6, wherein, The step of determining transmittance based on the brightness image of the input image and the atmospheric photometric value further includes: A fourth threshold for transmittance updating is determined based on the atmospheric photometry, wherein the fourth threshold is a value greater than 0 and less than or equal to 1; and The larger of the transmittance and the fourth threshold is determined as the updated transmittance.

8. The image processing method according to claim 5, wherein, The step of determining the dehazed image based at least on the chroma image of the input image and the luminance image of the dehazed image includes: The fusion weights are determined based on the atmospheric photometric data and the brightness image; and The dehazed image is obtained by applying the enhanced saturation value and the fusion weight to the chroma image and the dehazed luminance image.

9. An image processing apparatus, comprising: The dark channel image determination unit is configured to determine the dark channel image of the input image; The atmospheric photometric determination unit is configured to determine atmospheric photometric based on the grayscale histogram of the dark channel image; as well as The dehazing processing unit is configured to determine the dehazed image of the input image based on the atmospheric photometric values. The atmospheric photometric determination unit is configured to determine atmospheric photometric values ​​based on the grayscale histogram of the dark channel image, using the following operation: Filter the grayscale histogram; By traversing the filtered grayscale histogram along the first direction, the first point satisfying the first condition in the first direction is obtained, where the first direction is the direction of grayscale decrease; By traversing the filtered grayscale histogram along the first direction from the first point, it is determined whether there exists a second point corresponding to the trough that satisfies the second condition; and The atmospheric luminance is determined based on the determination that there is no second point, or the atmospheric luminance is determined based on the determination that there is a second point, or the atmospheric luminance is determined based on the determination that there is a second point.

10. The image processing apparatus according to claim 9, wherein, The atmospheric photometric determination unit is also configured as follows: The grayscale histogram of the dark channel image is obtained by statistically analyzing the pixels of the dark channel image.

11. The image processing apparatus according to claim 9 or 10, wherein, The atmospheric photometric determination unit is configured to determine the atmospheric photometric value corresponding to the first point as the atmospheric photometric value based on the following operations: either by determining that a second point does not exist, or by determining that a second point exists, the gray value corresponding to the second point as the atmospheric photometric value. Based on the existence of a second point corresponding to a trough and satisfying the second condition, the gray value corresponding to this second point is determined as the atmospheric luminosity, wherein this second point is the initial second point in the first direction; and Based on the absence of a second point that corresponds to a trough and satisfies the second condition, the gray value corresponding to the first point is determined as the atmospheric luminosity.

12. The image processing apparatus according to claim 9 or 10, wherein, The first condition is that the number of pixels corresponding to the first point is greater than or equal to the first threshold, and the second condition is that the number of pixels corresponding to the second point is less than or equal to the second threshold and the gray value corresponding to the second point is greater than or equal to the third threshold.

13. The image processing apparatus according to claim 9, wherein, The dehazing unit is configured to determine a dehazed image of the input image based on the atmospheric photometric parameters by: Transmittance is determined based on the brightness image of the input image and the atmospheric photometric data. The transmittance mapping weights are determined based on the transmittance. The dehazing brightness image is determined based on the brightness image, the atmospheric photometric value, and the transmittance mapping weight; and The dehazed image is determined based at least on the chroma image of the input image and the luminance image of the dehazed image.

14. The image processing apparatus according to claim 13, wherein, The dehazing unit is configured to determine transmittance based on the brightness image of the input image and the atmospheric photometric parameters, using the following operations: The basic transmittance is determined based on the brightness image and the atmospheric photometric data. Based on the aforementioned basic transmittance, a refined transmittance is obtained; and The transmittance is obtained based on the refined transmittance.

15. The image processing apparatus according to claim 14, wherein, The dehazing unit is also configured to determine transmittance based on the brightness image of the input image and the atmospheric photometric parameters: A fourth threshold for transmittance updating is determined based on the atmospheric photometry, wherein the fourth threshold is a value greater than 0 and less than or equal to 1; and The larger of the transmittance and the fourth threshold is determined as the updated transmittance.

16. The image processing apparatus according to claim 13, wherein, The dehazing unit is configured to determine a dehazed image based at least on the chroma image of the input image and the luminance image of the dehazed image, using the following operations: The fusion weights are determined based on the atmospheric photometric data and the brightness image. and The dehazed image is obtained by applying the enhanced saturation value and the fusion weight to the chroma image and the dehazed luminance image.

17. An electronic device comprising: At least one processor; At least one non-volatile memory configured to store computer-executable instructions. The computer-executable instructions, when executed by the at least one processor, cause the at least one processor to perform the image processing method as described in claim 1.

18. A computer-readable non-volatile storage medium, wherein, The instructions in the computer-readable non-volatile storage medium are executed by at least one processor, causing the at least one processor to perform the image processing method as described in claim 1.

Images