WO2022213372A1

WO2022213372A1 - Image dehazing method and apparatus, and electronic device and computer-readable medium

Info

Publication number: WO2022213372A1
Application number: PCT/CN2021/086221
Authority: WO
Inventors: 伦朝林; 卢庆博; 丁蕾
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2021-04-09
Filing date: 2021-04-09
Publication date: 2022-10-13

Abstract

Disclosed in the embodiments of the present application are an image dehazing method and apparatus, and an electronic device and a computer-readable medium. The method comprises: acquiring haze intensity information of an image to be processed; determining a target parameter set on the basis of the haze intensity information, a preset parameter set in a haze-free scenario, and a parameter set in a dense haze scenario; and determining a target mapping function on the basis of the target parameter set, and performing, on the basis of the target mapping function, dehazing processing on the image to be processed, so as to obtain a dehazed target image, wherein the target mapping function is a continuous function comprising multiple piecewise functions. By means of the implementation, the image quality after dehazing processing is performed is improved.

Description

Image dehazing method, apparatus, electronic device and computer readable medium

technical field

The embodiments of the present application relate to the field of computer technologies, and in particular, to an image defogging method, apparatus, electronic device, and computer-readable medium.

Background technique

In foggy or hazy weather, the images and videos taken usually have poor image quality and low definition. In order to improve the quality of the image and improve the definition of the image, it is usually necessary to dehaze the image.

In the prior art, the image is usually dehazed by a dark channel dehazing algorithm. The dark channel dehazing algorithm uses a single linear function to brighten the pixels larger than a certain value in a fixed way, and directly adjust the pixels smaller than a certain value to zero, which is prone to overexposure of bright details and loss of dark details in the image. situation, resulting in poor image quality.

SUMMARY OF THE INVENTION

The embodiments of the present application propose an image defogging method, apparatus, electronic device, and computer-readable medium, so as to solve the technical problem of poor image quality after the image is defogged in the prior art.

In a first aspect, an embodiment of the present application provides an image dehazing method, including: acquiring fog intensity information of an image to be processed; based on the fog intensity information, a preset parameter set in a fog-free scene and a fog-free scene Determine the target parameter set based on the target parameter set; determine the target mapping function based on the target parameter set, and perform dehazing processing on the to-be-processed image based on the target mapping function to obtain the target image after dehazing, wherein, The target mapping function is a continuous function including a plurality of piecewise functions.

In a second aspect, embodiments of the present application provide an image defogging device, including: an acquisition unit configured to acquire fog intensity information of an image to be processed; a determination unit configured to, based on the fog intensity information, preset The parameter set in the fog-free scene and the parameter set in the dense fog scene determine a target parameter set; the processing unit is configured to determine a target mapping function based on the target parameter set, and based on the target mapping function The image is dehazed to obtain a target image after dehazing, wherein the target mapping function is a continuous function including a plurality of piecewise functions.

In a third aspect, embodiments of the present application provide an electronic device, including: a processor and a memory; a memory for storing program instructions; a processor for executing program instructions stored in the memory, and when the program instructions are executed, processing The device is configured to perform the following steps: obtaining fog intensity information of the image to be processed; determining a target parameter set based on the fog intensity information, a preset parameter set in a fog-free scene and a parameter set in a dense fog scene; based on the target The parameter set determines a target mapping function, and based on the target mapping function, the image to be processed is subjected to dehazing processing to obtain a target image after dehazing, wherein the target mapping function is a multi-segment function. Continuous function.

In a fourth aspect, an embodiment of the present application provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, implements the method described in the first aspect.

The embodiments of the present application provide an image dehazing method, device, electronic device, and computer-readable medium, by acquiring fog intensity information of an image to be processed, and then based on the fog intensity information, a preset parameter set in a fog-free scene and a dense fog The parameter set in the fog scene is determined, the target parameter set is determined, and then the target mapping function is determined based on the target parameter set, so that the image to be processed can be dehazed based on the target mapping function, and the target image after dehazing can be obtained. Since the target mapping function is a continuous function including multiple piecewise functions, different piecewise functions can be used to process pixel values in different numerical ranges, avoiding the overexposure of bright details in the image due to the use of a single linear function. As well as a large loss of details in the shadows, the quality of the image is improved.

Description of drawings

Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

1 is a flowchart of an embodiment of an image dehazing method according to the present application;

Fig. 2 is according to the graph of the target mapping function in the image dehazing method of the present application;

3 is a schematic structural diagram of an embodiment of an image defogging device according to the present application;

FIG. 4 is a schematic structural diagram of an embodiment of an electronic device according to the present application.

specific embodiment

The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the related invention, but not to limit the invention. In addition, it should be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

Please refer to FIG. 1 , which shows a flowchart of an image dehazing method according to the present application. The image dehazing method of the present application can be run on various electronic devices, which may include but are not limited to: servers, smart phones, tablet computers, laptop computers, vehicle-mounted computers, desktop computers, set-top boxes, wearable devices, etc. Wait.

The process of the image dehazing method includes the following steps:

Step 101: Obtain fog intensity information of the image to be processed.

In this embodiment, the execution body of the image defogging method (such as the above-mentioned electronic device) may first acquire the image to be processed. The image to be processed can be captured by the above-mentioned executive body through the image acquisition device (such as a camera) installed in it, or can be stored locally in advance (such as stored in a local album), or can be obtained by the above-mentioned executive body from the Internet or other devices. Obtain. The image to be processed may be an image to be dehazed.

After acquiring the to-be-processed image, the above-mentioned execution body may acquire the fog intensity information of the to-be-processed image. The fog intensity information can be used to indicate the fog intensity of the image, which can be a value in a preset value interval, such as a value in [0,1]. The stronger the fog, the higher the value.

In some scenarios, the fog intensity information of the image to be processed can be preset by a technician, and the above-mentioned execution body can directly read it in this case.

In other scenarios, if the image to be processed is an image captured by the execution subject through the image acquisition device installed therein, the execution subject may query current weather conditions to determine fog intensity information based on the weather conditions.

In other scenarios, the above-mentioned execution body can automatically detect the fog intensity of the image to be processed to obtain fog intensity information. For example, the image to be processed may be input into a pre-trained neural network for fog intensity detection to obtain a fog intensity detection result. Among them, the neural network can be trained using a large number of samples and supervised learning.

It should be noted that the method for obtaining the fog intensity information may also be set to other settings as required, and is not limited to the above-mentioned ones.

Step 102: Determine the target parameter set based on the fog intensity information, the preset parameter set in the fog-free scene, and the parameter set in the dense fog scene.

In this embodiment, a parameter set in a fog-free scene and a parameter set in a dense fog scene may be preset in the above-mentioned execution body. The parameter set in the fog-free scene and the parameter set in the dense fog scene can respectively contain multiple parameters and correspond one-to-one. The parameters in the two parameter sets are the parameters of the preset mapping function. The mapping function can be used to characterize the correspondence between the pixel values before dehazing and the pixel values after dehazing. That is, after inputting the pixel value of a certain pixel in the image before the defogging process into the mapping function, the pixel value of the pixel after the defogging process can be obtained. Here, the mapping function is a continuous function containing multiple piecewise functions.

In practice, the parameters of the mapping function can be adjusted for the fog-free scene and the dense fog scene in advance to obtain the parameter set in the fog-free scene and the parameter set in the dense fog scene. As an example, for a fog-free scene, during the parameter adjustment process, the image quality of the fog-free image can be compared with different parameters, and the parameters used to obtain the best image quality can be summarized into the fog-free scene. parameter set. Similarly, for dense fog scenes, in the process of parameter adjustment, the image quality after dehazing the dense fog image with different parameters can be compared, and the parameters used to obtain the best image quality can be summarized into the dense fog scene. parameter set.

In this embodiment, the above-mentioned execution subject may determine the target parameter set based on the fog intensity information, the preset parameter set in the fog-free scene, and the parameter set in the dense fog scene. The target parameter set is the parameter set applicable to the current fog intensity.

In some optional implementation manners, the above-mentioned executive body may perform interpolation on the preset parameter set in the fog-free scene and the parameter set in the dense fog scene based on the fog intensity information to obtain the target parameter set. As an example, if the parameter set in the fog-free scene includes x ₀ ', x ₁ ', x ₂ ', y ₁ ', y ₂ ', the parameter set in the dense fog scene includes x ₀ ', x ₁ '', x ₂ ”, y ₁ ”, y ₂ ”, then you can interpolate based on the fog intensity information, x ₀ ' and x ₀ ” to obtain x ₀ ; perform interpolation based on the fog intensity information, x ₁ ' and x ₁ ” to obtain x ₁ ; Interpolate based on the fog intensity information, x ₂ ' and x ₂ ″ to obtain x ₂ ; perform interpolation based on the fog intensity information, y ₁ ' and y ₁ ″ to obtain y ₁ ; Based on the fog intensity information, y ₂ ' and y ₂ ″ Interpolate to get y ₂ .

The interpolation method may adopt various interpolation methods such as linear interpolation and nonlinear interpolation, which are not limited here. Taking the interpolation of x ₁ ' and x ₁ ' as an example, if the fog intensity information is represented as M, then x ₁ can be x ₁ '+M(x ₁ ''-x ₁ ').

Step 103: Determine a target mapping function based on the target parameter set, and perform dehazing processing on the image to be processed based on the target mapping function to obtain a target image after dehazing.

In this embodiment, a preset mapping function may be stored in the above-mentioned execution body. A mapping function is a continuous function containing multiple piecewise functions, which contain multiple parameters. Depending on the fog intensity, the parameters used by the mapping function can be different.

The above-mentioned execution body may use a preset mapping function using target parameters as the target mapping function, and thus, the target mapping function is also a continuous function including a plurality of segment functions. The above-mentioned execution body may perform dehazing processing on the to-be-processed image based on the target mapping function to obtain the target image after dehazing. Specifically, each piecewise function may correspond to a pixel value interval. For each pixel in the image to be processed, the above-mentioned execution body may determine a piecewise function for processing the pixel according to the pixel value of the pixel, so as to input the pixel value into the piecewise function to obtain the pixel The new pixel value of the point. After performing the above operations on all pixels, the target image after dehazing can be obtained.

In some optional implementations of this embodiment, the target mapping function may include a first piecewise function. The target parameter set may include a first parameter (which can be marked as x ₀ ), the first parameter is a positive number smaller than the target value, and the target value is determined based on the ambient light brightness value (which can be marked as A) and the transmittance (which can be marked as t) . The ambient light brightness value and transmittance are commonly used parameters in the dark channel dehazing algorithm, and will not be described here. The above-mentioned execution body may adjust the pixel values in the image to be processed that are less than or equal to the first parameter based on the first piecewise function.

In some examples, the first piecewise function may be a constant (eg, 0), and the target value may be A(1-t), where 0<x ₀ <A(1-t). If a certain pixel value of the image to be processed is less than x ₀ , the pixel value can be adjusted to a constant (eg, 0).

Since the conventional dark channel dehazing algorithm usually directly adjusts the pixel value less than A(1-t) to 0, the conventional dark channel dehazing algorithm is prone to the loss of a large number of dark details in the image. In this implementation manner, since x ₀ <A(1-t), fewer pixel values are adjusted to 0, so that more dark details are protected, thereby improving the image quality after dehazing.

In some optional implementations of this embodiment, the target mapping function may further include a second piecewise function. The second piecewise function may be a monotonically increasing function (eg, a monotonically increasing linear function or a monotonically increasing nonlinear function). The target parameter set also includes a second parameter (may be denoted as x ₁ ), and the second parameter may be greater than the first parameter (x ₀ ) and smaller than the ambient light brightness value A, ie A(1-t)<x ₁ <A. At this time, the above-mentioned execution body may adjust the pixel value (denoted as x) in the image to be processed that is larger than the first parameter and smaller than the second parameter based on the second piecewise function. That is, when x ₀ <x<x ₁ , use the second piecewise function to adjust x to obtain the adjusted pixel value (denoted as y).

In some examples, the target parameter set further includes a third parameter (which may be denoted as y ₁ ), and the third parameter is a positive number smaller than the ambient light brightness value A, that is, y ₁ <A. The second piecewise function may be a linear function, and the slope of the second piecewise function is determined based on the first parameter, the second parameter and the third parameter. For example, the second piecewise function can be:

Since the conventional dark channel dehazing algorithm usually directly adjusts the pixel value less than A(1-t) to 0, the conventional dark channel dehazing algorithm is prone to the loss of a large number of dark details in the image. In this implementation, x ₀ <A(1-t), the pixel values in the range of (x ₀ , A(1-t)) are all adjusted to a number greater than 0, so that fewer pixel values are adjusted to 0, so that more dark details are protected, thereby improving the image quality after dehazing.

In some optional implementations of this embodiment, the target mapping function further includes a third piecewise function, and the third piecewise function may be a monotonically increasing function (such as a monotonically increasing linear function or a monotonically increasing nonlinear function) . The above-mentioned execution body may adjust the pixel value (may be denoted as x) in the image to be processed that is greater than or equal to the second parameter x ₁ and less than or equal to the ambient light brightness value A based on the third piecewise function. That is, if x ₁ ≤x≤A, use the third piecewise function to adjust x to obtain the adjusted pixel value (denoted as y).

In some examples, the third piecewise function may be a linear function, and the slope of the third piecewise function may be determined based on the transmittance, such as directly using the slope 1/t of the mapping function in the conventional dark channel dehazing algorithm, at this time , the second piecewise function can be:

In some optional implementations of this embodiment, the target mapping function further includes a fourth piecewise function, and the fourth piecewise function is a monotonically increasing function (eg, a monotonically increasing linear function or a monotonically increasing nonlinear function). The above-mentioned execution body may adjust the pixel value (which may be denoted as x) in the image to be processed that is greater than the ambient light brightness value A based on the fourth piecewise function. That is, if x>A, use the fourth piecewise function to adjust x to obtain the adjusted pixel value (denoted as y).

In some examples, the target parameter set further includes a fifth parameter (denoted as x ₂ ) and a sixth parameter (denoted as y ₂ ). The fifth parameter is greater than the ambient light brightness value A and smaller than the maximum pixel value (eg, 255). The six parameter is less than or equal to the maximum pixel value (eg 255). That is, A<x ₂ <255, and y ₂ ≤255. The fourth piecewise function may be a linear function, and the slope of the fourth piecewise function may be smaller than the slope (eg, 1/t) adopted by the conventional dark channel dehazing algorithm. Specifically, the slope of the fourth piecewise function may be determined based on the fifth parameter, the sixth parameter and the ambient light brightness value, and the fourth piecewise function may be:

Since the conventional dark channel dehazing algorithm usually directly adjusts the pixel value x greater than A to A+(x-A)/t, it is easy to adjust the pixel value greater than A to the maximum value of 255, resulting in overexposure of bright details in the image. In this implementation, since the slope of the fourth piecewise function is less than 1/t, for pixel values greater than A, the adjusted value can be reduced, so that more bright details can be protected, thereby further improving the dehazing process. post image quality.

As an example, FIG. 2 shows a graph of an object mapping function in an image dehazing method according to the present application. As shown in FIG. 2 , the graph of the target mapping function includes four parts, corresponding to the first piecewise function, the second piecewise function, the third piecewise function and the fourth piecewise function respectively. The horizontal axis represents the original pixel value, and the vertical axis represents the pixel value after dehazing. As can be seen from Figure 2, the target mapping function is as follows:

It should be noted that, in addition to the above examples, the target mapping function may also use other functional forms that can achieve similar functions, such as multi-segment linear mapping functions, smooth curve functions, etc., which are not specifically limited in this embodiment of the present application.

In the method provided by the above embodiments of the present application, the fog intensity information of the image to be processed is obtained, and then the target parameter set is determined based on the fog intensity information, a preset parameter set in a fog-free scene, and a parameter set in a dense fog scene , and then determine the target mapping function based on the target parameter set, so that the image to be processed can be dehazed based on the target mapping function, and the target image after dehazing can be obtained. Since the target mapping function is a continuous function including multiple piecewise functions, different piecewise functions can be used to process pixel values in different numerical ranges, avoiding the overexposure of bright details in the image due to the use of a single linear function. As well as a large loss of details in the shadows, the quality of the image is improved.

Further referring to FIG. 3 , as an implementation of the above method, the present application provides an embodiment of an image defogging apparatus, and the apparatus embodiment corresponds to the method embodiment shown in FIG. 1 . The electronic device can be among various electronic devices.

As shown in FIG. 3 , the above-mentioned image defogging apparatus 300 in this embodiment includes: an acquiring unit 301 configured to acquire fog intensity information of an image to be processed; a determining unit 302 configured to, based on the above fog intensity information, a preset The parameter set in the fog-free scene and the parameter set in the dense fog scene determine the target parameter set; the processing unit 303 is configured to determine the target mapping function based on the above target parameter set, and based on the above target mapping function. Dehazing is performed to obtain a target image after dehazing, wherein the target mapping function is a continuous function including a plurality of piecewise functions.

In some optional implementations of this embodiment, the target mapping function includes a first piecewise function, the first piecewise function is a constant, the target parameter set includes a first parameter, and the first parameter is smaller than the target value The above-mentioned target value is determined based on the brightness value of the ambient light and the transmittance; the above-mentioned processing unit is further configured to: based on the above-mentioned first piecewise function, the pixel values in the above-mentioned to-be-processed image that are less than or equal to the above-mentioned first parameter are processed. Adjustment.

In some optional implementations of this embodiment, the foregoing first piecewise function is a constant.

In some optional implementations of this embodiment, the target mapping function further includes a second piecewise function, the second piecewise function is a monotonically increasing function, the target parameter set further includes a second parameter, and the second parameter Greater than the first parameter and less than the ambient light brightness value; the processing unit is further configured to: based on the second piecewise function, the pixel values in the to-be-processed image that are greater than the first parameter and less than the second parameter are processed. Adjustment.

In some optional implementations of this embodiment, the target parameter set further includes a third parameter, and the third parameter is a positive number smaller than the ambient light brightness value; the second piecewise function is a linear function, and the third parameter is a linear function. The slope of the bipartite function is determined based on the aforementioned first parameter, the aforementioned second parameter, and the aforementioned third parameter.

In some optional implementations of this embodiment, the above-mentioned target mapping function further includes a third piecewise function, and the above-mentioned third piecewise function is a monotonically increasing function; the above-mentioned processing unit is further configured to: based on the above-mentioned third The piecewise function adjusts pixel values in the image to be processed that are greater than or equal to the second parameter and less than or equal to the ambient light brightness value.

In some optional implementations of this embodiment, the third piecewise function is a linear function, and the slope of the third piecewise function is determined based on the transmittance.

In some optional implementations of this embodiment, the above-mentioned target mapping function further includes a fourth piecewise function, and the above-mentioned fourth piecewise function is a monotonically increasing function; the above-mentioned processing unit is further configured to: based on the above-mentioned fourth The piecewise function adjusts pixel values in the image to be processed that are greater than the ambient light brightness value.

In some optional implementations of this embodiment, the target parameter set further includes a fifth parameter and a sixth parameter, the fifth parameter is greater than the ambient light brightness value and less than the maximum pixel value, and the sixth parameter is less than or equal to The above-mentioned maximum pixel value; the above-mentioned fourth piecewise function is a linear function, and the slope of the above-mentioned fourth piecewise function is determined based on the above-mentioned fifth parameter, the above-mentioned sixth parameter and the above-mentioned ambient light brightness value.

In some optional implementations of this embodiment, the above determining unit is further configured to: perform interpolation on a preset parameter set in a fog-free scene and a parameter set in a dense fog scene based on the above fog intensity information, Get the target parameter set.

The image defogging device provided by the above-mentioned embodiments of the present application obtains the fog intensity information of the image to be processed, and then determines the fog intensity information based on the fog intensity information, the preset parameter set in the fog-free scene and the parameter set in the dense fog scene. A target parameter set, and then a target mapping function is determined based on the target parameter set, so that the image to be processed can be dehazed based on the target mapping function, and a dehazed target image can be obtained. Since the target mapping function is a continuous function including multiple piecewise functions, different piecewise functions can be used to process pixel values in different numerical ranges, avoiding the overexposure of bright details in the image due to the use of a single linear function. As well as a large loss of details in the shadows, the quality of the image is improved.

Further referring to Fig. 4 , as an implementation of the method shown in Fig. 1 above, the present application provides an embodiment of an electronic device, which corresponds to the method embodiment shown in Fig. 1 . Specifically, the electronic device may include: a processor 401 and a memory 402 .

The above-mentioned memory 401 can be used to store program instructions.

The above-mentioned processor 402 can be used to execute the program instructions stored in the above-mentioned memory. When the program instructions are executed, the above-mentioned processor can be used to perform the following steps: obtaining fog intensity information of the image to be processed; The parameter set in the fog-free scene and the parameter set in the dense fog scene are determined, and the target parameter set is determined; the target mapping function is determined based on the above target parameter set, and the image to be processed is dehazed based on the above target mapping function. The target image after fog post-processing, wherein the target mapping function is a continuous function including multiple piecewise functions.

In some optional implementations of this embodiment, the target mapping function includes a first piecewise function, the first piecewise function is a constant, the target parameter set includes a first parameter, and the first parameter is smaller than the target value The above-mentioned target value is determined based on the ambient light brightness value and transmittance; the above-mentioned processor is further configured to perform the following steps: based on the above-mentioned first piecewise function, the pixel value in the above-mentioned to-be-processed image that is less than or equal to the above-mentioned first parameter is determined. make adjustments.

In some optional implementations of this embodiment, the target mapping function further includes a second piecewise function, the second piecewise function is a monotonically increasing function, the target parameter set further includes a second parameter, and the second parameter greater than the first parameter and less than the ambient light brightness value; the processor is further configured to perform the following steps: based on the second piecewise function, the pixel value in the image to be processed that is greater than the first parameter and less than the second parameter is analyzed. make adjustments.

In some optional implementations of this embodiment, the above-mentioned target mapping function further includes a third piecewise function, and the above-mentioned third piecewise function is a monotonically increasing function; the above-mentioned processor is further configured to perform the following steps: based on the above-mentioned first The three-piece function adjusts the pixel values in the image to be processed that are greater than or equal to the second parameter and less than or equal to the ambient light brightness value.

In some optional implementations of this embodiment, the above-mentioned target mapping function further includes a fourth piecewise function, and the above-mentioned fourth piecewise function is a monotonically increasing function; the above-mentioned processor is further configured to perform the following steps: based on the above-mentioned first The four-segment function adjusts the pixel values in the image to be processed that are greater than the ambient light brightness value.

In some optional implementations of this embodiment, the above-mentioned processor is further configured to perform the following steps: based on the above-mentioned fog intensity information, perform interpolation on a preset parameter set in a fog-free scene and a parameter set in a dense fog scene , get the target parameter set.

The electronic device provided by the above-mentioned embodiments of the present application obtains the fog intensity information of the image to be processed, and then determines the target based on the fog intensity information, the preset parameter set in the fog-free scene and the parameter set in the dense fog scene parameter set, and then determine the target mapping function based on the target parameter set, so that the image to be processed can be dehazed based on the target mapping function, and the target image after dehazing can be obtained. Since the target mapping function is a continuous function including multiple piecewise functions, different piecewise functions can be used to process pixel values in different numerical ranges, avoiding the overexposure of bright details in the image due to the use of a single linear function. As well as a large loss of details in the shadows, the quality of the image is improved.

In practice, an electronic device can be either a processing chip or a processing unit in the device, or a product, such as a camera, a mobile phone, or a camera-equipped gimbal, drone, or unmanned vehicle. The electronic device is not specifically limited here.

As for the electronic device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the partial description of the method embodiment.

Embodiments of the present application further provide a computer-readable medium, where a computer program is stored on the computer-readable medium. When the computer program is executed by a processor, each process of the above-mentioned embodiments of the image dehazing method can be achieved, and the same technology can be achieved. Effect. In order to avoid repetition, when the computer program is executed by the processor, each process of the embodiments of the above-mentioned methods is implemented, which will not be repeated here.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments may be referred to each other.

It should be understood by those skilled in the art that the embodiments of the present application may be provided as a method, an apparatus, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable media having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, and the like.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal equipment to produce a machine that causes the instructions to be executed by the processor of the computer or other programmable data processing terminal equipment Means are created for implementing the functions specified in the flow or flows of the flowcharts and/or the blocks or blocks of the block diagrams.

These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal equipment to operate in a particular manner, such that the instructions stored in the computer readable memory result in an article of manufacture comprising instruction means, the The instruction means implement the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing terminal equipment, so that a series of operational steps are performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby executing on the computer or other programmable terminal equipment The instructions executed on the above provide steps for implementing the functions specified in the flowchart or blocks and/or the block or blocks of the block diagrams.

While the preferred embodiments of the present application have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiment and all changes and modifications that fall within the scope of this application.

Finally, it should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or that there is any such actual relationship or sequence between operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or terminal device comprising a list of elements includes not only those elements, but also a non-exclusive list of elements. other elements, or also include elements inherent to such a process, method, article or terminal equipment. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, article or terminal device comprising said element.

The image defogging method, device, electronic device, and computer-readable medium provided by the present application have been described in detail above. The principles and implementations of the present application are described with specific examples. The descriptions of the above embodiments are only It is used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there will be changes in the specific embodiments and application scope. The contents of the description should not be construed as limiting the application.

Claims

An image dehazing method, characterized in that the method comprises:

Obtain the fog intensity information of the image to be processed;

determining a target parameter set based on the fog intensity information, a preset parameter set in a fog-free scene, and a parameter set in a dense fog scene;

Determine a target mapping function based on the target parameter set, and perform dehazing processing on the to-be-processed image based on the target mapping function to obtain a target image after dehazing, where the target mapping function includes a plurality of A continuous function of a piecewise function.
The method according to claim 1, wherein the target mapping function comprises a first piecewise function, the target parameter set comprises a first parameter, the first parameter is a positive number smaller than a target value, and the The target value is determined based on the ambient light brightness value and transmittance;

The performing dehazing processing on the to-be-processed image based on the target mapping function includes:

Pixel values less than or equal to the first parameter in the image to be processed are adjusted based on the first piecewise function.
The method of claim 2, wherein the first piecewise function is a constant.
The method according to claim 2, wherein the target mapping function further comprises a second piecewise function, the second piecewise function is a monotonically increasing function, the target parameter set further comprises a second parameter, the the second parameter is greater than the first parameter and less than the ambient light brightness value;

The performing dehazing processing on the to-be-processed image based on the target mapping function includes:

Pixel values in the image to be processed that are larger than the first parameter and smaller than the second parameter are adjusted based on the second piecewise function.
The method according to claim 4, wherein the target parameter set further includes a third parameter, and the third parameter is a positive number smaller than the ambient light brightness value;

The second piecewise function is a linear function, and a slope of the second piecewise function is determined based on the first parameter, the second parameter and the third parameter.
The method according to claim 4, wherein the target mapping function further comprises a third piecewise function, and the third piecewise function is a monotonically increasing function;

The performing dehazing processing on the to-be-processed image based on the target mapping function includes:

Adjusting pixel values in the image to be processed that are greater than or equal to the second parameter and less than or equal to the ambient light brightness value based on the third piecewise function.
The method of claim 6, wherein the third piecewise function is a linear function, and a slope of the third piecewise function is determined based on the transmittance.
The method according to claim 6, wherein the target mapping function further comprises a fourth piecewise function, and the fourth piecewise function is a monotonically increasing function;

The performing dehazing processing on the to-be-processed image based on the target mapping function includes:

Adjusting pixel values in the image to be processed that are greater than the ambient light brightness value based on the fourth piecewise function.
The method according to claim 8, wherein the target parameter set further includes a fifth parameter and a sixth parameter, the fifth parameter is greater than the ambient light brightness value and less than a maximum pixel value, and the sixth parameter The parameter is less than or equal to the maximum pixel value;

The fourth piecewise function is a linear function, and the slope of the fourth piecewise function is determined based on the fifth parameter, the sixth parameter and the ambient light brightness value.
The method according to claim 1, wherein determining the target parameter set based on the fog intensity information, a preset parameter set in a fog-free scene, and a parameter set in a dense fog scene, comprising:

Based on the fog intensity information, the preset parameter set in the fog-free scene and the parameter set in the dense fog scene are interpolated to obtain the target parameter set.
An image defogging device, characterized in that the device comprises:

an acquisition unit, configured to acquire fog intensity information of the image to be processed;

a determining unit, configured to determine a target parameter set based on the fog intensity information, a preset parameter set in a fog-free scene, and a parameter set in a dense fog scene;

a processing unit, configured to determine a target mapping function based on the target parameter set, and perform dehazing processing on the to-be-processed image based on the target mapping function to obtain a target image after dehazing, wherein the target The mapping function is a continuous function containing multiple piecewise functions.
The apparatus according to claim 11, wherein the target mapping function comprises a first piecewise function, the first piecewise function is a constant, the target parameter set comprises a first parameter, and the first parameter is a positive number smaller than the target value, and the target value is determined based on the ambient light brightness value and transmittance;

The processing unit is further configured to:

Pixel values less than or equal to the first parameter in the image to be processed are adjusted based on the first piecewise function.
The apparatus of claim 12, wherein the first piecewise function is a constant.
The apparatus according to claim 12, wherein the target mapping function further comprises a second piecewise function, the second piecewise function is a monotonically increasing function, the target parameter set further comprises a second parameter, and the the second parameter is greater than the first parameter and less than the ambient light brightness value;

The processing unit is further configured to:

Pixel values in the image to be processed that are larger than the first parameter and smaller than the second parameter are adjusted based on the second piecewise function.
The device according to claim 14, wherein the target parameter set further includes a third parameter, and the third parameter is a positive number smaller than the ambient light brightness value;

The second piecewise function is a linear function, and a slope of the second piecewise function is determined based on the first parameter, the second parameter and the third parameter.
The device according to claim 14, wherein the target mapping function further comprises a third piecewise function, and the third piecewise function is a monotonically increasing function;

The processing unit is further configured to:

Adjusting pixel values in the image to be processed that are greater than or equal to the second parameter and less than or equal to the ambient light brightness value based on the third piecewise function.
The apparatus of claim 16, wherein the third piecewise function is a linear function, and a slope of the third piecewise function is determined based on the transmittance.
The device according to claim 16, wherein the target mapping function further comprises a fourth piecewise function, and the fourth piecewise function is a monotonically increasing function;

The processing unit is further configured to:

Adjusting pixel values in the image to be processed that are greater than the ambient light brightness value based on the fourth piecewise function.
The device according to claim 18, wherein the target parameter set further includes a fifth parameter and a sixth parameter, the fifth parameter is greater than the ambient light brightness value and less than a maximum pixel value, and the sixth parameter The parameter is less than or equal to the maximum pixel value;

The fourth piecewise function is a linear function, and the slope of the fourth piecewise function is determined based on the fifth parameter, the sixth parameter and the ambient light brightness value.
The device according to claim 11, wherein the determining unit is further configured to:

Based on the fog intensity information, the preset parameter set in the fog-free scene and the parameter set in the dense fog scene are interpolated to obtain the target parameter set.
An electronic device, comprising:

processor and memory;

the memory for storing program instructions;

The processor executes the program instructions stored in the memory, and when the program instructions are executed, the processor is configured to perform the following steps:

Obtain the fog intensity information of the image to be processed;

determining a target parameter set based on the fog intensity information, a preset parameter set in a fog-free scene, and a parameter set in a dense fog scene;

Determine a target mapping function based on the target parameter set, and perform dehazing processing on the to-be-processed image based on the target mapping function to obtain a target image after dehazing, where the target mapping function includes a plurality of A continuous function of a piecewise function.
The electronic device according to claim 21, wherein the target mapping function comprises a first piecewise function, the first piecewise function is a constant, the target parameter set comprises a first parameter, and the first The parameter is a positive number smaller than a target value, and the target value is determined based on the ambient light brightness value and transmittance;

The processor is further configured to perform the following steps:

Pixel values less than or equal to the first parameter in the image to be processed are adjusted based on the first piecewise function.
The electronic device of claim 22, wherein the first piecewise function is a constant.
The electronic device according to claim 22, wherein the target mapping function further comprises a second piecewise function, the second piecewise function is a monotonically increasing function, and the target parameter set further comprises a second parameter, the second parameter is greater than the first parameter and less than the ambient light brightness value;

The processor is further configured to perform the following steps:

Pixel values in the image to be processed that are larger than the first parameter and smaller than the second parameter are adjusted based on the second piecewise function.
The electronic device according to claim 24, wherein the target parameter set further includes a third parameter, and the third parameter is a positive number smaller than the ambient light brightness value;

The second piecewise function is a linear function, and a slope of the second piecewise function is determined based on the first parameter, the second parameter and the third parameter.
The electronic device according to claim 24, wherein the target mapping function further comprises a third piecewise function, and the third piecewise function is a monotonically increasing function;

The processor is further configured to perform the following steps:

Adjusting pixel values in the image to be processed that are greater than or equal to the second parameter and less than or equal to the ambient light brightness value based on the third piecewise function.
The electronic device of claim 26, wherein the third piecewise function is a linear function, and a slope of the third piecewise function is determined based on the transmittance.
The electronic device according to claim 26, wherein the target mapping function further comprises a fourth piecewise function, and the fourth piecewise function is a monotonically increasing function;

The processor is further configured to perform the following steps:

Adjusting pixel values in the image to be processed that are greater than the ambient light brightness value based on the fourth piecewise function.
The electronic device according to claim 28, wherein the target parameter set further includes a fifth parameter and a sixth parameter, the fifth parameter is greater than the ambient light brightness value and less than a maximum pixel value, and the sixth parameter The six parameters are less than or equal to the maximum pixel value;

The fourth piecewise function is a linear function, and the slope of the fourth piecewise function is determined based on the fifth parameter, the sixth parameter and the ambient light brightness value.
The electronic device according to claim 21, wherein the processor is further configured to perform the following steps:

Based on the fog intensity information, the preset parameter set in the fog-free scene and the parameter set in the dense fog scene are interpolated to obtain the target parameter set.
A computer-readable medium, wherein a computer program is stored in the computer-readable medium, and when the computer program is executed by a processor, the method according to any one of claims 1-9 is implemented.