Image processing method, device, storage medium and computer equipment

Abstract

Embodiments of the present invention provide an image processing method, apparatus, storage medium, and computer device. The method includes: obtaining an original image; performing calculations on the original image according to a data processing algorithm to generate at least one first image corresponding to the original image; and performing calculations on each of the first images according to a local motion algorithm to generate a second image corresponding to each of the first images, thereby improving image processing efficiency.

Description

Technical field

[0001] The embodiments of the present invention relate to the field of image processing technology, and specifically to an image processing method, apparatus, storage medium, and computer equipment. [Background Technology]

[0002] Unlike tasks like object detection, multi-frame image fusion using deep learning models has become a common technique. Multi-frame fusion combines data from different exposure sequences to enhance the image's dynamic range and achieve higher quality High Dynamic Range (HDR) imaging. Image fusion can be learned using datasets, but acquiring a suitable dataset is crucial. The multiple images in the dataset must exhibit varying exposure, global motion, and local motion.

[0003] Image fusion technology can directly leverage public datasets for learning, but this often fails to achieve good generalization capabilities. Furthermore, currently, there are relatively few public datasets for multi-frame fusion tasks, which often fail to meet the requirements. Image fusion technology can also collect real multi-frame images for training, but this requires pre-labeling, which consumes significant labor and time, reducing image processing efficiency. [Summary of the invention]

[0004] In view of this, embodiments of the present invention provide an image processing method, apparatus, storage medium, and computer device to solve the problem of reduced image processing efficiency in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides a method for image processing, comprising:

[0006] Get the original image;

[0007] Calculating the original image according to a data processing algorithm to generate at least one first image corresponding to the original image;

[0008] Calculate each of the first pictures according to a local motion algorithm to generate a second picture corresponding to each of the first pictures.

[0009] In a possible implementation, the performing calculation on the original picture according to the data processing algorithm to generate at least one first picture corresponding to the original picture includes:

[0010] Calculating the original image according to an exposure simulation algorithm to generate at least one third image corresponding to the original image;

[0011] The at least one third picture is calculated according to a global motion algorithm to generate the first picture corresponding to each third picture.

[0012] In a possible implementation, calculating the original image according to an exposure simulation algorithm to generate at least one third image corresponding to the original image includes:

[0013] Converting pixel values ​​in the original image into floating-point data;

[0014] Calculating the floating-point data according to a right-shift rounding algorithm to generate first data;

[0015] The first data is calculated according to a data truncation algorithm to generate the third image.

[0016] In a possible implementation, before calculating the at least one third picture according to the global motion algorithm to generate the first picture corresponding to each third picture, the method further includes:

[0017] adjusting the size of each third picture;

[0018] Calculating the at least one third picture according to a global motion algorithm to generate the first picture corresponding to each third picture includes:

[0019] performing calculations on each of the resized third images according to a data augmentation algorithm to generate a fourth image corresponding to each of the third images;

[0020] Calculate each of the fourth images according to a center cropping algorithm to generate the first image corresponding to each of the fourth images.

[0021] In a possible implementation, calculating each of the first pictures according to a local motion algorithm to generate a second picture corresponding to each of the first pictures includes:

[0022] The second picture corresponding to each first picture is generated according to the set local motion area of ​​each first picture.

[0023] In a possible implementation, generating the second picture corresponding to each first picture according to the set local motion region of each first picture includes:

[0024] Setting the starting coordinates of the local motion region in each of the first pictures;

[0025] According to the starting coordinates of the local motion area in each of the first images, the local motion area is translated so that the designated coordinates of the local motion area coincide with the starting coordinates of the local motion area in each of the first images, so as to generate a second image corresponding to each of the first images.

[0026] In a possible implementation, a first picture of at least two first pictures is a start frame picture, a last picture is an end frame picture, any first picture other than the start frame picture and the end frame picture of the at least two first pictures is an intermediate frame picture, and setting the starting coordinates of the local motion area set in each first picture includes:

[0027] Set the starting coordinates of the local motion area in the start frame image and the starting coordinates in the end frame image;

[0028] The starting coordinates of the local motion region in the start frame picture and the starting coordinates of the local motion region in the end frame picture are calculated using a motion smoothing function to generate the starting coordinates of the local motion region in the intermediate frame picture.

[0029] In a second aspect, an embodiment of the present invention provides an image processing device, including:

[0030] Acquisition module, used to obtain the original image;

[0031] A first generating module, configured to calculate the original image according to a data processing algorithm to generate at least one first image corresponding to the original image;

[0032] The second generating module is configured to calculate each of the first images according to a local motion algorithm to generate a second image corresponding to each of the first images.

[0033] In a third aspect, an embodiment of the present invention provides a storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the image processing method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0034] In a fourth aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, and when the program instructions are loaded and executed by the processor, the steps of the image processing method in the above-mentioned first aspect or any possible implementation of the first aspect are implemented.

[0035] In a technical solution of a method, apparatus, storage medium, and computer device for image processing provided by an embodiment of the present invention, an original image is obtained; the original image is calculated according to a data processing algorithm to generate at least one first image corresponding to the original image; each first image is calculated according to a local motion algorithm to generate a second image corresponding to each first image, thereby improving the processing efficiency of the images.

Brief Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A flowchart of an image processing method provided by an embodiment of the present invention;

[0038] Figure 2 A flowchart of another image processing method provided by an embodiment of the present invention;

[0039] Figure 3 A flowchart of generating a third image provided by an embodiment of the present invention;

[0040] Figure 4 A flowchart of generating a second image provided by an embodiment of the present invention;

[0041] Figure 5 A schematic structural diagram of an image processing device provided by an embodiment of the present invention;

[0042] Figure 6 A schematic diagram of a computer device provided in an embodiment of the present invention. [Specific implementation method]

[0043] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0044] It should be understood that the embodiments described are only a portion of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0045] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0046] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0047] It should be understood that although the terms first, second, third, etc. may be used to describe numbers in embodiments of the present invention, these numbers should not be limited to these terms. These terms are merely used to distinguish numbers from each other. For example, a first number may also be referred to as a second number, and similarly, a second number may also be referred to as a first number without departing from the scope of embodiments of the present invention.

[0048] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0049] Figure 1 A flowchart of a method for processing an image provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method includes:

[0050] Step 101: Get the original image.

[0051] Each step of the embodiment of the present invention may be performed by a computer device, which includes a server and electronic devices, including but not limited to mobile phones, tablet computers, portable PCs, desktop computers, wearable devices, etc.

[0052] Step 102: Calculate the original image according to a data processing algorithm to generate at least one first image corresponding to the original image.

[0053] In an embodiment of the present invention, the data processing algorithm includes an exposure simulation algorithm and / or a global motion algorithm. As an optional solution, the data processing algorithm includes an exposure simulation algorithm and a global motion algorithm.

[0054] Step 103: Calculate each first image according to a local motion algorithm to generate a second image corresponding to each first image.

[0055] In the embodiment of the present invention, the computer device sets a local motion region for each first image, and generates a second image corresponding to each first image according to the set local motion region for each first image.

[0056] In a technical solution of an image processing method provided by an embodiment of the present invention, an original image is obtained; the original image is calculated according to a data processing algorithm to generate at least one first image corresponding to the original image; each first image is calculated according to a local motion algorithm to generate a second image corresponding to each first image, thereby improving the processing efficiency of the image.

[0057] Figure 2 A flowchart of another image processing method provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the method includes:

[0058] Step 201: Get the original image.

[0059] In the embodiment of the present invention, the computer device obtains any one picture from multiple pictures as the original picture.

[0060] Step 202: Calculate the original image according to an exposure simulation algorithm to generate at least one third image corresponding to the original image.

[0061] In the embodiment of the present invention, the exposure simulation algorithm includes a data rounding algorithm and a data truncation algorithm.

[0062] In the embodiment of the present invention, Figure 3 A flowchart of generating a third picture is provided in an embodiment of the present invention, such as Figure 3 As shown, step 202 may specifically include:

[0063] Step 2021: Convert the pixel values ​​in the original image into floating-point data.

[0064] In the embodiment of the present invention, the computer device converts the pixel values ​​of the original image into floating-point data of the floating-point type.

[0065] Step 2022: Calculate the floating-point data according to a right-shift rounding algorithm to generate first data.

[0066] In an embodiment of the present invention, since the human eye is more sensitive to bright areas and insensitive to dark areas, the data in the original image is converted into floating-point data, and then the floating-point data is right-shifted and rounded to compensate for the loss of details in the dark areas of the data. The computer device brings the floating-point data into the right-shifted and rounded formula to generate the first data corresponding to the floating-point data. The computer device calculates each floating-point data according to the right-shifted and rounded formula to generate the first data corresponding to each floating-point data. Since the exponential parameter in the right-shifted and rounded formula can be replaced, multiple first data images corresponding to the original image under different exposures can be simulated. For example, the right-shifted and rounded formula is y=2 n x, where x is any data in the floating point data image, and n is the exponent parameter. When n = 2, the right shift rounding formula is y = 2 2 When the original image is an 8-bit image, the value range of any pixel value in the original image is greater than or equal to 0 and less than or equal to 255. Since the computer device converts the pixel value data of the original image into floating-point data, the value range of any floating-point data is greater than or equal to 0 and less than or equal to 255. For example, any floating-point data is 128. The computer device converts the pixel value data of the original image into floating-point data according to y=2 2 x, x=128, and the result is y=512.

[0067] Step 2023: Calculate the first data according to the data truncation algorithm to generate a third image.

[0068] In an embodiment of the present invention, a computer device right-shifts, rounds, and then truncates floating-point data to compensate for detail loss in bright areas. Thus, under different exposure conditions, the exposure performance of the data in the third image generated by the computer device is consistent with the exposure performance of the real data. The computer device determines the value range of the first data based on the bit value of the original image; the computer device truncates the first data that is not within the value range based on the value range of the first data, thereby obtaining first data within the value range, allowing the computer device to generate a third image based on the first data within the value range. For example, the bit value of the original image is 8 bits, and the value range of any first data is greater than or equal to 0 and less than or equal to 255. Any first data is 512; the computer device performs data truncation calculation on 512 based on the value range of any first data being greater than or equal to 0 and less than or equal to 255, obtaining y as 255.

[0069] Step 203: Calculate at least one third picture according to a global motion algorithm to generate a first picture corresponding to each third picture.

[0070] In the embodiment of the present invention, before step 203, the further step includes: adjusting the size of each third image. For example, the computer device adjusts the size of the third image by at least one of downsampling, cropping, and upsampling.

[0071] The global motion algorithm includes a data augmentation algorithm and a center cropping algorithm. The computer device performs calculations on each resized third image according to the data augmentation algorithm to generate a fourth image corresponding to each third image. The data augmentation algorithm includes at least one of a rotation algorithm, a translation algorithm, and a flipping algorithm. The computer device performs calculations on each fourth image according to the center cropping algorithm to generate a first image corresponding to each fourth image. The fourth image is then cropped from the center to the target size, effectively avoiding the problem of abnormal loss of data detail caused by the need to use specified pixel values ​​for edge padding.

[0072] Step 204: Generate a second picture corresponding to each first picture according to the set local motion area of ​​each first picture.

[0073] In the embodiment of the present invention, Figure 4 A flowchart of generating a second image is provided in an embodiment of the present invention, such as Figure 4 As shown, step 204 may specifically include:

[0074] Step 2041: Set the starting coordinates of the local motion area in each first image.

[0075] In an embodiment of the present invention, the number of first images is at least two. The first image of at least two first images is a start frame image, the last image is an end frame image, and any first image other than the start frame image and the end frame image of at least two first images is an intermediate frame image. The computer device sets the starting coordinates of the local motion area in the start frame image and the starting coordinates in the end frame image; calculates the starting coordinates of the local motion area in the start frame image and the starting coordinates of the local motion area in the end frame image through a motion smoothing function, and generates the starting coordinates of the local motion area in the intermediate frame image, thereby maintaining the continuity and consistency of the local motion, which is more consistent with the local motion in a real scene.

[0076] Step 2042: According to the starting coordinates of the local motion region in each first image, translate the local motion region so that the designated coordinates of the local motion region coincide with the starting coordinates of the local motion region in each first image, so as to generate a second image corresponding to each first image.

[0077] In the embodiment of the present invention, the designated coordinates of the local motion region are the coordinates of any point in the local motion region. For example, the designated coordinates of the local motion region are the coordinates of the upper left point of the local motion region.

[0078] In one possible implementation of the embodiments of the present invention, step 204 may further include: generating an image sequence set based on the original image and at least two second images, wherein the image sequence set includes the original image and the at least two second images; or generating an image sequence set based on the at least two second images, wherein the image sequence set includes the at least two second images. This enables the use of a single image frame to simulate multiple images, saving significant labor and time costs in data acquisition and processing.

[0079] In a technical solution of an image processing method provided by an embodiment of the present invention, an original image is obtained; the original image is calculated according to a data processing algorithm to generate at least one first image corresponding to the original image; each first image is calculated according to a local motion algorithm to generate a second image corresponding to each first image, thereby improving the processing efficiency of the image.

[0080] Figure 5 A schematic diagram of the structure of an image processing device provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the device includes: an acquisition module 11, a first generation module 12 and a second generation module 13.

[0081] The acquisition module 11 is connected to the first generation module 12 , and the first generation module 12 is connected to the second generation module 13 .

[0082] The acquisition module 11 is used to obtain the original image; the first generation module 12 is used to calculate the original image according to the data processing algorithm to generate at least one first image corresponding to the original image; the second generation module 13 is used to calculate each first image according to the local motion algorithm to generate a second image corresponding to each first image.

[0083] In the embodiment of the present invention, the first generation module 12 includes: a first generation submodule 121 and a second generation submodule 122. The first generation submodule 121 and the second generation submodule 122 are connected.

[0084] The first generation submodule 121 is used to calculate the original image according to the exposure simulation algorithm to generate at least one third image corresponding to the original image; the second generation submodule 122 is used to calculate the at least one third image according to the global motion algorithm to generate a first image corresponding to each third image.

[0085] In an embodiment of the present invention, the first generation submodule 121 is specifically used to convert the pixel values ​​in the original image into floating-point data; calculate the floating-point data according to the right shift and integer algorithm to generate the first data; and calculate the first data according to the data truncation algorithm to generate the third image.

[0086] In the embodiment of the present invention, the device further includes: an adjustment module 14. The adjustment module 14 is connected to the first generation submodule 121 and the second generation submodule 122.

[0087] The adjusting module 14 is configured to adjust the size of each third picture.

[0088] The second generation submodule 122 is specifically configured to calculate each resized third image according to a global motion algorithm to generate a fourth image corresponding to each third image; and calculate each fourth image according to a center cropping algorithm to generate a first image corresponding to each fourth image.

[0089] In this embodiment of the present invention, the second generation module 13 is specifically configured to generate the second image corresponding to each first image based on the local motion region of each first image. The second generation module 13 includes a setting submodule 131 and a third generation submodule 132. The setting submodule 131 and the third generation submodule 132 are connected.

[0090] The setting submodule 131 is used to set the starting coordinates of the local motion area in each first image; the third generation submodule 132 is used to translate the local motion area according to the starting coordinates of the local motion area in each first image so that the specified coordinates of the local motion area coincide with the starting coordinates of the local motion area in each first image, so as to generate a second image corresponding to each first image.

[0091] In an embodiment of the present invention, the first picture of at least two first pictures is a start frame picture, the last picture is an end frame picture, and any first picture other than the start frame picture and the end frame picture of at least two first pictures is an intermediate frame picture. The setting submodule 131 is specifically used to set the starting coordinates of the local motion area in the start frame picture and the starting coordinates in the end frame picture; the starting coordinates of the local motion area in the start frame picture and the starting coordinates of the local motion area in the end frame picture are calculated by a motion smoothing function to generate the starting coordinates of the local motion area in the intermediate frame picture.

[0092] In the embodiment of the present invention, the device further includes a third generating module 15 . The third generating module 15 is connected to the second generating module 13 .

[0093] The third generating module 15 is used to generate an image sequence set according to the original picture and at least two second pictures; or, the third generating module 15 is used to generate an image sequence set according to at least two second pictures.

[0094] In a technical solution of an image processing device provided by an embodiment of the present invention, an original image is obtained; the original image is calculated according to a data processing algorithm to generate at least one first image corresponding to the original image; each first image is calculated according to a local motion algorithm to generate a second image corresponding to each first image, thereby improving the processing efficiency of the image.

[0095] An embodiment of the present invention provides a storage medium, which includes a stored program. When the program is running, the device where the storage medium is located is controlled to execute the steps of the embodiment of the above-mentioned image processing method. For a specific description, please refer to the embodiment of the above-mentioned image processing method.

[0096] An embodiment of the present invention provides a computer device including a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. When the program instructions are loaded and executed by the processor, the steps of the embodiment of the above-mentioned image processing method are implemented. For a specific description, please refer to the embodiment of the above-mentioned image processing method.

[0097] Figure 6 Schematic diagram of a computer device provided by an embodiment of the present invention. Figure 6 As shown, the computer device 30 of this embodiment includes: a processor 31, a memory 32, and a computer program 33 stored in the memory 32 and executable by the processor 31. When executed by the processor 31, the computer program 33 implements the image processing method of the embodiment. To avoid repetition, the details are not described here. Alternatively, when executed by the processor 31, the computer program implements the functions of each model / unit in the data processing device of the embodiment. To avoid repetition, the details are not described here.

[0098] The computer device 30 includes, but is not limited to, a processor 31 and a memory 32. Those skilled in the art will understand that Figure 6 This is merely an example of the computer device 30 and does not constitute a limitation of the computer device 30 . The computer device 30 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device 30 may also include input and output devices, network access devices, buses, etc.

[0099] The processor 31 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0100] The memory 32 can be an internal storage unit of the computer device 30, such as a hard drive or memory of the computer device 30. The memory 32 can also be an external storage device of the computer device 30, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the computer device 30. Furthermore, the memory 32 can include both an internal storage unit of the computer device 30 and an external storage device. The memory 32 is used to store computer programs and other programs and data required by the computer device 30. The memory 32 can also be used to temporarily store data that has been output or is about to be output.

[0101] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0102] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0104] In addition, the functional units in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional units.

[0105] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform some steps of the method described in various embodiments of the present invention. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., various media that can store program code.

[0106] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for image processing, characterized in that: include: Get the original image; Calculating the original image according to a data processing algorithm to generate at least one first image corresponding to the original image; Calculate each of the first pictures according to a local motion algorithm to generate a second picture corresponding to each of the first pictures; The calculating the original picture according to the data processing algorithm to generate at least one first picture corresponding to the original picture includes: Calculating the original image according to an exposure simulation algorithm to generate at least one third image corresponding to the original image; Calculate the at least one third picture according to a global motion algorithm to generate the first picture corresponding to each third picture; The calculating each of the first pictures according to the local motion algorithm to generate a second picture corresponding to each of the first pictures includes: The second picture corresponding to each first picture is generated according to the set local motion area of ​​each first picture.

2. The method according to claim 1, characterized in that The calculating the original image according to the exposure simulation algorithm to generate at least one third image corresponding to the original image includes: Converting pixel values ​​in the original image into floating-point data; Calculating the floating-point data according to a right-shift rounding algorithm to generate first data; The first data is calculated according to a data truncation algorithm to generate the third image.

3. The method according to claim 1, characterized in that Before calculating the at least one third picture according to the global motion algorithm to generate the first picture corresponding to each third picture, the method further includes: adjusting the size of each third picture; Calculating the at least one third picture according to a global motion algorithm to generate the first picture corresponding to each third picture includes: performing calculations on each of the resized third images according to a data augmentation algorithm to generate a fourth image corresponding to each of the third images; Calculate each of the fourth images according to a center cropping algorithm to generate the first image corresponding to each of the fourth images.

4. The method according to claim 1, wherein Generating the second picture corresponding to each first picture according to the set local motion area of ​​each first picture includes: Setting the starting coordinates of the local motion region in each of the first pictures; According to the starting coordinates of the local motion area in each of the first images, the local motion area is translated so that the designated coordinates of the local motion area coincide with the starting coordinates of the local motion area in each of the first images, so as to generate a second image corresponding to each of the first images.

5. The method according to claim 4, characterized in that The first picture of the at least two first pictures is a start frame picture, and the last picture is an end frame picture. Any first picture other than the start frame picture and the end frame picture of the at least two first pictures is an intermediate frame picture. Setting the starting coordinates of the local motion area in each of the first pictures includes: Set the starting coordinates of the local motion area in the start frame image and the starting coordinates in the end frame image; The starting coordinates of the local motion region in the start frame picture and the starting coordinates of the local motion region in the end frame picture are calculated using a motion smoothing function to generate the starting coordinates of the local motion region in the intermediate frame picture.

6. A picture processing device, characterized in that: include: Acquisition module, used to obtain the original image; A first generating module, configured to calculate the original image according to a data processing algorithm to generate at least one first image corresponding to the original image; a second generating module, configured to calculate each of the first images according to a local motion algorithm to generate a second image corresponding to each of the first images; The first generating module is further configured to calculate the original image according to an exposure simulation algorithm to generate at least one third image corresponding to the original image; Calculate the at least one third picture according to a global motion algorithm to generate the first picture corresponding to each third picture; The second generating module is further configured to generate the second image corresponding to each first image according to the set local motion region of each first image.

7. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the device where the storage medium is located is controlled to execute the image processing method according to any one of claims 1 to 5.

8. A computer device comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that: When the program instructions are loaded and executed by the processor, the steps of the image processing method described in any one of claims 1 to 5 are implemented.

Images