A dynamic rendering adjustment method, device and storage medium

Abstract

The present invention relates to the field of image data processing technology, and specifically discloses a dynamic rendering adjustment method, device and storage medium, including the following steps: S01, retrieve the original image data of a predetermined range of the target area according to the input target location; S02, match the original image data with a grid mask to form a number of rectangular pixel blocks with coordinates; S03, correct each of the rectangular pixel blocks according to a correction model to obtain a corrected pixel block; S04, fill the obtained corrected pixel block with the grid mask corresponding to the coordinate to obtain a corrected image. The invention extracts pixels from the image data and processes them through a correction model to obtain corrected pixels, and then processes the saturation to give a high-definition image, so as to better implement the smart city tourist guide system.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a dynamic rendering adjustment method, device and storage medium. Background Art

[0002] Image processing technology (reference publication (announcement) number: CN104599304B, publication (announcement) date: 2018-06-08, a disclosed image processing technology) is to perform operations such as denoising, enhancing contrast, adjusting brightness and color balance on images to improve image quality, and then repairing damaged images or removing noise in images to obtain images that are clear enough to be recognized.

[0003] With the rapid development of the tourism industry, more and more young people tend to travel by themselves, and use navigation systems and public software platforms to obtain local attractions and photo-taking spots. The use of the navigation system is to navigate to the vicinity of the scenic spot, and then find the destination by asking, etc., and the terrain is not clear, so it is necessary to rely on navigation frequently. If the signal is poor, navigation deviation will occur. How to use smart cities to solve the above problems, so as to greatly facilitate tourists who travel by themselves to understand the road conditions of the scenic spots more quickly, is expected to be well solved. Summary of the invention

[0004] The purpose of the present invention is to provide a dynamic rendering adjustment method, device and storage medium to solve the above problems.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a dynamic rendering adjustment method, comprising the following steps:

[0006] S01, retrieving original image data of a predetermined range of a target area according to an input target location;

[0007] S02, matching the original image data with a grid mask to form a number of rectangular pixel blocks with coordinates;

[0008] S03, correcting each of the rectangular pixel blocks according to the correction model to obtain a corrected pixel block;

[0009] S04, filling the obtained corrected pixel block with the grid mask corresponding to the coordinates to obtain a corrected image;

[0010] S05, respectively extracting saturation data of adjacent corrected pixel blocks at the grid mask lines corresponding to the corrected image, and respectively performing repairs to obtain a high-definition image;

[0011] S06. Input the high-definition image into the dynamic model to obtain a set of several frames of high-definition proportional images.

[0012] Preferably, the division of a number of rectangular pixel blocks with coordinates in step S02 includes:

[0013] S21, identifying image units in the original image data, creating a new framed area, and filling the framed areas in sequence according to the color scale order;

[0014] S22, extracting rectangular pixel blocks from the framed area in sequence according to the color scale, and generating pixel sets x1, ..., x1 according to the color scale. n , where: the extracted rectangular pixel block generates coordinates with a grid mask;

[0015] S23, pixel sets x1, ..., x n After executing step S03 respectively, the selected area is backfilled into the grid mask to obtain a corrected pixel block.

[0016] Preferably, the division of a number of rectangular pixel blocks with coordinates in step S02 further comprises:

[0017] S24, backfilling the image acquired in the grid mask based on the primary correction pixel block, dividing it into rectangular pixel blocks again according to the grid mask, and then executing step S03 to obtain a secondary correction pixel block.

[0018] Preferably, the correction model in step S03 corrects each correction pixel block separately, including:

[0019] S31, creating color level groups for corrected pixel blocks of the same color level;

[0020] S32, creating a convolution kernel of a Gaussian function, and convolving the Gaussian kernel with the image, wherein the convolution refers to multiplying each value of the kernel with the corresponding pixel value in the image and summing the results to finally obtain each pixel value of the new image;

[0021] S33. Use a generative adversarial network or autoencoder to repair each pixel value.

[0022] Preferably, the step S05 of repairing and extracting the saturation data of the adjacent corrected pixel blocks at the corresponding grid mask line includes:

[0023] S51, converting the adjacent corrected pixel blocks from BRG to HSV color space;

[0024] S52, extracting the S channel in the HSV color space of each positive pixel block to obtain the extracted saturation;

[0025] S53, obtaining statistical data for calculating saturation based on the standard deviation;

[0026] S54, setting a saturation adjustment factor based on statistical data;

[0027] S55 , creating an adjusted HSV image based on the saturation adjustment factor, and finally converting it into a BRG format.

[0028] Preferably, the standard deviation of saturation in step S53 is ;

[0029] Among them, Mean is the saturation mean, S i is the saturation value of the i-th pixel, and N is the total number of pixels.

[0030] Preferably, the step S06 of obtaining a set of several frames of high-definition equal-scale images includes:

[0031] S61, obtaining the length h and w of the high-definition image based on the grid mask;

[0032] S62, then import the formula:

[0033] ;

[0034] ;

[0035] Among them, L w is the width center offset, W i is the window width, W j To represent the image width, L h is the height center offset, H i is the window height, H j To represent the image height, P w is the image pixel width magnification ratio, P h The image pixel height magnification ratio;

[0036] S62. Perform scaling based on the acquired width center offset and height center offset and by setting a random origin within the coordinates.

[0037] In the above technical solution, the present invention provides a dynamic rendering adjustment method, device and storage medium, which have the following beneficial effects:

[0038] 1. By acquiring the image data of smart transportation and smart security in smart cities, the image data is sorted out to form a smart city tourist guide system. By inputting the geographic location, the building and road data of the predetermined community around the geographic location can be obtained, so that tourists can judge their geographic location with the scenic spot based on the image data;

[0039] 2. The data is updated in real time. Tourists can judge the current flow of people in the scenic area through image data, which facilitates entry during peak hours and improves the tourists' experience;

[0040] 3. By extracting pixels from image data and processing them through a correction model, corrected pixels are obtained, and then saturation processing is performed to produce a high-definition image. By using the preset image scaling process, it is ensured that when the image is enlarged, it can be kept clear in seconds. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0042] Figure 1 A flowchart provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1

[0045] like Figure 1 As shown, a dynamic rendering adjustment method includes the following steps:

[0046] S01, retrieving original image data of a predetermined range of a target area according to an input target location;

[0047] S02, matching the original image data with the grid mask to form a number of rectangular pixel blocks with coordinates;

[0048] S03, correcting each rectangular pixel block according to the correction model to obtain a corrected pixel block;

[0049] S04, filling the obtained corrected pixel block according to the grid mask corresponding to the coordinates to obtain a corrected image;

[0050] S05, respectively extracting saturation data of adjacent corrected pixel blocks at the grid mask lines corresponding to the corrected image, and performing repairs respectively to obtain a high-definition image;

[0051] S06, inputting the high-definition image into the dynamic model, and obtaining the length h and w of the high-definition image based on the grid mask;

[0052] Then import the formula:

[0053] ;

[0054] ;

[0055] Among them, L w is the width center offset, W i is the window width, W j To represent the image width, L h is the height center offset, H i is the window height, H j To represent the image height, P w is the image pixel width magnification ratio, P h The image pixel height magnification ratio;

[0056] Based on the obtained width center offset and height center offset, a random origin is set within the coordinates to perform scaling, and the data is aggregated to obtain a set of high-definition proportional images of several frames.

[0057] Specifically, the above technology obtains the image data of smart transportation and smart security in the smart city, and then organizes them to form a smart city tourist guide system. By inputting the geographical location, the building and road data of the predetermined community around the geographical location can be obtained, so that tourists can judge their geographical location with the scenic spot according to the image data. In addition, the data is updated in real time. Tourists can judge the current flow of people in the scenic spot through the image data, so as to facilitate entry during peak hours and improve the tourists' experience.

[0058] Secondly, the above step S01 acquires the original image data according to the set window period, and after acquisition, the original image data of the previous window period is formatted to fill the running memory and avoid data processing jams caused by insufficient memory.

[0059] Embodiment 2

[0060] Based on the first embodiment, this embodiment aims to solve the processing of dividing a number of rectangular pixel blocks with coordinates, and the detailed steps are as follows:

[0061] S21, identifying image units in the original image data, creating a new framed area, and filling the framed areas in sequence according to the color scale order;

[0062] S22, extracting rectangular pixel blocks from the framed area in sequence according to the color scale, and generating pixel sets x1, ..., x1 according to the color scale. n , where: the extracted rectangular pixel block generates coordinates with a grid mask;

[0063] S23, pixel sets x1, ..., x n After executing step S03 respectively, the selected area is backfilled into the grid mask to obtain a corrected pixel block.

[0064] Specifically, the image unit recognition in the embodiment is based on the target algorithm to recognize specific objects in the original image, such as YOLO, SSD and Faster R-CNN. In this embodiment, pixel processing is performed by the image unit, and then processed by the correction model in step S03, so as to obtain the corrected pixel of the image unit.

[0065] Embodiment 3

[0066] Based on the second embodiment, after obtaining the corrected pixels of the image unit, this embodiment backfills them into the grid mask according to the coordinates to generate a corrected image, and then divides the obtained primary image into rectangular pixel blocks again according to the grid mask, and then executes step S03 to obtain a secondary corrected pixel block.

[0067] Specifically, through the staged correction process, local optimization can be performed at each stage to gradually improve the overall correction effect of the image. After the first correction image is generated, the second correction is performed in blocks, which can more accurately handle the pixel problems in the local area, thereby improving the correction accuracy.

[0068] Secondly, some problems in the image may not be completely solved by a single correction. Using multiple correction methods can better handle complex image problems, such as missing details or uneven correction in the image. After the first correction, a refined secondary correction can further repair details and local defects in the image.

[0069] Furthermore, in a single global correction, errors in local areas may be magnified or masked. By dividing the image into rectangular pixel blocks, more precise adjustments and corrections can be made locally, thereby reducing the errors that may occur in global correction.

[0070] Through staged correction, each stage can focus on specific quality improvement goals. That is, the first correction may focus on the overall smoothing and denoising of the image, while the second correction can further enhance the details and edge clarity of the image, thereby improving the overall quality of the final image.

[0071] Embodiment 3

[0072] Based on the first embodiment, this embodiment aims to solve the problem that the correction model in step S03 corrects each correction pixel block separately, including:

[0073] S31, creating color level groups for corrected pixel blocks of the same color level;

[0074] S32, creating a convolution kernel of a Gaussian function, and convolving the Gaussian kernel with the image, where convolution refers to multiplying each value of the kernel with the corresponding pixel value in the image and summing the results to finally obtain each pixel value of the new image;

[0075] S33. Use a generative adversarial network or autoencoder to repair each pixel value.

[0076] In the above embodiment, the pixel blocks of the same color level are collected together to form a color level group. The purpose of doing so is probably to find the pattern or law of the color, so that correction can be performed more effectively.

[0077] Secondly, a function is a common mathematical expression that can help us find local features and changes in an image. In this step, we use a Gaussian kernel (a matrix determined by a Gaussian function) to perform a convolution operation with the image. The convolution operation is a mathematical operation that overlaps and weighted sums the Gaussian kernel matrix with each part of the image to produce a new image, and this process can help enhance the edges in the image or smooth the image.

[0078] Secondly, Generative Adversarial Networks (GANs) or Autoencoders are used to repair defects in images. Generative Adversarial Networks is a technique that trains two neural networks to compete with each other, one responsible for generating new images and the other responsible for determining whether the generated images are real. Through such adversarial training, the performance of the generated network can be improved. Autoencoders are neural network models that learn to encode input data into a latent space representation and decode the original input data from it. They can also learn the structure of the input data, which can be used to repair images.

[0079] Embodiment 4

[0080] Based on the first embodiment, this embodiment aims to restore and extract the saturation data of the adjacent corrected pixel blocks at the corresponding grid mask line in step S05, and adjust the intensity of the color in the image to make the image appear more vivid or softer. The detailed steps include:

[0081] S51, converting the adjacent corrected pixel blocks from BRG to HSV color space;

[0082] S52, extracting the S channel in the HSV color space of each positive pixel block to obtain the extracted saturation;

[0083] S53, obtaining statistical data for calculating saturation based on the standard deviation;

[0084] S54, setting a saturation adjustment factor based on statistical data;

[0085] S55. Create an adjusted HSV image based on the saturation adjustment factor, and finally convert it into BRG format.

[0086] Furthermore, the standard deviation of saturation in step S53 = ;

[0087] Among them, Mean is the saturation mean, S i is the saturation value of the i-th pixel, and N is the total number of pixels.

[0088] In the embodiment, the above saturation calculation method is explained by the following example:

[0089] Suppose you have an image with the following saturation value set: S={100, 150, 200, 250}, calculate the mean:

[0090] Calculate the sum of all saturation values: 100+150+200+250=700;

[0091] Total number of pixels: N=4;

[0092] Mean: Mean=700 / 4=175;

[0093] Compute the difference of each value from the mean and square it:

[0094] (100-175) 2 =5625;

[0095] (150-175) 2 =625;

[0096] (200-175) 2 =625;

[0097] (250-175) 2 =5625;

[0098] Find the average of these square differences: (5625+625+625+562) / 4=3125;

[0099] Calculate the standard deviation: .

[0100] By extracting pixels from the image data and processing them through a correction model, corrected pixels are obtained, and then saturation is processed to produce a high-definition image.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0103] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all steps of the method in the above embodiments, and the electronic device specifically includes the following contents:

[0104] Processor, memory, communications interface and bus;

[0105] Wherein, the processor, memory, and communication interface communicate with each other via the bus;

[0106] The processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the method in the above embodiment are implemented.

[0107] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps of the method in the above embodiments are implemented.

[0108] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Although the embodiment of this specification provides the method operation steps as described in the embodiment or flowchart, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way of executing the order of many steps, and does not represent the only execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiments of this specification.

[0110] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradicting each other. The above is only an embodiment of the embodiment of this specification and is not intended to limit the embodiment of this specification. For those skilled in the art, the embodiment of this specification may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of this specification shall be included in the scope of the claims of the embodiment of this specification.

Claims

1. A dynamic rendering adjustment method, characterized in that: The following steps are involved: S01, retrieving original image data of a predetermined range of a target area according to an input target location; S02, matching the original image data with a grid mask to form a number of rectangular pixel blocks with coordinates; S03, correcting each of the rectangular pixel blocks according to the correction model to obtain a corrected pixel block; S04, filling the obtained corrected pixel block with the grid mask corresponding to the coordinates to obtain a corrected image; S05, respectively extracting saturation data of adjacent corrected pixel blocks at the grid mask lines corresponding to the corrected image, and respectively performing repairs to obtain a high-definition image; S06, inputting the high-definition image into the dynamic model to obtain a set of high-definition equal-scale images of several frames; The division of a number of rectangular pixel blocks with coordinates in step S02 includes: S21, identifying image units in the original image data, creating a new framed area, and filling the framed areas in sequence according to the color scale order; S22, extracting rectangular pixel blocks from the framed area in sequence according to the color scale, and generating pixel sets x1, ..., x1 according to the color scale. n , where: the extracted rectangular pixel block generates coordinates with a grid mask; S23, pixel sets x1, ..., x n After executing step S03 respectively, backfilling is performed into the grid mask according to the framed area to obtain a corrected pixel block; The division of a number of rectangular pixel blocks with coordinates in step S02 further includes: S24, backfilling the image acquired in the grid mask based on the primary correction pixel block, dividing it into rectangular pixel blocks again according to the grid mask, and then executing step S03 again to obtain a secondary correction pixel block; The correction model in step S03 corrects each correction pixel block respectively, including: S31, creating color level groups for corrected pixel blocks of the same color level; S32, creating a convolution kernel of a Gaussian function, and convolving the Gaussian kernel with the image, wherein the convolution refers to multiplying each value of the kernel with the corresponding pixel value in the image and summing the results to finally obtain each pixel value of the new image; S33. Use a generative adversarial network or autoencoder to repair each pixel value.

2. A dynamic rendering adjustment method according to claim 1, characterized in that: The step S05 of repairing and extracting the saturation data of the adjacent corrected pixel blocks at the corresponding grid mask line includes: S51, converting the adjacent corrected pixel blocks from BRG to HSV color space; S52, extracting the S channel in the HSV color space of each positive pixel block to obtain the extracted saturation; S53, obtaining statistical data for calculating saturation based on the standard deviation; S54, setting a saturation adjustment factor based on statistical data; S55 , creating an adjusted HSV image based on the saturation adjustment factor, and finally converting it into a BRG format.

3. A dynamic rendering adjustment method according to claim 2, characterized in that: The standard deviation of saturation in step S53 = ; Among them, Mean is the saturation mean, S i is the saturation value of the i-th pixel, and N is the total number of pixels.

4. The dynamic rendering adjustment method according to claim 1, characterized in that: The step S06 of obtaining a set of several frames of high-definition equal-scale images includes: S61, obtaining the length h and w of the high-definition image based on the grid mask; S62, then import the formula: ; ； Among them, L w is the width center offset, W i is the window width, W j To represent the image width, L h is the height center offset, H i is the window height, H j To represent the image height, P w is the image pixel width magnification ratio, P h is the image pixel height magnification ratio; S63. Perform scaling based on the acquired width center offset and height center offset and by setting a random origin within the coordinates.

5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the dynamic rendering adjustment method according to any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the dynamic rendering adjustment method according to any one of claims 1 to 4 are implemented.

Images