Color cast calibration method and device in virtual shooting and electronic equipment

Abstract

The invention relates to the technical field of virtual shooting, and discloses a color cast calibration method and device in virtual shooting and electronic equipment. The method comprises the steps of obtaining an input color and a target color; determining a ternary cubic linear model based on the input color and the target color; solving the ternary cubic linear model to obtain a target linear model; and inputting the target color into the target linear model to obtain the color value of the input color, thereby realizing mapping from the target color to the input color, and avoiding color shift while realizing color coordination of the synthesized picture.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of virtual shooting, and in particular to a color deviation calibration method and device in virtual shooting and an electronic device. BACKGROUND

[0002] With the continuous progress of display and control technology, virtual shooting is increasingly applied in film and television shooting production. Virtual shooting usually displays part of virtual scene pictures as a background by using multiple LED screens, uses real objects as foreground, and uses an image acquisition device to shoot the foreground and the background to obtain a target image. Then, a rendering system is used to fuse the target image and virtual pictures that are not displayed on the LED screen, so that virtual information and real environment can be combined ingeniously.

[0003] The currently used LED screen cannot cover the entire color space due to the color gamut area, so that the displayed picture has a certain color deviation. At the same time, due to the different performances of image acquisition devices, the image color obtained after the picture displayed on the LED screen is shot by the image acquisition device has a color deviation relative to the virtual background color, which greatly affects the normal viewing experience after shooting of the material. SUMMARY

[0004] Therefore, it is necessary to provide a color deviation calibration method and device in virtual shooting and an electronic device to avoid color deviation.

[0005] In a first aspect, an embodiment of the present application provides a color deviation calibration method in virtual shooting, and the method comprises the following steps.

[0006] Obtaining an input color and a target color;

[0007] Determining a ternary cubic linear model based on the input color and the target color;

[0008] Solving the ternary cubic linear model to obtain a target linear model;

[0009] Inputting the target color into the target linear model to obtain a color value of the input color.

[0010] In some embodiments, the ternary cubic linear model is used to represent the association between each color channel of the input color and the target color.

[0011] In some embodiments, the input color and the target color are obtained by the following steps.

[0012] Obtaining an RGB-based color space;

[0013] Equidistantly collecting part of color values from the color space as input colors;

[0014] control the LED display screen to display the same input color;

[0015] obtain a target color corresponding to the input color.

[0016] In some embodiments, the solving the ternary cubic linear model to obtain a target linear model comprises:

[0017] using a root mean square error as a loss function of the ternary cubic linear model to calculate a loss value of the ternary cubic linear model;

[0018] optimizing the ternary cubic linear model by a gradient descent algorithm to obtain the target linear model.

[0019] In the second aspect, the embodiments of the present application further provide a color cast calibration device in virtual shooting, and the device comprises:

[0020] an acquisition module, configured to acquire an input color and a target color;

[0021] a determination module, configured to determine a ternary cubic linear model based on the input color and the target color;

[0022] a calculation module, configured to solve the ternary cubic linear model to obtain a target linear model;

[0023] an input module, configured to input the target color into the target linear model to obtain a color value of the input color.

[0024] In some embodiments, the acquisition module is specifically configured to:

[0025] acquire an RGB-based color space;

[0026] collect part of color values as input colors at equal intervals from the color space;

[0027] control the LED display screen to display the same input color;

[0028] obtain a target color corresponding to the input color.

[0029] In some embodiments, the calculation module is specifically configured to:

[0030] use a root mean square error as a loss function of the ternary cubic linear model to calculate a loss value of the ternary cubic linear model;

[0031] optimize the ternary cubic linear model by a gradient descent algorithm to obtain the target linear model.

[0032] In the third aspect, the embodiments of the present application further provide an electronic device, comprising:

[0033] At least one processor; and,

[0034] A memory communicatively connected to the at least one processor; wherein,

[0035] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of the first aspect described above.

[0036] Fourthly, embodiments of this application also provide a non-volatile computer-readable storage medium storing computer-executable instructions that, when executed by a processor, cause the processor to perform the method described in the first aspect.

[0037] Fifthly, embodiments of this application also provide a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, implement the method described in the first aspect above.

[0038] Compared with the prior art, the beneficial effects of this application are as follows: Unlike the prior art, the color cast calibration method in virtual shooting provided by the embodiments of this application obtains the input color and the target color, determines a ternary cubic linear model based on the input color and the target color, solves the ternary cubic linear model to obtain the target linear model, and finally inputs the target linear model into the target linear model to obtain the color value of the input color. This realizes the mapping from the target color to the input color, and avoids color shift while achieving color coordination in the composite image. Attached Figure Description

[0039] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0040] Figure 1 This is a schematic flowchart of a color cast calibration method in virtual shooting provided in one embodiment of this application;

[0041] Figure 2 This is a schematic diagram of the structure of a color cast calibration device in virtual shooting provided in one embodiment of this application;

[0042] Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] It should be noted that, unless there is a conflict, the various features in the embodiments of this application can be combined with each other, all of which are within the protection scope of this application. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this application do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0045] like Figure 1 As shown, this application embodiment provides a color cast calibration method in virtual shooting. The method is executed by an electronic device and includes:

[0046] Step 100: Obtain the input color and the target color.

[0047] In this embodiment, RGB is selected as the color space for both the input and target colors. Then, partial color values ​​are collected at equal intervals from the entire color space as the input colors. Next, each LED display screen is controlled to display the same input color, and the corresponding target color is collected on each LED display screen using an image acquisition device.

[0048] Step 110: Determine a ternary cubic linear model based on the input color and the target color.

[0049] Since the values ​​of each channel in the target color are proportional to the luminous intensity of the entire LED display background wall, and the luminous intensity is jointly determined by the components of the RGB color space, the values ​​of the red, green, and blue components in the target color are jointly determined by the input color space. The input color in the collected data is [Ri n, Gi n, Bin], and the corresponding target color is [Rtarget, Gtarget, Btarget]. A ternary cubic linear model is used to characterize the relationship between each color channel of the input color and the target color.

[0050] R in =a1R target 3 +a2R target 2 Gtarget +a3R target 2 B target +a4R target G target 2

[0051] +a5R target B target 2 +a6G target 3 +a7G target 2 R target

[0052] +a8G target 2 B target +a9G target R target 2

[0053] +a 10 G target B target 2 a 11 B target 3 +a 12 B target 2 R target

[0054] +a 13 B target 2 G target +a 14 B target R target 2 +a 15 B target G target 2

[0055] G in 1R target 3 +a2R target 2 G target +a3R target 2 B target +a4R target G target 2

[0056] +a5R target B target 2+a6G target 3 +a7G target 2 R target

[0057] +a8G target 2 B target +a9G target R target 2

[0058] +a 10 G target B target 2 a 11 B target 3 +a 12 B target 2 R target

[0059] +a 13 B target 2 G target +a 14 B target R target 2 +a 15 B target G target 2

[0060] B in 1R target 3 +a2R target 2 G target +a3R target 2 B target +a4R target G target 2

[0061] +a5R target B target 2 +a6G target 3 +a7G target 2 R target

[0062] +a8G target 2 B target +a9G target Rtarget 2

[0063] +a 10 G target B target 2 a 11 B target 3 +a 12 B target 2 R target

[0064] +a 13 B target 2 G target +a 14 B target R target 2 +a 15 B target G target 2

[0065] Step 120: Solve the ternary cubic linear model to obtain the target linear model.

[0066] To solve for the model parameters, the root mean square error is used as the loss function of the ternary cubic linear model, and the loss value of the ternary cubic linear model is calculated. Then, the ternary cubic linear model is optimized by the gradient descent algorithm to obtain the target linear model.

[0067] loss = MSE(color) in ,color target )

[0068] Step 130: Input the target color into the target linear model to obtain the color value of the input color.

[0069] Because the solved target linear model can cover the entire color space, it can predict the mapping relationship between the target color and the input color based on the missing data in the low and high value regions of the target color. Inputting the target color into the target linear model yields the corresponding color value. In practical applications, the parameters of the linear model are usually sparse, requiring less computation and storage space compared to a color mapping table.

[0070] The color cast calibration method in virtual shooting provided in this application embodiment obtains the input color and the target color, determines a ternary cubic linear model based on the input color and the target color, solves the ternary cubic linear model to obtain the target linear model, and finally inputs the target linear model into the target linear model to obtain the color value of the input color. This realizes the mapping from the target color to the input color, achieving color coordination in the composite image while avoiding color shift.

[0071] Accordingly, embodiments of this application also provide a color cast calibration device 200 for virtual shooting, such as... Figure 2 As shown, the device 200 includes:

[0072] The acquisition module 210 is used to acquire the input color and the target color;

[0073] The determination module 220 is used to determine a ternary cubic linear model based on the input color and the target color;

[0074] Calculation module 230 is used to solve the ternary cubic linear model to obtain the target linear model;

[0075] The input module 240 is used to input the target color into the target linear model to obtain the color value of the input color.

[0076] The color cast calibration device for virtual shooting provided in this application embodiment acquires the input color and the target color through an acquisition module, then determines a ternary cubic linear model based on the input color and the target color through a determination module, then solves the ternary cubic linear model through a calculation module to obtain the target linear model, and finally inputs the target color into the target linear model through an input module to obtain the color value of the input color. This realizes the mapping from the target color to the input color, achieving color coordination in the composite image while avoiding color shift.

[0077] Optionally, in other embodiments of the device, the acquisition module 210 is specifically used for:

[0078] Obtain the RGB-based color space;

[0079] The color values ​​are sampled at equal intervals from the color space as input colors;

[0080] Control the LED display to show the same input color;

[0081] Obtain the target color corresponding to the input color.

[0082] Alternatively, in other embodiments of the device, the computing module 230 is specifically used for:

[0083] The root mean square error is used as the loss function of the ternary cubic linear model to calculate the loss value of the ternary cubic linear model.

[0084] The ternary cubic linear model is optimized using the gradient descent algorithm to obtain the target linear model.

[0085] It should be noted that the color cast calibration device in the virtual shooting described above can perform the corresponding functional modules and beneficial effects of the color cast calibration method in the virtual shooting provided in the embodiments of this application. For technical details not described in detail in the embodiments of the color cast calibration device in the virtual shooting, please refer to the color cast calibration method in the virtual shooting provided in the embodiments of this application.

[0086] Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application, such as... Figure 3 As shown, the electronic device 300 includes:

[0087] One or more processors 301 and memory 302, Figure 3 Let's take a processor as an example.

[0088] Processor 301 and memory 302 can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0089] The memory 302, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the color cast calibration method in the virtual shooting embodiment of this application. The processor 301 executes various functional applications and data processing of the electronic device by running the non-volatile software programs, instructions, and modules stored in the memory 302, thereby implementing the color cast calibration method in the virtual shooting of the above method embodiment.

[0090] Memory 302 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the color calibration device in virtual shooting, etc. Furthermore, memory 302 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 302 may optionally include memory remotely located relative to processor 301, and this remote memory can be connected to the color calibration device in virtual shooting via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0091] This application also provides a non-volatile computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are executed by one or more processors, they enable the processors to perform the color cast calibration method in virtual shooting in any of the above method embodiments.

[0092] This application also provides a machine program product, including a computer program or computer executable instructions, which, when executed by a processor, implements the color cast calibration method in virtual shooting in any of the above method embodiments.

[0093] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. 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 the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software and a general-purpose hardware platform, or of course, using hardware. Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them; under the concept of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of this application as described above, which are not provided in detail for the sake of brevity; although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for color cast calibration in virtual photography, characterized in that, The method comprises: acquiring an input color and a target color; determining a ternary cubic linear model based on the input color and the target color; solving the ternary cubic linear model to obtain a target linear model; inputting the target color into the target linear model to obtain a color value of the input color.

2. The method of claim 1, wherein, The ternary cubic linear model is used to represent the association between each color channel of the input color and the target color.

3. The method of claim 1, wherein, The acquiring of the input color and the target color comprises: acquiring an RGB-based color space; collecting part of color values as input colors from the color space at equal intervals; controlling an LED display screen to display the same input colors; acquiring target colors corresponding to the input colors.

4. The method of claim 1, wherein, The solving of the ternary cubic linear model to obtain the target linear model comprises: using a root mean square error as a loss function of the ternary cubic linear model to calculate a loss value of the ternary cubic linear model; optimizing the ternary cubic linear model through a gradient descent algorithm to obtain the target linear model.

5. A device for color cast calibration in virtual photography, characterized in that The device comprises: an acquisition module configured to acquire an input color and a target color; a determination module configured to determine a ternary cubic linear model based on the input color and the target color; a calculation module configured to solve the ternary cubic linear model to obtain a target linear model; an input module configured to input the target color into the target linear model to obtain a color value of the input color.

6. The apparatus of claim 5, wherein, The acquisition module is specifically configured to: acquire an RGB-based color space; collect part of color values as input colors from the color space at equal intervals; control an LED display screen to display the same input colors; acquire target colors corresponding to the input colors.

7. The apparatus of claim 5, wherein, The calculation module is specifically configured to: use a root mean square error as a loss function of the ternary cubic linear model to calculate a loss value of the ternary cubic linear model; optimize the ternary cubic linear model through a gradient descent algorithm to obtain the target linear model.

8. An electronic device, comprising: comprise: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

9. A non-transitory computer readable storage medium, comprising: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the processor performs the method of any one of claims 1-4.

10. A computer program product comprising computer programs or computer executable instructions, characterized in that, The computer program or computer-executable instructions are executed by a processor to implement the method of any one of claims 1-4.

Images