Attached seam brightness difference correction method and intelligent terminal

Abstract

The invention provides a splicing seam brightness difference correction method and an intelligent terminal, and the method comprises the steps: splicing images collected by a multi-view camera, and dividing each image into a plurality of first blocks; wherein two adjacent images have an overlapping region; obtaining first brightness data of each first block in each image, and determining the type of the current scene; the type of the current scene comprises a front light scene and a back light scene; determining a first weight of each first block in each image based on the type of the current scene, and determining second brightness data of each image based on each first weight; acquiring third brightness data and second weights of the overlapping areas in the images, and determining first target brightness data after correction of the images based on the second brightness data, the third brightness data and the second weights; and correcting the exposure parameters of the cameras based on the first target brightness data. According to the embodiment, the brightness of the spliced image is more uniform, and the correction effect is better.

Description

Technical Field

[0001] The present application relates to the technical field of electronic equipment, and in particular to a method for correcting brightness differences in seams and a smart terminal. Background Art

[0002] There are many splicing products on the market, which are mainly divided into device-side splicing and back-end splicing. When splicing on the device side, the preview can display multiple separate images as well as the spliced ​​images. Back-end splicing mainly uses the server to stitch images. When using it, you will find that there will be brightness differences at the seams, which is particularly prominent in night environments.

[0003] For the above two splicing methods, the relevant technology will perform brightness correction at the splicing seam, but the effect is not good. Summary of the invention

[0004] Based on this, it is necessary to provide a method for correcting the brightness difference of a patchwork seam and an intelligent terminal to address the above technical issues.

[0005] In a first aspect, an embodiment of the present application provides a method for correcting brightness differences in a patchwork seam, the method comprising: Stitching the images respectively captured by the multi-cameras, and dividing each of the images into a plurality of first blocks; wherein there is an overlapping area between two adjacent images; Acquire the first brightness data of each of the first blocks in each of the images to determine the type of the current scene; the type of the current scene includes a front-lit scene and a back-lit scene; Determining a first weight of each of the first blocks in each of the images based on the type of the current scene, and determining second brightness data of each of the images based on each of the first weights; Acquire the third brightness data and the second weight of the overlapping area in each of the images, and determine the first target brightness data after correction of each of the images based on each of the second brightness data, each of the third brightness data and each of the second weights; Based on the brightness data of each first target, the exposure parameters of each eyepiece camera are corrected.

[0006] This embodiment has the following technical effects: according to the type judgment of the current scene, the first weight of each of the first blocks is determined, so that the second brightness data of each of the images is calculated more accurately, thereby improving the brightness correction effect at the seam. In addition, the third brightness data and the second weight of the overlapping area in each image are considered, so that the brightness difference at the seam is reduced, and the brightness difference of adjacent images is ensured to be closer, so that the brightness of the spliced ​​image is more uniform and the correction effect is better.

[0007] In some embodiments, acquiring the first brightness data of each of the first blocks in each of the images to determine the type of the current scene includes: Determining a first brightness factor of a current scene based on first brightness data of each of the first blocks in each of the images; Based on the first brightness factor, the type of the current scene is determined.

[0008] In some embodiments, determining the first brightness factor of the current scene based on the first brightness data of each of the first blocks in each of the images includes: Determining a maximum value and a minimum value of each of the first blocks in each of the images based on the first brightness data of each of the first blocks in each of the images; Determine the number of bright area blocks in each of the images and the sum of first brightness data of the bright area blocks in each of the images based on the maximum value of each of the first areas in each of the images; determine the number of dark area blocks in each of the images and the sum of first brightness data of the dark area blocks in each of the images based on the minimum value of each of the first areas in each of the images; A first brightness factor of the current scene is determined based on the sum of the number of bright area blocks in all images, the sum of the first brightness data of the bright area blocks, the sum of the number of dark area blocks, and the sum of the first brightness data of the dark area blocks.

[0009] In some embodiments, determining the type of the current scene based on the first brightness factor includes: If the first brightness factor is greater than a first brightness factor threshold, it is determined to be a front-lit scene; If the first brightness factor is greater than the second brightness factor threshold and less than the first brightness factor threshold, it is determined to be a front-lit scene.

[0010] In some embodiments, when the sum of the numbers of the bright area blocks is greater than a first number threshold and the sum of the numbers of the dark area blocks is greater than a second number threshold, the type of the current scene is determined based on the first brightness factor.

[0011] In a second aspect, an embodiment of the present application provides a method for correcting brightness differences in a seam, the method comprising: Stitching images respectively captured by multiple cameras, dividing the stitched images into a plurality of second blocks, and dividing the plurality of second blocks into a plurality of first blocks; Acquire the first brightness data of each of the first blocks to determine the light source type of the current scene; the light source type includes a fixed light source and a non-fixed light source; If the light source type is a fixed light source, determining a first weight of each of the first blocks based on the first brightness data of each of the first blocks; determining fourth brightness data of each of the second blocks based on the first weights of each of the first blocks in each of the second blocks; Determining second target brightness data of the fill light area of ​​each of the fill lights based on the fourth brightness data of each of the second blocks; Based on the second target brightness data of the fill light area of ​​each of the fill light lamps, the fill light parameters of each of the fill light lamps are corrected.

[0012] This embodiment has the following technical effects: judging the light source type of the current scene, correcting the brightness difference at the joint when the light source is fixed, and improving the correction effect. Correcting the fill light parameters of each fill light according to the second target brightness data of the fill light area, making the correction more accurate and further improving the correction effect.

[0013] In some embodiments, acquiring the first brightness data of each of the first blocks to determine the light source type of the current scene includes: Determining a second brightness factor based on the first brightness data of each of the first blocks; If the second brightness factor is greater than the third brightness factor threshold, obtaining the similarity between the spliced ​​image corresponding to the current frame and the spliced ​​image corresponding to the adjacent frame; If the similarity is greater than the similarity threshold, it is determined that the light source type of the current scene is a fixed light source; otherwise, it is determined that the light source type of the current scene is a non-fixed light source.

[0014] In some embodiments, determining the first weight of each of the first blocks based on the first brightness data of each of the first blocks includes: If the first brightness data is less than a first brightness threshold, the first weight is a first weight value; If the first brightness data is greater than a second brightness threshold, the first weight is a second weight value; and the second weight value is greater than the first weight value; If the first brightness data is greater than a first brightness threshold value and less than a second brightness threshold value, an intermediate difference is calculated based on the first brightness data, the first weight value, and the second weight value as a first weight.

[0015] In a third aspect, an embodiment of the present application provides a method for correcting brightness differences in a seam, the method comprising: In a natural light scene, using the method described in the first aspect, calibrate the exposure parameters of each eyepiece camera; In a non-natural light scene, the fill light parameters of each fill light are calibrated using the method described in the second aspect.

[0016] This embodiment has the following technical effects: different seam brightness difference correction methods are adopted for natural light scenes and non-natural light scenes, and the fill light parameters of each fill light are corrected, thereby achieving all-weather correction.

[0017] In a fourth aspect, an embodiment of the present application provides an intelligent terminal, comprising a multi-eye camera, a display, a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect, the second aspect or the third aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Schematic diagram of the process of the method for correcting the brightness difference of the patchwork seam in the first embodiment of the present application; Figure 2 This is a flow chart of a method for determining the current scene type in the first embodiment of the present application; Figure 3 This is a schematic diagram of the flow of a method for determining a first brightness factor in the first embodiment of the present application; Figure 4 This is a schematic diagram of stitching images in the first exemplary embodiment of the present application; Figure 5 Schematic diagram of the process of the method for correcting the brightness difference of the patchwork in the second embodiment of the present application; Figure 6 This is a flow chart of a method for determining a light source type in a second embodiment of the present application; Figure 7 A schematic diagram of stitching images in the second exemplary embodiment of the present application; Figure 8 FIG. 4 is a diagram showing the internal structure of a smart terminal in one embodiment. DETAILED DESCRIPTION

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0020] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0021] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on a computing device and / or processor. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0022] It should be understood that when a unit or module is described as being "connected," "coupled" to other units, modules, or blocks, it may refer to being directly connected or coupled, or communicating with other units, modules, or blocks, or there may be intermediate units, modules, or blocks, unless the context clearly indicates otherwise. The term "and / or" as used herein may include any and all combinations of one or more of the associated listed items.

[0023] like Figure 1 As shown, the first embodiment of the present application proposes a method for correcting brightness differences in a seam, the method comprising: S102: stitching images respectively captured by multiple cameras, and dividing each of the images into a plurality of first blocks.

[0024] The seam brightness difference correction method proposed in the embodiment of the present application can be applied to multi-eye stitching products, including multi-eye cameras, such as four-eye cameras, each camera captures its own image, and after capturing their own images, the four images are stitched together.

[0025] There is an overlapping area between two adjacent images, and there is a seam between two adjacent images.

[0026] S104: Acquire first brightness data of each of the first blocks in each of the images to determine the type of the current scene.

[0027] The types of the current scene include a front-lit scene and a back-lit scene.

[0028] The first brightness data can be calculated by counting the average values ​​of r, g, and b of all pixels in the first block of each block.

[0029] S106: Determine a first weight of each of the first blocks in each of the images based on the type of the current scene, and determine second brightness data of each of the images based on each of the first weights.

[0030] In this embodiment, the first weight of the first block is determined according to the type of the current scene. In a backlit scene, the first weight of the bright area is small, and the first weight of the dark area is large, so that the overall brightness is appropriate; the opposite is true in a frontlit scene.

[0031] S108: Acquire the third brightness data and the second weight of the overlapping area in each of the images, and determine the first target brightness data after correction of each of the images based on each of the second brightness data, each of the third brightness data and each of the second weights.

[0032] In this embodiment, the weight of the non-overlapping area can be calculated based on the second weight of the overlapping area, and the brightness data of the non-overlapping area can be calculated based on the second brightness data and the weight of the non-overlapping area. The data is then summed with the third brightness data of the overlapping area to obtain the first target brightness data after image correction.

[0033] S110: Correcting exposure parameters of each eyepiece camera based on each of the first target brightness data.

[0034] It can be understood that the exposure parameters of the camera can control the brightness data, so the corresponding exposure parameters of the camera can be determined according to the first target brightness data, and the brightness difference at the seam can be corrected by correcting the exposure parameters.

[0035] This embodiment has the following technical effects: according to the type judgment of the current scene, the first weight of each of the first blocks is determined, so that the second brightness data of each of the images is calculated more accurately, thereby improving the brightness correction effect at the seam. In addition, the third brightness data and the second weight of the overlapping area in each image are considered, so that the brightness difference at the seam is reduced, and the brightness difference of adjacent images is ensured to be closer, so that the brightness of the spliced ​​image is more uniform and the correction effect is better.

[0036] In some embodiments, Figure 2 As shown, the obtaining of the first brightness data of each of the first blocks in each of the images to determine the type of the current scene includes: S202: Determine a first brightness factor of a current scene based on first brightness data of each of the first blocks in each of the images; S204: Determine the type of the current scene based on the first brightness factor.

[0037] In a specific embodiment, if Figure 3 As shown, determining the first brightness factor of the current scene based on the first brightness data of each of the first blocks in each of the images includes: S302: determining a maximum value and a minimum value of each of the first blocks in each of the images based on first brightness data of each of the first blocks in each of the images; S304: determining the number of bright area blocks in each of the images and the sum of first brightness data of the bright area blocks in each of the images based on the maximum value of each of the first areas in each of the images; determining the number of dark area blocks in each of the images and the sum of first brightness data of the dark area blocks in each of the images based on the minimum value of each of the first areas in each of the images; S306: Determine a first brightness factor of the current scene based on the sum of the number of bright area blocks in all images, the sum of the first brightness data of the bright area blocks, the sum of the number of dark area blocks, and the sum of the first brightness data of the dark area blocks.

[0038] In a specific embodiment, determining the type of the current scene based on the first brightness factor includes: if the first brightness factor is greater than a first brightness factor threshold, determining it as a front-lit scene; if the first brightness factor is greater than a second brightness factor threshold and less than the first brightness factor threshold, determining it as a front-lit scene.

[0039] In other cases, it is determined to be a normal scene.

[0040] According to the type judgment of the current scene, the first weight of each of the first blocks is determined, so that the second brightness data of each of the images is calculated more accurately, thereby improving the brightness correction effect at the seam.

[0041] In some embodiments, when the sum of the numbers of the bright area blocks is greater than a first number threshold and the sum of the numbers of the dark area blocks is greater than a second number threshold, the type of the current scene is determined based on the first brightness factor.

[0042] In this embodiment, by limiting the number of bright area blocks and the number of dark area blocks, the influence of a small number of bright and dark areas on the result is eliminated, so that the type of the current scene is determined more accurately.

[0043] In an exemplary embodiment, the method is described in detail by taking a four-mesh splicing product as an example. Figure 4 is the image after stitching the four images from the quad-camera. The red area indicates the overlapped area of ​​adjacent images. Each image is divided into I×J first blocks. The first brightness data corresponding to the first block is calculated, y represents the first brightness data, r, g, b represent the average values ​​of r, g, b of all pixels in the first block. The specific steps of this method are as follows: Step 1: According to the first brightness data of each first block in the four images, the maximum value and the minimum value of the first brightness data in the four images are calculated and recorded as

[0044] Step 2: Count the first brightness data of all first blocks of each image that are greater than and less than The number of blocks is recorded as the number of bright area blocks in each image , the number of dark blocks in each image , calculate the number of 4 images and record it as the sum of the number of bright area blocks in all images , and the number of dark area blocks , and the sum of the first brightness data of the bright area blocks in all corresponding images , the sum of the first brightness data of the dark area block .in is the threshold parameter, here we take

[0045] Calculate the first brightness factor of the current scene

[0046] Step 3: According to the first brightness factor and Determine the scene type. Then the scene type is judged to eliminate the influence of a small number of bright and dark areas on the result. When When , it is marked as front-lit scene, and the others are marked as normal scene. represents the first quantity threshold, represents the second quantity threshold, represents the first brightness factor threshold, Indicates the second brightness factor threshold.

[0047] Step 4: Determine the first weight of the first block according to the type of the current scene, marked as , calculate the second brightness data of each image here represents the number of first blocks in each image, For the i In the image j The first luminance data of the first block is obtained.

[0048] Step 5: Calculate the first target brightness data of each image to perform exposure parameter correction. It consists of two parts: the brightness data of the non-overlapping area and the third brightness data of the overlapping area of ​​adjacent images. , here is the third brightness data The calculation method is the same as the second brightness data , only the first brightness data of the first block in the overlapping area is taken into account for calculation. For example:

[0049] in, represents the weight of each overlapping area, represents the weight of each non-overlapping area, The third brightness data representing each overlapping area.

[0050] The second embodiment of the present application provides a method for correcting the brightness difference of a patchwork seam. Figure 5 As shown, the method includes: S502: stitching images respectively captured by the multi-eye cameras, dividing the stitched images into a plurality of second blocks, and dividing the plurality of second blocks into a plurality of first blocks.

[0051] S504: Acquire first brightness data of each of the first blocks to determine the light source type of the current scene.

[0052] The method for acquiring the first brightness data may refer to the above embodiment.

[0053] The light source types include fixed light sources and non-fixed light sources.

[0054] By determining the light source type of the current scene, it is confirmed whether the brightness is affected by the actual scene or by moving objects, such as moving car lights, street lights, reflections from close-range fill lights, and other non-fixed light sources.

[0055] S506: If the light source type is a fixed light source, determine a first weight of each of the first blocks based on the first brightness data of each of the first blocks.

[0056] When it is determined to be a non-fixed light source such as a car light, the fill light will not be adjusted temporarily to avoid frequent adjustment of the fill light due to changes in the car light, which will cause obvious changes in the picture brightness and affect the user experience. For fixed light sources such as street lights and close-range reflections, the fill light is adjusted.

[0057] S508: Determine fourth brightness data of each of the second blocks based on the first weights of each of the first blocks in each of the second blocks.

[0058] S510: Determine second target brightness data of a fill light area of ​​each of the fill lights based on the fourth brightness data of each of the second blocks.

[0059] After obtaining the fourth brightness data of each second block, the second target brightness data of each fill light area can be calculated according to the fill light area of ​​the fill light.

[0060] S512: Correcting fill light parameters of each of the fill light lamps based on the second target brightness data of the fill light area of ​​each of the fill light lamps.

[0061] It is understandable that the fill light parameters of the camera can control the brightness data, so the corresponding fill light parameters of the fill light can be determined according to the second target brightness data, and the brightness difference at the seam can be corrected by correcting the fill light parameters.

[0062] This embodiment has the following technical effects: judging the light source type of the current scene, correcting the brightness difference at the joint when the light source is fixed, and improving the correction effect. Correcting the fill light parameters of each fill light according to the second target brightness data of the fill light area, making the correction more accurate and further improving the correction effect.

[0063] In some embodiments, Figure 6 As shown, the acquiring the first brightness data of each of the first blocks and determining the light source type of the current scene includes: S602: Determine a second brightness factor based on the first brightness data of each of the first blocks; S604: If the second brightness factor is greater than the third brightness factor threshold, obtain the similarity between the stitched image corresponding to the current frame and the stitched image corresponding to the adjacent frame; if the similarity is greater than the similarity threshold, determine that the light source type of the current scene is a fixed light source; otherwise, determine that the light source type of the current scene is a non-fixed light source.

[0064] The similarity can be expressed as the absolute error and ( sum absolute difference , SAD), or other similarity representations.

[0065] In some embodiments, determining the first weight of each first block based on the first brightness data of each first block includes: if the first brightness data is less than a first brightness threshold, the first weight is a first weight value; if the first brightness data is greater than a second brightness threshold, the first weight is a second weight value; the second weight value is greater than the first weight value; if the first brightness data is greater than the first brightness threshold and less than the second brightness threshold, then calculating the intermediate difference based on the first brightness data, the first weight value, and the second weight value as the first weight.

[0066] In an exemplary embodiment, the method is described in detail by taking a four-mesh splicing product as an example. Figure 7It is the image after stitching four images of the four-eye camera. Each image is divided into two second blocks, and each second block is divided into J×K first blocks. The stitched image is sequentially divided into the central area, the surrounding area, and the peripheral area from the inside to the outside. The middle rectangle in the figure represents the range of the fill light in the central area, the outer rectangle represents the range of the fill light in the surrounding area, and the outermost rectangle represents the range of the fill light in the peripheral area. At the same time, combined with the field of view of the camera, several groups of fill lights with different angles are designed in each area. The fill light in the central area has a small range and concentrated energy. It is mainly used for observing far away. The fill light in the surrounding area has a moderate range and acts on the normal monitoring range. The fill light in the peripheral area has a large range and weak energy, which is mainly used for nearby. The specific steps of this method are as follows: Step 1: Obtain the first brightness data of each first block to determine the light source type of the current scene. For each image, obtain the mean value of the first brightness data of the bright area block and the average first brightness data of the first blocks in a circle around , calculate the corresponding second brightness factor when When it is judged as a suspected non-fixed light source, here is the third brightness factor threshold. Then, the frame difference information is used to obtain the SAD of adjacent frames, and the SAD in a video is counted to see whether it is greater than the similarity threshold. When the SAD is greater than the similarity threshold and is close to the suspected non-fixed light source, the light source type of the current scene is set as a non-fixed light source, and the fill light of the fill light is not adjusted temporarily. and The calculation method of is the same as that of the first embodiment and will not be repeated here.

[0067] Step 2: When it is determined to be a fixed light source such as a street lamp, the fourth brightness data of the corresponding 8 second blocks are calculated. When calculating the fourth brightness data, a dynamic weighting method is used to calculate, and the corresponding weight is determined according to the value of the first brightness data of each first block. :

[0068] in Indicates m In the second block n The statistical brightness of the block, represents the first brightness threshold, represents the second brightness threshold, represents the first weight value, represents the second weight value, for example , thereby obtaining the fourth brightness data of each second block . ,in, , indicating the number of first blocks in the second block.

[0069] Step 3: According to the brightness value of each second block , combined with the fill-in area of ​​each fill-in light, determine the second target brightness data of the fill-in area of ​​each fill-in light, that is, the second target brightness data of the central area, the surrounding area, and the peripheral area , the second target brightness data is compared with the corresponding third brightness threshold to determine the adjustment direction of the fill light. When the environment is dark, increase the fill light intensity. When the environment is too bright, reduce the fill light intensity. are two third brightness thresholds.

[0070] A third embodiment of the present application provides a method for correcting brightness differences in a seam, the method comprising: In a natural light scene, the exposure parameters of each eyepiece camera are calibrated using the method described in the first embodiment; In a non-natural light scene, the fill light parameters of each fill light are calibrated using the method described in the second embodiment.

[0071] This embodiment has the following technical effects: different seam brightness difference correction methods are adopted for natural light scenes and non-natural light scenes, and the fill light parameters of each fill light are corrected, thereby achieving all-weather correction.

[0072] The fourth embodiment of the present application provides an intelligent terminal, including a multi-eye camera, a display, a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first embodiment, the second embodiment or the third embodiment are implemented.

[0073] In an exemplary embodiment, a smart terminal is provided. The smart terminal may be a server, and its internal structure diagram may be as follows: Figure 8 The intelligent terminal includes a processor, a memory, an input / output interface ( Input / Output , referred to as I / O) and a communication interface. The processor, memory and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the intelligent terminal is used to store data. The input / output interface of the intelligent terminal is used to exchange information between the processor and an external device. The communication interface of the intelligent terminal is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the method of the above embodiment is implemented.

[0074] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the smart terminal to which the scheme of the present application is applied. The specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0075] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory ( Read - OnlyMemory , ROM ), magnetic tape, floppy disk, flash memory or optical storage, etc. Volatile memory may include random access memory ( RandomAccessMemory , RAM ) or external cache memory. By way of illustration and not limitation, RAM Can be in many forms, such as static random access memory ( StaticRandomAccessMemory , SRAM ) or dynamic random access memory ( DynamicRandomAccessMemory , DRAM )wait.

[0076] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0077] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for correcting brightness differences in a patchwork seam, characterized in that: The method comprises: Stitching the images respectively captured by the multi-cameras, and dividing each of the images into a plurality of first blocks; wherein there is an overlapping area between two adjacent images; Acquire the first brightness data of each of the first blocks in each of the images to determine the type of the current scene; the type of the current scene includes a front-lit scene and a back-lit scene; Determining a first weight of each of the first blocks in each of the images based on the type of the current scene, and determining second brightness data of each of the images based on each of the first weights; Acquire the third brightness data and the second weight of the overlapping area in each of the images, and determine the first target brightness data after correction of each of the images based on each of the second brightness data, each of the third brightness data and each of the second weights; Based on the brightness data of each first target, the exposure parameters of each eyepiece camera are corrected.

2. The method according to claim 1, characterized in that The acquiring the first brightness data of each of the first blocks in each of the images to determine the type of the current scene includes: Determining a first brightness factor of a current scene based on first brightness data of each of the first blocks in each of the images; Based on the first brightness factor, the type of the current scene is determined.

3. The method according to claim 2, characterized in that The determining the first brightness factor of the current scene based on the first brightness data of each of the first blocks in each of the images comprises: Determining a maximum value and a minimum value of each of the first blocks in each of the images based on the first brightness data of each of the first blocks in each of the images; Determine the number of bright area blocks in each of the images and the sum of first brightness data of the bright area blocks in each of the images based on the maximum value of each of the first areas in each of the images; determine the number of dark area blocks in each of the images and the sum of first brightness data of the dark area blocks in each of the images based on the minimum value of each of the first areas in each of the images; A first brightness factor of the current scene is determined based on the sum of the number of bright area blocks in all images, the sum of the first brightness data of the bright area blocks, the sum of the number of dark area blocks, and the sum of the first brightness data of the dark area blocks.

4. The method according to claim 3, characterized in that: The determining the type of the current scene based on the first brightness factor includes: If the first brightness factor is greater than a first brightness factor threshold, it is determined to be a front-lit scene; If the first brightness factor is greater than the second brightness factor threshold and less than the first brightness factor threshold, it is determined to be a front-lit scene.

5. The method according to claim 4, characterized in that When the sum of the numbers of the bright area blocks is greater than a first number threshold and the sum of the numbers of the dark area blocks is greater than a second number threshold, the type of the current scene is determined based on the first brightness factor.

6. A method for correcting brightness differences in a patchwork seam, characterized in that: The method comprises: Stitching images respectively captured by multiple cameras, dividing the stitched images into a plurality of second blocks, and dividing the plurality of second blocks into a plurality of first blocks; Acquire the first brightness data of each of the first blocks to determine the light source type of the current scene; the light source type includes a fixed light source and a non-fixed light source; If the light source type is a fixed light source, determining a first weight of each of the first blocks based on the first brightness data of each of the first blocks; determining fourth brightness data of each of the second blocks based on the first weights of each of the first blocks in each of the second blocks; Determining second target brightness data of the fill light area of ​​each fill light based on the fourth brightness data of each of the second blocks; Based on the second target brightness data of the fill light area of ​​each of the fill light lamps, the fill light parameters of each of the fill light lamps are corrected.

7. The method according to claim 6, characterized in that The acquiring the first brightness data of each of the first blocks and determining the light source type of the current scene includes: Determining a second brightness factor based on the first brightness data of each of the first blocks; If the second brightness factor is greater than the third brightness factor threshold, obtaining the similarity between the spliced ​​image corresponding to the current frame and the spliced ​​image corresponding to the adjacent frame; If the similarity is greater than the similarity threshold, it is determined that the light source type of the current scene is a fixed light source; otherwise, it is determined that the light source type of the current scene is a non-fixed light source.

8. The method according to claim 7, characterized in that The determining the first weight of each of the first blocks based on the first brightness data of each of the first blocks comprises: If the first brightness data is less than a first brightness threshold, the first weight is a first weight value; If the first brightness data is greater than a second brightness threshold, the first weight is a second weight value; and the second weight value is greater than the first weight value; If the first brightness data is greater than a first brightness threshold value and less than a second brightness threshold value, an intermediate difference is calculated based on the first brightness data, the first weight value, and the second weight value as a first weight.

9. A method for correcting brightness differences in a seam, characterized in that: The method comprises: In a natural light scene, using the method described in any one of claims 1 to 5 to calibrate the exposure parameters of each eyepiece camera; In a non-natural light scene, the fill light parameters of each fill light are calibrated using the method described in any one of claims 6 to 8.

10. An intelligent terminal, comprising a multi-camera, a display, a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images