Method and device for detecting effect of spliced image, equipment and storage medium

Abstract

The invention provides an effect detection method and device for a spliced image, equipment and a storage medium, relates to the technical field of image processing, and can synthesize index requirements for performing different effect detection on the spliced image into a detection image card to realize one-time effect detection on the spliced image so as to improve the detection efficiency of the spliced image. And the consistency and the accuracy of detection results are ensured. The method comprises the steps that an effect detection graph card is constructed, wherein the effect detection graph card comprises a graph array used for detecting different image effect indexes; according to the effect detection graph card, image detection areas representing different splicing effects are selected from a spliced image, and the spliced image is obtained by shooting the effect detection graph card in a combined mode through a camera; performing corresponding effect detection on the image detection areas representing different splicing effects to obtain detection results of different image effect indexes; and determining an effect detection result of the spliced image according to detection results of different image effect indexes.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, equipment and storage medium for detecting the effect of spliced ​​images. Background Art

[0002] Multi-camera stitching is designed to meet the needs of comprehensive, accurate observation and recording of large-scale scenes in various fields. Typically, the angles of multi-camera stitching are relatively large, resulting in changes in the clarity of the stitched image. The stitched image can also experience pixel misalignment and expansion.

[0003] Conventional detection methods can measure the clarity of stitched images through TV line resolution, modulation transfer function, and spatial frequency response. However, due to the angles between multiple cameras and the large stitching angle, traditional detection methods require testing stitched images individually or in batches. This makes it difficult to perform a single-shot test of the stitched image quality, making it difficult to ensure consistent test results. Summary of the Invention

[0004] In view of the above problems, the present application is proposed to provide a method, device, equipment, and storage medium for detecting the effect of stitched images that overcomes or at least partially solves the above problems. This method can solve the problem that related technologies only detect stitched images individually or in batches, cannot perform a one-time effect detection on the stitched images, and are difficult to ensure the consistency of the detection results. The technical solution is as follows:

[0005] In a first aspect, a method for detecting the effect of a spliced ​​image is provided, the method comprising:

[0006] Constructing an effect detection chart, wherein the effect detection chart includes a graphic array for detecting different image effect indicators;

[0007] Selecting image detection areas representing different stitching effects in a stitched image based on the effect detection chart, where the stitched image is obtained by photographing the effect detection chart with a camera combination;

[0008] Performing corresponding effect detection on the image detection areas representing different splicing effects respectively to obtain detection results of different image effect indicators;

[0009] An effect detection result of the spliced ​​image is determined according to the detection results of the different image effect indicators.

[0010] Furthermore, the construction effect detection chart includes:

[0011] Determining size information of the effect detection chart based on stitching field of view parameters of a camera combination, wherein the camera combination includes at least two cameras, and the stitching field of view parameters include parameters describing overall field of view characteristics after the plurality of cameras are combined;

[0012] Determining layout information of different graphic arrays in the effect detection chart according to a stitching position parameter of the camera combination, wherein the stitching position parameter is a connection position between adjacent images when stitching images captured by the camera combination;

[0013] An effect detection chart card is constructed according to the size information of the effect detection chart card and the layout information of different graphic arrays in the effect detection chart card.

[0014] Furthermore, determining the size information of the effect detection chart according to the splicing field of view parameters of the camera combination includes:

[0015] According to the stitching field of view parameters of the camera combination, calculate the field of view range corresponding to the camera combination at the test distance:

[0016] Determining size information of the effect detection chart according to the field of view range corresponding to the camera combination at the test distance;

[0017] Accordingly, after determining the size information of the effect detection chart according to the stitching field of view parameters of the camera combination, the method further includes:

[0018] When the test distance of the camera combination changes, the size information of the effect detection chart is adjusted according to the field of view range corresponding to the camera combination at the changed test distance.

[0019] Furthermore, the effect detection chart includes at least a first graphic array for detecting clarity effect and a second graphic array for detecting stitching effect;

[0020] Accordingly, the first graphic array and the second graphic array are laid out and spliced ​​to construct an effect detection chart;

[0021] Accordingly, according to the effect detection chart, a first image detection area and a second image detection area are respectively selected in the stitched image, wherein the first image detection area includes a first graphic array, and the second image detection area includes a second graphic array;

[0022] Performing a clarity effect detection on the first image detection area to obtain a clarity detection result, and performing a stitching effect detection on the second image detection area to obtain a stitching detection result;

[0023] An effect detection result of the spliced ​​image is determined according to the clarity detection result and the seam detection result.

[0024] Furthermore, selecting the first image detection area and the second image detection area in the stitched image according to the effect detection chart includes:

[0025] Determining an image area of ​​the first graphic array and an image area of ​​the second graphic array in the spliced ​​image according to the effect detection chart;

[0026] Selecting a graphic area for representing a clarity effect in the image area of ​​the first graphic array to obtain a first image detection area, wherein the first image detection area includes at least one edge area;

[0027] The image area of ​​the second graphic array is used as the graphic area representing the stitching effect to obtain a second image detection area, wherein the second image detection area includes at least one stitching area, and each stitching area is composed of multiple different second graphic sub-areas.

[0028] Furthermore, performing a clarity effect detection on the first image detection area to obtain a clarity detection result includes:

[0029] For the first image detection area, calculating a modulation transfer function value of at least one edge area;

[0030] If the modulation transfer function value of the at least one edge area is less than a first preset threshold, determining that the clarity detection result is qualified; otherwise, determining that the clarity detection result is unqualified;

[0031] And performing seam effect detection on the second image detection area to obtain a seam detection result includes:

[0032] For the second image detection area, calculating the coordinates of the corner points of a plurality of different second graphic sub-areas;

[0033] Comparing the corner point position coordinates of the plurality of different second graphic sub-regions with the standard corner point position coordinates of the corresponding second graphic sub-regions respectively, to obtain corner point position coordinate differences of the plurality of different sub-graphic sub-regions;

[0034] If the coordinate differences of the corner points of the plurality of different sub-graphic regions are all smaller than a second preset threshold, the seam detection result is determined to be qualified; otherwise, the seam detection result is determined to be unqualified;

[0035] Correspondingly, if the clarity detection result is qualified and the seam detection result is qualified, then the effect detection result of the spliced ​​image is qualified; otherwise, the effect detection result of the spliced ​​image is unqualified.

[0036] Furthermore, before calculating the modulation transfer function value of at least one edge area for the first image detection area, the method further includes:

[0037] Calculating a line pair width value of a modulation transfer function for the stitched image according to the number of line pairs of the camera combination;

[0038] If the line pair width value of the modulation transfer function is within a preset value range, a clarity effect detection is performed on the first image detection area.

[0039] Furthermore, at least two cameras in the camera combination are fixed on a supporting component, and the supporting component provides a function of adjusting the posture of each camera in the camera combination, so as to calculate the corresponding field of view range of the camera combination according to the adjusted posture of each camera.

[0040] In a second aspect, a device for detecting the effect of a stitched image is provided, comprising a camera assembly and a support assembly for carrying the camera assembly, the support assembly comprising a mounting base for fixing each camera in the camera assembly;

[0041] The mounting seat is provided with a posture adjustment function, and the posture adjustment function includes a position adjustment function and / or an angle adjustment function;

[0042] The support assembly is used to adjust the posture of each camera in the camera combination through the mounting seat to accordingly adjust the field of view range of the camera combination.

[0043] In a third aspect, a device for detecting the effect of splicing images is provided, the device comprising:

[0044] A construction unit, configured to construct an effect detection chart, wherein the effect detection chart includes a graphic array for detecting different image effect indicators;

[0045] a selection unit configured to select image detection areas representing different stitching effects in a stitched image based on the effect detection chart, wherein the stitched image is obtained by shooting the effect detection chart with a combination of cameras;

[0046] A detection unit, configured to perform corresponding effect detection on the image detection areas representing different splicing effects, and obtain detection results of different image effect indicators;

[0047] The determining unit is configured to determine an effect detection result of the spliced ​​image according to the detection results of the different image effect indicators.

[0048] Furthermore, the construction unit includes:

[0049] A first determining module is configured to determine size information of an effect detection chart based on a stitching field of view parameter of a camera combination, wherein the camera combination includes at least two cameras, and the stitching field of view parameter includes parameters describing overall field of view characteristics after the plurality of cameras are combined;

[0050] a second determining module, configured to determine layout information of different graphic arrays in the effect detection chart according to a stitching position parameter of the camera combination, wherein the stitching position parameter is a connection position between adjacent images when stitching images captured by the camera combination;

[0051] A construction module is used to construct an effect detection chart card according to the size information of the effect detection chart card and the layout information of different graphic arrays in the effect detection chart card.

[0052] Furthermore, the first determining module is specifically configured to:

[0053] According to the stitching field of view parameters of the camera combination, calculate the field of view range corresponding to the camera combination at the test distance:

[0054] Determining size information of the effect detection chart according to the field of view range corresponding to the camera combination at the test distance;

[0055] Correspondingly, the first determination module is further specifically used to adjust the size information of the effect detection chart according to the field of view range corresponding to the camera combination at the changed test distance when the test distance of the camera combination changes after determining the size information of the effect detection chart according to the stitching field of view parameters of the camera combination.

[0056] Furthermore, at least two cameras in the camera combination are fixed on a supporting component, and the supporting component provides a function of adjusting the posture of each camera in the camera combination, so as to calculate the corresponding field of view range of the camera combination according to the adjusted posture of each camera.

[0057] Furthermore, the effect detection chart includes at least a first graphic array for detecting clarity effect and a second graphic array for detecting stitching effect;

[0058] Accordingly, the construction unit is specifically configured to layout and splice the first graphic array and the second graphic array to construct an effect detection chart;

[0059] Accordingly, the selection unit is specifically configured to select a first image detection area and a second image detection area in the stitched image according to the effect detection chart, wherein the first image detection area includes a first graphic array and the second image detection area includes a second graphic array;

[0060] The detection unit is specifically configured to perform a clarity effect detection on the first image detection area to obtain a clarity detection result, and perform a stitching effect detection on the second image detection area to obtain a stitching detection result;

[0061] The determining unit is specifically configured to determine an effect detection result of the spliced ​​image according to the clarity detection result and the seam detection result.

[0062] Furthermore, the selection unit is further configured to:

[0063] Determining an image area of ​​the first graphic array and an image area of ​​the second graphic array in the spliced ​​image according to the effect detection chart;

[0064] Selecting a graphic area for representing a clarity effect in the image area of ​​the first graphic array to obtain a first image detection area, wherein the first image detection area includes at least one edge area;

[0065] The image area of ​​the second graphic array is used as the graphic area representing the stitching effect to obtain a second image detection area, wherein the second image detection area includes at least one stitching area, and each stitching area is composed of multiple different second graphic sub-areas.

[0066] Furthermore, the detection unit is further configured to:

[0067] For the first image detection area, calculating a modulation transfer function value of at least one edge area;

[0068] If the modulation transfer function value of the at least one edge area is less than a first preset threshold, determining that the clarity detection result is qualified; otherwise, determining that the clarity result is unqualified;

[0069] and calculating the position coordinates of corner points of a plurality of different second graphic sub-regions for the second image detection region;

[0070] Comparing the corner point position coordinates of the plurality of different second graphic sub-regions with the standard corner point position coordinates of the corresponding second graphic sub-regions respectively, to obtain corner point position coordinate differences of the plurality of different sub-graphic sub-regions;

[0071] If the coordinate differences of the corner points of the plurality of different sub-graphic regions are all smaller than a second preset threshold, the seam detection result is determined to be qualified; otherwise, the seam detection result is determined to be unqualified;

[0072] Accordingly, the determining unit is further configured to:

[0073] If the clarity detection result is qualified and the seam detection result is qualified, then the effect detection result of the spliced ​​image is qualified; otherwise, the effect detection result of the spliced ​​image is unqualified.

[0074] Furthermore, the detection unit is further configured to:

[0075] Before calculating the modulation transfer function value of at least one edge area for the first image detection area, a line pair width value of the modulation transfer function is calculated for the stitched image based on the number of line pairs of the camera combination; if the line pair width value of the modulation transfer function is within a preset value range, a clarity effect detection is performed on the first image detection area.

[0076] In a fourth aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for detecting the effect of stitching images when executing the computer program.

[0077] In a fifth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for detecting the effect of stitching images are implemented.

[0078] By means of the above technical solution, the effect detection method, device, equipment and storage medium of the stitched image provided by the embodiment of the present application are compared with the method of performing individual or batch detection on the stitched images in the existing technology. The present application constructs an effect detection chart, wherein the effect detection chart includes a graphic array for detecting different image effect indicators; according to the effect detection chart, image detection areas representing different stitching effects are selected in the stitched image, where the stitched image is obtained by shooting the effect detection chart with a camera combination; corresponding effect detection is performed on the image detection areas representing different stitching effects respectively, and detection results of different image effect indicators are obtained; and the effect detection result of the stitched image is determined based on the detection results of different image effect indicators. The whole process can synthesize the detection requirements of different image effect indicators of the stitched image into one detection chart by arranging graphic arrays of different image effect indicators in the effect detection chart, thereby realizing a one-time effect detection of the stitched image, saving stitching detection resources, improving the effect detection efficiency of the stitched image, and ensuring the consistency and accuracy of the detection results.

[0079] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments of the present application.

[0081] Figure 1 1 is a flow chart of a method for detecting the effect of stitching images provided in an embodiment of the present application;

[0082] Figure 2 yes Figure 1 A schematic flow chart of a specific implementation of step 101;

[0083] Figure 3 1 is a flow chart of another method for detecting the effect of stitching images provided in an embodiment of the present application;

[0084] Figure 4 yes Figure 3 A schematic flow chart of a specific implementation of step 302;

[0085] Figure 5 This is a schematic diagram of a minimum computing unit composed of the first graph provided in an embodiment of the present application;

[0086] Figure 6 This is a schematic diagram of a first graphic array composed of multiple minimum computing units provided in an embodiment of the present application;

[0087] Figure 7 is a schematic diagram of a second graph provided in an embodiment of the present application;

[0088] Figure 8 is a schematic diagram of a second graphic array composed of second graphics provided in an embodiment of the present application;

[0089] Figure 9 This is a schematic diagram of an effect detection chart provided in an embodiment of the present application;

[0090] Figure 10 This is a schematic diagram of a spliced ​​image with a graphic area selected in a frame provided by an embodiment of the present application;

[0091] Figure 11 1 is a flow chart of another method for detecting the effect of stitching images provided in an embodiment of the present application;

[0092] Figure 12 This is a structural diagram of a support assembly of a camera assembly provided in one embodiment of the present application;

[0093] Figure 13 This is a structural block diagram of a device for detecting the effect of stitching images provided in one embodiment of the present application. DETAILED DESCRIPTION

[0094] The following describes exemplary embodiments of the present application in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0095] It should be noted that the terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that such usage is interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "including" and its variations are to be interpreted as open-ended terms meaning "including but not limited to."

[0096] It should be noted that the image stitching effect detection method provided in this application can be applied to terminals. For example, the terminal can be various commercial large tablets, mobile phones or computers, ordinary consumer tablets, smart TVs, portable computer terminals, or fixed terminals such as desktop computers. For ease of explanation, this application uses the terminal as the execution subject for example.

[0097] Embodiments of the present application may be applied to a computer system / server that is operable with numerous other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations suitable for use with the computer system / server include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the foregoing.

[0098] Computer systems / servers may be described in the general context of computer system-executable instructions, such as program modules, executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, and the like, that perform specific tasks or implement specific abstract data types. Computer systems / servers may be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices linked through a communications network. In a distributed cloud computing environment, program modules may be located on local or remote computer system storage media, including storage devices.

[0099] The embodiment of the present application provides a method for detecting the effect of a spliced ​​image, which can solve the problem of low efficiency of effect detection of spliced ​​images in related technologies, and can realize a one-time effect detection of the spliced ​​image, saving splicing detection resources while ensuring the consistency and accuracy of the detection results. Figure 1 As shown, the method may include:

[0100] 101. Construction effect detection chart.

[0101] In this embodiment, the effect detection chart is a characteristic card used to evaluate the effect of a spliced ​​image, typically featuring a designed pattern. The effect detection chart includes a graphic array for detecting different image effect indicators. These image effect indicators may include, but are not limited to, the stitching accuracy, color consistency, clarity, and seam quality of the spliced ​​image. Typically, different image effect indicators are detected using different types of image elements. In other words, the effect detection chart is composed of different types of graphic arrays, which can be determined based on the image effect indicator to be detected. For image effect indicators that detect image stitching accuracy, regularly arranged geometric shapes such as circles, squares, and triangles can be used. These shapes have clear and sharp edges and are easy to identify and locate in the image. For image effect indicators that detect color consistency, an array of square or rectangular solid color blocks of different colors can be used. By comparing the color differences of the solid color blocks captured by different cameras after stitching, color consistency can be evaluated. For image effect indicators that detect image clarity, black and white stripes of different frequencies can be used. The clarity of the spliced ​​image can be evaluated by observing the clarity and variability of the stripes in the spliced ​​image. For image effect indicators for detecting image stitching quality, specific identification patterns, such as checkerboard, black and white grid, sawtooth, etc., can be used to detect the continuity and accuracy of the stitching image at the stitching joint through the specific identification patterns to evaluate the stitching quality of the stitching image.

[0102] Furthermore, after determining the graphic arrays included in the effect detection chart, taking into account the positional layout of different graphic arrays in the effect detection chart, the different graphic arrays in the effect detection chart can be positioned according to factors such as the number of cameras, field of view, and stitching method, so that the stitched image obtained by shooting the effect detection chart with a combination of cameras has graphic arrays with different detection effects. For example, in a dual-camera horizontal stitching scene, a 10×10 checkerboard grid is placed in the center of the overlapping image area of ​​the effect detection chart to detect the stitching effect, and red and blue stripes are placed at the edge of the image area to detect the chromatic aberration effect. Accordingly, in the stitched image obtained by shooting the effect detection chart with a combination of cameras, the center of the overlapping image area is a 10×10 checkerboard grid, and the edge of the image area is a red and blue stripes.

[0103] 102. Select image detection areas representing different stitching effects in the stitched image according to the effect detection chart.

[0104] The stitched image is obtained by shooting an effect detection chart with a camera combination, and the camera combination includes at least two cameras. The stitched image here is achieved using multi-camera stitching, which refers to the technology of seamlessly stitching pictures or videos shot by the camera combination to form a panoramic image or video with a wider field of view. Specifically, the camera combination can be installed according to a certain layout and angle, and the effect detection chart is shot at the same time. Each camera obtains a portion of the image information of the effect detection chart, and the correspondence between the images is determined through feature extraction and matching. The transformation relationship between the images is calculated based on the feature matching results, and the transformed images are fused to obtain a stitched image.

[0105] In actual application scenarios, on the one hand, considering that the stitched image is composed of images taken by a combination of cameras, stitching seams and overlapping areas are inevitable. If the stitching effect is not good, the stitching seams may be obvious, affecting the continuity of the stitched image. On the other hand, factors such as different camera performance, parameter settings, and shooting environment may lead to differences in the quality of the captured images, resulting in inconsistent clarity in different areas of the stitched image, affecting the overall quality of the stitched image. This requires the use of effect detection charts to clarify the requirements of image effect indicators, perform corresponding effect detection on the stitched images, and promptly discover problems in the stitching process, including stitching quality, image quality, perspective differences, and geometric deformation, to meet the requirements of stitched images in different scenarios.

[0106] In this embodiment, since the effect detection chart is composed of pattern arrays for detecting different image effect indicators, the stitched image obtained by combining cameras to capture the effect detection chart also includes image areas corresponding to the pattern arrays. Specifically, based on the pattern arrays contained in the effect detection chart, the stitched image obtained by combining cameras to capture the effect detection chart can be divided into image areas of different pattern arrays. Based on the detection targets of different image effect indicators, regional positioning is performed within the image areas of different pattern arrays to obtain image detection areas representing different stitching effects.

[0107] For example, the effect detection card is provided with a color block pattern for detecting color consistency and a stripe pattern for detecting edge clarity. After the camera combination shoots the effect detection card to obtain a spliced ​​image, the spliced ​​image area correspondingly contains an image area of ​​the color block pattern and an image area of ​​the stripe pattern. Further, according to the detection target of color consistency, an area containing at least two color block patterns is selected in the image area of ​​the color block pattern to obtain an image detection area representing color consistency. Correspondingly, according to the detection target of edge clarity, an edge area is selected in the image area of ​​the stripe pattern to obtain an image detection area representing edge clarity.

[0108] 103. Perform corresponding effect detection on the image detection areas representing different splicing effects respectively to obtain detection results of different image effect indicators.

[0109] In this embodiment, the image detection areas representing different stitching effects contain image characteristics corresponding to image effect indicators, and need to be detected using the detection methods of the corresponding image effect indicators. For example, the overlapping area represents the image characteristics of the stitching effect, and the overlapping area can be detected using the stitching effect detection method. For another example, the edge area represents the image characteristics of the clarity effect, and the edge area can be detected using the clarity effect detection method.

[0110] Specifically, the stitching effect can be detected by comparing the corresponding pixels of the images on both sides of the stitching area, counting the ratio of the number of overlapping pixels to the total number of pixels in the overlapping area, and then calculating the pixel overlap ratio of the two images in the overlapping area. The stitching effect is then evaluated based on the pixel overlap ratio. The higher the ratio, the higher the overlap in the stitching area and the better the image stitching effect.

[0111] Specifically, for edge area clarity testing, the gradient amplitude method can be used to calculate the gradient amplitude of all pixels within the edge area and the average of the pixel gradient amplitudes. This average value is then used to assess the clarity of the edge area. If the average value of the pixel gradient amplitudes is greater than a preset threshold, the edge area is considered clear; otherwise, it is considered unclear.

[0112] 104. Determine an effect detection result of the spliced ​​image according to the detection results of the different image effect indicators.

[0113] Considering that the test results of different image effect indicators only reflect one aspect of the stitching effect, in order to comprehensively evaluate the stitching effect, the test results of different image effect indicators can be quantified into scores. The quantitative scores are used to characterize the stitching effect of the stitched image on different image effect indicators. Here, the quantitative scores are set with the score thresholds of the corresponding image effect indicators. If the quantitative scores of any image effect indicator do not meet the standards, the effect test result of the stitched image is unqualified. If the quantitative scores of all image effect indicators meet the standards, the effect test result of the stitched image is qualified.

[0114] For example, the image quality indicator for brightness consistency can be quantified based on the average brightness difference and standard deviation of the two images. The smaller the brightness difference and the smaller the standard deviation, the higher the score. For example, if the average brightness difference is less than 5 and the standard deviation is less than 3, the score is 80-100; if the brightness difference is between 5-10 and the standard deviation is between 3-5, the score is 60-80. For the image quality indicator of seam quality, the score can be quantified based on seam overlap. If the seam overlap is greater than 90%, the score is 90-100; if the seam overlap is between 80% and 90%, the score is 70-90.

[0115] Furthermore, on the basis that the effect detection result of the stitched image is qualified, in order to quantitatively evaluate the stitching effect, weights can be configured for different image effect indicators according to actual needs, and the weights of different image effect indicators can be used to perform weighted calculation on the quantitative scores of different image effect indicators to achieve quantitative scoring of the effect detection result of the stitched image.

[0116] The effect detection method for stitched images provided in the embodiment of the present application is compared with the existing method of individually detecting or batch-detecting stitched images. The present application constructs an effect detection chart, wherein the effect detection chart includes a graphic array for detecting different image effect indicators; according to the effect detection chart, image detection areas representing different stitching effects are selected in the stitched image, where the stitched image is obtained by shooting the effect detection chart with a camera combination; corresponding effect detection is performed on the image detection areas representing different stitching effects, respectively, to obtain detection results of different image effect indicators; and according to the detection results of different image effect indicators, the effect detection result of the stitched image is determined. The entire process, by arranging graphic arrays of different image effect indicators in the effect detection chart, can synthesize the detection requirements of different image effect indicators for the stitched image into one detection chart, thereby realizing a one-time effect detection of the stitched image, saving stitching detection resources, improving the effect detection efficiency of the stitched image, and ensuring the consistency and accuracy of the detection results.

[0117] In actual application scenarios, such as Figure 2 As shown, step 101 specifically includes the following steps:

[0118] 201. Determine the size information of the effect detection image card according to the stitching field of view parameters of the camera combination.

[0119] 202. Determine layout information of different graphic arrays in the effect detection chart according to the seam position parameters of the camera combination.

[0120] 203. Construct an effect detection chart card according to the size information of the effect detection chart card and the layout information of different graphic arrays in the effect detection chart card.

[0121] In this embodiment, the camera assembly includes at least two cameras, and the stitched field of view parameters include parameters that describe the overall field of view characteristics of the camera assembly. Specifically, they may include, but are not limited to, the camera assembly resolution, field of view size, and detection distance. The camera assembly resolution is the number of pixels in the captured image, the field of view size is the range of the field of view that the camera assembly can capture, and the detection distance is the distance between the camera assembly and the effect detection chart.

[0122] Specifically, when determining the size of the effect detection chart, the corresponding field of view of the camera combination at the test distance can be calculated based on the camera combination's stitching field of view parameters. The size of the effect detection chart is determined based on the corresponding field of view of the camera combination at the test distance. Typically, the camera combination is a multi-camera combination, and the resulting stitching angle is relatively large, falling within the ultra-wide-angle range. The horizontal field of view of the camera combination can be D, the vertical field of view of the camera combination can be V, and the corresponding field of view can be D*V. When the detection distance is L, the horizontal field of view of the camera combination at the detection distance L is d = 2tan(D / 2)*L, the vertical field of view of the camera combination at the detection distance L is v = 2tan(V / 2)*L, and the corresponding field of view of the camera combination at the detection distance L is d*v. After determining the field of view, ensure that the size of the effect detection chart at least covers the corresponding field of view of the camera combination. To facilitate operation and ensure the accuracy of the test results, the size of the effect detection chart will be slightly larger than the field of view. For example, the horizontal size of the effective detection chart is set to 1.2 times the horizontal field of view size, and the vertical size is set to 1.2 times the vertical field of view size to ensure that images at the edge of the field of view can also be fully detected.

[0123] In actual application scenarios, at least two cameras in the camera combination are fixed on a supporting component, and the supporting component provides the function of adjusting the posture of each camera in the camera combination, so as to calculate the corresponding field of view range of the camera combination according to the adjusted posture of each camera.

[0124] Specifically, the camera combination is fixed on the supporting assembly as a whole, which is equivalent to a camera module, or an independent camera device composed of multiple cameras, rather than multiple cameras installed separately in different positions. The independent camera device has a corresponding field of view, which can be adjusted accordingly through the posture adjustment of the camera combination, enabling the camera combination to accurately establish a mathematical model during the calibration process, thereby improving the accuracy of the calibration results.

[0125] It should be noted that the size information of the effect detection chart is affected by the field of view range. Once the test distance changes, the corresponding field of view range will also change. Accordingly, after determining the size information of the effect detection chart based on the stitching field of view parameters of the camera combination, when the test distance of the camera combination changes, adjust the size information of the effect detection chart based on the field of view range corresponding to the camera combination at the changed test distance.

[0126] In this embodiment, the seam position parameter refers to the connection position between adjacent images captured by the camera combination when stitching. Specifically, it may include, but is not limited to, seam coordinates, seam angles, and overlapping areas. Specifically, when determining the layout information of different graphic arrays in the effect detection chart, the correspondence between different areas in the effective detection chart and the image ranges captured by different cameras can be determined based on the seam coordinates and angles. For example, if the seam is horizontal, the effective detection chart can be divided into upper and lower areas, corresponding to the image areas of the two cameras respectively. If the seam is tilted, the areas need to be divided according to the specific angle. At the same time, considering the overlapping area, corresponding space can be reserved on the effective detection chart for the overlapping portion. Then, based on the image effect indicators corresponding to the graphic arrays, corresponding graphic layouts are performed in different areas of the effect detection chart.

[0127] In practical application scenarios, the effect detection chart includes at least a first graphic array for detecting clarity effects and a second graphic array for detecting seam effects; accordingly, Figure 3 As shown, the above steps 101 to 104 can be implemented by the following steps:

[0128] 301. Layout and splice the first graphic array and the second graphic array to construct an effect detection chart.

[0129] 302. Select a first image detection area and a second image detection area in the stitched image according to the effect detection chart.

[0130] 303. Perform a clarity effect detection on the first image detection area to obtain a clarity detection result, and perform a stitching effect detection on the second image detection area to obtain a stitching detection result.

[0131] 304. Determine an effect detection result of the spliced ​​image according to the clarity detection result and the seam detection result.

[0132] In this embodiment, the first graphic array may use a checkerboard, black and white stripes, or any other pattern capable of detecting clarity effects. The second graphic array may use black and white grids, a checkerboard, or any other pattern capable of detecting seam effects. Accordingly, during the layout and splicing process of the first and second graphic arrays, the seam location area of ​​the effect detection chart may be laid out with the second graphic array, and the remaining area with the first graphic array. Alternatively, the seam location area of ​​the effect detection chart may be laid out with the second graphic array, the edge location area may be laid out with the first graphic array, and the remaining area may be left blank.

[0133] Accordingly, the first image detection area in the stitched image obtained by the camera combination shooting effect detection chart includes the first pattern array, and the second image detection area in the stitched image includes the second pattern array. For the first image detection area, clarity detection can be performed based on the calculated modulation transfer function value, and for the second image detection area, seam effect detection can be performed based on the comparison of the seam position coordinates with the standard seam position coordinates.

[0134] Considering that the positional layout of the first and second graphic arrays in the stitched image can be fully utilized, during the layout of the effect detection chart, the first and second graphic arrays are completely arranged in standard areas according to the corresponding image effect indicators. For example, the first graphic array is arranged in the four corner areas of the effect detection chart for detecting clarity effects, and the second graphic area is arranged in the seam area of ​​the effect detection chart for detecting stitching effects. In this way, in the stitched image obtained by the camera combination shooting the effect detection chart, the image area of ​​the first graphic array can be directly used for clarity detection, and the image area of ​​the second graphic array can be used for stitching effect detection.

[0135] However, in actual application scenarios, factors such as shooting angles may affect the effect detection of the stitched image. This requires that the first and second graphic arrays, based on the standard area layout, expand the size of the area of ​​the corresponding graphic array in the effect detection chart. Furthermore, after obtaining the stitched image, a representative image area is selected from the image area of ​​the corresponding graphic array as the image detection area, and the stitching effect detection is performed on the image detection area. Specifically, Figure 4 As shown, step 302 specifically includes the following steps:

[0136] 401. Determine an image area of ​​a first graphic array and an image area of ​​a second graphic array in a spliced ​​image according to the effect detection chart.

[0137] 402. Select a graphic area for representing a clarity effect from the image area of ​​the first graphic array to obtain a first image detection area.

[0138] 403. Use the image area of ​​the second pattern array as a pattern area representing a stitching effect to obtain a second image detection area.

[0139] In this embodiment, considering that the first image detection area is used to detect clarity, and the edge area in the stitched image directly reflects the image clarity, the edge area is selected from the image area of ​​the first pattern array as the pattern area representing the clarity. Thus, the first image detection area includes at least one edge area, which can be a portion of the four corners of the image area, or a portion of the image area extending a certain distance inward from the outer border.

[0140] In this embodiment, the second image detection area is used to detect the stitching effect, and the location of the stitching seam in the stitched image directly reflects the stitching and fusion effect. Typically, the image area of ​​the second pattern array is located at the stitching seam location and can be directly used as the pattern area to characterize the stitching effect. Thus, the second image detection area includes at least one stitching seam area, each of which is composed of multiple different second pattern sub-areas.

[0141] Specifically, during the clarity test of the first image detection area, the modulation transfer function value of at least one edge region of the first image detection area is calculated. If the modulation transfer function value of at least one edge region is less than a first preset threshold, the clarity test result is determined to be qualified; otherwise, the clarity test result is determined to be unqualified. The first preset threshold is a qualified threshold for achieving a clear effect and can be adjusted accordingly based on the clarity requirements of the actual scene.

[0142] Specifically, in the process of performing stitching effect detection on the second image detection area, the corner point position coordinates of multiple different second graphic sub-areas are calculated for the second image detection area; the corner point position coordinates of the multiple different second graphic sub-areas are respectively compared with the standard corner point position coordinates of the corresponding second graphic sub-areas to obtain the corner point position coordinate differences of the multiple different sub-graphic areas; if the corner point position coordinate differences of the multiple different sub-graphic areas are all less than the second preset threshold value, the stitching detection result is determined to be qualified, otherwise, the stitching detection result is determined to be unqualified. Here, the corner point position coordinates of the second image sub-area are the corner point coordinates of the image area formed by each second graphic of the effect detection card in the actual shooting scene, and correspondingly, the standard corner point position coordinates of the second image sub-area are the corner point coordinates of the image area formed by each second graphic of the effect detection card in the standard shooting scene.

[0143] Correspondingly, if the clarity detection result is qualified and the seam detection result is qualified, then the effect detection result of the stitched image is qualified; otherwise, the effect detection result of the stitched image is unqualified.

[0144] In actual application scenarios, we take the example of combining multiple cameras into three cameras. The first graphic uses black and white stripes. Figure 5 It is a minimum computing unit caused by the first graph, and the minimum computing unit is composed of 4 first graphs. Figure 6 It is the first graphic array composed of multiple minimum computing units. Similarly, the second graphic uses black and white grids. Figure 7 is the second graph, Figure 8 It is a second graphic array composed of multiple second graphics. After determining the first graphic array and the second graphic array, the first graphic array and the second graphic array are laid out and combined to construct an effect detection chart such as Figure 9 As shown, in Figure 9 In the figure, the second graphic array composed of black and white grids is located in the two seam areas of the stitched image obtained by the three-camera combination shooting effect detection chart, and the first graphic array composed of black and white stripes is located in the upper and lower edge areas of the stitched image obtained by the three-camera combination shooting effect detection chart.

[0145] Furthermore, the stitched image obtained by using the three cameras to shoot the effect detection chart contains the corresponding field of view range of each camera and two stitching areas, such as Figure 10 As shown in the figure, due to the phase difference problem, the clarity of the edge area of ​​each camera is lower than that of the center area of ​​the camera. Figure 10In the process of image clarity detection, the four corner areas of the field of view of each camera are usually used as image detection areas for image detection. At this time, the modulation transfer function value of the image detection area can be calculated. The calculation method of the modulation transfer function value MTF is MTF = (maximum brightness - minimum brightness) / (maximum brightness + minimum brightness). If the modulation transfer function value meets the clarity requirements, the clarity detection result is determined to be qualified. Otherwise, the clarity detection result is determined to be unqualified. Similarly, since the second graphic array composed of black and white grids is located in the stitching area of ​​the stitched image obtained by the three-camera combination shooting effect detection chart, when the stitching area falls on the black and white grid, the stitching pixel dislocation and expansion will cause the black and white grid to be dislocated or expanded. At this time, the horizontal corner point position difference and vertical corner point position difference formed by the black and white grid area and the standard black and white grid area in the corner point position coordinates can be directly calculated for each black and white grid area in the stitching area, and the horizontal corner point position difference is compared with the horizontal difference threshold △x to obtain the horizontal position coordinate comparison result, and the vertical corner point position difference is compared with the vertical difference threshold △y to obtain the vertical position coordinate comparison result. If the horizontal position coordinate comparison result and the vertical position coordinate comparison result both meet the position requirements, the stitching detection result is judged to be qualified; otherwise, the stitching detection result is judged to be unqualified.

[0146] For example, in a scene where the black and white grids are misaligned, the coordinates of the four corner points of the black and white grid area are calculated as (X 7L1 ,Y 7L1 ,X 7L2 ,Y 7L2 ,X 7L3 ,Y 7L3 ,X 7L4 ,Y 7L4 ), the coordinate positions of the four corner points of the standard black and white grid area are (X 9L1 ,Y 9L1 ,X 9L2 ,Y 9L2 ,X 9L3 ,Y 9L3 ,X 9L4 ,Y 9L4 ), compare the coordinates of the four corner points and find the difference Δx7=X 7L1 -X 9L1 , Δy7=Y 7L1 -Y 9L1 The rest of the corner points can be deduced in the same way. Only when Δx7<Δx and Δy7<Δy, the seam detection result is determined to be qualified.

[0147] For example, in a scene where the black and white grid expands, the coordinates of the four corner points of the black and white grid area are calculated as (X 8L1 ,Y 8L1 ,X8L2 ,Y 8L2 ,X 8L3 ,Y 8L3 ,X 8L4 ,Y 8L4 ), the coordinate positions of the four corner points of the standard black and white grid area are (X 9L1 ,Y 9L1 ,X 9L2 ,Y 9L2 ,X 9L3 ,Y 9L3 ,X 9L4 ,Y 9L4 ), compare the coordinates of the four corner points and find the difference Δx8=X 8L1 -X 9L1 , Δy8=Y 8L1 -Y 9L1 The rest of the corner points can be deduced in the same way. Only when Δx8<Δx and Δy8<Δy, the seam detection result is determined to be qualified.

[0148] Furthermore, considering the accuracy of image definition detection, before using the modulation transfer function value to perform definition detection, the definition detection line pair width value is limited to a range, specifically, as follows: Figure 11 As shown, before step 303, the method further includes the following steps:

[0149] 501. Calculate a line pair width value of a modulation transfer function for the stitched image according to the number of line pairs of the camera combination.

[0150] 502. If the line pair width value of the modulation transfer function is within a preset value range, perform a clarity effect detection on the first image detection area.

[0151] It's understandable that the line-pair width of a camera assembly is directly related to the spatial frequency, reflecting the number of alternating light and dark patterns per unit length in the image. Different cameras have different frequency response characteristics. Each camera has a specific range of spatial frequencies that it can effectively process and reproduce. Beyond this range, imaging performance degrades significantly, and image detail may even be inaccurately reproduced. For example, at higher spatial frequencies, a camera may be limited by factors such as diffraction and aberrations, causing a sharp drop in the modulation transfer function (MTF). Therefore, limiting the line-pair width of the MTF ensures that when testing clarity, the focus is on performance within the actual operating range, avoiding unrealistic results due to exceeding capabilities.

[0152] Specifically, in the process of calculating the line pair width value X of the modulation transfer function for the stitched image according to the number of line pairs of the camera combination, it can be calculated by the following formula:

[0153] X=v / (EFL*(Lp / 4)*2)

[0154] Where v is the vertical field of view corresponding to the detection distance L, EFL is the focal length of the lens, Lp is the number of line pairs of the camera combination, Lp = 1000 / (2*Pixel), and Pixel is the pixel size of the sensor.

[0155] Furthermore, based on the same inventive concept, an embodiment of the present application also provides a device for detecting the effect of stitched images, which includes a camera combination and a support assembly for supporting the camera combination, the support assembly including a mounting base for fixing each camera in the camera combination; the mounting base provides a posture adjustment function, and the posture adjustment function includes a position adjustment function and / or an angle adjustment function; the support assembly is used to adjust the posture of each camera in the camera combination through the mounting base to adjust the corresponding field of view range of the camera combination accordingly.

[0156] As a practical application scenario, the effect detection device of the spliced ​​image is equivalent to a support component based on a multi-camera integrated design. The support component includes a safety seat for fixing the camera. Figure 12 As shown, when three cameras are used to detect the effect of stitching images, the support assembly includes three safety seats for fixing the cameras. Each camera is placed on a mounting seat of the support assembly, and the position of the camera can be fixed by the safety seat. In this way, multiple cameras are fixed in position by the support assembly to form a camera combination, so that the relative position between the cameras remains stable, which is conducive to the calibration of the camera combination, and can enable the camera combination to accurately establish a mathematical model during the calibration process, thereby improving the accuracy of the calibration results.

[0157] Furthermore, based on the same inventive concept, the embodiment of the present application also provides a device for detecting the effect of splicing images, such as Figure 13 As shown, the device includes: a construction unit 61, a selection unit 62, a detection unit 63 and a determination unit 64.

[0158] A construction unit 61 is configured to construct an effect detection chart, wherein the effect detection chart includes a graphic array for detecting different image effect indicators;

[0159] a selection unit 62 for selecting image detection areas representing different stitching effects in a stitched image based on the effect detection chart, wherein the stitched image is obtained by shooting the effect detection chart with a combination of cameras;

[0160] The detection unit 63 is used to perform corresponding effect detection on the image detection areas representing different splicing effects respectively, and obtain detection results of different image effect indicators;

[0161] The determining unit 64 is configured to determine an effect detection result of the spliced ​​image according to the detection results of the different image effect indicators.

[0162] The effect detection device for stitched images provided by the embodiment of the present invention is compared with the method of performing individual or batch detection on stitched images in the current prior art. The present application constructs an effect detection chart, wherein the effect detection chart includes a graphic array for detecting different image effect indicators; according to the effect detection chart, image detection areas representing different stitching effects are selected in the stitched image, where the stitched image is obtained by shooting the effect detection chart with a camera combination; corresponding effect detection is performed on the image detection areas representing different stitching effects, respectively, to obtain detection results of different image effect indicators; and according to the detection results of different image effect indicators, the effect detection result of the stitched image is determined. The entire process, by arranging graphic arrays of different image effect indicators in the effect detection chart, can synthesize the detection requirements of different image effect indicators for the stitched image into one detection chart, thereby realizing a one-time effect detection of the stitched image, saving stitching detection resources, improving the effect detection efficiency of the stitched image, and ensuring the consistency and accuracy of the detection results.

[0163] In a specific application scenario, the construction unit includes:

[0164] A first determining module is configured to determine size information of an effect detection chart based on a stitching field of view parameter of a camera combination, wherein the camera combination includes at least two cameras, and the stitching field of view parameter includes parameters describing overall field of view characteristics after the plurality of cameras are combined;

[0165] a second determining module, configured to determine layout information of different graphic arrays in the effect detection chart according to a stitching position parameter of the camera combination, wherein the stitching position parameter is a connection position between adjacent images when stitching images captured by the camera combination;

[0166] A construction module is used to construct an effect detection chart card according to the size information of the effect detection chart card and the layout information of different graphic arrays in the effect detection chart card.

[0167] In a specific application scenario, the first determining module is specifically configured to:

[0168] According to the stitching field of view parameters of the camera combination, calculate the field of view range corresponding to the camera combination at the test distance:

[0169] Determining size information of the effect detection chart according to the field of view range corresponding to the camera combination at the test distance;

[0170] Correspondingly, the first determination module is further specifically used to adjust the size information of the effect detection chart according to the field of view range corresponding to the camera combination at the changed test distance when the test distance of the camera combination changes after determining the size information of the effect detection chart according to the stitching field of view parameters of the camera combination.

[0171] In a specific application scenario, at least two cameras in the camera combination are fixed on a supporting component, and the supporting component provides the function of adjusting the posture of each camera in the camera combination, so as to calculate the corresponding field of view range of the camera combination according to the adjusted posture of each camera.

[0172] In a specific application scenario, the effect detection chart includes at least a first graphic array for detecting clarity effects and a second graphic array for detecting stitching effects;

[0173] Accordingly, the construction unit is specifically configured to layout and splice the first graphic array and the second graphic array to construct an effect detection chart;

[0174] Accordingly, the selection unit is specifically configured to select a first image detection area and a second image detection area in the stitched image according to the effect detection chart, wherein the first image detection area includes a first graphic array and the second image detection area includes a second graphic array;

[0175] The detection unit is specifically configured to perform a clarity effect detection on the first image detection area to obtain a clarity detection result, and perform a stitching effect detection on the second image detection area to obtain a stitching detection result;

[0176] The determining unit is specifically configured to determine an effect detection result of the spliced ​​image according to the clarity detection result and the seam detection result.

[0177] In a specific application scenario, the selection unit is further configured to:

[0178] Determining an image area of ​​the first graphic array and an image area of ​​the second graphic array in the spliced ​​image according to the effect detection chart;

[0179] Selecting a graphic area for representing a clarity effect in the image area of ​​the first graphic array to obtain a first image detection area, wherein the first image detection area includes at least one edge area;

[0180] The image area of ​​the second graphic array is used as the graphic area representing the stitching effect to obtain a second image detection area, wherein the second image detection area includes at least one stitching area, and each stitching area is composed of multiple different second graphic sub-areas.

[0181] In a specific application scenario, the detection unit is further used to:

[0182] For the first image detection area, calculating a modulation transfer function value of at least one edge area;

[0183] If the modulation transfer function value of the at least one edge area is less than a first preset threshold, determining that the clarity detection result is qualified; otherwise, determining that the clarity detection result is unqualified;

[0184] and calculating the position coordinates of corner points of a plurality of different second graphic sub-regions for the second image detection region;

[0185] Comparing the corner point position coordinates of the plurality of different second graphic sub-regions with the standard corner point position coordinates of the corresponding second graphic sub-regions respectively, to obtain corner point position coordinate differences of the plurality of different sub-graphic sub-regions;

[0186] If the coordinate differences of the corner points of the plurality of different sub-graphic regions are all smaller than a second preset threshold, the seam detection result is determined to be qualified; otherwise, the seam detection result is determined to be unqualified;

[0187] Accordingly, the determining unit is further configured to:

[0188] If the clarity detection result is qualified and the seam detection result is qualified, then the effect detection result of the spliced ​​image is qualified; otherwise, the effect detection result of the spliced ​​image is unqualified.

[0189] In a specific application scenario, the detection unit is further used to:

[0190] Before calculating the modulation transfer function value of at least one edge area for the first image detection area, a line pair width value of the modulation transfer function is calculated for the stitched image based on the number of line pairs of the camera combination; if the line pair width value of the modulation transfer function is within a preset value range, a clarity effect detection is performed on the first image detection area.

[0191] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, wherein the computer program is configured to execute the effect detection method of the spliced ​​image of any of the above embodiments when running.

[0192] Those skilled in the art will clearly understand that the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the aforementioned method embodiments, and for the sake of brevity, they will not be further described here.

[0193] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that, within the spirit and principles of the present application, they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate from the protection scope of the present application.

Claims

1. A method for detecting the effect of splicing images, characterized in that: The method comprises: Constructing an effect detection chart, wherein the effect detection chart includes a graphic array for detecting different image effect indicators; Selecting image detection areas representing different stitching effects in a stitched image based on the effect detection chart, where the stitched image is obtained by photographing the effect detection chart with a camera combination; Performing corresponding effect detection on the image detection areas representing different splicing effects respectively to obtain detection results of different image effect indicators; An effect detection result of the spliced ​​image is determined according to the detection results of the different image effect indicators.

2. The method according to claim 1, characterized in that The structural effect detection chart includes: Determining size information of the effect detection chart based on stitching field of view parameters of a camera combination, wherein the camera combination includes at least two cameras, and the stitching field of view parameters include parameters describing overall field of view characteristics after the plurality of cameras are combined; Determining layout information of different graphic arrays in the effect detection chart according to a stitching position parameter of the camera combination, wherein the stitching position parameter is a connection position between adjacent images when stitching images captured by the camera combination; An effect detection chart card is constructed according to the size information of the effect detection chart card and the layout information of different graphic arrays in the effect detection chart card.

3. The method according to claim 2, characterized in that Determining the size information of the effect detection chart according to the stitching field of view parameters of the camera combination includes: According to the stitching field of view parameters of the camera combination, calculate the field of view range corresponding to the camera combination at the test distance: Determining size information of the effect detection chart according to the field of view range corresponding to the camera combination at the test distance; Accordingly, after determining the size information of the effect detection chart according to the stitching field of view parameters of the camera combination, the method further includes: When the test distance of the camera combination changes, the size information of the effect detection chart is adjusted according to the field of view range corresponding to the camera combination at the changed test distance.

4. The method according to claim 1, wherein The effect detection chart at least includes a first graphic array for detecting clarity effects and a second graphic array for detecting stitching effects; Accordingly, the first graphic array and the second graphic array are laid out and spliced ​​to construct an effect detection chart; Accordingly, according to the effect detection chart, a first image detection area and a second image detection area are respectively selected in the stitched image, wherein the first image detection area includes a first graphic array, and the second image detection area includes a second graphic array; Performing a clarity effect detection on the first image detection area to obtain a clarity detection result, and performing a stitching effect detection on the second image detection area to obtain a stitching detection result; An effect detection result of the spliced ​​image is determined according to the clarity detection result and the seam detection result.

5. The method according to claim 4, characterized in that The selecting, according to the effect detection chart, a first image detection area and a second image detection area in the stitched image respectively includes: Determining an image area of ​​the first graphic array and an image area of ​​the second graphic array in the spliced ​​image according to the effect detection chart; Selecting a graphic area for representing a clarity effect in the image area of ​​the first graphic array to obtain a first image detection area, wherein the first image detection area includes at least one edge area; The image area of ​​the second graphic array is used as the graphic area representing the stitching effect to obtain a second image detection area, wherein the second image detection area includes at least one stitching area, and each stitching area is composed of multiple different second graphic sub-areas.

6. The method according to any one of claims 1 to 5, characterized in that At least two cameras in the camera combination are fixed on a supporting component, and the supporting component provides a function of adjusting the posture of each camera in the camera combination, so as to calculate the corresponding field of view range of the camera combination according to the adjusted posture of each camera.

7. A device for detecting the effect of splicing images, characterized in that: It includes a camera assembly and a support assembly for carrying the camera assembly, wherein the support assembly includes a mounting base for fixing each camera in the camera assembly; The mounting seat is provided with a posture adjustment function, and the posture adjustment function includes a position adjustment function and / or an angle adjustment function; The support assembly is used to adjust the posture of each camera in the camera combination through the mounting seat to accordingly adjust the field of view range of the camera combination.

8. A device for detecting the effect of splicing images, characterized in that: The device comprises: A construction unit, configured to construct an effect detection chart, wherein the effect detection chart includes a graphic array for detecting different image effect indicators; a selection unit configured to select image detection areas representing different stitching effects in a stitched image based on the effect detection chart, wherein the stitched image is obtained by shooting the effect detection chart with a combination of cameras; A detection unit, configured to perform corresponding effect detection on the image detection areas representing different splicing effects, and obtain detection results of different image effect indicators; The determining unit is configured to determine an effect detection result of the spliced ​​image according to the detection results of the different image effect indicators.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for detecting the effect of stitched images according to any one of claims 1 to 6 are implemented.

10. 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 method for detecting the effect of stitching images according to any one of claims 1 to 6 are implemented.

Images