Image edge fusion method and device for projection, equipment and medium

Abstract

The invention discloses an image edge fusion method and device for projection, equipment and a medium. The method comprises the steps that color sampling is carried out on each target picture through an RGB color space according to a preset sampling rule, a sampling pixel set is obtained, and the sampling pixel set comprises the pixel value of at least one sampling point; processing the pixel value of each sampling point in the sampling color set by using an edge fusion model to obtain a fusion weight set matched with the sampling pixel set; and performing interpolation processing on the fusion weight set by using a preset algorithm to obtain a weight set matched with the target pictures, and performing edge fusion operation on each target picture by using the weight set. Through the technical scheme of the invention, the edge fusion of each picture can be realized, the efficiency of image edge fusion operation is improved, and the quality of an edge fusion result is also improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to an image edge fusion method, device, equipment and medium for projection. Background Art

[0002] In the multi-channel projection image splicing and fusion system, edge fusion technology is the key to achieve seamless image splicing. Its principle is to attenuate the brightness of the edge parts of adjacent images, so that the spliced ​​images can transition naturally in the middle to form an integrated and continuous image.

[0003] At present, the commonly used edge fusion methods are mainly the following: 1. Parameter-based brightness attenuation curve: The edge fusion curve is generated by adjusting the curve parameters. However, for some projectors, it may not be possible to adjust the appropriate parameter combination, resulting in poor fusion effect of the final picture. 2. Customized brightness attenuation curve: The user can adjust the position of the curve control point according to the display picture effect, and then generate a smooth brightness attenuation curve. Although this method can accurately adjust the brightness of the overlapping area of ​​the projected picture and achieve good splicing and fusion effect on most display colors, for some colors, there is a significant brightness difference between the intermediate fusion area and the adjacent area after fusion, resulting in poor visual consistency of the entire picture. 3. Automatically calculate the edge fusion brightness attenuation curve of the projector based on camera acquisition data: This method collects data through the camera, calculates the brightness response function of the projector, and then infers the edge fusion curve of each projector. However, it has certain limitations. On the one hand, this method requires high-precision and expensive cameras for data acquisition, which is not conducive to wide application; on the other hand, image data acquisition needs to be carried out in a relatively dark environment, and has specific requirements for ambient light.

[0004] In summary, the existing image edge fusion technology has the problem of poor fusion operation efficiency and poor quality of the obtained edge fusion results. Summary of the invention

[0005] The present invention provides an image edge fusion method, device, equipment and medium for projection, which can solve the problems of poor fusion operation efficiency and poor quality of edge fusion results in existing image edge fusion technologies.

[0006] In a first aspect, an embodiment of the present invention provides an image edge fusion method for projection, the method comprising:

[0007] Performing color sampling on each target image according to a preset sampling rule through the RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes a pixel value of at least one sampling point;

[0008] Using an edge fusion model to process the pixel value of each sampling point in the sampled color set, to obtain a fusion weight set matching the sampled pixel set;

[0009] The fusion weight set is interpolated using a preset algorithm to obtain a weight set that matches the target image, and the weight set is used to perform an edge fusion operation on each target image.

[0010] In a second aspect, an embodiment of the present invention provides an image edge fusion device for projection, the device comprising:

[0011] A sampling module is used to perform color sampling on each target image according to a preset sampling rule through an RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes a pixel value of at least one sampling point;

[0012] A fusion weight calculation module is used to process the pixel value of each sampling point in the sampled color set using an edge fusion model to obtain a fusion weight set matching the sampled pixel set;

[0013] The interpolation calculation module is used to use a preset algorithm to perform interpolation processing on the fusion weight set to obtain a weight set matching the target image, and use the weight set to perform an edge fusion operation on each target image.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the image edge fusion method for projection described in any embodiment of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement an image edge fusion method for projection described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention performs color sampling on each target image according to a preset sampling rule through an RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes the pixel value of at least one sampling point, and then uses an edge fusion model to process the pixel value of each sampling point in the sampled color set to obtain a fusion weight set matching the sampled pixel set, and finally uses a preset algorithm to perform interpolation processing on the fusion weight set to obtain a weight collection matching the target image, and uses the weight collection to perform an edge fusion operation on each target image, thereby solving the problem that the fusion operation efficiency of the existing image edge fusion technology is poor and the quality of the edge fusion result obtained is poor, and the edge fusion of each image is realized, the efficiency of the image edge fusion operation is improved, and the quality of the edge fusion result is also improved.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of an image edge fusion method for projection provided according to Embodiment 1 of the present invention;

[0023] Figure 2 is a flow chart of an image edge fusion method for projection provided according to Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic structural diagram of an image edge fusion device for projection provided according to Embodiment 3 of the present invention;

[0025] Figure 4 The invention is a schematic structural diagram of an electronic device for implementing an image edge fusion method for projection according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, any variation of the terms "including" and "having" is intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 A flowchart of an image edge fusion method for projection is provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation where edge fusion of multiple target images for projection is performed. The method can be executed by an image edge fusion device for projection. The image edge fusion device for projection can be implemented in the form of hardware and / or software. The image edge fusion device for projection can be configured in a terminal or server with an edge fusion function for projecting images.

[0030] like Figure 1 As shown, the method includes:

[0031] S110 , performing color sampling on each target image according to a preset sampling rule in an RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes a pixel value of at least one sampling point.

[0032] The preset sampling rule includes uniform sampling or non-uniform sampling.

[0033] The RGB color space is a common color model that represents various colors by superimposing three color channels: red, green, and blue. For example, pure red can be represented as (255, 0, 0), pure green as (0, 255, 0), and pure blue as (0, 0, 255).

[0034] In this embodiment, each target image can be specifically a portion of the image to be fused of each image to be edge-fused. The specific size of the portion to be fused can be set and adjusted by relevant staff according to the actual image size and fusion range, and this embodiment does not impose any restrictions on this.

[0035] Furthermore, the preset sampling rules include two methods: uniform sampling and non-uniform sampling. Uniform sampling is like selecting sampling points at equal intervals on a piece of uniform cloth; while non-uniform sampling is to selectively sample at different positions and at different intervals according to specific rules or needs, such as collecting more samples in areas where color changes are more frequent or important in the image. It should be noted that in a specific implementation scenario of this embodiment, when the brightness and color consistency of multiple projectors projecting each target image is good, uniform sampling can generally be used; when the brightness and color consistency of multiple projectors projecting each target image is poor, in order to obtain a better fusion effect, in addition to matching the uniformly sampled colors, it is also necessary to match certain special colors. At this time, the obtained sampling color set is non-uniform, that is, non-uniform sampling. In this implementation, the specific content of the sampling rules can be pre-set by relevant personnel according to the actual implementation scenario to achieve a better sampling effect.

[0036] S120 , using an edge fusion model to process the pixel value of each sampling point in the sampled color set to obtain a fusion weight set matching the sampled pixel set.

[0037] The edge fusion model is an algorithm or mathematical model specifically used to achieve smooth transition and fusion effects of image edges; illustratively, the edge fusion model can be a deep learning algorithm that learns how to accurately process pixel values ​​to achieve an ideal fusion effect through a large amount of training data, or a traditional image processing algorithm, such as a gradient-based method, a filtering-based method, etc. It should be noted that the edge fusion model is a mature existing technology, and this embodiment does not elaborate on its principle or implementation process.

[0038] S130 , using a preset algorithm to perform interpolation processing on the fusion weight set to obtain a weight set that matches the target image, and using the weight set to perform an edge fusion operation on each target image.

[0039] Wherein, the preset algorithm is trilinear interpolation method or tetrahedral interpolation method.

[0040] Among them, the fusion weight set is interpolated using a preset algorithm to obtain a weight collection that matches the target image, including: when it is recognized that the current preset sampling rule is uniform sampling, the fusion weight set is interpolated using a trilinear interpolation method to obtain a weight collection that matches the target image; when it is recognized that the current preset sampling rule is non-uniform sampling, the fusion weight set is interpolated using a tetrahedron interpolation method to obtain a weight collection that matches the target image, and the number of edge fusion weights contained in the weight collection is equal to the total number of pixels of each target image.

[0041] On the basis of the above steps, if it is identified that the current preset sampling rule belongs to the case of uniform sampling, the trilinear interpolation method will be used to carry out interpolation processing for the fused weight set; wherein the trilinear interpolation method is a method for linear interpolation in three-dimensional space; for example, when processing three-dimensional image data, the grayscale values ​​of eight vertices are known, and the grayscale value of any point inside the cube can be estimated by the trilinear interpolation method. After the processing of the trilinear interpolation method, the weight set matching the target image can be obtained. When it is identified that the current preset sampling rule is non-uniform sampling, the tetrahedron interpolation method is used to interpolate the fused weight set; the tetrahedron interpolation method is to divide the data space into multiple tetrahedrons, and then calculate the value of the internal point according to the value of the tetrahedron vertex. For example, in a complex three-dimensional model, it is divided into multiple tetrahedrons. If the attribute value of the tetrahedron vertex is known, the attribute value of any point inside the model can be estimated by this method. Through the processing of the tetrahedron interpolation method, the weight set matching the target image can also be obtained. It should be noted that the number of edge fusion weights contained in this weight collection is equal to the total number of pixels in each target image.

[0042] Furthermore, the weight collection is used to perform an edge fusion operation on each target image, including: in the weight collection, obtaining a target weight that matches each pixel point respectively, and simultaneously obtaining an original brightness value of the pixel point and a preset target brightness value; according to the formula: brightness weight = original brightness value × (1-target weight) + target brightness value × target weight, respectively calculating brightness weights that match each pixel point respectively; and adjusting the brightness of each pixel point based on each brightness weight to complete the edge fusion operation on each target image.

[0043] Specifically, the brightness of each pixel is adjusted based on each brightness weight, including: obtaining an adjusted brightness value matching the current pixel through the brightness weight calculation, and applying the adjusted brightness value to the pixel matching the brightness weight, so as to achieve the purpose of edge fusion of the projected image. Exemplarily, first, determine the original brightness value and the target brightness value, the original brightness value is the current brightness level of the pixel, and the target brightness value is the brightness level that the pixel is expected to reach. Then, obtain the corresponding brightness weight. Next, substitute the original brightness value, the target brightness value and the brightness weight into the formula for calculation. For example, if the formula "adjusted brightness value = original brightness value × (1-brightness weight) + target brightness value × brightness weight" is used, assuming that the original brightness value of pixel A is 150, the target brightness value is 200, and the brightness weight is 0.7, then the adjusted brightness value is equal to 185, so the brightness of pixel A is adjusted to 150. In actual image processing, each pixel in the image can be calculated and adjusted in this way to achieve edge fusion operations on each target image; it should be noted that due to differences in factors such as target image type, delivery equipment, and scene in actual implementation scenarios, the method of adjusting the brightness value after extreme adjustment can also be adjusted by relevant staff according to actual implementation scenarios, and this embodiment does not impose any restrictions on this.

[0044] The technical solution of the embodiment of the present invention performs color sampling on each target image according to a preset sampling rule through an RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes the pixel value of at least one sampling point, and then uses an edge fusion model to process the pixel value of each sampling point in the sampled color set to obtain a fusion weight set matching the sampled pixel set, and finally uses a preset algorithm to perform interpolation processing on the fusion weight set to obtain a weight collection matching the target image, and uses the weight collection to perform an edge fusion operation on each target image, thereby realizing edge fusion of each image, improving the efficiency of the image edge fusion operation, and also improving the quality of the edge fusion result.

[0045] Embodiment 2

[0046] Figure 2 A flowchart of an image edge fusion method for projection provided in Embodiment 2 of the present invention is provided. This embodiment is refined based on the above-mentioned embodiment. In this embodiment, the pixel values ​​of each sampling point in the sampled color set are processed using an edge fusion model to obtain a fusion weight set that matches the sampled pixel set.

[0047] like Figure 2 As shown, the method includes:

[0048] S210 , performing color sampling on each target image according to a preset sampling rule in an RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes a pixel value of at least one sampling point.

[0049] S220: Use an edge fusion model to process the pixel value of each sampling point in the sampled color set to obtain a fusion curve set that matches the sampled pixel set.

[0050] Specifically, the pixel value of each sampling point in the sampled color set is processed using an edge fusion model to obtain a fusion curve set matching the sampled pixel set, including: inputting the pixel value of each sampling point in the sampled color set into the edge fusion model respectively to obtain a fusion curve matching each sampling point respectively; aggregating and storing each fusion curve to obtain a fusion curve set matching the sampled pixel set, wherein the number of fusion curves in the fusion curve set is consistent with the number of sampling points in the sampled color set.

[0051] Specifically, the edge fusion model is used to process the pixel values ​​of each sampling point in the sampled color set to obtain a fusion curve set that matches the sampled pixel set. The process includes the following steps: the first step is to input the pixel values ​​of each sampling point in the sampled color set into the edge fusion model respectively, and let the model analyze and calculate according to the characteristics and rules of these pixel values. After being processed by the model, a fusion curve corresponding to each sampling point is obtained. The second step is to aggregate and store each fusion curve, and finally obtain a fusion curve set that matches the sampled pixel set. It should be noted that in this fusion curve set, the number of fusion curves is exactly the same as the number of sampling points in the sampled color set. In other words, each sampling point has a fusion curve generated specifically for it.

[0052] S230 . Obtain the fusion weight set matching the sampled pixel set by tetrahedral interpolation calculation according to the sampled pixel set and the fusion curve set.

[0053] Specifically, according to the sampling pixel set and the fusion curve set, the fusion weight set matching the sampling pixel set is obtained by tetrahedral interpolation calculation, including: tetrahedral division of each pixel value in the sampling data set to obtain division data respectively matching each pixel value; searching for a fusion curve matching the pixel value in the fusion curve set as a target fusion curve of the division data matching the pixel value; processing the division data and the target fusion curve matching the division data based on the tetrahedral interpolation method to obtain a fusion weight matching the pixel value; and aggregating and storing the fusion weights to obtain a fusion weight set matching the sampling pixel set.

[0054] Specifically, according to the sampling pixel set and the fusion curve set, the fusion weight set matching the sampling pixel set is obtained by tetrahedral interpolation calculation, which includes the following steps: the first step is to tetrahedralize each pixel value in the sampling data set. The tetrahedralization is to divide the spatial area where the pixel value is located into small tetrahedral units, so as to obtain the segmented data matching each pixel value. The second step is to search for the fusion curve matching the pixel value in the fusion curve set, and use it as the target fusion curve of the segmented data matching the pixel value. The third step is to process the segmented data and the target fusion curve matching the segmented data based on the tetrahedral interpolation method to obtain the fusion weight matching the pixel value. The tetrahedral interpolation method is a method for numerical interpolation in three-dimensional space. In mathematics and computational science, it is often used to deal with interpolation and estimation problems of three-dimensional data. Its basic idea is to divide the three-dimensional space area under study into a series of tetrahedrons. For the point whose value needs to be estimated, the tetrahedron containing the point is first determined. Then, based on the known values ​​of the tetrahedron vertices and the positional relationship of the point relative to the tetrahedron vertices, the interpolation result of the point is calculated through a specific mathematical formula. Correspondingly, in this embodiment, the segmentation data of some pixel points obtained by tetrahedron segmentation are known. To estimate the segmentation data of other pixel points in the image, the tetrahedron interpolation method can be used to obtain the segmentation data of other pixels based on the target fusion curve. The advantage of the tetrahedron interpolation method is that it can better handle irregular three-dimensional data distribution and to a certain extent ensure the accuracy and rationality of the interpolation results. However, its computational complexity is relatively high, and effective management and calculation of the data structure are required. The fourth step is to aggregate and store the various fusion weights to obtain a fusion weight set that matches the sampled pixel set.

[0055] S240: Use a preset algorithm to perform interpolation processing on the fusion weight set to obtain a weight set that matches the target image, and use the weight set to perform an edge fusion operation on each target image.

[0056] The technical solution of the embodiment of the present invention performs color sampling on each target image according to a preset sampling rule through an RGB color space to obtain a sampling pixel set, wherein the sampling pixel set includes the pixel value of at least one sampling point, and then uses an edge fusion model to process the pixel value of each sampling point in the sampled color set to obtain a fusion curve set matching the sampled pixel set, and obtains the fusion weight set matching the sampled pixel set through tetrahedral interpolation calculation based on the sampled pixel set and the fusion curve set, and finally uses a preset algorithm to perform interpolation processing on the fusion weight set to obtain a weight collection matching the target image, and uses the weight collection to perform an edge fusion operation on each target image, thereby realizing edge fusion of each projected image, improving the efficiency of the edge fusion operation of the projected image, and also improving the quality of the edge fusion result of the projected image.

[0057] Embodiment 3

[0058] Figure 3 This is a schematic diagram of the structure of an image edge fusion device for projection provided by Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0059] The sampling module 310 is used to perform color sampling on each target image according to a preset sampling rule in the RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes a pixel value of at least one sampling point;

[0060] A fusion weight calculation module 320 is used to process the pixel value of each sampling point in the sampled color set using an edge fusion model to obtain a fusion weight set matching the sampled pixel set;

[0061] The interpolation calculation module 330 is used to perform interpolation processing on the fusion weight set using a preset algorithm to obtain a weight set matching the target image, and use the weight set to perform an edge fusion operation on each target image.

[0062] The technical solution of the embodiment of the present invention performs color sampling on each target image according to a preset sampling rule through an RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes the pixel value of at least one sampling point, and then uses an edge fusion model to process the pixel value of each sampling point in the sampled color set to obtain a fusion weight set matching the sampled pixel set, and finally uses a preset algorithm to perform interpolation processing on the fusion weight set to obtain a weight collection matching the target image, and uses the weight collection to perform an edge fusion operation on each target image, thereby realizing edge fusion of the projected image, improving the efficiency of the edge fusion operation of the projected image, and also improving the quality of the edge fusion result of the projected image.

[0063] Based on the above embodiment, the fusion weight calculation module 320 includes:

[0064] A curve acquisition unit, used to process the pixel value of each sampling point in the sampled color set using an edge fusion model to obtain a fusion curve set matching the sampled pixel set;

[0065] The tetrahedron interpolation unit is used to obtain the fusion weight set matching the sampling pixel set through tetrahedron interpolation calculation according to the sampling pixel set and the fusion curve set.

[0066] Based on the above embodiment, the curve acquisition unit further includes:

[0067] A fusion curve unit, used to input the pixel value of each sampling point in the sampled color set into the edge fusion model to obtain a fusion curve that matches each sampling point;

[0068] The curve storage unit is used to aggregate and store the fusion curves to obtain a fusion curve set matching the sampling pixel set, wherein the number of fusion curves in the fusion curve set is consistent with the number of sampling points in the sampling color set.

[0069] Based on the above embodiment, the tetrahedron interpolation unit further comprises:

[0070] A tetrahedron partitioning unit is used to perform tetrahedron partitioning on each pixel value in the sample data set to obtain partitioned data that matches each pixel value;

[0071] A target curve search unit, used to search for a fusion curve matching the pixel value in a fusion curve set as a target fusion curve of the segmented data matching the pixel value;

[0072] A fusion weight calculation unit, used for processing the segmented data and a target fusion curve with the segmented data based on a tetrahedral interpolation method to obtain a fusion weight matching the pixel value;

[0073] The weight storage unit is used to aggregate and store the fusion weights to obtain a fusion weight set that matches the sampled pixel set.

[0074] Based on the above embodiment, the interpolation calculation module 330 includes:

[0075] A first interpolation unit, configured to, when identifying that the currently preset sampling rule is uniform sampling, use a trilinear interpolation method to interpolate the fused weight set to obtain a weight set matching the target image;

[0076] The second interpolation unit is used to use the tetrahedron interpolation method to interpolate the fusion weight set when it is recognized that the current preset sampling rule is non-uniform sampling, so as to obtain a weight collection that matches the target image, and the number of edge fusion weights contained in the weight collection is equal to the total number of pixels of each target image.

[0077] Based on the above embodiment, the interpolation calculation module 330 further includes:

[0078] A brightness value acquisition unit, used to acquire, from the weight set, a target weight value that matches each pixel point, and simultaneously acquire an original brightness value of the pixel point and a preset target brightness value;

[0079] A brightness weight calculation unit is used to calculate the brightness weights that match each pixel point according to the formula: brightness weight = original brightness value × (1-target weight) + target brightness value × target weight;

[0080] The edge fusion unit is used to adjust the brightness of each pixel based on each brightness weight to complete the edge fusion operation of each target image.

[0081] An image edge fusion device for projection provided by an embodiment of the present invention can execute an image edge fusion method for projection provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0082] Embodiment 4

[0083] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0084] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0085] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0086] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as an image edge fusion method for projection.

[0087] Accordingly, the method comprises:

[0088] Performing color sampling on each target image according to a preset sampling rule through the RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes a pixel value of at least one sampling point;

[0089] Using an edge fusion model to process the pixel value of each sampling point in the sampled color set, to obtain a fusion weight set matching the sampled pixel set;

[0090] The fusion weight set is interpolated using a preset algorithm to obtain a weight set that matches the target image, and the weight set is used to perform an edge fusion operation on each target image.

[0091] In some embodiments, a method for image edge fusion for projection may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for image edge fusion for projection described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute a method for image edge fusion for projection in any other appropriate manner (e.g., by means of firmware).

[0092] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0094] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0096] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0097] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0098] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

Claims

1. A method for edge fusion of an image for projection, characterized in that: include: Performing color sampling on each target image according to a preset sampling rule through the RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes a pixel value of at least one sampling point; Using an edge fusion model to process the pixel value of each sampling point in the sampled color set, to obtain a fusion weight set matching the sampled pixel set; The fusion weight set is interpolated using a preset algorithm to obtain a weight set that matches the target image, and the weight set is used to perform an edge fusion operation on each target image.

2. The method according to claim 1, characterized in that The preset sampling rule includes uniform sampling or non-uniform sampling.

3. The method according to claim 1, characterized in that The pixel value of each sampling point in the sampled color set is processed using an edge fusion model to obtain a fusion weight set matching the sampled pixel set, including: Using an edge fusion model to process the pixel value of each sampling point in the sampled color set, to obtain a fusion curve set matching the sampled pixel set; According to the sampling pixel set and the fusion curve set, the fusion weight set matching the sampling pixel set is obtained through tetrahedral interpolation calculation.

4. The method according to claim 3, characterized in that The pixel value of each sampling point in the sampled color set is processed using an edge fusion model to obtain a fusion curve set matching the sampled pixel set, including: Input the pixel values ​​of each sampling point in the sampled color set into the edge fusion model to obtain fusion curves that match each sampling point; The fusion curves are aggregated and stored to obtain a fusion curve set that matches the sampling pixel set, wherein the number of fusion curves in the fusion curve set is consistent with the number of sampling points in the sampling color set.

5. The method according to claim 3, characterized in that: According to the sampling pixel set and the fusion curve set, the fusion weight set matching the sampling pixel set is obtained by tetrahedral interpolation calculation, including: Performing tetrahedral division on each pixel value in the sampled data set to obtain divided data that matches each pixel value; Searching for a fusion curve matching the pixel value in a fusion curve set as a target fusion curve of the segmented data matching the pixel value; Processing the segmented data and a target fusion curve with the segmented data based on a tetrahedral interpolation method to obtain a fusion weight matching the pixel value; The fusion weights are aggregated and stored to obtain a fusion weight set that matches the sampled pixel set.

6. The method according to any one of claims 1-2, characterized in that: Using a preset algorithm to interpolate the fused weight set to obtain a weight set matching the target image, including: When it is identified that the currently preset sampling rule is uniform sampling, the fusion weight set is interpolated using a trilinear interpolation method to obtain a weight set matching the target image; When it is identified that the current preset sampling rule is non-uniform sampling, the fusion weight set is interpolated using the tetrahedron interpolation method to obtain a weight set that matches the target image, and the number of edge fusion weights contained in the weight set is equal to the total number of pixels of each target image.

7. The method according to claim 1, characterized in that Using the weight set to perform edge fusion operation on each target image includes: In the weight collection, a target weight matching each pixel is obtained, and an original brightness value of the pixel and a preset target brightness value are obtained; According to the formula: brightness weight = original brightness value × (1-target weight) + target brightness value × target weight, the brightness weights matching each pixel are calculated respectively; The brightness of each pixel is adjusted based on each brightness weight to complete the edge fusion operation of each target image.

8. An image edge fusion device for projection, characterized in that: include: A sampling module is used to perform color sampling on each target image according to a preset sampling rule through an RGB color space to obtain a sampled pixel set, wherein the sampled pixel set includes a pixel value of at least one sampling point; A fusion weight calculation module is used to process the pixel value of each sampling point in the sampled color set using an edge fusion model to obtain a fusion weight set matching the sampled pixel set; The interpolation calculation module is used to use a preset algorithm to perform interpolation processing on the fusion weight set to obtain a weight set matching the target image, and use the weight set to perform an edge fusion operation on each target image.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the image edge fusion method for projection according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement an image edge fusion method for projection according to any one of claims 1 to 7 when executed.

Images