Image splicing method and device, nonvolatile storage medium and computer equipment

Through feature recognition and determination of transformation parameters, the image stitching is automated, the problem of low efficiency of traditional image stitching methods is solved, and the stitching efficiency and flexibility are improved.

CN119067844APending Publication Date: 2024-12-03CHINA TELECOM BESTPAY CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411116350.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Traditional image stitching methods are inefficient, require manual intervention and poor flexibility, and cannot adapt to various shooting scenes and conditions.

Method used

By obtaining the images to be stitched, feature recognition and matching, determining the transformation parameters, image transformation and stitching, and automatic stitching is achieved.

Benefits of technology

The efficiency of image stitching is improved, automated stitching is realized, and the problem of low efficiency of traditional methods is solved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067844A_ABST
    Figure CN119067844A_ABST
Patent Text Reader

Abstract

The invention discloses an image splicing method and device, a nonvolatile storage medium and computer equipment. The method comprises the following steps: acquiring a plurality of to-be-spliced images; feature recognition is carried out on the multiple to-be-spliced images, multiple matching feature points are determined, and the multiple matching feature points are common feature points in the multiple to-be-spliced images; according to the plurality of matching feature points, determining respective transformation parameters of the plurality of to-be-spliced images; performing image transformation on the plurality of to-be-spliced images based on the respective transformation parameters of the plurality of to-be-spliced images to obtain a plurality of adjusted images; and splicing the plurality of adjusted images to obtain a target image, the target image including respective information of the plurality of images to be spliced. According to the invention, the technical problem of low efficiency of the image splicing method in the prior art is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to an image stitching method, an image stitching device, a non-volatile storage medium and a computer device. Background Art

[0002] Image stitching refers to the process of stitching multiple images together to form a larger image. Typically, image stitching is used to process oversized images or to merge images from multiple angles or perspectives to obtain more comprehensive or detailed information. Traditional image stitching methods usually require manual intervention to manually adjust the stitching positions between multiple images in order to achieve seamless stitching or reasonable layout. This method is not only time-consuming, but also requires high skills and experience from the operator. In addition, in order to achieve effective image stitching, traditional methods often require the camera to maintain a certain arrangement when taking pictures, such as equal distance, equal angle, etc. This limits the flexibility of the stitching method and makes it unable to adapt to a variety of different shooting scenes and conditions.

[0003] Due to the above factors, the efficiency of traditional image stitching methods is usually low. In the case of needing to process a large number of images quickly, this method may not meet the needs.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide an image stitching method, an apparatus, a non-volatile storage medium and a computer device to at least solve the technical problem of low efficiency of the image stitching method in the related art.

[0006] According to one aspect of an embodiment of the present invention, there is provided an image stitching method, comprising: acquiring a plurality of images to be stitched; performing feature recognition on the plurality of images to be stitched to determine a plurality of matching feature points, wherein the plurality of matching feature points are common feature points in the plurality of images to be stitched; determining, according to the plurality of matching feature points, respective transformation parameters of the plurality of images to be stitched; performing image transformation on the plurality of images to be stitched based on the respective transformation parameters of the plurality of images to be stitched to obtain a plurality of adjusted images; and stitching the plurality of adjusted images to obtain a target image, wherein the target image includes respective information of the plurality of images to be stitched.

[0007] Optionally, performing feature recognition on multiple images to be stitched together to determine multiple matching feature points includes: performing feature recognition on the multiple images to be stitched together to obtain feature points of each of the multiple images to be stitched together; determining the degree of similarity between the feature points of each of the multiple images to be stitched together; and determining multiple matching feature points from the feature points of each of the multiple images to be stitched together according to the degree of similarity between the feature points of each of the multiple images to be stitched together.

[0008] Optionally, feature recognition is performed on multiple images to be stitched respectively to obtain feature points of each of the multiple images to be stitched, including: using the following method to perform feature recognition on a target stitched image to obtain feature points of the target stitched image, feature recognition is performed on multiple images to be stitched respectively to obtain feature points of each of the multiple images to be stitched: determining a degree of distinction of each of multiple pixels in the target stitched image, wherein the degree of distinction of each of the multiple pixels represents a distinction between the corresponding pixel and other pixels within a predetermined distance; and determining pixels whose degrees of distinction meet predetermined conditions as feature points of the target stitched image.

[0009] Optionally, determining the transformation parameters of each of the multiple images to be stitched according to the multiple matching feature points includes: determining the distances between the multiple matching feature points in the multiple images to be stitched respectively to obtain the characteristic distances of each of the multiple stitched images; obtaining a predetermined standard distance; and determining the transformation parameters of each of the multiple images to be stitched according to the characteristic distances and the standard distances of each of the multiple stitched images.

[0010] Optionally, multiple adjusted images are spliced ​​to obtain a target image, wherein the target image includes information of each of the multiple images to be spliced, including: marking multiple matching feature points in the multiple adjusted images respectively; determining respective positions of the multiple adjusted images, wherein when the multiple adjusted images are at their respective positions, the multiple matching feature points marked in the multiple adjusted images respectively overlap; and splicing the multiple adjusted images according to their respective positions to obtain the target image.

[0011] Optionally, the method further includes: determining a central image among multiple images to be stitched; determining color adjustment coefficients of other images among the multiple images to be stitched based on the pixel colors of matching feature points of the central image; and performing color correction on the image to be stitched according to the color adjustment coefficients of the other images to obtain a color-corrected image to be stitched.

[0012] According to another aspect of an embodiment of the present invention, an image stitching device is further provided, comprising: an acquisition module, used to acquire a plurality of images to be stitched; a first determination module, used to perform feature recognition on the plurality of images to be stitched, and determine a plurality of matching feature points, wherein the plurality of matching feature points are common feature points in the plurality of images to be stitched; a second determination module, used to determine, based on the plurality of matching feature points, respective transformation parameters of the plurality of images to be stitched; a transformation module, used to perform image transformation on the plurality of images to be stitched based on the respective transformation parameters of the plurality of images to be stitched, and obtain a plurality of adjusted images; and a stitching module, used to stitch the plurality of adjusted images, and obtain a target image, wherein the target image includes respective information of the plurality of images to be stitched.

[0013] According to another aspect of an embodiment of the present invention, a nonvolatile storage medium is provided. The nonvolatile storage medium includes a stored program, wherein when the program is running, the device where the nonvolatile storage medium is located is controlled to execute any one of the above-mentioned image stitching methods.

[0014] According to another aspect of the embodiments of the present invention, a computer device is provided. The computer device includes a processor, and the processor is used to run a program. When the program is run, any one of the above-mentioned image stitching methods is executed.

[0015] According to yet another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, any one of the above-mentioned image stitching methods is implemented.

[0016] In an embodiment of the present invention, a plurality of images to be stitched are acquired; feature recognition is performed on the plurality of images to be stitched to determine a plurality of matching feature points, wherein the plurality of matching feature points are common feature points in the plurality of images to be stitched; transformation parameters of the plurality of images to be stitched are determined according to the plurality of matching feature points; image transformation is performed on the plurality of images to be stitched based on the respective transformation parameters of the plurality of images to be stitched to obtain a plurality of adjusted images; the plurality of adjusted images are stitched to obtain a target image, wherein the target image includes information of the plurality of images to be stitched, thereby achieving the purpose of automatically stitching images, thereby realizing the technical effect of improving the efficiency of image stitching, and further solving the technical problem of low efficiency of image stitching methods in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a computer terminal for implementing an image stitching method is shown;

[0019] Figure 2 is a flowchart of an image stitching method provided according to an embodiment of the present invention;

[0020] Figure 3 4 is a structural block diagram of an image stitching device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] 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.

[0022] 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, the terms "including" and "having" and any variations thereof are 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, a method embodiment of image stitching is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing an image stitching method. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1Different configurations are shown.

[0025] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0026] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the image stitching method in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the image stitching method of the above-mentioned application is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0028] Figure 2 FIG. 1 is a flow chart of an image stitching method according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0029] Step S201, obtaining a plurality of images to be stitched.

[0030] In this step, you first need to collect multiple images that need to be stitched. These images may come from different angles of the same scene, or from the same scene at different time points. The collected images should have enough overlapping areas to facilitate subsequent feature matching and image stitching.

[0031] Step S202 , performing feature recognition on the multiple images to be stitched, and determining multiple matching feature points, wherein the multiple matching feature points are common feature points in the multiple images to be stitched.

[0032] In this step, feature points in the image are detected and described by applying a feature recognition algorithm to each image. There can be multiple feature points in an image. As long as they can reflect the more prominent features of the image, they can be used as feature points of the image, such as corners, edges, etc. Once the feature points of each image are identified, the next step is to match them between different images. This can be achieved by comparing feature descriptors. The matching feature points found are feature points that appear in multiple images, which are the basis for subsequent image transformation.

[0033] Step S203: determining the transformation parameters of the plurality of images to be stitched according to the plurality of matching feature points.

[0034] In this step, the spatial transformation parameters of each image relative to other images can be calculated based on the point pairs formed by multiple matched feature points. This usually includes transformations such as rotation, scaling, and translation. These parameters can be obtained by solving one or more similarity transformation matrices.

[0035] Step S204 , performing image transformation on the multiple images to be stitched based on the transformation parameters of each of the multiple images to be stitched, to obtain multiple adjusted images.

[0036] In this step, the transformation parameters obtained in the previous step can be used to spatially transform each image so that it is aligned to a common reference coordinate system. This step ensures that all images can be seamlessly connected when stitched together, reducing stitching errors.

[0037] Step S205 , stitching the multiple adjusted images to obtain a target image, wherein the target image includes information of each of the multiple images to be stitched.

[0038] Through the above steps, the purpose of automatically stitching images is achieved, thereby achieving the technical effect of improving the efficiency of image stitching, and further solving the technical problem of low efficiency of image stitching methods in related technologies.

[0039] As an optional embodiment, feature recognition is performed on multiple images to be stitched to determine multiple matching feature points, including: feature recognition is performed on the multiple images to be stitched respectively to obtain feature points of the multiple images to be stitched; similarity between the feature points of the multiple images to be stitched; and multiple matching feature points are determined from the feature points of the multiple images to be stitched according to the similarity between the feature points of the multiple images to be stitched.

[0040] Optionally, feature recognition can be performed on each image to be spliced ​​to obtain feature points in each image. Feature recognition can be achieved through various computer vision technologies, such as scale-invariant feature transformation, etc., which can detect key points in the image and extract corresponding descriptors for subsequent feature matching. The feature points of the image can represent the unique and identifiable areas in the image, and obtain the feature points of each of the multiple images to be spliced: after completing feature recognition, each image to be spliced ​​will have a set of feature points, which can be represented as a set of coordinates and corresponding descriptors. Next, the feature points between different images can be compared to determine the similarity between them. Specifically, it can be achieved by comparing the feature description characters of each feature point. Finally, according to the similarity between the feature points, one or two groups of feature points with higher similarity are selected as matching feature points. These matching feature points will be used in the subsequent image splicing process to achieve better image fusion and transition effects. This optional embodiment can realize feature recognition of multiple images to be spliced ​​and determine multiple matching feature points, which helps to improve the quality and accuracy of the spliced ​​image and make the spliced ​​image more natural and coherent in vision and content.

[0041] As an optional embodiment, feature recognition is performed on multiple images to be stitched respectively to obtain feature points of each of the multiple images to be stitched, including: adopting the following method to perform feature recognition on a target stitched image to obtain feature points of the target stitched image, feature recognition is performed on multiple images to be stitched respectively to obtain feature points of each of the multiple images to be stitched: determining the degree of distinction of each of multiple pixels in the target stitched image, wherein the degree of distinction of each of the multiple pixels represents the difference between the corresponding pixel and other pixels within a predetermined distance; and determining pixels whose degree of distinction meets predetermined conditions as feature points of the target stitched image.

[0042] Optionally, the feature point recognition process depends on analyzing the difference between each pixel and its surrounding pixels. This optional embodiment mainly describes how to process the target spliced ​​image and determine the feature points of the target spliced ​​image. The feature points of the target spliced ​​image can be determined by identifying other images separately to obtain the feature points of each of the multiple images to be spliced.

[0043] When performing feature recognition on the target stitched image, first, for each pixel in the target stitched image, calculate the degree of difference between it and other pixels within a predetermined distance. The degree of difference can be measured by a variety of methods, such as color difference, brightness difference, texture difference, etc. Secondly, a threshold value of the degree of difference can be set. Only when the degree of difference between a pixel and its surrounding pixels exceeds this threshold, the pixel is considered to be a potential feature point. Then, all pixels in the target stitched image can be traversed, and for each pixel, the degree of difference between it and the surrounding pixels is calculated. If the degree of difference meets or exceeds the predetermined condition, the pixel is marked as a feature point. After completing the above steps, a set of feature points will be obtained, which have high uniqueness and identifiability in the image. The above feature recognition steps can be applied to each image to be stitched, so as to obtain a set of feature points for each image to be stitched.

[0044] The advantage of this optional embodiment is that it does not rely on a specific feature detection algorithm, but directly analyzes the intrinsic properties of image pixels to identify feature points. This method is suitable for images with obvious local changes or textures, such as natural landscapes, urban buildings, etc.

[0045] As an optional embodiment, determining the transformation parameters of each of the multiple images to be stitched according to the multiple matching feature points includes: determining the distances between the multiple matching feature points in the multiple images to be stitched respectively to obtain the characteristic distances of each of the multiple stitched images; obtaining a predetermined standard distance; and determining the transformation parameters of each of the multiple images to be stitched according to the characteristic distances and the standard distances of each of the multiple stitched images.

[0046] Optionally, the determination of the transformation parameters can be achieved by analyzing the relationship between multiple matching feature points. First, find the matching feature points in each image to be stitched. Second, for each image to be stitched, calculate the distance between the matching feature points. This can be achieved by calculating the coordinate difference of the feature points. For example, if there are two feature points A and B, their coordinates in the image are (x1, y1) and (x2, y2), respectively, then the distance d between them can be determined by the Euclidean distance formula.

[0047] Then, the standard distance can be obtained. The standard distance is a predefined reference distance that can be set manually or calculated from a reference image. This distance can be used to compare and adjust the feature distance to determine the appropriate transformation parameters for each of the multiple images to be stitched. Then, the feature distance in each image to be stitched can be compared with the standard distance. If the feature distance is close to the standard distance, the current size of the image is considered suitable for stitching; if the feature distance is significantly different from the standard distance, the transformation parameters of the image need to be adjusted.

[0048] Then, appropriate transformation parameters can be determined for each image to be spliced ​​based on the comparison result between the characteristic distance and the standard distance. These parameters can include the resizing of the image, etc. Specifically, the transformation parameters (translation, rotation, scaling) of each image can be calculated by mathematical methods (such as the least squares method). And the determined transformation parameters are applied to each image to be spliced ​​to achieve image alignment. In practical applications, multiple iterations may be required to continuously adjust the transformation parameters to obtain the best splicing effect. This optional embodiment directly utilizes the feature point information of the image, which can more accurately determine the relative size between the images and adjust the images accordingly.

[0049] As an optional embodiment, multiple adjusted images are spliced ​​to obtain a target image, wherein the target image includes information of each of the multiple images to be spliced, including: marking multiple matching feature points in the multiple adjusted images respectively; determining the positions of the multiple adjusted images respectively, wherein when the multiple adjusted images are at their respective positions, the multiple matching feature points marked in the multiple adjusted images respectively overlap; and splicing the multiple adjusted images according to their respective positions to obtain the target image.

[0050] Optionally, the process of stitching multiple adjusted images involves marking and aligning matching feature points, and a final stitching operation. First, based on the determined matching feature points, the matched feature points can be marked in each adjusted image. These marks can be highlighting of the points, marking boxes or other visual indications for subsequent image alignment reference.

[0051] Secondly, the specific position of each adjusted image in the stitching process can be determined according to the relative position and direction of the feature points. Specifically, the matching feature points in the multiple stitching images can be aligned and overlapped according to the corresponding relationship, and the position where the matching feature points can overlap is determined to be the position of the multiple images to be stitched. In other words, when the multiple adjusted images are in their respective positions, the multiple matching feature points marked in the multiple adjusted images overlap.

[0052] Finally, the multiple adjusted images can be stitched together according to their respective positions to obtain a target image. During the stitching process, techniques such as image fusion and image interpolation can be used to obtain a smooth, continuous, and natural target image.

[0053] As an optional embodiment, the method also includes: determining a central image among multiple images to be stitched; determining color adjustment coefficients of other images among the multiple images to be stitched based on the pixel colors of matching feature points of the central image; and performing color correction on the image to be stitched according to the color adjustment coefficients of the other images to obtain a color-corrected image to be stitched.

[0054] Optionally, in order to further improve the stitching effect of the target image, especially the color consistency, the image stitching method can also perform color correction on the graphics. Specifically, first, an image can be selected as the central image from multiple images to be stitched. The selection of the central image can be determined based on factors such as the clarity of the image and the center position of the image. Secondly, the color adjustment coefficients of other images can be determined based on the pixel color of the matching feature points of the central image. The color adjustment coefficient can be determined based on the color difference between the central image and the image to be adjusted. The color adjustment coefficient can be global or based on a specific area. Then, the image to be stitched can be color corrected according to the color adjustment coefficients corresponding to the other images. Color correction can be performed in a variety of ways, for example, using color transformation, color correction matrix, etc. The purpose of color correction is to make the color of the image to be stitched as close as possible to the color of the central image. The image to be stitched after color correction can further improve the stitching effect and quality of the panoramic image.

[0055] Through this optional embodiment, the common color inconsistency problem in the image stitching process can be effectively solved, and the overall quality and visual effect of the stitched image can be improved. At the same time, the color correction algorithm can be optimized and improved according to specific needs to adapt to different application scenarios and image quality requirements.

[0056] It should be noted that the above-mentioned multiple images to be stitched can be two images that need to be stitched, or multiple images that need to be stitched. Among the multiple images that need to be stitched, feature matching can be performed in every two images that need to be stitched, so that every two stitched images have overlapping matching feature points, so as to determine the stitching position in the subsequent steps.

[0057] As a specific embodiment of stitching images, first, a series of images to be stitched can be collected. These images can be taken at different angles of the same scene, or multiple images with overlapping areas. Then, the images can be preprocessed as necessary, such as adjusting brightness and contrast, and cutting unnecessary parts to reduce the complexity of subsequent processing. Secondly, a feature recognition algorithm can be used to identify significant feature points in each image. Then, for each pair of images, a feature matching algorithm is used to find matching feature points between them. These matching points are feature points that represent the same thing in the two images. Then, based on the matched feature points, the transformation parameters between the images can be estimated using a homography matrix or a basic matrix. These parameters include translation, rotation, and scaling. Secondly, each image can be transformed using the estimated transformation parameters so that they are aligned in space. According to the matching feature points, the transformed images are adjusted in position, and the adjusted images are stitched together in the correct order to form a continuous, seamless large image. Then, the stitched images can be finally adjusted to ensure the consistency of the entire image in terms of color, brightness, etc. Finally, the processed and stitched images are saved as the final target image.

[0058] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0059] Through the description of the above implementation methods, those skilled in the art can clearly understand that the image stitching method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0060] According to an embodiment of the present invention, there is also provided an image stitching device for implementing the above-mentioned image stitching method. Figure 3 is a structural block diagram of an image stitching device provided according to an embodiment of the present invention, such as Figure 3As shown, the image stitching device includes: an acquisition module 31, a first determination module 32, a second determination module 33, a change module 34 and a stitching module 35. The image stitching device is described below.

[0061] The acquisition module 31 is used to acquire a plurality of images to be stitched.

[0062] The first determination module 32 is connected to the acquisition module 31 and is used to perform feature recognition on the multiple images to be spliced ​​and determine multiple matching feature points, wherein the multiple matching feature points are common feature points in the multiple images to be spliced.

[0063] The second determination module 33 is connected to the first determination module 32 and is used to determine the transformation parameters of each of the plurality of images to be spliced ​​according to the plurality of matching feature points.

[0064] The transformation module 34 is connected to the second determination module 33 and is used to perform image transformation on the multiple images to be spliced ​​based on the transformation parameters of each of the multiple images to be spliced ​​to obtain multiple adjusted images.

[0065] The stitching module 35 is connected to the changing module 34 and is used to stitch the multiple adjusted images to obtain a target image, wherein the target image includes the respective information of the multiple images to be stitched.

[0066] It should be noted that the acquisition module 31, the first determination module 32, the second determination module 33, the change module 34 and the splicing module 35 correspond to steps S202 to S206 in the embodiment, and the examples and application scenarios implemented by the multiple modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above modules, as part of the device, can be run in the computer terminal 10 provided in the embodiment.

[0067] An embodiment of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one network device among multiple network devices of a computer network. The computer device includes a memory and a processor.

[0068] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the image stitching method and device in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned image stitching method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0069] The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: obtain multiple images to be stitched; perform feature recognition on the multiple images to be stitched to determine multiple matching feature points, wherein the multiple matching feature points are common feature points in the multiple images to be stitched; determine the transformation parameters of the multiple images to be stitched according to the multiple matching feature points; perform image transformation on the multiple images to be stitched based on the transformation parameters of the multiple images to be stitched to obtain multiple adjusted images; stitch the multiple adjusted images to obtain a target image, wherein the target image includes the information of the multiple images to be stitched.

[0070] Optionally, the processor may also execute program codes of the following steps: performing feature recognition on a plurality of images to be stitched together and determining a plurality of matching feature points, including: performing feature recognition on the plurality of images to be stitched together respectively to obtain feature points of the plurality of images to be stitched together; determining a degree of similarity between the feature points of the plurality of images to be stitched together; and determining a plurality of matching feature points from the feature points of the plurality of images to be stitched together according to the degree of similarity between the feature points of the plurality of images to be stitched together.

[0071] Optionally, the processor may also execute program code of the following steps: performing feature recognition on multiple images to be stitched respectively to obtain feature points of each of the multiple images to be stitched, including: using the following method to perform feature recognition on a target stitched image to obtain feature points of the target stitched image, performing feature recognition on multiple images to be stitched respectively to obtain feature points of each of the multiple images to be stitched: determining a degree of distinction of each of multiple pixels in the target stitched image, wherein the degree of distinction of each of the multiple pixels represents a distinction between the corresponding pixel and other pixels within a predetermined distance; determining pixels whose degree of distinction meets predetermined conditions as feature points of the target stitched image.

[0072] Optionally, the processor may also execute program code of the following steps: determining transformation parameters of each of the multiple images to be stitched according to the multiple matching feature points, including: determining the distances between the multiple matching feature points in the multiple images to be stitched respectively to obtain characteristic distances of each of the multiple stitched images; obtaining a predetermined standard distance; determining transformation parameters of each of the multiple images to be stitched according to the characteristic distances and the standard distances of each of the multiple stitched images.

[0073] Optionally, the processor may also execute program code for the following steps: stitching a plurality of adjusted images to obtain a target image, wherein the target image includes information of each of the plurality of images to be stitched, including: marking a plurality of matching feature points in the plurality of adjusted images respectively; determining respective positions of the plurality of adjusted images, wherein when the plurality of adjusted images are at their respective positions, the plurality of matching feature points marked in the plurality of adjusted images respectively overlap; stitching the plurality of adjusted images according to their respective positions to obtain the target image.

[0074] Optionally, the processor may also execute the program code of the following steps: the method also includes: determining a central image among multiple images to be stitched; determining color adjustment coefficients of other images among the multiple images to be stitched based on the pixel colors of matching feature points of the central image; and performing color correction on the image to be stitched according to the color adjustment coefficients of the other images to obtain a color-corrected image to be stitched.

[0075] The embodiment of the present invention provides a solution for image stitching. In the embodiment of the present invention, by acquiring multiple images to be stitched; performing feature recognition on the multiple images to be stitched to determine multiple matching feature points, wherein the multiple matching feature points are common feature points in the multiple images to be stitched; determining the transformation parameters of the multiple images to be stitched according to the multiple matching feature points; performing image transformation on the multiple images to be stitched based on the transformation parameters of the multiple images to be stitched to obtain multiple adjusted images; stitching the multiple adjusted images to obtain a target image, wherein the target image includes the information of the multiple images to be stitched, the purpose of automatically stitching the images is achieved, thereby achieving the technical effect of improving the efficiency of image stitching, and further solving the technical problem of low efficiency of the image stitching method in the related art.

[0076] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a non-volatile storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0077] The embodiment of the present invention further provides a non-volatile storage medium. Optionally, in this embodiment, the non-volatile storage medium can be used to store the program code executed by the image stitching method provided in the embodiment.

[0078] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0079] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: acquiring multiple images to be stitched; performing feature recognition on the multiple images to be stitched, and determining multiple matching feature points, wherein the multiple matching feature points are common feature points in the multiple images to be stitched; determining transformation parameters of each of the multiple images to be stitched based on the multiple matching feature points; performing image transformation on the multiple images to be stitched based on the transformation parameters of each of the multiple images to be stitched, and obtaining multiple adjusted images; stitching the multiple adjusted images to obtain a target image, wherein the target image includes information of each of the multiple images to be stitched.

[0080] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: performing feature recognition on multiple images to be stitched together and determining multiple matching feature points, including: performing feature recognition on the multiple images to be stitched together respectively to obtain feature points of each of the multiple images to be stitched together; determining the degree of similarity between the feature points of each of the multiple images to be stitched together; and determining multiple matching feature points among the feature points of each of the multiple images to be stitched together according to the degree of similarity between the feature points of each of the multiple images to be stitched together.

[0081] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: performing feature recognition on multiple images to be stitched respectively to obtain feature points of each of the multiple images to be stitched, including: using the following method to perform feature recognition on a target stitched image to obtain feature points of the target stitched image, performing feature recognition on multiple images to be stitched respectively to obtain feature points of each of the multiple images to be stitched: determining a degree of distinction of each of multiple pixels in the target stitched image, wherein the degree of distinction of each of the multiple pixels represents a distinction between the corresponding pixel and other pixels within a predetermined distance; determining pixels whose degree of distinction meets predetermined conditions as feature points of the target stitched image.

[0082] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: determining the transformation parameters of each of the multiple images to be stitched according to the multiple matching feature points, including: determining the distances between the multiple matching feature points in the multiple images to be stitched respectively to obtain the characteristic distances of each of the multiple stitched images; obtaining a predetermined standard distance; determining the transformation parameters of each of the multiple images to be stitched according to the characteristic distances and the standard distances of each of the multiple stitched images.

[0083] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: stitching multiple adjusted images to obtain a target image, wherein the target image includes information about each of the multiple images to be stitched, including: marking multiple matching feature points in the multiple adjusted images respectively; determining respective positions of the multiple adjusted images, wherein when the multiple adjusted images are at their respective positions, the multiple matching feature points marked in the multiple adjusted images respectively overlap; stitching the multiple adjusted images according to their respective positions to obtain the target image.

[0084] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: the method also includes: determining a central image among multiple images to be stitched; determining color adjustment coefficients of other images among the multiple images to be stitched based on the pixel colors of matching feature points of the central image; and performing color correction on the image to be stitched according to the color adjustment coefficients of the other images to obtain a color-corrected image to be stitched.

[0085] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the steps of the image stitching method in each embodiment of the present application when the computer program is executed by a processor.

[0086] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0087] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0089] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0090] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0091] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0092] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An image stitching method, characterized in that: include: Acquire multiple images to be stitched; Performing feature recognition on the multiple images to be stitched together to determine multiple matching feature points, wherein the multiple matching feature points are common feature points in the multiple images to be stitched together; Determining, according to the plurality of matching feature points, respective transformation parameters of the plurality of images to be stitched; Based on the transformation parameters of each of the multiple images to be stitched, performing image transformation on the multiple images to be stitched to obtain multiple adjusted images; The multiple adjusted images are stitched together to obtain a target image, wherein the target image includes information of each of the multiple images to be stitched together.

2. The method according to claim 1, characterized in that: The step of performing feature recognition on the plurality of images to be stitched to determine a plurality of matching feature points includes: Performing feature recognition on the multiple images to be stitched respectively to obtain feature points of the multiple images to be stitched; Determining the similarity between the feature points of the plurality of images to be stitched; According to the similarity between the feature points of the plurality of images to be stitched, the plurality of matching feature points are determined from the feature points of the plurality of images to be stitched.

3. The method according to claim 2, characterized in that The step of performing feature recognition on the plurality of images to be stitched respectively to obtain feature points of the plurality of images to be stitched respectively includes: The following method is used to perform feature recognition on the target stitching image to obtain the feature points of the target stitching image, and feature recognition is performed on the multiple images to be stitched respectively to obtain the feature points of each of the multiple images to be stitched: Determining a degree of distinction between each of a plurality of pixels in the target stitched image, wherein the degree of distinction between each of the plurality of pixels represents a distinction between the corresponding pixel and other pixels within a predetermined distance; The pixels whose difference degree meets the predetermined condition are determined as the feature points of the target spliced ​​image.

4. The method according to claim 1, characterized in that The step of determining the transformation parameters of each of the plurality of images to be stitched according to the plurality of matching feature points comprises: Determining the distances between the plurality of matching feature points in the plurality of images to be stitched respectively, to obtain the feature distances of the plurality of stitched images; Obtaining a predetermined standard distance; Determine the transformation parameters of each of the plurality of images to be stitched according to the characteristic distance of each of the plurality of stitched images and the standard distance.

5. The method according to claim 1, characterized in that The step of stitching the plurality of adjusted images to obtain a target image includes information of each of the plurality of images to be stitched, including: marking the plurality of matching feature points in the plurality of adjusted images respectively; Determining respective positions of the plurality of adjusted images, wherein when the plurality of adjusted images are at their respective positions, the plurality of matching feature points marked in the plurality of adjusted images respectively overlap; The target image is obtained by splicing the multiple adjusted images according to their respective positions.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: Determining a central image among the multiple images to be stitched; Determine the color adjustment coefficients of other images in the plurality of images to be stitched based on the pixel colors of the matching feature points of the central image; Color correction is performed on the image to be spliced ​​according to the color adjustment coefficients of the other images to obtain the image to be spliced ​​after color correction.

7. An image stitching device, characterized in that: include: An acquisition module, used for acquiring a plurality of images to be stitched; A first determination module is used to perform feature recognition on the multiple images to be stitched, and determine multiple matching feature points, wherein the multiple matching feature points are common feature points in the multiple images to be stitched; A second determination module, configured to determine the transformation parameters of each of the plurality of images to be stitched according to the plurality of matching feature points; A transformation module, configured to perform image transformation on the plurality of images to be stitched based on the respective transformation parameters of the plurality of images to be stitched, so as to obtain a plurality of adjusted images; The stitching module is used to stitch the multiple adjusted images to obtain a target image, wherein the target image includes the information of each of the multiple images to be stitched.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the image stitching method according to any one of claims 1 to 6.

9. A computer device, characterized in that: include: Memory and processor, The memory stores a computer program; The processor is used to execute the computer program stored in the memory, and when the computer program is running, the processor executes the image stitching method according to any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that The computer instructions are executed by a processor to implement the image stitching method described in any one of claims 1 to 6.

Citation Information

Cited By

  • Simulation model construction method and device based on image features, equipment and medium

    CN119418005A