Method, System, Electronic Device, and Storage Medium for Repeated Texture Filtering

Abstract

The present application relates to a method, a system, an electronic device and a storage medium for repeated texture filtering. The method includes: obtaining an image matching map of a video sequence, performing FH verification on the matching map to obtain an image containing repeated textures, and performing co-visibility verification on the image containing repeated textures, where the repeated textures include continuous repeated textures and single-plane textures; then, performing hierarchical clustering and convex polygon fitting on the repeated texture image after co-visibility verification to obtain a convex polygon seed image containing repeated texture features; finally, performing depth progressive transmission on the convex polygon seed image containing repeated texture features, and filtering the feature matching pairs falling within the convex polygon in the image to obtain a filtered image matching map. Through the present application, mis-matched images of repeated textures are filtered, and the accuracy of map building is improved.

Description

Technical Field

[0001] The present application relates to the field of three-dimensional reconstruction technology, and in particular to a method, system, electronic device and storage medium for repeated texture filtering. Background Art

[0002] In the SFM reconstruction process, the first step is to extract features from each image, and the second step is to perform feature matching and two-view geometric verification on any two images; after these two steps, a graph is formed with images as nodes and the matching relationships between images as edges, which is the "image matching graph". However, in the reconstruction process, there will be repeated texture feature matching pairs. In order to avoid this situation, it is necessary to filter and delete such mis-matched graphs.

[0003] In the related art, in filtering mis-matches, on the one hand, the view graph is mainly used, that is, the relative orientation between two images is used as an undirected edge, and all images are used as nodes to construct a graph. Finally, the inconsistency of the transmitted observations is used to filter out the wrong matches. For example, there are image matching pairs: A - B, B - C, and A - C. Assuming that A - C is the matching pair with the highest confidence, A - C^ can be obtained through A - B - C. Calculate the difference between A - C^ and A - C. If the difference is too large, the wrong matches A - B and B - C can be filtered out. However, for the view graph algorithm, it is assumed that the relative orientation view between two images is known. When solving the view between two images, it is necessary to know the H matrix or the E matrix (the E matrix is obtained by decomposing the matrix after obtaining the camera internal parameters through the F matrix). However, in general SFM scenarios, the camera internal parameters are not known, so the E matrix cannot be obtained, and it is impossible for all image matching pairs to be H matrices. Therefore, such algorithms cannot be directly applied to actual scenarios. On the other hand, based on the global feature match algorithm to filter out wrong matching pairs. However, this algorithm will mis-delete matching pairs with large view changes, and for scenes with repeated textures, it still cannot be filtered. In addition, the track length algorithm can also be used to accumulate weights for the feature points of the image, sort according to the weights, and register the order; however, this method essentially avoids wrong matches and does not really filter wrong matches, and still cannot solve the problem for scenes with repeated textures.

[0004] Currently, in the related art, when filtering image mis-matches that occur during the three-dimensional reconstruction process, there are problems of lack of repeated texture detection and filtering, and lack of practicality, and no effective solution has been proposed yet. Summary of the Invention

[0005] An embodiment of the present application provides a method, a system, an electronic device, and a storage medium for repeated texture filtering, so as to at least solve the problems of lack of repeated texture detection and filtering and lack of practicality in filtering image mismatches that occur during 3D reconstruction in related technologies.

[0006] In a first aspect, an embodiment of the present application provides a method for repeated texture filtering, and the method includes:

[0007] Obtain an image matching map of a video sequence, perform FH verification on the matching map to obtain an image containing repeated textures, and perform coplanarity verification on the image containing repeated textures, where the repeated textures include continuous repeated textures and single-plane textures;

[0008] Perform hierarchical clustering and convex polygon fitting on the repeated texture image after coplanarity verification to obtain a convex polygon seed image containing repeated texture features;

[0009] Perform depth progressive transmission on the convex polygon seed image containing repeated texture features, and filter the feature matching pairs in the image that fall within the convex polygon to obtain a filtered image matching map.

[0010] In some embodiments, obtaining an image matching map of a video sequence and performing FH verification on the matching map includes:

[0011] Match the images in the video sequence to obtain different types of matching pairs, and perform FH verification on the different types of matching pairs, where the H verification is to verify the matching relationship between two images in a plane, and the F verification is to verify the matching relationship between multiple objects not in the same plane in three dimensions.

[0012] In some embodiments, after performing FH verification on the different types of matching pairs, the method includes:

[0013] When all the different types of matching pairs can pass the H verification or all can pass the F verification, the images in the video sequence are images that do not contain repeated textures;

[0014] When the number of matching pairs that can pass the H verification is the same as the number of matching pairs that can pass the F verification among the different types of matching pairs, it cannot be determined whether the images in the video sequence contain repeated textures;

[0015] When the number of matching pairs that can pass the H verification is greater than the number of matching pairs that can pass the F verification, or the number of matching pairs that can pass the H verification is less than the number of matching pairs that can pass the F verification among the different types of matching pairs, the image is an image containing repeated textures.

[0016] In some of these embodiments, performing co-visibility verification on the image containing repeated textures includes:

[0017] Constructing a feature map of the image containing repeated textures and retaining the images in which the co-visibility count of feature points is greater than or equal to a first preset value.

[0018] In some of these embodiments, performing hierarchical clustering and convex polygon fitting on the repeated texture image after co-visibility verification includes:

[0019] Performing hierarchical clustering on the feature points in the repeated texture image after co-visibility verification whose number is greater than or equal to a second preset value to obtain feature point clusters;

[0020] Deleting the feature point clusters with the number of feature points less than a third preset value, and performing convex polygon fitting on the retained feature point clusters, and outputting the convex polygon seed image containing the repeated texture features.

[0021] In a second aspect, an embodiment of the present application provides a system for repeated texture filtering, and the system includes:

[0022] A verification module, configured to obtain an image matching map of a video sequence, perform FH verification on the matching map to obtain an image containing repeated textures, and perform co-visibility verification on the image containing repeated textures, where the repeated textures include continuous repeated textures and single-plane textures;

[0023] A clustering and fitting module, configured to perform hierarchical clustering and convex polygon fitting on the repeated texture image after co-visibility verification to obtain a convex polygon seed image containing repeated texture features;

[0024] A transfer and filtering module, configured to perform depth progressive transfer on the convex polygon seed image containing repeated texture features, and filter the feature matching pairs falling within the convex polygon in the image to obtain a filtered image matching map.

[0025] In some of these embodiments, the verification module is further configured to match the images in the video sequence to obtain different types of matching pairs, and perform FH verification on the different types of matching pairs, where the H verification is to verify the matching relationship between two images in a plane, and the F verification is to verify the matching relationship between multiple objects not in the same plane in three dimensions.

[0026] In some of these embodiments, after performing FH verification on the different types of matching pairs,

[0027] The verification module is further configured to, when all the different types of matching pairs can pass the H verification or all can pass the F verification, the images in the video sequence are images not containing repeated textures;

[0028] When the number of matching pairs that can pass the H check is the same as the number of matching pairs that can pass the F check among the different types of matching pairs, it is impossible to determine whether the images in the video sequence contain repeated textures;

[0029] When the number of matching pairs that can pass the H check is greater than the number of matching pairs that can pass the F check, or the number of matching pairs that can pass the H check is less than the number of matching pairs that can pass the F check among the different types of matching pairs, the image is an image containing repeated textures.

[0030] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for filtering repeated textures as described in the first aspect above is implemented.

[0031] In a fourth aspect, an embodiment of the present application provides a storage medium, on which a computer program is stored. When the program is executed by a processor, the method for filtering repeated textures as described in the first aspect above is implemented.

[0032] Compared with the related art, the method for filtering repeated textures provided by the embodiment of the present application obtains an image matching map of a video sequence, performs FH checks on the matching map to obtain an image containing repeated textures, and performs a co-visibility check on the image containing repeated textures, where the repeated textures include continuous repeated textures and single-plane textures; then, hierarchical clustering and convex polygon fitting are performed on the repeated texture image after the co-visibility check to obtain a convex polygon seed image containing repeated texture features; finally, depth progressive transmission is performed on the convex polygon seed image containing repeated texture features, and the feature matching pairs falling within the convex polygon in the image are filtered to obtain a filtered image matching map.

[0033] In the present application, multiple video sequences are used for 3D reconstruction. There is temporal prior information between each video sequence. The FH check algorithm can be used to check and obtain potential repeated texture images, and then the clustering and convex polygon fitting algorithms are used to obtain the convex polygons of the repeated textures. Finally, the repeated texture feature matching pairs are deleted to avoid incorrect image registration and ensure successful mapping. It solves the problems of lack of repeated texture detection and filtering and lack of practicality when filtering image mis-matches that occur during the 3D reconstruction process, filters the mis-matched images of the repeated textures, and improves the accuracy of mapping. Description of the Drawings

[0034] The accompanying drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The schematic embodiments and descriptions thereof of the present application are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0035] Figure 1 is a flowchart of a method for repeated texture filtering according to an embodiment of the present application;

[0036] Figure 2 is a structural block diagram of a system for repeated texture filtering according to an embodiment of the present application;

[0037] Figure 3 is a schematic internal structure diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0038] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described and explained below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments provided in the present application without creative efforts belong to the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacturing or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be understood as insufficient disclosure of the content of the present application.

[0039] Reference to "embodiment" in the present application means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those of ordinary skill in the art will explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0040] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the ordinary meanings understood by those with ordinary skills in the technical field to which this application belongs. The words such as "a", "one", "kind", "the" and the like involved in this application do not indicate a quantity limitation and may represent a singular or plural number. The terms "including", "comprising", "having" and any variations thereof involved in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include steps or units not listed, or may further include other steps or units inherent to these processes, methods, products or devices. The words such as "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application means greater than or equal to two. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may represent: A exists alone, A and B exist simultaneously, and B exists alone. The terms "first", "second", "third" and the like involved in this application are only used to distinguish similar objects and do not represent a specific order of the objects.

[0041] This embodiment provides a method for repeated texture filtering. Figure 1 It is a flowchart of the method for repeated texture filtering according to the embodiment of the present application, as Figure 1 shown, and this process includes the following steps:

[0042] Step S101, obtain an image matching map of a video sequence, perform FH verification on the matching map to obtain an image containing repeated textures, and perform co-visibility verification on the image containing repeated textures, where the repeated textures include continuous repeated textures and single-plane textures;

[0043] Preferably, after obtaining the video sequence images in this embodiment, the images in the video sequence are matched to obtain different types of matching pairs. For example, after obtaining an image t in a certain video sequence, four different matching pair types are obtained by matching the image t: t-2 and t, t-1 and t, t+1 and t, t+2 and t; then, FH verification is performed on these different types of matching pairs, where the H verification is to verify the matching relationship between two images in a plane, and the F verification is to verify the matching relationship between multiple objects not in the same plane in three dimensions.

[0044] Preferably, when all matching pairs of different types can pass the H check or all can pass the F check, the image in the video sequence is an image without repeated textures. For example, when checking the above 4 matching pairs and getting 4F or 4H, the image t is "good", that is, the image t is an image without repeated textures;

[0045] When the number of matching pairs that can pass the H check is the same as the number of matching pairs that can pass the F check among different types of matching pairs, it cannot be determined whether the image in the video sequence contains repeated textures. For example, when checking the above 4 matching pairs and getting 2F2H, the image t is "unknown", that is, it cannot be determined whether the image t contains repeated textures;

[0046] When the number of matching pairs that can pass the H check is greater than the number of matching pairs that can pass the F check, or the number of matching pairs that can pass the H check is less than the number of matching pairs that can pass the F check among different types of matching pairs, the image is an image containing repeated textures. For example, when checking the above 4 matching pairs and getting 3F1H or 3H1F, the image t is "bad", that is, the image t is an image containing repeated textures.

[0047] It should be noted that the repeated textures found by the above FH check include continuous repeated textures and isolated single-plane textures. By finding the repeated textures in the image through the FH check in this embodiment, the matching risk can be reduced and the false matching in map building can be reduced. For example, when taking a picture of a flat poster and obtaining the poster image, and performing the FH check on the image, if there is a continuous F situation, it may be that the features of the poster are few, or it may be that the structural textures of the poster are particularly many. In this case, the isolated single-plane texture does not pose a false matching hazard. However, when performing the FH check, if a situation of 3F1H appears, then, it may be that when taking the picture of the poster, the field of view is not large enough and most areas are the poster; or the field of view is large enough, but the structural texture of the poster is very poor, resulting in a large proportion of feature points of the poster. At this time, there will be a situation where a single poster is used for matching connection, and this matching relationship has a great risk. If there is the same poster in other positions in this scene, there will be a false matching that seriously affects the correctness of map building.

[0048] Further, after obtaining the image containing repeated textures through the above steps, a co-visibility check is performed on the image containing repeated textures. Specifically, a feature map of the image containing repeated textures is constructed, where the feature points are nodes and the feature point matching pairs that conform to the two-view geometric matching are edges; only the images with the co-visibility number of feature points greater than or equal to the first preset value are retained, and "repeated textures" with a very high probability can be extracted through the co-visibility check;

[0049] Step S102: Perform hierarchical clustering and convex polygon fitting on the repeated texture images after co-visibility verification to obtain convex polygon seed images containing repeated texture features;

[0050] Preferably, in this embodiment, first, perform hierarchical clustering on the feature points in the above-mentioned repeated texture images after co-visibility verification whose number is greater than or equal to the second preset value to obtain feature point clusters, where the clustering threshold is ratio * min(image_height, image_width);

[0051] Next, delete the feature point clusters with the number of feature points less than the third preset value, and perform convex polygon fitting on the remaining feature point clusters;

[0052] Finally, output the convex polygon seed images containing repeated texture features.

[0053] Through the above hierarchical clustering algorithm and convex polygon fitting, the repeated texture is expressed by regions, enhancing the filtering effect;

[0054] Step S103: Perform depth progressive transmission on the convex polygon seed images containing repeated texture features, and filter the feature matching pairs falling within the convex polygons in the images to obtain a filtered image matching map.

[0055] In this embodiment, perform depth progressive transmission on the convex polygon seed images containing repeated texture features. First, transmit it to the inside with a depth of 0 to obtain convex polygon seed images containing more complete information, then transmit from depth 0 to depth 1 to obtain convex polygon seed images with a depth of 1, and so on, recursively transmit from depth N - 1 to depth N to obtain convex polygon seed images with a depth of N. Through the above progressive transmission, all images containing repeated texture in the image matching map can be found;

[0056] Furthermore, filter all the images obtained after the depth transmission above, filter the feature matching pairs falling within the convex polygons, and obtain a filtered image matching map to ensure that there are no false matches in the image matching map.

[0057] Through the above steps S101 to S103, this embodiment uses multiple video sequences for 3D reconstruction. There is temporal prior information between each video sequence. The FH verification algorithm can verify and obtain potential repeated texture images, and then use the clustering and convex polygon fitting algorithms to obtain convex polygons of repeated texture. Finally, delete the repeated texture feature matching pairs to avoid incorrect image registration and ensure successful mapping. It solves the problems of lack of repeated texture detection and filtering and lack of practicality when filtering image false matches during the 3D reconstruction process, filters the false matching images of repeated texture, and improves the accuracy of mapping.

[0058] It should be noted that the steps shown in the above process or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0059] This embodiment also provides a system for repeated texture filtering. This system is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0060] Figure 2 is a structural block diagram of a system for repeated texture filtering according to an embodiment of the present application. As Figure 2 shown, the system includes a verification module 21, a clustering fitting module 22, and a transfer filtering module 23:

[0061] The verification module 21 is used to obtain an image matching map of a video sequence, perform FH verification on the matching map to obtain an image containing repeated textures, and perform co-visibility verification on the image containing repeated textures. Among them, the repeated textures include continuous repeated textures and single-plane textures; the clustering fitting module 22 is used to perform hierarchical clustering and convex polygon fitting on the repeated texture image after co-visibility verification to obtain a convex polygon seed image containing repeated texture features; the transfer filtering module 23 is used to perform depth progressive transfer on the convex polygon seed image containing repeated texture features, and filter the feature matching pairs falling into the convex polygon in the image to obtain a filtered image matching map.

[0062] Through the above system, this embodiment uses multiple video sequences for three-dimensional reconstruction. There is temporal prior information between each video sequence. The verification module 21 can verify and obtain potential repeated texture images using the FH verification algorithm. The clustering fitting module 22 uses clustering and convex polygon fitting algorithms to obtain convex polygons of repeated textures. Finally, the transfer filtering module 23 deletes repeated texture feature matching pairs to avoid incorrect image registration and ensure successful mapping. It solves the problems of lack of repeated texture detection and filtering and lack of practicality when filtering image mis-matches that occur during the three-dimensional reconstruction process, filters mis-matched images of repeated textures, and improves the accuracy of mapping.

[0063] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and alternative implementation manners, and will not be repeated here.

[0064] In addition, it should be noted that each of the above modules can be a functional module or a program module, and can be implemented either by software or by hardware. For the modules implemented by hardware, each of the above modules can be located in the same processor; or each of the above modules can also be located in different processors in any combined form.

[0065] This embodiment also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0066] Optionally, the above electronic device may further include a transmission device and an input / output device. Among them, the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0067] In addition, in combination with the method of repeated texture filtering in the above embodiments, an embodiment of the present application can be implemented by providing a storage medium. A computer program is stored on the storage medium; when the computer program is executed by a processor, it implements any one of the methods of repeated texture filtering in the above embodiments.

[0068] In one embodiment, a computer device is provided. The computer device can be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method of repeated texture filtering. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0069] In one embodiment, Figure 3 is a schematic internal structure diagram of an electronic device according to an embodiment of the present application. As Figure 3 shown, an electronic device is provided. The electronic device can be a server, and its internal structure diagram can be as Figure 3As shown in the figure. The electronic device includes a processor, a network interface, an internal memory, and a non-volatile memory connected by an internal bus. Among them, the non-volatile memory stores an operating system, computer programs, and a database. The processor is used to provide computing and control capabilities. The network interface is used to communicate with external terminals through a network connection. The internal memory is used to provide an environment for the operation of the operating system and computer programs. The computer program, when executed by the processor, implements a method for repetitive texture filtering. The database is used to store data.

[0070] Those skilled in the art can understand that Figure 3 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0071] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to memory, storage, database, or other media used in the various embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or an external cache. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0072] Those skilled in the art should understand that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0073] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for repeated texture filtering, characterized in that, the method includes: obtaining an image matching map of a video sequence, performing FH verification on the matching map to obtain an image containing repeated textures, and performing co-visibility verification on the image containing repeated textures, wherein the repeated textures include continuous repeated textures and single-plane textures; performing hierarchical clustering and convex polygon fitting on the repeated texture image after co-visibility verification to obtain a convex polygon seed image containing repeated texture features; performing depth progressive transmission on the convex polygon seed image containing repeated texture features, and filtering the feature matching pairs falling within the convex polygon in the image to obtain a filtered image matching map; wherein, obtaining an image matching map of a video sequence and performing FH verification on the matching map includes: matching the images in the video sequence to obtain different types of matching pairs, and performing FH verification on the different types of matching pairs, wherein the H verification is to verify the matching relationship between two images in a plane, and the F verification is to verify the matching relationship between multiple objects not in the same plane in three dimensions.

2. The method according to claim 1, characterized in that, after performing FH verification on the different types of matching pairs, the method includes: when all the different types of matching pairs can pass the H verification or all can pass the F verification, the images in the video sequence are images not containing repeated textures; when the number of matching pairs that can pass the H verification is the same as the number of matching pairs that can pass the F verification among the different types of matching pairs, it cannot be determined whether the images in the video sequence contain repeated textures; when the number of matching pairs that can pass the H verification is greater than the number of matching pairs that can pass the F verification, or the number of matching pairs that can pass the H verification is less than the number of matching pairs that can pass the F verification among the different types of matching pairs, the image is an image containing repeated textures.

3. The method according to claim 1, characterized in that, performing co-visibility verification on the image containing repeated textures includes: constructing a feature map of the image containing repeated textures, and retaining the images in which the co-visibility number of feature points is greater than or equal to a first preset value.

4. The method according to claim 1, characterized in that, performing hierarchical clustering and convex polygon fitting on the repeated texture image after co-visibility verification includes: performing hierarchical clustering on the feature points with a number greater than or equal to a second preset value in the repeated texture image after co-visibility verification to obtain feature point clusters; deleting the feature point clusters with a feature point number less than a third preset value, and performing convex polygon fitting on the retained feature point clusters, and outputting to obtain the convex polygon seed image containing repeated texture features.

5. A system for repeated texture filtering, characterized in that, the system includes: a verification module, configured to obtain an image matching map of a video sequence, perform FH verification on the matching map to obtain an image containing repeated textures, and perform co-visibility verification on the image containing repeated textures, wherein the repeated textures include continuous repeated textures, single-plane textures; A clustering and fitting module, configured to perform hierarchical clustering and convex polygon fitting on the repeated texture images after co-visibility verification, so as to obtain a convex polygon seed image containing repeated texture features; A transfer and filtering module, configured to perform depth progressive transfer on the convex polygon seed image containing repeated texture features, and filter the feature matching pairs falling within the convex polygon in the image, so as to obtain a filtered image matching map; Wherein, when the verification module obtains an image matching map of a video sequence and performs FH verification on the matching map, it is configured to: Match the images in the video sequence to obtain different types of matching pairs, and perform FH verification on the different types of matching pairs. Among them, the H verification is to verify the matching relationship between two images in a plane, and the F verification is to verify the matching relationship between multiple objects not in the same plane in three dimensions.

6. The system according to claim 5, characterized in that after performing FH verification on the different types of matching pairs, the verification module is further configured to, when all the different types of matching pairs can pass the H verification or all can pass the F verification, the images in the video sequence are images not containing repeated textures; when the number of matching pairs that can pass the H verification is the same as the number of matching pairs that can pass the F verification among the different types of matching pairs, it cannot be determined whether the images in the video sequence contain repeated textures; when the number of matching pairs that can pass the H verification is greater than the number of matching pairs that can pass the F verification, or the number of matching pairs that can pass the H verification is less than the number of matching pairs that can pass the F verification among the different types of matching pairs, the images are images containing repeated textures.

7. An electronic device, comprising a memory and a processor, characterized in that a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for filtering repeated textures according to any one of claims 1 to 4.

8. A storage medium, characterized in that a computer program is stored in the storage medium, wherein the computer program is configured to execute the method for filtering repeated textures according to any one of claims 1 to 4 when running.

Images