Method, system, electronic device and storage medium for generating a scene map

Abstract

The application relates to a method, a system, an electronic device and a storage medium for generating a scene map, wherein the method comprises the following steps: acquiring a repetitive texture image, determining a repetitive texture feature in a scene image set according to the repetitive texture image; for each image in the scene image set, determining whether the repetitive texture feature exists in the image, if yes, determining a region of the repetitive texture feature on the image; removing image content in the region to obtain a target scene image set, and performing visual reconstruction according to the target scene image set to obtain a scene map, or acquiring image features outside the region to obtain a target feature set, and performing visual reconstruction according to the target feature set to obtain a scene map. Through the application, the problem that a scene map reconstructed from a scene with repetitive texture has spatial errors is solved, and a correct three-dimensional scene map can be obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of scene three-dimensional reconstruction, in particular to a method and system for generating a scene map, an electronic device and a storage medium. BACKGROUND

[0002] Scene reconstruction, that is, reconstructing the spatial information of a real scene, which can be indoor, such as a museum, a living room, an office, etc., or outdoor, such as a house, a square building, etc., and the scale of the scene can be tens of square meters or even tens of thousands of square meters.

[0003] With the rise of concepts such as augmented reality, robots, and digital twins, the demand for constructing spatial information of specific scenes is also expanding. A high-quality scene model can provide accurate spatial references and reliable digital archives, which is an important basis for the implementation and application of the above technologies.

[0004] In related technologies, the reconstruction of a large-scale scene is generally achieved by laser scanning or visual shooting. However, the sensor for laser scanning costs tens of thousands or hundreds of thousands of dollars, and the device needs to be maintained by a dedicated person, and the scanning operation also needs to be operated by a professional, which is costly. In the case of limited cost, the reconstruction of a large-scale scene is generally achieved by visual shooting, which only requires shooting of RGB pictures, the device is simple and the operation threshold is low, and it is the lowest cost solution at present.

[0005] However, due to the presence of repeated textures in the scene, such as multiple identical decoration posters in the scene, which are distributed at different positions in the scene, the spatial ambiguity caused by repeated textures cannot be distinguished visually. Therefore, the visual shooting method has low reconstruction robustness for scenes with many repeated textures, and the reconstructed map may have serious spatial errors.

[0006] There is no effective solution to the problem of spatial errors in the reconstructed scene map when reconstructing a scene with repeated textures in related technologies. SUMMARY

[0007] The embodiments of the present application provide a method, system, electronic device and storage medium for generating a scene map to at least solve the problem of spatial errors in the reconstructed scene map when reconstructing a scene with repeated textures in related technologies.

[0008] In a first aspect, the embodiments of the present application provide a method for generating a scene map, the method comprising:

[0009] obtaining a repeated texture image, and determining repeated texture features in a scene image set according to the repeated texture image.

[0010] For each image in the set of scene images, determine whether the repeated texture feature exists in the image, and if so, determine the area of the image where the repeated texture feature exists;

[0011] remove the image content in the area to obtain a set of target scene images, and perform visual reconstruction according to the set of target scene images to obtain a scene map,

[0012] or, obtain image features outside the area to obtain a set of target features, and perform visual reconstruction according to the set of target features to obtain a scene map.

[0013] In some embodiments, the repeated texture image is manually selected or selected by an algorithm from the set of scene images.

[0014] In some embodiments, the process of determining, for each image in the set of scene images, whether the repeated texture feature exists in the image, and if so, determining the area of the image where the repeated texture feature exists, comprises:

[0015] For each illegal feature pattern in the set of illegal feature patterns, determine whether the illegal feature pattern exists in each image in the set of scene images, and if so, determine the area of the image where the illegal feature pattern exists and cover the area with a mask,

[0016] wherein the process of creating the set of illegal feature patterns comprises: determining the area of the repeated texture image where the repeated texture feature exists and covering the area with a mask, generating one or more masks, defining each combination of a mask and the repeated texture image as an illegal feature pattern, and obtaining the set of illegal feature patterns.

[0017] In some embodiments, the process of determining whether the illegal feature pattern exists in the image comprises:

[0018] For each illegal feature pattern, extract feature points in the area covered by the mask so that each illegal feature pattern obtains a corresponding first set of feature points; and for each image in the set of scene images, extract feature points in the entire image so that each image obtains a corresponding second set of feature points.

[0019] determine whether there are identical feature points in the first set of feature points corresponding to the illegal feature pattern and the second set of feature points corresponding to the image;

[0020] If so, it indicates that the image contains the illegal feature pattern.

[0021] In some embodiments, the process of determining the area of the image where the illegal feature pattern is located comprises:

[0022] determining the locations of all the illegal feature points on the image, to obtain a set of illegal feature points of the image, wherein the illegal feature points are the same feature points in the second set of feature points and the first set of feature points;

[0023] clustering the illegal feature points in the set, calculating the convex hull of each class of illegal feature points, to obtain a plurality of convex hulls; determining the area covered by each convex hull, to obtain the area of the image where the illegal feature pattern is located.

[0024] In some embodiments, the process of obtaining the image features outside the area to obtain a target feature set comprises:

[0025] using a feature extraction algorithm to extract the image features on the image that are outside the area;

[0026] or, removing the image features in the second set of feature points that fall within the area to obtain the image features outside the area.

[0027] In a second aspect, the embodiments of the present application provide a system for generating a scene map, the system comprising:

[0028] a determining module configured to obtain a repeated texture image, determine a repeated texture feature in a set of scene images according to the repeated texture image; for each image in the set of scene images, determine whether the image has the repeated texture feature, and if so, determine the area of the image where the repeated texture feature is located;

[0029] a reconstructing module configured to remove the image content in the area to obtain a target set of scene images, and perform visual reconstruction according to the target set of scene images to obtain a scene map, or configured to obtain image features outside the area to obtain a target feature set, and perform visual reconstruction according to the target feature set to obtain a scene map.

[0030] In some embodiments, the process of, for each image in the set of scene images, determining whether the image has the repeated texture feature, and if so, determining the area of the image where the repeated texture feature is located comprises:

[0031] for each illegal feature pattern in the set of illegal feature patterns, determining whether the illegal feature pattern exists in each image in the set of scene images, if so, determining the area of the image where the illegal feature pattern is located, and covering the area with a mask,

[0032] The creating process of the illegal feature mode set comprises: determining a region of the repetitive texture feature on the repetitive texture image, covering the region with a mask, generating one or more masks, defining a combination of each mask and the repetitive texture picture as an illegal feature mode, and obtaining the illegal feature mode set.

[0033] In a third aspect, an electronic device is provided, which comprises a memory and a processor. The memory stores a computer program. The processor is configured to execute the computer program to perform the method for generating a scene map.

[0034] In a fourth aspect, a storage medium is provided, which stores a computer program. The computer program is configured to perform the method for generating a scene map when executed.

[0035] Compared with the related art, the method for generating a scene map provided in the embodiments of the present application solves the problem that the reconstructed scene map has spatial errors when reconstructing a scene with repetitive texture in the related art, and can obtain a correct three-dimensional scene map. BRIEF DESCRIPTION OF DRAWINGS

[0036] The accompanying drawings, which are included to provide a further understanding of the present application, form a part of the present application and illustrate the illustrative embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0037] Figure 1 FIG. 1 is a schematic diagram of an application environment of the method for generating a scene map according to an embodiment of the present application;

[0038] Figure 2 FIG. 2 is a flowchart of the method for generating a scene map according to a first embodiment of the present application;

[0039] Figure 3 FIG. 3 is a flowchart of the method for generating a scene map according to a second embodiment of the present application;

[0040] Figure 4 FIG. 4 is a schematic diagram of an illegal feature mode according to the second embodiment of the present application;

[0041] Figure 5 is a flow chart of the method of illegal feature pattern retrieval according to the second embodiment of the present application;

[0042] Figure 6 is a schematic diagram of the intermediate result of generating illegal feature mask according to the second embodiment of the present application;

[0043] Figure 7 is a schematic diagram of the internal structure of the electronic device according to the embodiments of the present application. DETAILED DESCRIPTION

[0044] In order to make the objects, technical solutions and advantages of the present application clearer, the present application is described and explained below in connection with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0045] It is obvious that the drawings described below are only some examples or embodiments of the present application, and those of ordinary skill in the art can apply the present application to other similar scenarios without creative labor on the basis of these drawings. In addition, it can be understood that although the efforts made in this development process can be complex and lengthy, some design, manufacture or production changes made on the basis of the technical content disclosed in the present application are only routine technical means for those of ordinary skill in the art related to the content disclosed in the present application, and should not be understood as insufficient disclosure of the present application.

[0046] In the present application, "embodiments" means that the specific features, structures or properties described in connection with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase at various places in the specification does not necessarily mean the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.

[0047] Unless otherwise defined, technical terms and scientific terms used in the present application shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. Unless otherwise defined, the terms "one" and "a" or "an" used in this application do not denote a singular noun, but can include plural referents. The terms "comprising", "having", "including", and any variations thereof in the present application are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a list of steps or modules (units) is not limited to the listed steps or units, but can further include other steps or units not listed or can further include other steps or units inherent to such process, method, product, or device. The terms "connected", "connected to", "coupled", and the like in the present application are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The term "multiple" in the present application refers to two or more. The term "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects. The terms "first", "second", "third", and the like in the present application are only to distinguish similar objects, and do not represent a specific order of the objects.

[0048] The method for generating a scene map provided in the present application can be applied to an application environment as shown in Figure 1 Figure 1 is a schematic diagram of an application environment of the method for generating a scene map according to an embodiment of the present application, as shown in Figure 1 The server 101 obtains a repeated texture image, determines a repeated texture feature in a scene image set according to the repeated texture image; the server 101 determines whether there is the repeated texture feature in each image in the scene image set, if yes, determines the area of the repeated texture feature on the image; the server 101 removes the image content in the area to obtain a target scene image set, and performs visual reconstruction according to the target scene image set to obtain a scene map, or the server 101 obtains image features outside the area to obtain a target feature set, and performs visual reconstruction according to the target feature set to obtain a scene map, wherein the server 101 can be implemented by an independent server or a server cluster composed of multiple servers.

[0049] The present embodiment provides a method for generating a scene map, Figure 2 is a flowchart of the method for generating a scene map according to the first embodiment of the present application, as shown in Figure 2 The flowchart includes the following steps:

[0050] ​Step S201, a repeated texture image is acquired, and a repeated texture feature in a scene image set is determined according to the repeated texture image, wherein the scene image set is a set of original images captured for a scene;

[0051] Step S202, for each image in the scene image set, it is determined whether the repeated texture feature exists in the image, and if yes, a region of the repeated texture feature on the image is determined;

[0052] Step S203, image content in the region is removed to obtain a target scene image set, and visual reconstruction is performed according to the target scene image set to obtain a scene map,

[0053] Or, image features outside the region are acquired to obtain a target feature set, and visual reconstruction is performed according to the target feature set to obtain a scene map.

[0054] Through steps S201 to S203, compared with the problem that a reconstructed scene map has spatial errors when a scene with repeated textures is reconstructed in the related art, the repeated texture feature with spatial ambiguity is filtered out from original images before map reconstruction, and then a conventional visual mapping process is continuously performed, so that a correct scene three-dimensional map is obtained, and the problem that a reconstructed scene map has spatial errors when a scene with repeated textures is reconstructed in the related art is solved.

[0055] Optionally, Figure 3 is a flowchart of a method for generating a scene map according to the second embodiment of the present application, as shown in Figure 3 The flowchart includes the following steps:

[0056] Step S301, illegal feature pattern generation; according to image data (hereinafter referred to as scene data) captured in a scene, a repeated texture pattern in the scene is found out as an illegal feature pattern (Invalid Feature Pattern) set of the scene;

[0057] Step S302, illegal feature pattern retrieval; for each illegal feature pattern, the pattern is retrieved in each image of the scene data; if the pattern is retrieved, a position and a range (represented by a mask of an image) of the pattern in the image are recorded;

[0058] Step S303, illegal feature filtering; after step S302 is completed, a mask of an illegal feature pattern of each image in the scene data is obtained; according to the mask, all image features falling within the mask range can be filtered out;

[0059] Step S304, three-dimensional reconstruction; using the scene image data in which illegal feature has been filtered, three-dimensional reconstruction of the scene map is performed.

[0060] The following is a detailed explanation of each of the steps S301 to S304.

[0061] (1) Explanation of illegal feature pattern generation:

[0062] Illegal feature pattern is defined as a piece of image content, which belongs to repeated texture in the scene and has serious negative impact on three-dimensional reconstruction; in order to represent this piece of image content, a piece of image content can be specified by the combination of original image and mask image, for example, a poster appears many times in different positions of the scene, which belongs to repeated texture, the original image in which the repeated texture is located, plus the mask image corresponding to the repeated texture in the original image, constitutes a representation of illegal feature pattern; Figure 4 is a schematic diagram for representing illegal feature pattern according to the second embodiment of the present application, as shown in Figure 4 The white area is the position of the poster, which is covered by the mask image, the image content covered by the mask image in the original image all belongs to repeated texture, the combination of the original image and the mask image is the illegal feature pattern;

[0063] It should be noted that in the scene image data, there may be many images that have captured such a poster, and the distance and angle of shooting are inconsistent, and only one or more representative images can be selected as the illegal feature pattern of the texture of this poster; a robust feature pattern retrieval algorithm can retrieve the same feature pattern shot from different distances and angles according to the representative feature pattern; on the other hand, the image of the illegal feature pattern here does not necessarily come directly from the image data of the scene, a photo of a certain repeated texture can be taken separately to generate the illegal feature pattern corresponding to the texture;

[0064] In addition, there may be multiple illegal feature patterns in the scene, so there will be multiple sets of illegal feature pattern data; even a picture contains multiple illegal feature patterns, then a mask image contains multiple white areas; in the case of containing several other illegal feature patterns in the scene, these feature patterns together with the above-mentioned poster feature pattern constitute the set of illegal feature patterns;

[0065] Finally, in order to obtain these illegal feature patterns, in addition to manual selection or shooting, the task can also be completed automatically by algorithm, for example, through a deep learning network, automatically identify the representative illegal feature pattern from the image data of the scene.

[0066] (2) Description of illegal feature pattern retrieval:

[0067] The purpose of this step is to retrieve, for each feature pattern in the illegal feature pattern set, in each image of the scene data, and record the mask range of the pattern in the image if the pattern exists in the image. Finally, each image of the scene data has a mask image of an illegal feature pattern, and some images can also contain multiple illegal feature patterns. Of course, for the scene images without illegal feature patterns, no mask image can be generated to represent that the image does not contain illegal feature patterns. Figure 5 is a flowchart of the method for illegal feature pattern retrieval according to the second embodiment of the present application, as shown in Figure 5 , the flowchart includes the following steps:

[0068] Step S501, for each scene image, extract the features of the whole image, for example, the features can be SIFT features;

[0069] Step S502, for each illegal feature pattern image, extract the features of the illegal feature region in combination with the mask image of the pattern, for example, the features can be SIFT features;

[0070] Step S503, match the features of each illegal feature pattern image with the features of each scene image; record the positions of the feature points matched by the illegal features in each scene image as a set of illegal feature points of the scene image;

[0071] Step S504, cluster the illegal feature points in the set of illegal feature points of each scene image, and calculate the convex hull for each class of feature points. The area covered by each convex hull is the illegal feature region of the image, and the mask of the illegal feature pattern is generated accordingly. Optionally, the obtained mask can be appropriately post-processed, for example, the post-processing can be image dilation, so as to obtain a better illegal feature pattern mask;

[0072] Figure 6 is a schematic diagram of the intermediate result of generating an illegal feature mask according to the second embodiment of the present application, as shown in Figure 6 , the granular points represent the retrieved illegal feature points, and the polygons represent the convex hulls of each class after clustering. The black area represents the normal feature region, and the non-black area is the generated illegal feature region.

[0073] (3) Description of illegal feature filtering:

[0074] The purpose of illegal feature filtering is to prevent the image content corresponding to the illegal feature mode from participating in the three-dimensional reconstruction process, otherwise, due to the repeated texture of the image content, the three-dimensional reconstruction algorithm will output an incorrect three-dimensional map; the filtering of illegal features can be achieved in various ways, two implementation methods are listed as follows:

[0075] Method one: directly deleting the image content corresponding to the illegal feature mode; since the illegal feature mask (the non-black area is an illegal feature area) corresponding to each scene image has been obtained in the description of illegal feature mode retrieval, the image content of the illegal feature area can be deleted according to the mask, for example, the pixel value falling in the illegal feature area can be directly set to 0, and then the processed scene image data is sent to the subsequent three-dimensional reconstruction link;

[0076] Method two: deleting the image feature points corresponding to the illegal feature mode; generally, the three-dimensional reconstruction algorithm based on pure vision (for example, the SFM algorithm) will first extract image feature points (for example, SIFT feature points) on the original image, and then perform three-dimensional reconstruction based on the feature points; in this case, the original image and the illegal feature mask can be input at the same time when the feature is extracted, at this time, the feature extraction algorithm will not extract feature points in the illegal feature area, that is, the feature points corresponding to the illegal feature mode are deleted; then the filtered feature points are input into the subsequent three-dimensional reconstruction algorithm.

[0077] (4) Description of three-dimensional reconstruction:

[0078] The scene data after filtering out the illegal features can be sent to the commonly used three-dimensional reconstruction algorithm based on pure vision (for example, the SFM algorithm) for three-dimensional reconstruction of the scene map; if the feature filtering is performed by the above-mentioned method one, the modified scene image can be sent to the SFM algorithm; if the feature filtering is performed according to method two, the filtered scene feature point data can be sent to the SFM algorithm, it should be noted that the SFM algorithm no longer performs the feature extraction process at this time; since SFM is relatively common and mature, the reconstruction process is not described in detail here.

[0079] In addition, in combination with the method of generating a scene map in the above-mentioned embodiments, the present embodiment can provide a storage medium for implementation. The storage medium has a computer program stored thereon; the computer program is executed by a processor to implement any one of the methods of generating a scene map in the above-mentioned embodiments.

[0080] In one embodiment, a computer device is provided, which can be a terminal. The computer device comprises a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises 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 running the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a method for generating a scene map. 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 overlaid on the display screen, or a key, trackball or touchpad arranged on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0081] In one embodiment, Figure 7 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, as Figure 7 shown, an electronic device is provided, which can be a server, and the internal structure diagram thereof can be as Figure 7 shown. The electronic device comprises a processor, a network interface, an internal memory and a non-volatile memory connected through an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is configured to provide computing and control capabilities, the network interface is configured to communicate with an external terminal through a network connection, the internal memory is configured to provide an environment for running the operating system and the computer program, the computer program is executed by the processor to implement a method for generating a scene map, and the database is configured to store data.

[0082] Those skilled in the art can understand that Figure 7 the structure shown in the above embodiment is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device can comprise more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0083] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the 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 external cache memory. As an illustration but 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.

[0084] Those skilled in the art should understand that each technical feature of the above embodiments can be combined arbitrarily, and in order to make the description simple, not all possible combinations of each technical feature in the above embodiments are described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0085] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the patent of the present application should be subject to the appended claims.

Claims

1. A method for generating a scene map, characterized in that, The method includes: Acquire repeating texture images with inconsistent shooting distances and angles, and determine repeating texture features in the scene image set based on the repeating texture images; For each image in the scene image set, determine whether the repeating texture feature exists; if so, determine the region of the repeating texture feature on the image, including: For each illegal feature pattern in the illegal feature pattern set, determine whether it exists in each image in the scene image set. If it does, determine the region of the illegal feature pattern in the image and cover the region with a mask. The illegal feature pattern set is a set of masks corresponding to the repeated texture feature regions in the repeated texture image and the repeated texture image. The image content within the defined area is removed to obtain a target scene image set. Visual reconstruction is then performed based on this target scene image set to obtain a scene map. Alternatively, image features outside the region can be acquired to obtain a target feature set, and visual reconstruction can be performed based on the target feature set to obtain a scene map.

2. The method according to claim 1, characterized in that, The repeating texture images are selected manually or by an algorithm from the set of scene images.

3. The method according to claim 1 or 2, characterized in that, The process of creating the illegal feature pattern set includes: determining the region of the repeating texture feature on the repeating texture image, covering the region with a mask, generating one or more masks, defining each mask and the repeating texture image as an illegal feature pattern, and obtaining the illegal feature pattern set.

4. The method according to claim 3, characterized in that, The process of determining whether the illegal feature pattern exists in the image includes: For each illegal feature pattern, feature points are extracted from the mask-covered area so that each illegal feature pattern obtains a corresponding first feature point set; for each image in the scene image set, feature points of the entire image are extracted so that each image obtains a corresponding second feature point set. Determine whether there are any identical feature points in the second feature point set corresponding to the image and in the first feature point set corresponding to the illegal feature pattern; If so, it indicates that the image contains the illegal feature pattern.

5. The method according to claim 4, characterized in that, The process of determining the region of the illegal feature pattern in the image includes: The positions of all the illegal feature points on the image are determined to obtain a set of illegal feature points of the image, wherein the illegal feature points are the same feature points in the second feature point set and the first feature point set; The illegal feature points in the set are clustered, and the convex hull of each illegal feature point is calculated to obtain multiple convex hulls; the region covered by each convex hull is determined to obtain the region of the illegal feature pattern in the image.

6. The method according to claim 4, characterized in that, The process of acquiring image features outside the region to obtain the target feature set includes: Using a feature extraction algorithm, extract image features located outside the region in the image; Alternatively, image features falling within the region from the second set of feature points can be removed to obtain image features outside the region.

7. A system for generating scene maps, characterized in that, The system includes: A determination module is used to acquire repeating texture images with inconsistent shooting distances and angles, determine repeating texture features in a set of scene images based on the repeating texture images, and for each image in the set of scene images, determine whether the repeating texture feature exists; if so, determine the region of the repeating texture feature on the image, including: For each illegal feature pattern in the illegal feature pattern set, determine whether it exists in each image in the scene image set. If it does, determine the region of the illegal feature pattern in the image and cover the region with a mask. The illegal feature pattern set is a set of masks corresponding to the repeated texture feature regions in the repeated texture image and the repeated texture image. The reconstruction module is used to remove image content within the area to obtain a target scene image set, and perform visual reconstruction based on the target scene image set to obtain a scene map; or, it is used to obtain image features outside the area to obtain a target feature set, and perform visual reconstruction based on the target feature set to obtain a scene map.

8. The system according to claim 7, characterized in that, The process of creating the illegal feature pattern set includes: determining the region of the repeating texture feature on the repeating texture image, covering the region with a mask, generating one or more masks, defining each mask and the repeating texture image as an illegal feature pattern, and obtaining the illegal feature pattern set.

9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method of generating a scene map as described in any one of claims 1 to 6.

10. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the method for generating a scene map according to any one of claims 1 to 6 when running.

Images