Three-dimensional map construction method and system and robot equipment

Abstract

The invention discloses a three-dimensional map construction method and system and robot equipment, and relates to the technical field of image processing. The three-dimensional map construction method comprises the following steps: acquiring a first image of a detection space through robot equipment, and dividing the first image into a plurality of second images representing independent spaces; afterwards, the robot device determines the boundaries of the second images, and removes the overlapped boundaries in the adjacent second images, thereby obtaining a third image with a spatial attribute. And finally, the robot equipment adds three-dimensional space construction information into the third image to obtain a three-dimensional map. According to the method provided by the invention, the image analysis is performed on the two-dimensional map during the construction of the three-dimensional map, the real-time construction of the two-dimensional map and the three-dimensional map can be met at the same time, the construction of the three-dimensional map can be completed under the condition of using one sensor, and the cost of a three-dimensional map construction scheme is reduced.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a three-dimensional map construction method, system and robotic device. Background Art

[0002] A 3D map is a three-dimensional, abstract description of one or more aspects of the real world or a portion of it, based on a 3D map database and scaled to a certain scale. In the field of the Internet of Things (IoT), combining 3D maps with IoT data provides powerful technical support for real-time data visualization and management. For example, it can intuitively display indoor device status, environmental parameters, and monitoring and management requirements. Therefore, the accurate construction of 3D maps is crucial.

[0003] Existing technologies require the coordinated use of multiple sensors to construct 3D maps. For example, optical sensors capture image data, while lidar sensors acquire precise distance data. However, this approach results in high costs. Therefore, finding a way to reduce costs by building 3D maps using a single sensor has become a pressing technical challenge in this field. Summary of the Invention

[0004] In order to address the deficiencies of the prior art, the purpose of this application is to provide a three-dimensional map construction method, system and robotic device that can reduce the cost of three-dimensional map construction.

[0005] To achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a three-dimensional map construction method, which includes: obtaining a first image of a detection space, wherein the first image is a plane image; dividing the first image into several second images representing independent spaces, wherein the several independent spaces constitute the detection space; determining the boundaries of the second images, and removing overlapping boundaries in adjacent second images to obtain a third image with spatial attributes; adding three-dimensional space construction information to the third image to obtain a three-dimensional map.

[0007] Furthermore, morphological processing is performed on the second image to obtain vertex model information of the second image; and collision detection is performed on the second image with the vertex model information obtained to determine a boundary of the second image.

[0008] Furthermore, the vertex model information includes coordinate information of the second image in a plane coordinate system to determine the coordinate information of the boundary of the second image; removing the overlapping boundaries in adjacent second images includes: determining the coordinate information of the boundary of the second image; defining the boundaries in adjacent second images with the same coordinate information as overlapping boundaries, and removing the overlapping boundaries.

[0009] Furthermore, before adding the three-dimensional space construction information to the third image, the method further includes: screening out boundaries that do not have the same coordinate information and determining them as walls of the detection space.

[0010] Furthermore, removing the overlapping boundaries includes: performing a dilation operation on the second image to obtain a dilated second image; and performing an erosion operation on the dilated second image to remove the overlapping boundaries.

[0011] Furthermore, the three-dimensional space construction information includes at least one of the following information: the height of the detection space, the thickness of the floor arranged in the detection space, the material of the wall, and the thickness of the wall.

[0012] Furthermore, the first image is divided into several second images representing independent spaces, including: performing grayscale processing and / or edge detection on the first image, and extracting edge contour information of the first image, and obtaining several preliminary screening images based on the edge contour information; performing Gaussian blur processing on the preliminary screening image to obtain the second image.

[0013] In the second aspect, the present application provides a robot device, including: a sampling module, the sampling module includes a distance sensor, the sampling module establishes a first image representing the detection space based on the detection signals it receives and sends, wherein the first image is a plane image; a storage module, used to store two-dimensional space and three-dimensional space construction information; a processor, used to divide the first image into several second images representing independent spaces, wherein several independent spaces constitute the detection space; the processor is also used to determine the boundaries of the second image, and remove the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes, the processor obtains the three-dimensional space construction information, and adds the three-dimensional space construction information to the third image to obtain a three-dimensional map.

[0014] In a third aspect, the present application provides a three-dimensional map construction system, comprising the robot device of the second aspect, and a preset device, wherein the preset device includes a terminal and a server; the robot device includes: a sampling module, the sampling module includes a distance sensor, the sampling module establishes a first image representing the detection space based on the detection signals it receives and sends, wherein the first image is a plane image; a communication module, used to send the first image to the preset device; the preset device, used to determine the boundary of the second image, and remove the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes, and add three-dimensional space construction information to the third image to obtain a three-dimensional map, wherein the three-dimensional space construction information is stored in the preset device.

[0015] In a fourth aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores computer program instructions, and the processor is configured to execute the instructions stored in the memory to perform the method steps of the above-mentioned first aspect.

[0016] Compared with the existing technology, the three-dimensional map construction method proposed in this application uses a robotic device to obtain a first image of the detection space and divide the first image into several second images representing independent spaces. After that, the robotic device determines the boundaries of the second images and removes the overlapping boundaries of adjacent second images to obtain a third image with spatial attributes. Finally, Robotic equipment The three-dimensional spatial construction information is added to the third image to obtain a three-dimensional map. The method proposed in this application can simultaneously meet the real-time construction requirements of two-dimensional and three-dimensional maps by performing image analysis on the two-dimensional map during the construction of the three-dimensional map. It can also complete the construction of the three-dimensional map using a single sensor, reducing the cost of the three-dimensional map construction solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a flow chart of a three-dimensional map construction method provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of a first image constructed according to an embodiment of the present application;

[0019] Figure 3 A schematic diagram of a constructed second image provided in an embodiment of the present application;

[0020] Figure 4 A schematic diagram of a third image constructed according to an embodiment of the present application;

[0021] Figure 5 A schematic diagram of a three-dimensional image corresponding to a third image provided in an embodiment of the present application;

[0022] Figure 6A schematic diagram of the structure of a robotic device provided in an embodiment of the present application;

[0023] Figure 7 A schematic diagram of the structure of a three-dimensional map construction system provided in an embodiment of the present application;

[0024] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the specific implementation of the present application will be clearly and completely described below in conjunction with the drawings in the implementation of the present application.

[0026] It should be noted that the terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0027] As described in the above background technology, building a three-dimensional map in the field of the Internet of Things requires the cooperation of multiple sensors, which leads to problems such as high cost, difficulty in updating and maintenance, and compatibility during the construction process.

[0028] In view of this, an embodiment of the present application provides a three-dimensional map construction method, in which the present application obtains a first image of the detection space through a robotic device and divides the first image into several second images representing independent spaces. Afterwards, the robotic device determines the boundaries of the second image and removes the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes. Three-dimensional space construction information is added to the third image to obtain a three-dimensional map. The method proposed in the present application can simultaneously meet the real-time construction of two-dimensional and three-dimensional maps by performing image analysis on the two-dimensional map during the construction of the three-dimensional map, and can complete the construction of the three-dimensional map using a single sensor, thereby reducing the cost of the three-dimensional map construction solution.

[0029] The following is a detailed description of the three-dimensional map construction method, system and robotic device provided in the embodiments of the present application with reference to the accompanying drawings.

[0030] Figure 1 This is a flow chart of a three-dimensional map construction method provided in an embodiment of the present application. Figure 1As shown, the three-dimensional map construction method includes the following steps:

[0031] Step S101: Acquire a first image of a detection space.

[0032] The first image is a planar image. The detection space is an unknown or under-documented spatial area that needs to be sensed, located, and mapped using sensors and related technologies. For example, the detection space can be an indoor environment (such as a warehouse or office building).

[0033] As an implementation method, the robotic device can use a single distance sensor (camera or lidar or other image acquisition device) to scan the detection space, obtain captured image data, and form a first image of the detection space after image processing.

[0034] For example, a single distance sensor can be an image sensor (such as a CMOS or CCD), which can convert optical signals into electrical signals and perform digital processing. When the light signal passes through the sensor, each photosensitive element generates an electrical signal proportional to the intensity of the incident light. The electrical signal is converted into a digital signal by an analog-to-digital converter (ADC), thereby forming a first image of the detection space.

[0035] It should be noted that the first image captured by the robotic device can be adapted to a variety of terminals and platforms. Specifically, the robotic device can provide a unified data processing and analysis method, data structure, and access interface. Furthermore, the robotic device can provide a flexible data structure, analysis algorithm, and visualization display to ensure adaptability to a variety of terminals and platforms.

[0036] Step S102: Divide the first image into a plurality of second images representing independent spaces.

[0037] Among them, several independent spaces constitute the detection space.

[0038] As an implementation method, the robot device can identify the edge contour information (such as wall, door frame, etc.) of the collected first image through edge detection technology and / or grayscale processing, and obtain several second images based on the edge contour information. For example, the edge contour information of the collected first image can be expressed as Figure 2 .

[0039] Specifically, the robot device identifies the edge contour information of the collected first image through edge detection technology and / or grayscale processing, and extracts the edge contour information of the identified and collected first image. Afterwards, the robot device divides the full map coordinate data into independent spatial coordinate data based on the edge contour information to divide the first image into several preliminary screening images. Finally, the robot device performs Gaussian blur processing on the several preliminary screening images to obtain several second images, so as to better analyze and process the various information in the image. Gaussian blur technology can reduce the noise in the preliminary screening image to smooth the preliminary screening image. Among them, the second image after noise reduction is as follows Figure 3 shown.

[0040] Step S103: Determine the boundaries of the second images, and remove the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes.

[0041] The robotic device may perform morphological processing on the second image to obtain vertex model information of the second image. The vertex model information includes coordinate information of the second image in a plane coordinate system. The morphological processing may include dilation and erosion. Dilation may expand white areas in the second image, while erosion may reduce white areas in the second image.

[0042] As an implementation method, the robotic device can use an edge detection algorithm (such as the Canny or Sobel algorithm) to determine the edges of objects in the image. Based on the edge detection, the robotic device can then use a corner detection algorithm (such as Harris corner detection or Fast corner detection) to identify vertices to obtain vertex model information of the second image.

[0043] Furthermore, after morphological processing and edge detection, the robotic device can use a contour tracking algorithm to extract the overall contour of the second image. Finally, based on the extracted contour, the robotic device can use a polygon fitting technique to approximate the contour shape and thereby determine the boundary of the second image.

[0044] Furthermore, the robotic device can use collision detection technology to detect overlapping edges in the second image, which are typically marked as door frames. Specifically, the robotic device identifies and records the relationship between the coordinate information, including whether there is any coordinate information between the coordinate information that can be identified as a door frame. The robotic device then defines the boundaries of adjacent second images with the same coordinate information as overlapping boundaries, and marks the detected overlapping edges as door frames, while non-overlapping edges are marked as walls.

[0045] Finally, the robotic device can remove the overlapping edges of the second image through image processing techniques such as dilation and erosion. Specifically, the robotic device can perform a dilation operation on the second image to obtain a second image after dilation. Afterwards, the robotic device can perform an erosion operation on the second image after dilation to remove the overlapping edges and obtain a third image with spatial properties. For example, the third image can be represented as Figure 4 . Figure 4 In the figure, the black overlapping edges in the red frame removed by the robot are the door frames, and the black non-overlapping edges that are not removed are the walls.

[0046] Exemplarily, the robotic device identifies overlapping portions by comparing the expanded image with the original image or another space. After detecting overlapping boundaries, an erosion operation is performed to reduce the impact of the boundaries, thereby removing the overlapping boundaries from the image. The robotic device constructs a two-dimensional map model based on the independent spaces divided in step S102 above, including the edges and attributes of each space, such as the type (room, corridor, etc.), size, and shape of the space.

[0047] Step S104: Add three-dimensional space construction information to the third image to obtain a three-dimensional map.

[0048] The three-dimensional space construction information includes at least one of the height of the detection space, the thickness of the floor arranged in the detection space, the material of the wall, and the thickness of the wall. The three-dimensional space construction information can be stored in the robot device.

[0049] As an implementation method, the robotic device cleans and formats the stored three-dimensional spatial construction information, including operations such as data conversion, scaling and alignment, to ensure that it is consistent with the coordinate system and scale of the two-dimensional map model.

[0050] Furthermore, the robotic device creates a preliminary 3D model based on the preprocessed 3D spatial construction information in 3D modeling software (e.g., using WebGL), and establishes basic geometric shapes for the independent spaces. For example, the floor can be modeled as flat polygons, and walls can be modeled as cubes or cylinders. The robotic device can also assign material properties to different parts of the model, such as brick or wood effects for walls.

[0051] Finally, the robotic device configures appropriate light sources for the 3D model, including natural and artificial light, and sets the position, intensity, and color of the light source. It also selects a suitable renderer and rendering parameters, such as reflection, refraction, shadows, and global illumination, to generate highly realistic images and obtain a 3D map.

[0052] For example, Figure 4 By adding the three-dimensional space construction information, the obtained three-dimensional map can be expressed as Figure 5 . Figure 5 The 3D map is constructed as a 3D map of the room, including the spatial structural features and material features of the room. For example, spatial structural features include walls, doors and windows, and floor heights, while material features include wall and floor materials.

[0053] Based on the above method, a three-dimensional map construction method proposed in this application obtains a first image of the detection space through a robotic device and divides the first image into several second images representing independent spaces. Afterwards, the robotic device determines the boundaries of the second image and removes the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes. Finally, the robotic device adds three-dimensional space construction information to the third image to obtain a three-dimensional map. The method proposed in this application can simultaneously meet the real-time construction of two-dimensional maps and three-dimensional maps, and can complete the construction of three-dimensional maps using a single sensor, reducing the cost of the three-dimensional map construction solution.

[0054] Figure 6 Schematic diagram of a robot device 600 provided in an embodiment of the present application. Figure 6 As shown, the robot device 600 includes: a sampling module 61 , a storage module 62 and a processor 63 .

[0055] The sampling module 61 includes a distance sensor. The sampling module 61 establishes a first image representing the detection space based on the detection signal received and sent by the distance sensor. The first image is a plane image.

[0056] The storage module 62 is used to store two-dimensional space and three-dimensional space construction information.

[0057] The processor 63 is configured to divide the first image into a plurality of second images representing independent spaces, wherein the plurality of independent spaces constitute a detection space.

[0058] The processor 63 is also used to determine the boundaries of the second image and remove the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes. The processor 63 obtains three-dimensional space construction information and adds the three-dimensional space construction information to the third image to obtain a three-dimensional map.

[0059] It is understandable that the present application can be executed by a robot device 600 having computing capabilities. The robot device can be a single device, or a device cluster consisting of multiple robot devices 600. The present application does not limit the specific implementation of the robot device.

[0060] Figure 7 is a structural diagram of a three-dimensional map construction system 700 provided in an embodiment of the present application, such as Figure 7As shown, the three-dimensional map construction system 700 includes a robot device 71 and a preset device 72 .

[0061] The robot device 71 includes a sampling module 711 , which includes a distance sensor. The sampling module 711 creates a first image representing the detection space based on the detection signals received and sent by the sampling module, wherein the first image is a planar image.

[0062] The robot device 71 further includes a communication module 712 for sending the first image to a preset device.

[0063] The preset device 72 also includes a terminal 721 and a server 722. The terminal 721 is used to determine the boundaries of the second image and remove the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes, and add three-dimensional space construction information to the third image to obtain a three-dimensional map, wherein the server 722 stores the two-dimensional space and three-dimensional space construction information.

[0064] Exemplarily, the terminal 721 is used to receive a first image sent by the robot device 71, and process the first image to obtain a second image and a third image to construct a three-dimensional map. For example, the terminal 721 may include a multi-platform container layer, a cross-platform map data processing layer, and a map data rendering layer. The multi-platform container layer is used to connect different platforms to the robot device 71 and transmit data to the cross-platform map data processing layer. The cross-platform map data processing layer can be composed of a cross-platform middleware and a WebView container to provide cross-platform capabilities and realize the development of multi-platform deployment. The map data rendering layer is mainly composed of WebGL, which is used to receive real-time map rendering data from the WebView container, perform real-time construction and rendering of two-dimensional maps and three-dimensional maps, and render and display the two-dimensional maps and three-dimensional maps through the terminal 721.

[0065] Based on the above solution, the three-dimensional map construction system proposed in this application can be deployed on multiple platforms, solving the problem that non-cross-platform solutions require separate development of functional modules for different operating systems, resulting in repetitive work and time-consuming and labor-intensive work. In addition, in the construction of the three-dimensional map, a single sensor is used to complete the construction of the three-dimensional map, reducing the hardware cost of the three-dimensional map construction solution.

[0066] It should be noted that the execution entity of the three-dimensional map construction method provided in this application is the robot device 600, and it can also be the three-dimensional map construction system 700, without limitation.

[0067] It should also be noted that the embodiments of this application do not limit the application scenarios of the three-dimensional map construction method. The description of the solution in the embodiments of this application is intended to more clearly illustrate the technical solution of the embodiments of this application and does not constitute a limitation on the technical solution provided by the embodiments of this application. Those skilled in the art will understand that with the evolution of technology and the emergence of new business scenarios, the technical solution provided by the embodiments of this application will also be applicable to similar technical problems.

[0068] Figure 8 800 is a structural diagram of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device 800 includes a memory 81 and a processor 82 .

[0069] The memory 81 is used to store executable instructions of the processor 82. It is understandable that the processor 82 is configured to execute instructions to implement the three-dimensional map construction method in the above embodiment.

[0070] It should be noted that those skilled in the art can understand that Figure 8 The structure of the electronic device 800 shown in FIG. 8 does not limit the electronic device 800. The electronic device 800 may include Figure 8 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0071] The processor 82 is the control center of the electronic device 800. It connects the various components of the electronic device using various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 81 and accessing data stored in the memory 81, it performs various functions of the electronic device and processes data, thereby providing overall monitoring of the electronic device 800. Optionally, the processor 82 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into the processor 82.

[0072] Memory 81 can be used to store software programs and various data. Memory 81 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and application programs required by at least one functional module. Memory 81 may also include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state memory device.

[0073] In an exemplary embodiment, a computer-readable storage medium including instructions is further provided, such as a memory 81 including instructions. The instructions can be executed by the processor 82 of the electronic device 800 to implement the method in the above embodiment.

[0074] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0075] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, which can be executed by the processor 42 of the electronic device to implement the method in the above embodiment.

[0076] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned method embodiment are implemented and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0077] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete the full classification or partial functions described above.

[0078] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, 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 an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0079] Units described as separate components may or may not be physically separate, and components shown as modules may be one physical module or multiple physical modules, that is, they may be located in one place or distributed in multiple places. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0080] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The above-mentioned integrated units may be implemented in the form of hardware or software functional units.

[0081] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0082] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the claims appended to this application.

Claims

1. A three-dimensional map construction method, characterized in that: The method comprises: Acquire a first image of the detection space, wherein the first image is a plane image; Dividing the first image into a plurality of second images representing independent spaces, wherein the plurality of independent spaces constitute the detection space; Determine the boundary of the second image, and remove the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes; Three-dimensional space construction information is added to the third image to obtain a three-dimensional map.

2. The three-dimensional map construction method according to claim 1, characterized in that: The method further comprises: performing morphological processing on the second image to obtain vertex model information of the second image; A collision detection is performed on the second image from which the vertex model information is obtained, so as to determine a boundary of the second image.

3. The three-dimensional map construction method according to claim 2, characterized in that: The vertex model information includes coordinate information of the second image in a plane coordinate system to determine coordinate information of a boundary of the second image; and removing the overlapping boundaries in adjacent second images, including: Determining coordinate information of a boundary of the second image; Boundaries in adjacent second images having the same coordinate information are defined as overlapping boundaries, and the overlapping boundaries are removed.

4. The three-dimensional map construction method according to claim 3, characterized in that: Before adding the three-dimensional space construction information to the third image, the method includes: Boundaries that do not have the same coordinate information are screened out and determined to be walls of the detection space.

5. The three-dimensional map construction method according to claim 3, characterized in that: Removing the overlapping boundaries includes: Performing a dilation operation on the second image to obtain the second image after dilation; An erosion operation is performed on the second image after the dilation process to remove the overlapping boundaries.

6. The three-dimensional map construction method according to claim 4, characterized in that: The three-dimensional space construction information includes at least one of the following information: The height of the detection space, the thickness of the floor arranged in the detection space, the material of the wall, and the thickness of the wall.

7. The three-dimensional map construction method according to claim 1, characterized in that: Dividing the first image into a plurality of second images representing independent spaces, including: Performing grayscale processing and / or edge detection on the first image, and extracting edge contour information of the first image, and obtaining a plurality of preliminary screening images according to the edge contour information; The primary screening image is subjected to Gaussian blur processing to obtain the second image.

8. A robot device, characterized in that: include: A sampling module, the sampling module comprising a distance sensor, the sampling module establishing a first image representing the detection space based on the detection signal received and sent by the sampling module, wherein the first image is a plane image; A storage module, used for storing two-dimensional space and three-dimensional space construction information; A processor, configured to divide the first image into a plurality of second images representing independent spaces, wherein the plurality of the independent spaces constitute the detection space; The processor is also used to determine the boundaries of the second image and remove the overlapping boundaries in adjacent second images to obtain a third image with spatial attributes. The processor obtains the three-dimensional space construction information and adds the three-dimensional space construction information to the third image to obtain a three-dimensional map.

9. A three-dimensional map construction system, characterized in that: It includes a robot device and a preset device, wherein the preset device includes a terminal and a server; The robot device comprises: A sampling module, the sampling module comprising a distance sensor, the sampling module establishing a first image representing the detection space based on the detection signal received and sent by the sampling module, wherein the first image is a plane image; A communication module, used for sending the first image to the preset device; The preset device is used to determine the boundary of the second image, remove the overlapping boundaries in adjacent second images, obtain a third image with spatial attributes, and add three-dimensional space construction information to the third image to obtain a three-dimensional map, wherein the three-dimensional space construction information is stored in the preset device.

10. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer program instructions, and the processor is configured to execute the instructions stored in the memory to perform the method steps according to any one of claims 1 to 7.

Images