CN112767551B - Three-dimensional model construction method and device, electronic equipment and storage medium - Google Patents
Three-dimensional model construction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112767551B CN112767551B CN202110062430.6A CN202110062430A CN112767551B CN 112767551 B CN112767551 B CN 112767551B CN 202110062430 A CN202110062430 A CN 202110062430A CN 112767551 B CN112767551 B CN 112767551B
- Authority
- CN
- China
- Prior art keywords
- plane
- point cloud
- cloud information
- dimensional
- dimensional point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The disclosure provides a three-dimensional model construction method and device, electronic equipment and a storage medium, and relates to the technical field of computers, wherein the method comprises the following steps: processing the three-dimensional point cloud information based on a preset plane detection strategy to obtain a plane in the three-dimensional point cloud information; acquiring an arrangement constraint relation between planes; performing three-dimensional curved surface reconstruction on point cloud information which does not belong to a plane in the three-dimensional point cloud information to obtain a non-planar surface; generating a three-dimensional model corresponding to the three-dimensional point cloud information according to the plane, the constraint relation and the non-planar surface; according to the method, the device, the electronic equipment and the storage medium, the object is represented through the plane, meanwhile, the position of the plane in the three-dimensional space is adjusted to enable the whole structure to meet geometric constraint, higher-level geometric information can be provided, and the geometric accuracy and the complexity of the model are higher and lower; the complexity of the model is reduced while ensuring no loss of precision.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for building a three-dimensional model, an electronic device, and a storage medium.
Background
With advances in technology, it is becoming increasingly simple to acquire three-dimensional data for a large number of indoor scenes. How to represent a virtual scene of an indoor room source on a computer so as to be capable of reproducing large structures and various details in a room most realistically becomes important. At present, a commonly used three-dimensional model representation method is a triangular mesh model. The triangular mesh model consists of basic points, lines and planes, each plane consisting of triangles. The data structure has direct geometric topological relation among all parts, and simultaneously can simplify the number of points in the model and reduce the complexity of storage and operation. However, for an indoor scene, the number of the triangular patches corresponding to the three-dimensional model is mostly over 10 ten thousand orders of magnitude, which causes difficulty in subsequent real-time rendering and model matching.
Disclosure of Invention
The present disclosure is proposed to solve the above technical problems. The embodiment of the disclosure provides a three-dimensional model construction method and device, electronic equipment and a storage medium.
According to a first aspect of the embodiments of the present disclosure, there is provided a three-dimensional model building method, including: processing three-dimensional point cloud information based on a preset plane detection strategy to obtain a plane in the three-dimensional point cloud information; acquiring an arrangement constraint relation between the planes; performing three-dimensional curved surface reconstruction on the point cloud information which does not belong to the plane in the three-dimensional point cloud information to obtain a non-planar surface; and generating a three-dimensional model corresponding to the three-dimensional point cloud information according to the plane, the constraint relation and the non-planar surface.
Optionally, the processing the three-dimensional point cloud information based on a preset plane detection strategy, and the obtaining a plane in the three-dimensional point cloud information includes: carrying out plane detection processing on the three-dimensional point cloud information based on a preset plane detection algorithm to obtain a plurality of plane areas in the three-dimensional point cloud information; determining the boundary of the plane area based on a preset boundary determination algorithm to obtain a plurality of first planes; and combining the adjacent first planes by an iteration method to generate a second plane, and updating the connection relation between the second plane and the adjacent first plane and/or second plane.
Optionally, the plane detection method includes: RANSAC, region growing algorithm; the boundary determination algorithm includes: alpha-shape algorithm.
Optionally, the merging the adjacent first planes by an iterative method to generate a second plane includes: acquiring an adjacent first plane or an adjacent second plane at the periphery of the first plane or the second plane during each iteration; if the direction deviation between the normal vector of the first plane or the second plane and the normal vector of the adjacent first plane or the adjacent second plane is smaller than a preset deviation threshold value, combining the adjacent first plane or the adjacent second plane in the first plane or the second plane to serve as a new second plane; when it is determined that the new second plane cannot be generated, the iterative process ends.
Optionally, the obtaining of the arrangement constraint relationship between the planes includes: processing the first plane and/or the second plane which currently exists based on a preset plane optimization algorithm to determine an arrangement constraint relation between the first plane and/or the second plane; wherein the placement constraint relationship comprises: at least one of perpendicular, symmetrical, and parallel relationships.
Optionally, the performing three-dimensional curved surface reconstruction on the point cloud information not belonging to the plane in the three-dimensional point cloud information to obtain a non-planar surface includes: performing three-dimensional curved surface reconstruction on the point cloud information which does not belong to the plane by using a preset curved surface reconstruction algorithm to obtain the non-planar surface; wherein the surface reconstruction algorithm comprises: and (3) a Poisson surface reconstruction algorithm.
Optionally, optimizing the three-dimensional point cloud information; wherein the optimization process comprises: denoising and/or point cloud hole repairing.
Optionally, in generating the three-dimensional model, the non-planar surface is subjected to polygon division to generate a polygon mesh.
According to a second aspect of the embodiments of the present disclosure, there is provided a three-dimensional model building apparatus including: the plane acquisition module is used for processing the three-dimensional point cloud information based on a preset plane detection strategy to acquire a plane in the three-dimensional point cloud information; the constraint determining module is used for acquiring the arrangement constraint relation between the planes; the non-planar processing module is used for performing three-dimensional curved surface reconstruction on the point cloud information which does not belong to the plane in the three-dimensional point cloud information to obtain a non-planar surface; and the model generation module is used for generating a three-dimensional model corresponding to the three-dimensional point cloud information according to the plane, the constraint relation and the non-planar surface.
Optionally, the plane acquiring module includes: the area determining unit is used for carrying out plane detection processing on the three-dimensional point cloud information based on a preset plane detection algorithm to obtain a plurality of plane areas in the three-dimensional point cloud information; the boundary determining unit is used for determining the boundary of the plane area based on a preset boundary determining algorithm to obtain a plurality of first planes; and the plain film merging unit is used for merging the adjacent first planes by an iteration method to generate a second plane and updating the connection relation between the second plane and the adjacent first plane and/or second plane.
Optionally, the plane detection method includes: RANSAC, region growing algorithm; the boundary determination algorithm includes: alpha-shape algorithm.
Optionally, the flat sheet merging unit is configured to obtain an adjacent first plane or an adjacent second plane around one first plane or one second plane at each iteration; if the direction deviation between the normal vector of the first plane or the second plane and the normal vector of the adjacent first plane or the adjacent second plane is smaller than a preset deviation threshold value, combining the adjacent first plane or the adjacent second plane in the first plane or the second plane to be used as a new second plane; when it is determined that the new second plane cannot be generated, the iterative process ends.
Optionally, the constraint determining module is configured to process the first plane and/or the second plane that currently exists based on a preset plane optimization algorithm, so as to determine an arrangement constraint relationship between the first plane and/or the second plane; wherein the placement constraint relationship comprises: at least one of perpendicular, symmetrical, and parallel relationships.
Optionally, the non-planar processing module is configured to perform three-dimensional curved surface reconstruction on the point cloud information that does not belong to the plane by using a preset curved surface reconstruction algorithm, so as to obtain a non-planar surface; wherein the surface reconstruction algorithm comprises: and (3) a Poisson surface reconstruction algorithm.
Optionally, the point cloud optimizing module is configured to perform optimization processing on the three-dimensional point cloud information; wherein the optimization process comprises: denoising and/or point cloud hole repairing.
Optionally, the model generating module is further configured to perform polygon division on the non-planar surface when generating the three-dimensional model, so as to generate a polygon mesh.
According to a third aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the above-mentioned method.
According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing the processor-executable instructions; the processor is used for executing the method.
Based on the three-dimensional model construction method and device, the electronic device and the storage medium provided by the embodiments of the present disclosure, the object is represented by the plane, and meanwhile, the position of the plane in the three-dimensional space is adjusted to enable the overall structure to satisfy the geometric constraint, so that higher-level geometric information can be provided, the geometric accuracy of the model is higher, the complexity is lower, and the complexity of the model is reduced while the accuracy is not lost.
The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in more detail embodiments of the present disclosure with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the disclosure, and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure and not to limit the disclosure. In the drawings, like reference numbers generally represent like parts or steps.
FIG. 1 is a flow chart of one embodiment of a three-dimensional model building method of the present disclosure;
FIG. 2 is a flow chart of obtaining a plane in three-dimensional point cloud information in an embodiment of a three-dimensional model building method of the present disclosure;
FIGS. 3A to 3D are schematic views of a process for constructing a three-dimensional model;
FIG. 4 is a schematic structural diagram of one embodiment of a three-dimensional model building apparatus of the present disclosure;
FIG. 5 is a schematic structural diagram of a plane acquisition module in an embodiment of the three-dimensional model building apparatus of the present disclosure;
FIG. 6 is a schematic structural diagram of another embodiment of a three-dimensional model building apparatus according to the present disclosure;
FIG. 7 is a block diagram of one embodiment of an electronic device of the present disclosure.
Detailed Description
Example embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.
It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.
It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more than two and "at least one" may refer to one, two or more than two.
It is also to be understood that any reference to any component, data, or structure in the embodiments of the present disclosure may be generally understood as one or more, unless explicitly defined otherwise or indicated to the contrary hereinafter.
In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, such as a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Embodiments of the present disclosure may be implemented in electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with an electronic device, such as a terminal device, computer system, or server, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks may be performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Summary of the application
In the process of implementing the present disclosure, the inventors found that a large number of polygonal patches corresponding to a three-dimensional model would cause difficulty in subsequent real-time rendering and model matching, and that various structural objects having obvious geometric features exist in an indoor scene, but the existing three-dimensional model usually does not retain the features.
The three-dimensional model construction method provided by the disclosure obtains planes in three-dimensional point cloud information and an arrangement constraint relation between the planes; performing three-dimensional curved surface reconstruction on point cloud information which does not belong to a plane in the three-dimensional point cloud information to obtain a non-planar surface; generating a three-dimensional model corresponding to the three-dimensional point cloud information according to the plane, the constraint relation and the non-planar surface; structural objects are represented by planes, and meanwhile, the position of the planes in a three-dimensional space is adjusted to enable the overall structure to meet geometric constraints, so that higher-level geometric information can be provided, and the complexity of the model is reduced while the accuracy is not lost.
Exemplary method
Fig. 1 is a flowchart of an embodiment of a three-dimensional model building method of the present disclosure, and the method shown in fig. 1 includes the steps of: S101-S104. The following describes each step.
S101, processing the three-dimensional point cloud information based on a preset plane detection strategy to obtain a plane in the three-dimensional point cloud information.
In one embodiment, the three-dimensional point cloud information may be three-dimensional structure point cloud map information of indoor rooms, including living rooms, bedrooms, dining rooms, kitchens, toilets and the like. The point cloud collecting device can be a laser radar, a depth camera and the like, and the three-dimensional point cloud information can be three-dimensional point cloud information located under a global coordinate system. Various plane detection strategies can be preset to obtain planes in the three-dimensional point cloud information, and the obtained planes can be planes corresponding to the surfaces of walls, bottom plates and ceilings.
S102, acquiring an arrangement constraint relation between the planes. The placement constraint relationship may be parallel, perpendicular, symmetrical, etc.
S103, performing three-dimensional curved surface reconstruction on the point cloud information which does not belong to the plane in the three-dimensional point cloud information to obtain a non-planar surface.
And S104, generating a three-dimensional model corresponding to the three-dimensional point cloud information according to the plane, the constraint relation and the non-planar surface.
In one embodiment, the indoor scene has a plurality of structural objects, for example, the structural objects are walls, floors, door frames, etc., the structural objects have distinct geometric features, and most of the three-dimensional data points corresponding to each structural object fall on the same plane. However, the existing triangular mesh model usually does not retain the characteristic, and the triangular meshes forming the surfaces of all structural objects are mostly staggered and uneven, and the number of the triangular meshes is large; meanwhile, geometric constraints such as the fact that walls are perpendicular to the ground, the walls are parallel, the ground is perpendicular to a ceiling and the like are hidden among all structural objects, and cannot be expressed in the triangular mesh model.
The three-dimensional model building method disclosed by the invention adopts the plane to represent the structural object, simultaneously enables the whole structure to meet the geometric constraint by adjusting the position of the plane in the three-dimensional space, can have higher-level geometric information, and can represent other objects in an indoor scene, such as a schoolbag, a table, a chair, a cabinet and the like, by using a triangular grid; the three-dimensional model constructed by the three-dimensional model construction method disclosed by the invention can be higher in geometric accuracy and lower in complexity.
Fig. 2 is a flowchart of acquiring a plane in three-dimensional point cloud information in an embodiment of a three-dimensional model building method of the present disclosure, where the method shown in fig. 2 includes the steps of: S201-S203. The following describes each step.
S201, carrying out plane detection processing on the three-dimensional point cloud information based on a preset plane detection algorithm, and obtaining a plurality of plane areas in the three-dimensional point cloud information.
In one embodiment, the plane detection method includes RANSAC (RANdom SAmple Consensus), region growing algorithm, and the like. The region growing algorithm is an image segmentation technique, and similar pixels and the like are combined to form a region based on a discrimination rule. The existing RANSAC and region growing algorithm can be used for carrying out plane detection processing on the three-dimensional point cloud information so as to obtain a plane region and a non-plane region.
S202, determining the boundaries of the plane areas based on a preset boundary determination algorithm, and obtaining a plurality of first planes.
In an embodiment, the boundary determining algorithm comprises an alpha-shape algorithm and the like, and the boundary of the plane area is determined by using the existing alpha-shape algorithm and the like to obtain the first plane.
S203, combining the adjacent first planes through an iteration method to generate a second plane, and updating the connection relation between the second plane and the adjacent first plane and/or second plane.
In one embodiment, at each iteration, an adjacent first plane or an adjacent second plane around a first plane or a second plane is obtained, and if the direction deviation between the normal vector of the first plane or the second plane and the normal vector of the adjacent first plane or the adjacent second plane is smaller than a preset deviation threshold value, the adjacent first plane or the adjacent second plane is merged into the first plane or the second plane to be used as a new second plane. When it is determined that the new second plane cannot be generated, the iterative process ends.
For example, a deviation threshold value of a1 is preset, at each iteration, the direction deviation between the normal vector of a first plane or a second plane and the normal vector of a neighboring first plane or neighboring second plane at the periphery is obtained as a1, if a1 is smaller than the deviation threshold value a1, the neighboring first plane or the neighboring second plane is merged into the first plane or the second plane as a new second plane; and performing loop iteration processing by using the method to obtain a new second plane until the new second plane cannot be generated, and ending the loop iteration processing.
Processing the first plane and/or the second plane which currently exists based on a preset plane optimization algorithm to determine an arrangement constraint relation between the first plane and/or the second plane, wherein the arrangement constraint relation comprises: at least one of perpendicular, symmetrical, and parallel relationships. The plane optimization algorithm may be an LOD level detail algorithm or the like, and the vertical, symmetrical, parallel and the like relationships between the first plane and/or the second plane may be determined based on the existing LOD level detail algorithm.
In one embodiment, a preset curved surface reconstruction algorithm is used for performing three-dimensional curved surface reconstruction on point cloud information which does not belong to a plane in the three-dimensional point cloud information to obtain a non-planar surface. The curved surface reconstruction algorithm can be various, such as a poisson curved surface reconstruction algorithm and the like, and the existing poisson curved surface reconstruction algorithm is used for performing three-dimensional curved surface reconstruction on point cloud information which does not belong to a plane to obtain a non-planar surface.
After the three-dimensional point cloud information is obtained, optimization processing is carried out on the three-dimensional point cloud information, and the optimization processing comprises denoising, point cloud cavity repairing and the like. Various denoising, point cloud hole repairing and other processes can be adopted. For example, the denoising process is to eliminate isolated noise points and burrs from the three-dimensional point cloud information through filtering, so as to highlight the characteristic information of the point cloud. And determining the inner edge and the outer edge of the three-dimensional point cloud information after filtering and denoising, determining the inner edge as a cavity edge, and extracting the cavity edge. And point cloud hole repairing is to perform hole repairing by using local neighborhood information in the extracted hole edge.
When the three-dimensional model is generated, the non-planar surface is subjected to polygon division to generate a polygon mesh, wherein the polygon mesh can be a triangular mesh, a quadrilateral mesh, a pentagonal mesh and the like. For example, the non-planar surface is triangulated using a predetermined subdivision algorithm. The subdivision algorithm comprises a Delaunay triangulation algorithm and the like. The three-dimensional model corresponding to the three-dimensional point cloud information may be generated using a variety of existing methods based on the current first and/or second planes, non-planar surfaces, and the vertical, symmetric, and parallel relationships between the first and/or second planes.
In one embodiment, three-dimensional point cloud information of an indoor scene is obtained, as shown in fig. 3A. Planes (feature planes) are extracted from the three-dimensional point cloud information by using RANSAC or a region growing algorithm, the point cloud corresponding to each plane is projected onto the two-dimensional plane, an alpha-shape corresponding to the projection point is calculated, and the boundary of the plane is obtained, such as the alpha-shape corresponding to the plane in FIG. 3B.
Since some noise planes are included in the obtained planes and the planes do not satisfy the required geometric constraint with each other, two adjacent planes originally belonging to the same plane need to be continuously merged. For example, in each iteration process, two planes which are most likely to be coplanar are selected for combination, and the connection relation between the combined plane and the surrounding adjacent planes is updated; the above iterative process is repeated until no two planes satisfy the condition of plane merging.
By using the LOD level detail algorithm, the remaining planes meet the geometric constraints of vertical, parallel, symmetrical and the like, so that the planes have extremely high geometric accuracy, the geometric relationship among different structural objects can be better described, and redundant information is eliminated, as shown in FIG. 3C. For other objects which do not belong to structural objects, reconstructing a non-planar surface corresponding to the other objects by adopting a Poisson reconstruction algorithm, and carrying out triangular division to generate triangular meshes; the triangular mesh and the plane are superposed together to generate a three-dimensional model corresponding to the three-dimensional point cloud information, and the whole indoor scene can be represented as shown in fig. 3D.
Exemplary devices
In one embodiment, as shown in fig. 4, the present disclosure provides a three-dimensional model building apparatus including: a plane acquisition module 401, a constraint determination module 402, a non-plane processing module 403, and a model generation module 404. The plane obtaining module 401 processes the three-dimensional point cloud information based on a preset plane detection strategy to obtain a plane in the three-dimensional point cloud information. The constraint determination module 402 obtains placement constraint relationships between the planes. The non-planar processing module 403 performs three-dimensional surface reconstruction on the point cloud information that does not belong to a plane in the three-dimensional point cloud information to obtain a non-planar surface. The model generation module 404 generates a three-dimensional model corresponding to the three-dimensional point cloud information from the plane, the constraint relationship, and the non-planar surface.
In one embodiment, as shown in fig. 5, the plane acquisition module 401 includes: an area determination unit 4011, a boundary determination unit 4012, and a tile combination unit 4013. The area determination unit 4011 performs plane detection processing on the three-dimensional point cloud information based on a preset plane detection algorithm, and obtains a plurality of plane areas in the three-dimensional point cloud information. The boundary determining unit 4012 determines the boundaries of the plane areas based on a preset boundary determining algorithm, and obtains a plurality of first planes. The tile merging unit 4013 performs merging processing on the adjacent first planes by an iterative method, generates a second plane, and updates a connection relationship between the second plane and the adjacent first plane and/or second plane.
The tile combining unit 4013 obtains an adjacent first plane or an adjacent second plane at the periphery of the first plane or the second plane at each iteration. If the direction deviation between the normal vector of the first plane or the second plane and the normal vector of the adjacent first plane or the adjacent second plane is smaller than the preset deviation threshold, the tile merging unit 4013 merges the adjacent first plane or the adjacent second plane into the first plane or the second plane as a new second plane. When the tile combining unit 4013 determines that the new second plane cannot be generated, the iteration process ends.
The constraint determining module 402 processes the currently existing first plane and/or second plane based on a preset plane optimization algorithm to determine an arrangement constraint relationship between the first plane and/or the second plane, where the arrangement constraint relationship includes: perpendicular, symmetrical, and parallel relationships, and the like. The non-planar processing module 403 performs three-dimensional curved surface reconstruction on the point cloud information that does not belong to a plane by using a preset curved surface reconstruction algorithm to obtain a non-planar surface, where the curved surface reconstruction algorithm includes a poisson curved surface reconstruction algorithm and the like.
In one embodiment, as shown in fig. 6, the three-dimensional model building apparatus further includes a point cloud optimization module 405; the point cloud optimization module 405 performs optimization processing on the three-dimensional point cloud information, wherein the optimization processing includes: denoising, point cloud hole repairing and the like. The model generation module 404 performs polygon partitioning on the non-planar surface to generate a polygon mesh when generating the three-dimensional model.
FIG. 7 is a block diagram of one embodiment of an electronic device of the present disclosure, as shown in FIG. 7, the electronic device 71 includes one or more processors 711 and memory 712.
The processor 711 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 71 to perform desired functions.
The memory 712 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory, for example, may include: random Access Memory (RAM) and/or cache memory (cache), etc. The nonvolatile memory, for example, may include: read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor 711 to implement the three-dimensional model building methods of the various embodiments of the present disclosure above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.
In one example, the electronic device 71 may further include: input devices 713 and output devices 714, among other components, interconnected by a bus system and/or other form of connection mechanism (not shown). The input device 713 may also include, for example, a keyboard, a mouse, and the like. The output device 714 can output various information to the outside. The output devices 714 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, among others.
Of course, for simplicity, only some of the components of the electronic device 71 relevant to the present disclosure are shown in fig. 7, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 71 may include any other suitable components, depending on the particular application.
In addition to the methods and apparatus described above, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the three-dimensional model building method according to various embodiments of the present disclosure described in the "exemplary methods" section above of this specification.
The computer program product may write program code for performing the operations of embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the three-dimensional model building method according to various embodiments of the present disclosure described in the "exemplary methods" section above in this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium may include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
The three-dimensional model construction method and device, the electronic device and the storage medium in the embodiments above obtain planes in the three-dimensional point cloud information and an arrangement constraint relationship between the planes; performing three-dimensional curved surface reconstruction on point cloud information which does not belong to a plane in the three-dimensional point cloud information to obtain a non-planar surface; generating a three-dimensional model corresponding to the three-dimensional point cloud information according to the plane, the constraint relation and the non-planar surface; structural objects are represented by planes, and meanwhile, the position of the planes in a three-dimensional space is adjusted to enable the whole structure to meet geometric constraint, so that higher-level geometric information can be provided, and other objects in an indoor scene can be represented by polygonal meshes, so that the geometric accuracy of the model is higher, and the complexity is lower; the calculation complexity is low, the efficiency is high, and the complexity of the model is reduced while the accuracy is not lost; the real-time performance of three-dimensional model transmission and browsing is improved, and the customer experience is effectively improved.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, and systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," comprising, "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects, and the like, will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (8)
1. A method of building a three-dimensional model, comprising:
processing the three-dimensional point cloud information based on a preset plane detection strategy to obtain a plane in the three-dimensional point cloud information, wherein the processing method comprises the following steps:
carrying out plane detection processing on the three-dimensional point cloud information based on a preset plane detection algorithm to obtain a plurality of plane areas in the three-dimensional point cloud information; determining the boundary of the plane area based on a preset boundary determination algorithm to obtain a plurality of first planes; combining the adjacent first planes by an iteration method to generate a second plane; updating the connection relation between the second plane and the first plane and/or the second plane adjacent to the second plane;
acquiring an arrangement constraint relationship between the planes, including:
processing the first plane and/or the second plane which currently exists based on a preset plane optimization algorithm to determine an arrangement constraint relation between the first plane and/or the second plane; the placement constraint relationship includes: at least one of perpendicular, symmetrical, and parallel;
performing three-dimensional curved surface reconstruction on the point cloud information which does not belong to the plane in the three-dimensional point cloud information to obtain a non-planar surface;
generating a three-dimensional model corresponding to the three-dimensional point cloud information according to the plane, the arrangement constraint relation and the non-planar surface, including:
such that the arrangement constraint relationship is satisfied between the planes; performing polygon division on the non-planar surface to generate a polygon mesh; superimposing the generated polygon mesh with the plane not divided by polygons to generate the three-dimensional model corresponding to the three-dimensional point cloud information.
2. The method of claim 1, wherein,
the plane detection method comprises the following steps: at least one of RANSAC, region growing algorithm;
the boundary determination algorithm includes: alpha-shape algorithm.
3. The method of claim 1, wherein the merging adjacent first planes by an iterative method to generate a second plane comprises:
acquiring an adjacent first plane or an adjacent second plane at the periphery of the first plane or the second plane during each iteration;
if the direction deviation between the normal vector of the first plane or the second plane and the normal vector of the adjacent first plane or the adjacent second plane is smaller than a preset deviation threshold value, combining the adjacent first plane or the adjacent second plane in the first plane or the second plane to be used as a new second plane;
when it is determined that the new second plane cannot be generated, the iterative process ends.
4. The method of claim 1, wherein the reconstructing a three-dimensional curved surface for the point cloud information not belonging to the plane from the three-dimensional point cloud information to obtain a non-planar surface comprises:
performing three-dimensional curved surface reconstruction on the point cloud information which does not belong to the plane by using a preset curved surface reconstruction algorithm to obtain the non-planar surface;
wherein the surface reconstruction algorithm comprises: and (3) Poisson surface reconstruction algorithm.
5. The method of any of claims 1 to 4, further comprising:
optimizing the three-dimensional point cloud information;
wherein the optimization process comprises: denoising and/or point cloud hole repairing.
6. A three-dimensional model building apparatus comprising:
the plane acquisition module is used for processing the three-dimensional point cloud information based on a preset plane detection strategy to acquire a plane in the three-dimensional point cloud information;
wherein, the plane acquisition module includes: the area determining unit is used for carrying out plane detection processing on the three-dimensional point cloud information based on a preset plane detection algorithm to obtain a plurality of plane areas in the three-dimensional point cloud information; the boundary determining unit is used for determining the boundary of the plane area based on a preset boundary determining algorithm to obtain a plurality of first planes; the plain film merging unit is used for merging the adjacent first planes by an iteration method to generate a second plane and updating the connection relation between the second plane and the adjacent first plane and/or second plane;
the constraint determining module is used for acquiring the arrangement constraint relation between the planes;
the constraint determining module is specifically configured to process the first plane and/or the second plane that currently exists based on a preset plane optimization algorithm, so as to determine an arrangement constraint relationship between the first plane and/or the second plane; the placement constraint relationship includes: at least one of perpendicular, symmetrical, and parallel;
the non-planar processing module is used for performing three-dimensional curved surface reconstruction on the point cloud information which does not belong to the plane in the three-dimensional point cloud information to obtain a non-planar surface;
a model generation module for generating a three-dimensional model corresponding to the three-dimensional point cloud information from the plane, the arrangement constraint relationship, and the non-planar surface, comprising:
such that the arrangement constraint relationship is satisfied between the planes; performing polygon division on the non-planar surface to generate a polygon mesh; superimposing the generated polygon mesh with the plane not divided by polygons to generate the three-dimensional model corresponding to the three-dimensional point cloud information.
7. A computer-readable storage medium, the storage medium storing a computer program for performing the method of any of the preceding claims 1-5.
8. An electronic device, the electronic device comprising:
a processor; a memory for storing the processor-executable instructions;
the processor is used for reading the executable instructions from the memory and executing the instructions to realize the method of any one of the claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110062430.6A CN112767551B (en) | 2021-01-18 | 2021-01-18 | Three-dimensional model construction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110062430.6A CN112767551B (en) | 2021-01-18 | 2021-01-18 | Three-dimensional model construction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112767551A CN112767551A (en) | 2021-05-07 |
| CN112767551B true CN112767551B (en) | 2022-08-09 |
Family
ID=75702735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110062430.6A Active CN112767551B (en) | 2021-01-18 | 2021-01-18 | Three-dimensional model construction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112767551B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379895B (en) * | 2021-06-10 | 2022-02-22 | 贝壳找房(北京)科技有限公司 | Three-dimensional house model generation method and device and computer readable storage medium |
| CN113538562B (en) * | 2021-07-16 | 2022-05-13 | 贝壳找房(北京)科技有限公司 | Indoor area determination method and device, electronic equipment and storage medium |
| CN113805179B (en) * | 2021-08-30 | 2024-03-08 | 南京航空航天大学 | Three-dimensional modeling method for airborne weather radar target |
| CN113763537A (en) * | 2021-09-07 | 2021-12-07 | 岱悟智能科技(上海)有限公司 | Three-dimensional point cloud plane optimization method based on plane recognition |
| CN115439543B (en) * | 2022-09-02 | 2023-11-10 | 北京百度网讯科技有限公司 | Method for determining hole position and method for generating three-dimensional model in meta universe |
| CN115859749B (en) * | 2023-02-17 | 2023-07-07 | 合肥联宝信息技术有限公司 | Constraint building method and device of three-dimensional model, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472802A (en) * | 2018-11-26 | 2019-03-15 | 东南大学 | A kind of surface grid model construction method constrained certainly based on edge feature |
| CN111915723A (en) * | 2020-08-14 | 2020-11-10 | 广东申义实业投资有限公司 | Indoor three-dimensional panorama construction method and system |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8350850B2 (en) * | 2008-03-31 | 2013-01-08 | Microsoft Corporation | Using photo collections for three dimensional modeling |
| CN102855663B (en) * | 2012-05-04 | 2015-04-01 | 北京建筑工程学院 | Method for building CSG (Constructive Solid Geometry) model according to laser radar grid point cloud |
| WO2017113260A1 (en) * | 2015-12-30 | 2017-07-06 | 中国科学院深圳先进技术研究院 | Three-dimensional point cloud model re-establishment method and apparatus |
| CN107862735B (en) * | 2017-09-22 | 2021-03-05 | 北京航空航天大学青岛研究院 | RGBD three-dimensional scene reconstruction method based on structural information |
| CN108090960B (en) * | 2017-12-25 | 2019-03-05 | 北京航空航天大学 | A kind of Object reconstruction method based on geometrical constraint |
| CN108171780A (en) * | 2017-12-28 | 2018-06-15 | 电子科技大学 | A kind of method that indoor true three-dimension map is built based on laser radar |
| CN109887082A (en) * | 2019-01-22 | 2019-06-14 | 武汉大学 | A kind of interior architecture three-dimensional modeling method and device based on point cloud data |
| CN110176071B (en) * | 2019-05-06 | 2023-02-10 | 南京航空航天大学 | Three-dimensional point cloud reconstruction method based on feature template |
| CN111815776A (en) * | 2020-02-04 | 2020-10-23 | 山东水利技师学院 | Three-dimensional building fine geometric reconstruction method integrating airborne and vehicle-mounted three-dimensional laser point clouds and streetscape images |
| CN111508074B (en) * | 2020-03-12 | 2023-06-27 | 浙江工业大学 | Three-dimensional building model simplification method based on roof contour line |
| CN111932688B (en) * | 2020-09-10 | 2021-02-09 | 深圳大学 | Indoor plane element extraction method, system and equipment based on three-dimensional point cloud |
-
2021
- 2021-01-18 CN CN202110062430.6A patent/CN112767551B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472802A (en) * | 2018-11-26 | 2019-03-15 | 东南大学 | A kind of surface grid model construction method constrained certainly based on edge feature |
| CN111915723A (en) * | 2020-08-14 | 2020-11-10 | 广东申义实业投资有限公司 | Indoor three-dimensional panorama construction method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于二维投影的散乱点云曲面重建;何华等;《北京测绘》;20170908;第102-106页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112767551A (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112767551B (en) | Three-dimensional model construction method and device, electronic equipment and storage medium | |
| US7443393B2 (en) | Method, system, and program product for re-meshing of a three-dimensional input model using progressive implicit approximating levels | |
| CN107533771B (en) | Mesh simplification by 3D model reconstruction | |
| US10127720B2 (en) | Object modeling in multi-dimensional space | |
| CN107851332B (en) | Consistent subdivision via topology aware surface tracking | |
| Zhao et al. | Mathematical morphology-based generalization of complex 3D building models incorporating semantic relationships | |
| CN113470095B (en) | Processing method and device for indoor scene reconstruction model | |
| US9824494B2 (en) | Hybrid surfaces for mesh repair | |
| CN112991547A (en) | Model simplification processing method and device, electronic equipment and medium | |
| US10540454B2 (en) | System maintaining domain-specific 3D models as a graph within computer aided design | |
| US8060540B2 (en) | Data relationship visualizer | |
| CN111080792B (en) | Model simplification processing method and device, electronic equipment and storage medium | |
| CN113628343B (en) | Three-dimensional grid combination processing method and device and storage medium | |
| JP2023529790A (en) | Method, apparatus and program for generating floorplans | |
| US20160335799A1 (en) | Method, system and computer program product for 3d objects graphical representation | |
| CN113538562B (en) | Indoor area determination method and device, electronic equipment and storage medium | |
| US11281935B2 (en) | 3D object detection from calibrated 2D images | |
| CN115690120B (en) | Method, apparatus, device, medium and program product for generating three-dimensional grid | |
| CN115661407B (en) | Multi-detail-level model generation method and device, electronic equipment and storage medium | |
| US11182955B1 (en) | Utilizing dynamic filtering to adaptively generate control points of a vector object for display in a graphical user interface | |
| CN116245931B (en) | Method, device, equipment, medium and product for determining object attribute parameters | |
| CN111986300A (en) | Rendering point determination method and device for house decoration, storage medium and electronic equipment | |
| Rashidi et al. | Built infrastructure point cloud data cleaning: an overview of gap filling algorithms | |
| CN117205554A (en) | Terrain loading method and device for spherical virtual scene, medium and electronic equipment | |
| CN117677983A (en) | Method and system for image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210823 Address after: 100085 Floor 101 102-1, No. 35 Building, No. 2 Hospital, Xierqi West Road, Haidian District, Beijing Applicant after: Seashell Housing (Beijing) Technology Co.,Ltd. Address before: 101300 room 24, 62 Farm Road, Erjie village, Yangzhen Town, Shunyi District, Beijing Applicant before: Beijing fangjianghu Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |