CN112381947A - Method and terminal for extracting three-dimensional change information of building and recognizing semantics - Google Patents

Method and terminal for extracting three-dimensional change information of building and recognizing semantics Download PDF

Info

Publication number
CN112381947A
CN112381947A CN202110059451.2A CN202110059451A CN112381947A CN 112381947 A CN112381947 A CN 112381947A CN 202110059451 A CN202110059451 A CN 202110059451A CN 112381947 A CN112381947 A CN 112381947A
Authority
CN
China
Prior art keywords
entity
building
dimensional
external
point cloud
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.)
Granted
Application number
CN202110059451.2A
Other languages
Chinese (zh)
Other versions
CN112381947B (en
Inventor
李晓明
王伟玺
谢林甫
汤圣君
李游
罗文强
郭仁忠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen University
Original Assignee
Shenzhen University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen University filed Critical Shenzhen University
Priority to CN202110059451.2A priority Critical patent/CN112381947B/en
Publication of CN112381947A publication Critical patent/CN112381947A/en
Application granted granted Critical
Publication of CN112381947B publication Critical patent/CN112381947B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Graphics (AREA)
  • Software Systems (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention discloses a method and a terminal for extracting three-dimensional change information of a building and recognizing semantics, wherein the method comprises the following steps: inputting external point clouds of a two-stage building; respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate three-dimensional solid models of the buildings in the two stages; classifying the three-dimensional solid model of a two-stage building into an external entity and an internal entity; and respectively carrying out change detection on the external entity and the internal entity of the two-stage building by adopting a semantic recognition method, and outputting a recognition result. According to the invention, the external point clouds of the buildings in the two stages are respectively converted into the three-dimensional entity models, and then the three-dimensional entity models of the buildings in the two stages are classified into the top entity, the non-top entity and the internal entity according to the semantic information so as to realize the entity model change detection based on the member, so that the accurate identification result of the entity building change information is obtained, and convenience is brought to later evaluation.

Description

Method and terminal for extracting three-dimensional change information of building and recognizing semantics
Technical Field
The invention relates to the technical field of building three-dimensional change detection, in particular to a method, a terminal and a computer-readable storage medium for extracting building three-dimensional change information and recognizing semantics.
Background
With the acceleration of urban construction speed, the point cloud data is utilized to realize the detection of building change in different time phases, and the point cloud data becomes an indispensable means in the urban building change detection technology. In order to complete the change detection work quickly and efficiently, dense matching is often performed on two-stage aerial images of a building to obtain point cloud data, and then a simple difference method is adopted to calculate the point cloud variation of the two-stage building. However, the change detection only takes a building surface model as an object, the change information of the solid building is lacked, and the detection scale is not fine enough, which brings great difficulty to the evaluation work in the later period.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
The invention mainly aims to provide a method for extracting three-dimensional change information of a building and identifying semantics, a terminal and a computer-readable storage medium, and aims to solve the problems that change information of an entity building is lacked, and the detection scale is not fine enough, so that the evaluation of the building in the later period is inaccurate.
In order to achieve the above object, the present invention provides a method for extracting three-dimensional change information of a building and recognizing semantics, wherein the method for extracting three-dimensional change information of a building and recognizing semantics comprises the following steps:
inputting external point clouds of a two-stage building;
respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate three-dimensional solid models of the buildings in the two stages;
classifying the three-dimensional solid model of a two-stage building into an external entity and an internal entity;
and respectively carrying out change detection on the external entity and the internal entity of the two-stage building by adopting a semantic recognition method, and outputting a recognition result.
Optionally, the method for extracting three-dimensional change information of a building and recognizing semantics, wherein the two-stage building is a first-stage building before change and a second-stage building after change;
the external point cloud is point cloud data of an external facade of the building;
respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate a three-dimensional solid model, and specifically comprising the following steps:
calculating an outer bounding box of the external point cloud;
performing voxelization processing on the external point cloud, and calculating the voxel resolution;
uniformly filling point cloud data constructed by a computer in the outer bounding box according to the voxel resolution until the outer bounding box is filled;
layering the outer bounding boxes from the x direction, the y direction and the z direction according to the voxel resolution ratio, layering the three-dimensional outer bounding boxes into a plurality of two-dimensional planes, and eliminating point cloud data outside a building on each two-dimensional plane by adopting a scanning line algorithm to obtain a building point cloud with the inside filled with the point cloud;
and carrying out voxelization processing on the building point cloud to generate the three-dimensional solid model.
Optionally, the method for extracting three-dimensional change information of a building and recognizing semantics, wherein the voxelization processing is to divide a space into a plurality of voxel blocks with the same volume by a certain resolution;
the voxel resolution refers to the size of each voxel when the space is voxelized;
the calculating the voxel resolution specifically includes:
and calculating the total volume of the outer bounding box, and dividing the total volume by the number of the point clouds to obtain the voxel resolution.
Optionally, the method for extracting three-dimensional change information of a building and recognizing semantics, wherein the external entity includes: a top entity and a non-top entity;
the top entity is the roof of a building, and the non-top entity is the rest part except the roof;
the external entity is a voxel generated by building external point cloud data acquired by a photogrammetric dense matching technology;
the internal entity is a voxel generated by constructing point cloud data in the outer bounding box through a computer and carrying out voxelization processing.
Optionally, the method for extracting three-dimensional change information of a building and recognizing semantics, wherein the step of performing materialization operation on the external point clouds of the buildings in the two stages respectively to generate a three-dimensional solid model of the buildings in the two stages specifically includes:
storing the external entity and the internal entity in two different containers, respectively;
projecting the external entity from the z-axis direction to a two-dimensional plane with the ground as a reference;
extracting voxels of a first layer on the two-dimensional plane, storing the voxels in a container as the top entity of the building, and taking the remaining part of voxels as the non-top entity except the roof outside the building;
wherein the container refers to a variable used to store data in a computer programming language.
Optionally, the method for extracting three-dimensional change information of a building and recognizing semantics, wherein the method for recognizing semantics is used to detect changes of the external entity and the internal entity of a two-stage building respectively, and output a recognition result, and specifically includes:
respectively solving the difference of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, and judging the type of the change of the building;
and performing semantic recognition according to the type to obtain recognition results of change detection of the external entity and the internal entity of the two-stage building.
Optionally, the method for extracting three-dimensional change information of a building and recognizing semantics, wherein the types include: the anterior phase is absent, and the posterior phase is present; the anterior phase is present, and the posterior phase is absent; and both the front and rear time phases;
wherein, the front time phase is absent, the rear time phase is present, which indicates that the specific part of the building in the first-phase point cloud data is absent, and the specific part in the second-phase point cloud data is present;
the specific part of the building in the first-phase point cloud data is present, and the specific part in the second-phase point cloud data is absent;
the front time phase and the rear time phase are both present, and the specific part of the building exists in the first-phase point cloud data and the second-phase point cloud data;
the recognition result of the semantic recognition comprises:
top new construction, side new construction, top demolition, side demolition, unchanged, top appearance reconstruction, non-top appearance reconstruction, external overall reconstruction, top reconstruction, and side reconstruction.
Optionally, the method for extracting three-dimensional change information of the building and recognizing semantics, wherein the newly built top is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is zero, the rear time phase is present, the non-top entity is not increased, and the top entity and the internal entity are increased;
the side surface is newly built as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is zero, the rear time phase is present, the top entity is not increased, and the non-top entity and the internal entity are increased;
the top removal is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is present, the rear time phase is absent, the non-top entity is increased, and the top entity and the internal entity are reduced;
the side face dismantling is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is present, the rear time phase is absent, the top entity is increased, and the non-top entity and the internal entity are reduced;
the unchanged state is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, and a surface model is established by utilizing the external point cloud of the building, so that the textures of the surface model are completely consistent;
the top appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and only the texture of the top entity is changed;
the non-top appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and only the texture of the non-top entity is changed;
the external overall appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and the overall texture of the top entity and the non-top entity is changed;
the external whole reconstruction is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein front and rear time phases are uniform, three-dimensional geometries of external entities are not completely consistent, and the top entity and the non-top entity are changed;
the top is rebuilt as: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein front and rear time phases are uniform, three-dimensional geometries of external entities are not completely consistent, the top entity is changed, and the non-top entity is not changed;
the side surface is reconstructed as follows: the top entity, the non-top entity and the internal entity of the three-dimensional entity model of the building in the two stages are respectively subjected to difference calculation, the front time phase and the rear time phase are both identical, the three-dimensional geometry of the external entity is not completely consistent, the top entity is not changed, and the non-top entity is changed.
In addition, to achieve the above object, the present invention further provides a terminal, wherein the terminal includes: the system comprises a memory, a processor and a building three-dimensional change information extraction and semantic recognition program which is stored on the memory and can run on the processor, wherein when the processor executes the building three-dimensional change information extraction and semantic recognition program, the steps of the building three-dimensional change information extraction and semantic recognition method are realized.
In addition, in order to achieve the above object, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a building three-dimensional change information extraction and semantic recognition program, and the building three-dimensional change information extraction and semantic recognition program realizes the steps of the building three-dimensional change information extraction and semantic recognition method as described above when executed by a processor.
The invention inputs the external point cloud of the two-stage building; respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate three-dimensional solid models of the buildings in the two stages; classifying the three-dimensional solid model of a two-stage building into an external entity and an internal entity; and respectively carrying out change detection on the external entity and the internal entity of the two-stage building by adopting a semantic recognition method, and outputting a recognition result. According to the invention, the external point clouds of the buildings in the two stages are respectively converted into the three-dimensional entity models, and then the three-dimensional entity models of the buildings in the two stages are classified into the top entity, the non-top entity and the internal entity according to the semantic information so as to realize the entity model change detection based on the member, so that the accurate identification result of the entity building change information is obtained, and convenience is brought to later evaluation.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the method for extracting three-dimensional change information and recognizing semantics of a building according to the invention;
FIG. 2 is a flowchart of step S20 in the preferred embodiment of the method for extracting three-dimensional change information of a building and recognizing semantics of the present invention;
FIG. 3 is a flowchart of step S30 in the preferred embodiment of the method for extracting three-dimensional change information of a building and recognizing semantics of the present invention;
FIG. 4 is a flowchart of step S40 in the preferred embodiment of the method for extracting three-dimensional change information of a building and recognizing semantics of the present invention;
FIG. 5 is a schematic diagram of a semantic recognition change detection process in the preferred embodiment of the method for extracting three-dimensional change information of buildings and recognizing semantics according to the present invention;
FIG. 6 is a diagram illustrating an operating environment of a terminal according to a preferred embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, the method for extracting three-dimensional change information of a building and recognizing semantics according to the preferred embodiment of the present invention includes the following steps:
and step S10, inputting the external point cloud of the two-stage building.
Specifically, the two-stage buildings are a first-stage building before change and a second-stage building after change, the composition structures of the first-stage building and the second-stage building can be changed, and the invention aims to detect the change of the buildings; the external point cloud is point cloud data of an external facade of the building, for example, the external point cloud refers to point cloud data of the external facade of the building obtained by photogrammetry technology.
And step S20, respectively carrying out materialization operation on the external point clouds of the buildings at the two stages to generate three-dimensional solid models of the buildings at the two stages.
Please refer to fig. 2, which is a flowchart of step S20 in the method for extracting three-dimensional change information of a building and recognizing semantics according to the present invention.
As shown in fig. 2, the step S20 includes:
s21, calculating an outer enclosure box of the external point cloud;
s22, performing voxelization processing on the external point cloud, and calculating the voxel resolution;
s23, uniformly filling point cloud data constructed by a computer into the outer bounding box according to the voxel resolution until the outer bounding box is filled;
s24, layering the outer bounding boxes from the x direction, the y direction and the z direction respectively according to the voxel resolution, layering the three-dimensional outer bounding boxes into a plurality of two-dimensional planes, and eliminating point cloud data outside the building on each two-dimensional plane by adopting a scanning line algorithm to obtain a building point cloud filled with the point cloud inside;
and S25, performing the voxelization processing on the building point cloud to generate the three-dimensional solid model.
Specifically, an outer bounding box (bounding box) of the external point cloud of the building is calculated, the external point cloud of the building is subjected to voxelization processing, and the voxel resolution is calculated, wherein the voxelization processing refers to dividing a space into a plurality of voxel blocks with the same volume through a certain resolution; the voxel resolution refers to the size of each voxel when the space is voxelized; the calculating voxel resolution specifically comprises: and calculating the total volume of the outer bounding box (bounding box) of the point cloud group, and dividing the total volume by the number of the point clouds to obtain the voxel resolution. According to the voxel resolution calculated in the previous step, point cloud data constructed by a computer (here, the point cloud data is artificial points, namely three-dimensional points generated in space by the computer) is uniformly filled in an outer bounding box (bounding box) until the outer bounding box (bounding box) is filled. And then layering the bounding box (bounding box) from the directions of x, y and z according to voxel resolution, namely, carrying out chromatography (the chromatography refers to layering the bounding box according to a certain resolution, wherein the resolution is the voxel resolution), layering the three-dimensional bounding box (bounding box) into countless two-dimensional planes, and then removing point cloud data positioned outside the building on each two-dimensional plane by adopting a scanning line algorithm to obtain the building point cloud filled with the point cloud inside. And finally, voxelizing the building point cloud obtained in the last step to generate a three-dimensional solid model.
Step S30, classifying the three-dimensional solid model of the two-stage building into an external entity and an internal entity.
Wherein the external entity comprises: a top entity (the top entity refers to the roof of the building) and a non-top entity (the non-top entity refers to the rest of the exterior of the building except the roof); namely, the top entity is the roof of a building, and the non-top entity is the rest part except the roof; the external entity is a voxel generated by building external point cloud data acquired by a photogrammetric dense matching technology; the internal entity is a voxel generated by constructing point cloud data in the bounding box (bounding box) through a computer and performing voxelization processing.
Please refer to fig. 3, which is a flowchart of step S30 in the method for extracting three-dimensional change information of a building and recognizing semantics according to the present invention.
As shown in fig. 3, the step S30 includes:
s31, storing the external entity and the internal entity in two different containers respectively;
s32, projecting the external entity from the z-axis direction to a two-dimensional plane taking the ground as a reference;
and S33, extracting voxels of a first layer on the two-dimensional plane, storing the voxels of the first layer in a container separately to serve as the top entity of the building, wherein the remaining part of voxels are the part outside the building except the roof and are the non-top entities.
In particular, the container refers to a variable in a computer programming language that is used to store data. The internal entity and the external entity of the building entity are respectively stored in two different containers, the external entity is projected to a two-dimensional plane taking the ground as a reference from the z-axis direction, the first layer of voxels on the two-dimensional plane are extracted and are separately stored in one container to be used as the roof of the building, namely the top entity, and the rest part of voxels are the part outside the building except the roof, namely the non-top entity.
And step S40, respectively carrying out change detection on the external entity and the internal entity of the two-stage building by adopting a semantic recognition method, and outputting a recognition result.
Please refer to fig. 4, which is a flowchart of step S40 in the method for extracting three-dimensional change information of a building and recognizing semantics according to the present invention.
As shown in fig. 4, the step S40 includes:
s41, respectively calculating differences of a top entity, a non-top entity and an internal entity of the three-dimensional entity model of the two-stage building (namely, the top entity, the non-top entity and the internal entity of the first-stage building and the top entity, the non-top entity and the internal entity of the second-stage building), and judging the type of the change of the building;
and S42, performing semantic recognition according to the type to obtain recognition results of the change detection of the external entity and the internal entity of the two-stage building.
Specifically, as shown in fig. 5, the types include: the anterior phase is absent, and the posterior phase is present; the anterior phase is present, and the posterior phase is absent; and both the front and rear time phases; wherein, the front time phase is absent, the rear time phase is present, which indicates that the specific part of the building in the first-phase point cloud data is absent, and the specific part in the second-phase point cloud data is present; the specific part of the building in the first-phase point cloud data is present, and the specific part in the second-phase point cloud data is absent; the front and rear time phases are both present, which means that the specific part of the building is present in the first phase point cloud data and the second phase point cloud data.
As shown in fig. 5, the recognition result of semantic recognition includes: top new construction, side new construction, top demolition, side demolition, unchanged, top appearance reconstruction, non-top appearance reconstruction, external overall reconstruction, top reconstruction, and side reconstruction. The specific definition is as follows:
the new establishment at the top is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is zero, the rear time phase is present, the non-top entity is not increased, and the top entity and the internal entity are increased;
the side surface is newly built as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is zero, the rear time phase is present, the top entity is not increased, and the non-top entity and the internal entity are increased;
the top removal is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is present, the rear time phase is absent, the non-top entity is increased, and the top entity and the internal entity are reduced;
the side face dismantling is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is present, the rear time phase is absent, the top entity is increased, and the non-top entity and the internal entity are reduced;
the unchanged state is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, and a surface model is established by utilizing the external point cloud of the building, so that the textures of the surface model are completely consistent;
the top appearance rebuild, i.e. the top rebuild (appearance modification) in fig. 5, is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and only the texture of the top entity is changed;
the non-top appearance reconstruction, i.e. the non-top reconstruction (appearance modification) in fig. 5, is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and only the texture of the non-top entity is changed;
the external global appearance reconstruction, i.e. the external global reconstruction (appearance modification) in fig. 5, is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and the overall texture of the top entity and the non-top entity is changed;
the external whole reconstruction is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein front and rear time phases are uniform, three-dimensional geometries of external entities are not completely consistent, and the top entity and the non-top entity are changed;
the top is rebuilt as: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein front and rear time phases are uniform, three-dimensional geometries of external entities are not completely consistent, the top entity is changed, and the non-top entity is not changed;
the side surface is reconstructed as follows: the top entity, the non-top entity and the internal entity of the three-dimensional entity model of the building in the two stages are respectively subjected to difference calculation, the front time phase and the rear time phase are both identical, the three-dimensional geometry of the external entity is not completely consistent, the top entity is not changed, and the non-top entity is changed.
Further, as shown in fig. 5, the top entity, the non-top entity, and the internal entity of the three-dimensional solid model of the two-stage building are respectively subtracted (i.e., the top entity, the non-top entity, and the internal entity of the first-stage building and the top entity, the non-top entity, and the internal entity of the second-stage building are respectively subtracted), and it is determined whether the type of the building change belongs to (front time phase is absent, rear time phase is present), (front time phase is present, rear time phase is absent), or (both front and rear time phases are present).
If the non-top entity is not added, and the top entity and the internal entity are added, the identification result is newly established at the top; and when the top entity is not increased, the non-top entity and the internal entity are increased, and the recognition result is that the side face is newly built.
If the top-time-phase information belongs to (the front time phase is available, the rear time phase is unavailable), two identification results exist, and when the non-top entity is increased and the top entity and the internal entity are decreased, the identification result is that the top is removed; when the top entity is increased and the non-top entity and the internal entity are decreased, the recognition result is side detachment.
If the external entity three-dimensional geometry is completely consistent, whether the external entity three-dimensional geometry is completely consistent or not is continuously judged, if the external entity three-dimensional geometry is completely consistent, a surface model is established by using the point cloud outside the building, whether the texture of the surface model is completely consistent or not is judged, and when the texture of the surface model is completely consistent, the identification result is unchanged; when the surface model textures are not completely consistent, if the textures of the top entity (namely the top) are changed, the recognition result is top appearance reconstruction (appearance modification), if the textures of the non-top entity (namely the non-top) are changed, the recognition result is non-top appearance reconstruction (appearance modification), and if the overall textures of the top entity and the non-top entity are changed (namely the external overall texture is changed), the recognition result is external overall appearance reconstruction (appearance modification); if the three-dimensional geometry of the external entity is not completely consistent, if the top entity is changed, continuously judging whether the non-top entity is changed, if the non-top entity is changed, identifying the external entity as the whole reconstruction, and if the non-top entity is not changed, identifying the top reconstruction; and if the three-dimensional geometry of the external entity is not completely consistent, if the top entity is not changed and the non-top entity is changed, the recognition result is the side reconstruction.
The invention improves the traditional method for detecting the change based on the point cloud data outside the building, faces to a three-dimensional entity model, realizes the three-dimensional change detection and semantic identification based on components, and firstly establishes a three-dimensional entity model by utilizing the point cloud outside the building in two stages; then classifying the two-stage three-dimensional entity model into a top entity part, a non-top entity part and an internal entity part; and finally, carrying out change identification on three parts of entities of the two-stage point cloud by respectively adopting a semantic label definition method.
Further, as shown in fig. 6, based on the above method for extracting three-dimensional change information of a building and recognizing semantics, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Fig. 6 shows only some of the components of the terminal, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
The memory 20 may in some embodiments be an internal storage unit of the terminal, such as a hard disk or a memory of the terminal. The memory 20 may also be an external storage device of the terminal in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal. Further, the memory 20 may also include both an internal storage unit and an external storage device of the terminal. The memory 20 is used for storing application software installed in the terminal and various types of data, such as program codes of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 20 stores a building three-dimensional change information extraction and semantic recognition program 40, and the building three-dimensional change information extraction and semantic recognition program 40 can be executed by the processor 10, so as to implement the building three-dimensional change information extraction and semantic recognition method in the present application.
The processor 10 may be a Central Processing Unit (CPU), a microprocessor or other data Processing chip in some embodiments, and is configured to run program codes stored in the memory 20 or process data, such as performing the building three-dimensional change information extraction and semantic recognition method.
The display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch panel, or the like in some embodiments. The display 30 is used for displaying information at the terminal and for displaying a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.
In one embodiment, when the processor 10 executes the building three-dimensional change information extraction and semantic recognition program 40 in the memory 20, the following steps are implemented:
inputting external point clouds of a two-stage building;
respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate three-dimensional solid models of the buildings in the two stages;
classifying the three-dimensional solid model of a two-stage building into an external entity and an internal entity;
and respectively carrying out change detection on the external entity and the internal entity of the two-stage building by adopting a semantic recognition method, and outputting a recognition result.
Wherein the two-stage buildings are a first-stage building before change and a second-stage building after change;
the external point cloud is point cloud data of an external facade of the building;
respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate a three-dimensional solid model, and specifically comprising the following steps:
calculating an outer bounding box of the external point cloud;
performing voxelization processing on the external point cloud, and calculating the voxel resolution;
uniformly filling point cloud data constructed by a computer in the outer bounding box according to the voxel resolution until the outer bounding box is filled;
layering the outer bounding boxes from the x direction, the y direction and the z direction according to the voxel resolution ratio, layering the three-dimensional outer bounding boxes into a plurality of two-dimensional planes, and eliminating point cloud data outside a building on each two-dimensional plane by adopting a scanning line algorithm to obtain a building point cloud with the inside filled with the point cloud;
and carrying out voxelization processing on the building point cloud to generate the three-dimensional solid model.
The voxelization processing refers to dividing a space by a certain resolution, and dividing the space into a plurality of voxel blocks with the same volume;
the voxel resolution refers to the size of each voxel when the space is voxelized;
the calculating the voxel resolution specifically includes:
and calculating the total volume of the outer bounding box, and dividing the total volume by the number of the point clouds to obtain the voxel resolution.
Wherein the external entity comprises: a top entity and a non-top entity;
the top entity is the roof of a building, and the non-top entity is the rest part except the roof;
the external entity is a voxel generated by building external point cloud data acquired by a photogrammetric dense matching technology;
the internal entity is a voxel generated by constructing point cloud data in the outer bounding box through a computer and carrying out voxelization processing.
The method comprises the following steps of respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate a three-dimensional solid model of the buildings in the two stages, and specifically comprises the following steps:
storing the external entity and the internal entity in two different containers, respectively;
projecting the external entity from the z-axis direction to a two-dimensional plane with the ground as a reference;
extracting voxels of a first layer on the two-dimensional plane, storing the voxels in a container as the top entity of the building, and taking the remaining part of voxels as the non-top entity except the roof outside the building;
wherein the container refers to a variable used to store data in a computer programming language.
The method for semantic recognition is used for respectively detecting changes of the external entity and the internal entity of the two-stage building and outputting recognition results, and specifically comprises the following steps:
respectively solving the difference of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, and judging the type of the change of the building;
and performing semantic recognition according to the type to obtain recognition results of change detection of the external entity and the internal entity of the two-stage building.
Wherein the types include: the anterior phase is absent, and the posterior phase is present; the anterior phase is present, and the posterior phase is absent; and both the front and rear time phases;
wherein, the front time phase is absent, the rear time phase is present, which indicates that the specific part of the building in the first-phase point cloud data is absent, and the specific part in the second-phase point cloud data is present;
the specific part of the building in the first-phase point cloud data is present, and the specific part in the second-phase point cloud data is absent;
the front time phase and the rear time phase are both present, and the specific part of the building exists in the first-phase point cloud data and the second-phase point cloud data;
the recognition result of the semantic recognition comprises:
top new construction, side new construction, top demolition, side demolition, unchanged, top appearance reconstruction, non-top appearance reconstruction, external overall reconstruction, top reconstruction, and side reconstruction.
Wherein, the new establishment in top is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is zero, the rear time phase is present, the non-top entity is not increased, and the top entity and the internal entity are increased;
the side surface is newly built as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is zero, the rear time phase is present, the top entity is not increased, and the non-top entity and the internal entity are increased;
the top removal is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is present, the rear time phase is absent, the non-top entity is increased, and the top entity and the internal entity are reduced;
the side face dismantling is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is present, the rear time phase is absent, the top entity is increased, and the non-top entity and the internal entity are reduced;
the unchanged state is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, and a surface model is established by utilizing the external point cloud of the building, so that the textures of the surface model are completely consistent;
the top appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and only the texture of the top entity is changed;
the non-top appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and only the texture of the non-top entity is changed;
the external overall appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and the overall texture of the top entity and the non-top entity is changed;
the external whole reconstruction is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein front and rear time phases are uniform, three-dimensional geometries of external entities are not completely consistent, and the top entity and the non-top entity are changed;
the top is rebuilt as: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein front and rear time phases are uniform, three-dimensional geometries of external entities are not completely consistent, the top entity is changed, and the non-top entity is not changed;
the side surface is reconstructed as follows: the top entity, the non-top entity and the internal entity of the three-dimensional entity model of the building in the two stages are respectively subjected to difference calculation, the front time phase and the rear time phase are both identical, the three-dimensional geometry of the external entity is not completely consistent, the top entity is not changed, and the non-top entity is changed.
The invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a building three-dimensional change information extraction and semantic recognition program, and the building three-dimensional change information extraction and semantic recognition program realizes the steps of the building three-dimensional change information extraction and semantic recognition method when being executed by a processor.
In summary, the present invention provides a method and a terminal for extracting three-dimensional change information of a building and recognizing semantics, wherein the method comprises: inputting external point clouds of a two-stage building; respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate three-dimensional solid models of the buildings in the two stages; classifying the three-dimensional solid model of a two-stage building into an external entity and an internal entity; and respectively carrying out change detection on the external entity and the internal entity of the two-stage building by adopting a semantic recognition method, and outputting a recognition result. According to the invention, the external point clouds of the buildings in the two stages are respectively converted into the three-dimensional entity models, and then the three-dimensional entity models of the buildings in the two stages are classified into the top entity, the non-top entity and the internal entity according to the semantic information so as to realize the entity model change detection based on the member, so that the accurate identification result of the entity building change information is obtained, and convenience is brought to later evaluation.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Of course, it will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer readable storage medium, and when executed, the program can include the processes of the embodiments of the methods described above. The computer readable storage medium may be a memory, a magnetic disk, an optical disk, etc.
It is to be understood that the invention is not limited to the examples described above, but that modifications and variations may be effected thereto by those of ordinary skill in the art in light of the foregoing description, and that all such modifications and variations are intended to be within the scope of the invention as defined by the appended claims.

Claims (10)

1. A method for extracting three-dimensional change information of a building and recognizing semantics is characterized by comprising the following steps:
inputting external point clouds of a two-stage building;
respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate three-dimensional solid models of the buildings in the two stages;
classifying the three-dimensional solid model of a two-stage building into an external entity and an internal entity;
and respectively carrying out change detection on the external entity and the internal entity of the two-stage building by adopting a semantic recognition method, and outputting a recognition result.
2. The method for extracting three-dimensional change information of a building and recognizing semantics as claimed in claim 1, wherein the two-stage buildings are a first-stage building before change and a second-stage building after change;
the external point cloud is point cloud data of an external facade of the building;
respectively carrying out materialization operation on the external point clouds of the buildings in the two stages to generate a three-dimensional solid model, and specifically comprising the following steps:
calculating an outer bounding box of the external point cloud;
performing voxelization processing on the external point cloud, and calculating the voxel resolution;
uniformly filling point cloud data constructed by a computer in the outer bounding box according to the voxel resolution until the outer bounding box is filled;
layering the outer bounding boxes from the x direction, the y direction and the z direction according to the voxel resolution ratio, layering the three-dimensional outer bounding boxes into a plurality of two-dimensional planes, and eliminating point cloud data outside a building on each two-dimensional plane by adopting a scanning line algorithm to obtain a building point cloud with the inside filled with the point cloud;
and carrying out voxelization processing on the building point cloud to generate the three-dimensional solid model.
3. The method for extracting three-dimensional change information of a building and recognizing semantics as claimed in claim 2, wherein the voxelization processing is to divide a space into a plurality of voxel blocks having the same volume by a certain resolution;
the voxel resolution refers to the size of each voxel when the space is voxelized;
the calculating the voxel resolution specifically includes:
and calculating the total volume of the outer bounding box, and dividing the total volume by the number of the point clouds to obtain the voxel resolution.
4. The method for extracting and semantically recognizing three-dimensional building change information according to claim 2, wherein the external entity comprises: a top entity and a non-top entity;
the top entity is the roof of a building, and the non-top entity is the rest part except the roof;
the external entity is a voxel generated by building external point cloud data acquired by a photogrammetric dense matching technology;
the internal entity is a voxel generated by constructing point cloud data in the outer bounding box through a computer and carrying out voxelization processing.
5. The method for extracting three-dimensional change information of a building and recognizing semantics as claimed in claim 4, wherein the step of respectively performing materialization operation on the external point clouds of the buildings in two stages to generate a three-dimensional solid model of the buildings in two stages specifically comprises:
storing the external entity and the internal entity in two different containers, respectively;
projecting the external entity from the z-axis direction to a two-dimensional plane with the ground as a reference;
extracting voxels of a first layer on the two-dimensional plane, storing the voxels in a container as the top entity of the building, and taking the remaining part of voxels as the non-top entity except the roof outside the building;
wherein the container refers to a variable used to store data in a computer programming language.
6. The method for extracting three-dimensional change information of a building and recognizing semantics as claimed in claim 5, wherein the method for recognizing semantics is used for respectively detecting changes of the external entity and the internal entity of the two-stage building and outputting a recognition result, and specifically comprises:
respectively solving the difference of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, and judging the type of the change of the building;
and performing semantic recognition according to the type to obtain recognition results of change detection of the external entity and the internal entity of the two-stage building.
7. The method for extracting and semantically recognizing three-dimensional change information of buildings according to claim 6, wherein said types include: the anterior phase is absent, and the posterior phase is present; the anterior phase is present, and the posterior phase is absent; and both the front and rear time phases;
wherein, the front time phase is absent, the rear time phase is present, which indicates that the specific part of the building in the first-phase point cloud data is absent, and the specific part in the second-phase point cloud data is present;
the specific part of the building in the first-phase point cloud data is present, and the specific part in the second-phase point cloud data is absent;
the front time phase and the rear time phase are both present, and the specific part of the building exists in the first-phase point cloud data and the second-phase point cloud data;
the recognition result of the semantic recognition comprises:
top new construction, side new construction, top demolition, side demolition, unchanged, top appearance reconstruction, non-top appearance reconstruction, external overall reconstruction, top reconstruction, and side reconstruction.
8. The method for extracting three-dimensional change information of buildings and recognizing semantics of claim 7 is characterized in that the top new construction is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is zero, the rear time phase is present, the non-top entity is not increased, and the top entity and the internal entity are increased;
the side surface is newly built as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is zero, the rear time phase is present, the top entity is not increased, and the non-top entity and the internal entity are increased;
the top removal is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is present, the rear time phase is absent, the non-top entity is increased, and the top entity and the internal entity are reduced;
the side face dismantling is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase is present, the rear time phase is absent, the top entity is increased, and the non-top entity and the internal entity are reduced;
the unchanged state is: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, and a surface model is established by utilizing the external point cloud of the building, so that the textures of the surface model are completely consistent;
the top appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and only the texture of the top entity is changed;
the non-top appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and only the texture of the non-top entity is changed;
the external overall appearance is reconstructed as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein the front time phase and the rear time phase are the same, the three-dimensional geometry of the external entity is completely consistent, a surface model is established by utilizing the external point cloud of the building, and the overall texture of the top entity and the non-top entity is changed;
the external whole reconstruction is as follows: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein front and rear time phases are uniform, three-dimensional geometries of external entities are not completely consistent, and the top entity and the non-top entity are changed;
the top is rebuilt as: respectively solving differences of a top entity, a non-top entity and an internal entity of a three-dimensional entity model of a two-stage building, wherein front and rear time phases are uniform, three-dimensional geometries of external entities are not completely consistent, the top entity is changed, and the non-top entity is not changed;
the side surface is reconstructed as follows: the top entity, the non-top entity and the internal entity of the three-dimensional entity model of the building in the two stages are respectively subjected to difference calculation, the front time phase and the rear time phase are both identical, the three-dimensional geometry of the external entity is not completely consistent, the top entity is not changed, and the non-top entity is changed.
9. A terminal, characterized in that the terminal comprises: a memory, a processor and a building three-dimensional change information extraction and semantic recognition program stored on the memory and operable on the processor, the building three-dimensional change information extraction and semantic recognition program when executed by the processor implementing the steps of the building three-dimensional change information extraction and semantic recognition method according to any one of claims 1-8.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores a building three-dimensional change information extraction and semantic recognition program, and the building three-dimensional change information extraction and semantic recognition program, when executed by a processor, implements the steps of the building three-dimensional change information extraction and semantic recognition method according to any one of claims 1 to 8.
CN202110059451.2A 2021-01-18 2021-01-18 Method and terminal for extracting three-dimensional change information of building and recognizing semantics Active CN112381947B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110059451.2A CN112381947B (en) 2021-01-18 2021-01-18 Method and terminal for extracting three-dimensional change information of building and recognizing semantics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110059451.2A CN112381947B (en) 2021-01-18 2021-01-18 Method and terminal for extracting three-dimensional change information of building and recognizing semantics

Publications (2)

Publication Number Publication Date
CN112381947A true CN112381947A (en) 2021-02-19
CN112381947B CN112381947B (en) 2021-05-04

Family

ID=74581957

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110059451.2A Active CN112381947B (en) 2021-01-18 2021-01-18 Method and terminal for extracting three-dimensional change information of building and recognizing semantics

Country Status (1)

Country Link
CN (1) CN112381947B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112712596A (en) * 2021-03-29 2021-04-27 深圳大学 Dense matching point cloud building structured model fine reconstruction method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105869165A (en) * 2016-03-29 2016-08-17 中国科学院自动化研究所 Object varying monitoring method of multi-source and multi-temporal remote sensing image
US20170104154A1 (en) * 2015-10-08 2017-04-13 SK Hynix Inc. Variable resistive memory device having a phase change structure and method of manufacturing the same
US10275689B1 (en) * 2017-12-21 2019-04-30 Luminar Technologies, Inc. Object identification and labeling tool for training autonomous vehicle controllers
US10748247B2 (en) * 2017-12-26 2020-08-18 Facebook, Inc. Computing high-resolution depth images using machine learning techniques
CN111738329A (en) * 2020-06-19 2020-10-02 中南大学 Land use classification method for time series remote sensing images

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170104154A1 (en) * 2015-10-08 2017-04-13 SK Hynix Inc. Variable resistive memory device having a phase change structure and method of manufacturing the same
CN105869165A (en) * 2016-03-29 2016-08-17 中国科学院自动化研究所 Object varying monitoring method of multi-source and multi-temporal remote sensing image
US10275689B1 (en) * 2017-12-21 2019-04-30 Luminar Technologies, Inc. Object identification and labeling tool for training autonomous vehicle controllers
US10748247B2 (en) * 2017-12-26 2020-08-18 Facebook, Inc. Computing high-resolution depth images using machine learning techniques
CN111738329A (en) * 2020-06-19 2020-10-02 中南大学 Land use classification method for time series remote sensing images

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
周梦蝶: "融合影像匹配点云的机载LiDAR点云分类", 《中国优秀硕士学位论文全文数据库 基础科学辑》 *
柴路嘉: "基于影像点云的城市建筑物变化检测研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112712596A (en) * 2021-03-29 2021-04-27 深圳大学 Dense matching point cloud building structured model fine reconstruction method

Also Published As

Publication number Publication date
CN112381947B (en) 2021-05-04

Similar Documents

Publication Publication Date Title
JP6745328B2 (en) Method and apparatus for recovering point cloud data
Lin et al. Semantic decomposition and reconstruction of residential scenes from LiDAR data
Dick et al. Modelling and interpretation of architecture from several images
CN101944239B (en) Three-dimensional model dividing method, device and comprise the image processing system of this device
CN107464286B (en) Method, device, equipment and readable medium for repairing holes in three-dimensional city model
KR101626384B1 (en) Apparatus and method for search of 3d model data
Hohmann et al. CityFit-High-quality urban reconstructions by fitting shape grammars to images and derived textured point clouds
KR102620835B1 (en) CityGML-based building object information generation method using 3D geometric object information, building object information generation system, and computer program therefor
US8587586B2 (en) Electronic device and method for meshing curved surface
CN112381947B (en) Method and terminal for extracting three-dimensional change information of building and recognizing semantics
Bauchet et al. City reconstruction from airborne LiDAR: A computational geometry approach
Han Implementation of file-referring octree for huge 3D point clouds
CN116912817A (en) Three-dimensional scene model splitting method and device, electronic equipment and storage medium
CN114821055A (en) House model construction method and device, readable storage medium and electronic equipment
Namouchi et al. Piecewise horizontal 3d roof reconstruction from aerial lidar
CN113688261B (en) Image data cleaning method and device, electronic equipment and readable storage medium
CN111199086A (en) Three-dimensional geometric discretization processing system
CN115588082A (en) Method, device and equipment for displaying space digital model in real time and storage medium
CN115327553A (en) Rapid laser radar sample generation method for inducing variation
CN115527000A (en) Method and device for batch singularization of oblique photography models of unmanned aerial vehicle
CN115423852A (en) Point cloud data registration method and system, electronic device and storage medium
US11281935B2 (en) 3D object detection from calibrated 2D images
CN108151712B (en) Human body three-dimensional modeling and measuring method and system
KR100782152B1 (en) Method for obtaining 3-dimensional building data from aerial photograph db
CN112417924A (en) Method and device for acquiring space coordinates of marker post

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
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Chongqing Taihuo Xinniao Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026159

Denomination of invention: A Method and Terminal for Building 3D Change Information Extraction and Semantic Recognition

Granted publication date: 20210504

License type: Common License

Record date: 20221211

Application publication date: 20210219

Assignee: SHENZHEN MIGOU NETWORK TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026323

Denomination of invention: A Method and Terminal for Building 3D Change Information Extraction and Semantic Recognition

Granted publication date: 20210504

License type: Common License

Record date: 20221212

Application publication date: 20210219

Assignee: Shenzhen No.7 Network Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026329

Denomination of invention: A Method and Terminal for Building 3D Change Information Extraction and Semantic Recognition

Granted publication date: 20210504

License type: Common License

Record date: 20221212

Application publication date: 20210219

Assignee: Shenzhen Bangqi Technology Innovation Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026142

Denomination of invention: A Method and Terminal for Building 3D Change Information Extraction and Semantic Recognition

Granted publication date: 20210504

License type: Common License

Record date: 20221211

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Shenzhen Henghaojian Engineering Project Management Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026608

Denomination of invention: A Method and Terminal for Building 3D Change Information Extraction and Semantic Recognition

Granted publication date: 20210504

License type: Common License

Record date: 20221212

Application publication date: 20210219

Assignee: Shenzhen Guangsheng Curtain Wall Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026602

Denomination of invention: A Method and Terminal for Building 3D Change Information Extraction and Semantic Recognition

Granted publication date: 20210504

License type: Common License

Record date: 20221212

EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Beijing Taiflamingo Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026674

Denomination of invention: A method and terminal for building 3D change information extraction and semantic recognition

Granted publication date: 20210504

License type: Common License

Record date: 20230111

Application publication date: 20210219

Assignee: SHENZHEN ZHONGZHI INVESTMENT CO.,LTD.

Assignor: SHENZHEN University

Contract record no.: X2022980026718

Denomination of invention: A method and terminal for building 3D change information extraction and semantic recognition

Granted publication date: 20210504

License type: Common License

Record date: 20230109

Application publication date: 20210219

Assignee: Shenzhen wanrunda Industrial Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026651

Denomination of invention: A method and terminal for building 3D change information extraction and semantic recognition

Granted publication date: 20210504

License type: Common License

Record date: 20230111

Application publication date: 20210219

Assignee: Shenzhen Fengge Industrial Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026712

Denomination of invention: A method and terminal for building 3D change information extraction and semantic recognition

Granted publication date: 20210504

License type: Common License

Record date: 20230110

Application publication date: 20210219

Assignee: Guangdong Zhongke Huiju Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026706

Denomination of invention: A method and terminal for building 3D change information extraction and semantic recognition

Granted publication date: 20210504

License type: Common License

Record date: 20230110

Application publication date: 20210219

Assignee: Shenzhen Search Industry Operation Service Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026696

Denomination of invention: A method and terminal for building 3D change information extraction and semantic recognition

Granted publication date: 20210504

License type: Common License

Record date: 20230110

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Chongqing Taihuo Xinniao Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2022980026805

Denomination of invention: A method and terminal for building 3D change information extraction and semantic recognition

Granted publication date: 20210504

License type: Common License

Record date: 20230116

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Shenzhen Xinghu Decoration Technology Development Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980033774

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20230317

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: SHENZHEN YIBU ZHIZAO TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980034077

Denomination of invention: A Method and Terminal for Extracting and Semantic Recognition of Building 3D Change Information

Granted publication date: 20210504

License type: Common License

Record date: 20230324

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Lishui Taihuo Red Bird Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980034588

Denomination of invention: A Method and Terminal for Extracting and Semantic Recognition of Building 3D Change Information

Granted publication date: 20210504

License type: Common License

Record date: 20230411

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Shenzhen Yingqi Consulting Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980047348

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231116

Application publication date: 20210219

Assignee: Shenzhen Minghua Trading Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980047346

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231116

Application publication date: 20210219

Assignee: Shenzhen Dongfang Huilian Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980047336

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231116

Application publication date: 20210219

Assignee: Shenzhen Weigao Investment Development Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980047270

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231116

Application publication date: 20210219

Assignee: Shenzhen Pengyang Smart Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980047146

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231115

Application publication date: 20210219

Assignee: Shenzhen Zhenbing intelligent Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980047136

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231115

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Shenzhen Xunming Trading Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980047343

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231116

Application publication date: 20210219

Assignee: Shenzhen Haocai Digital Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980047340

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231116

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Weiyi Design (Shenzhen) Group Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980048290

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231123

Application publication date: 20210219

Assignee: Foshan Point to Intelligent Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980048054

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231123

Application publication date: 20210219

Assignee: Shenzhen Xinsheng interconnected technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980048035

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231123

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: SHENZHEN GRANDLAND FANGTE TECHNOLOGY CONSTRUCTION GROUP Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980048543

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231127

Application publication date: 20210219

Assignee: Guangdong Tongbo Information Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980048453

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231127

Application publication date: 20210219

Assignee: Shiyun Technology (Shenzhen) Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980048351

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231127

Application publication date: 20210219

Assignee: Huizhou Dabaihui Modern Fisheries Application Research Institute

Assignor: SHENZHEN University

Contract record no.: X2023980048341

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231128

EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Shenzhen Tianyi Survey Engineering Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049540

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231201

Application publication date: 20210219

Assignee: Shenzhen Guangfeng Hongye Engineering Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049510

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231201

Application publication date: 20210219

Assignee: Shenzhen Fulongsheng Industrial Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049215

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231130

Application publication date: 20210219

Assignee: Shenzhen Dechangsheng Electromechanical Decoration Engineering Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049197

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231130

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Shenzhen Jinchengyu Decoration Engineering Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980050232

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231205

Application publication date: 20210219

Assignee: Shenzhen Weitai Building Materials Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049901

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231204

Application publication date: 20210219

Assignee: Shenzhen Yajun Decoration Design Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049899

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231204

Application publication date: 20210219

Assignee: Shenzhen Yijia Construction Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049897

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231204

Application publication date: 20210219

Assignee: Shenzhen Yongji Construction Engineering Inspection Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049891

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231204

Application publication date: 20210219

Assignee: Zhenfeng Decoration Design Engineering (Shenzhen) Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980049887

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231204

EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Shenzhen Sanqi Zhilian Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980051156

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231208

Application publication date: 20210219

Assignee: SHENZHEN HUA,ANTAI INTELLIGENT & TECHNOLOGY Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980050859

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231208

Application publication date: 20210219

Assignee: Shenzhen Origin Innovation Investment Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980050851

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231208

Application publication date: 20210219

Assignee: Shenzhen Haiwei Hengtai Intelligent Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980050506

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231207

Application publication date: 20210219

Assignee: Shenzhen Ruisheng Engineering Research Institute Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980050487

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231207

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Shenzhen Shuimu Classic Culture Communication Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980052475

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231214

Application publication date: 20210219

Assignee: Shenzhen Yangxin Decoration Engineering Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980052132

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231213

Application publication date: 20210219

Assignee: Shenzhen Yuanlian Digital Intelligence Technology Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980052126

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231213

EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: Guangdong Weihao Construction Engineering Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980053730

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231222

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: AVIC intelligent construction (Shenzhen) Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2023980054566

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20231228

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210219

Assignee: SHENZHEN HONGHUI INDUSTRIAL Co.,Ltd.

Assignor: SHENZHEN University

Contract record no.: X2024980000463

Denomination of invention: A method and terminal for extracting three-dimensional change information and semantic recognition of buildings

Granted publication date: 20210504

License type: Common License

Record date: 20240110