CN115761138A - Three-dimensional house model determining method and device, electronic equipment and storage medium - Google Patents
Three-dimensional house model determining method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115761138A CN115761138A CN202211493718.XA CN202211493718A CN115761138A CN 115761138 A CN115761138 A CN 115761138A CN 202211493718 A CN202211493718 A CN 202211493718A CN 115761138 A CN115761138 A CN 115761138A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- model
- determining
- missing
- color information
- 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.)
- Pending
Links
Images
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention provides a method and a device for determining a three-dimensional house model, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, wherein the method comprises the following steps: acquiring three-dimensional point cloud data under at least two visual angles of a target space, wherein the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space; performing three-dimensional modeling based on the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to a target space; deleting three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model under the condition that at least one obstacle exists in the initial three-dimensional model to obtain a three-dimensional missing model; and determining target color information in a threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain the three-dimensional house model. The invention can realize the rapid determination of the three-dimensional house model and the house information, reduce manpower and material resources and improve the user experience.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for determining a three-dimensional house model, electronic equipment and a storage medium.
Background
At present, in the field of renting agents or real estate sales, the acquisition of house information, such as the current house display, the house area measurement, and the like, is mainly performed in a manual manner, for example: sampling and displaying are carried out through shooting equipment, measurement is carried out by using measuring tools such as a measuring tape and a painting brush, and even special drawing personnel are required to intervene to obtain relevant information of a room. However, the above method greatly increases labor costs and time costs when determining house information.
Disclosure of Invention
The invention provides a method and a device for determining a three-dimensional house model, electronic equipment and a storage medium, which are used for solving the defects of high labor cost and time cost for determining house information in the prior art, realizing the rapid determination of the three-dimensional house model and the house information, reducing manpower and material resources and improving the user experience.
The invention provides a method for determining a three-dimensional house model, which comprises the following steps:
acquiring three-dimensional point cloud data under at least two visual angles of a target space, wherein the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space;
performing three-dimensional modeling based on the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space;
under the condition that at least one obstacle exists in the initial three-dimensional model, deleting three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model to obtain a three-dimensional missing model, wherein the obstacle is an object for shielding a boundary line of the target space;
and determining target color information within a threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain a three-dimensional house model, wherein the missing pixel point lacks color information.
According to the method for determining the three-dimensional house model provided by the invention, the step of determining the target color information in the threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain the three-dimensional house model comprises the following steps:
determining at least one plane view based on the three-dimensional missing model under the condition that the three-dimensional missing model has at least one missing pixel point, wherein the plane view has at least one missing pixel point;
determining a missing boundary of the plane view, wherein the missing boundary divides the plane view into a missing region and a complete region, and at least one missing pixel point exists in the missing region;
determining target color information corresponding to the pixel points within the threshold range of the missing pixel points;
and determining the target color information as the color information of the missing pixel point.
According to the method for determining the three-dimensional house model, the step of determining the target color information corresponding to the pixel point in the threshold range of the missing pixel point comprises the following steps:
and under the condition that the color information in the complete area is consistent, determining the color information of any one pixel point in the complete area as target color information.
According to the method for determining the three-dimensional house model provided by the invention, the step of determining the target color information corresponding to the pixel point in the threshold range of the missing pixel point further comprises the following steps:
determining a first color change boundary where color information changes in the full area in a case where there is a change in the color information in the full area;
predicting a second color change boundary of the first color change boundary extending to the missing region based on the shape characteristics corresponding to the first color change boundary and the first color change boundary;
determining a threshold range corresponding to each missing pixel point based on the first color change boundary and the second color change boundary;
and determining the color information of each pixel point in the threshold range as target color information.
According to the three-dimensional house model determining method provided by the invention, the three-dimensional point cloud data comprises three-dimensional coordinate values, color information and reflection intensity;
the method for acquiring the three-dimensional point cloud data under at least two visual angles of the target space further comprises the following steps:
converting coordinate systems corresponding to the three-dimensional point cloud data under the visual angles into the same world coordinate system;
determining a target three-dimensional coordinate value corresponding to each three-dimensional point cloud data in the world coordinate system;
determining the difference between the target three-dimensional coordinate values corresponding to two adjacent three-dimensional point cloud data and the actual distance corresponding to two adjacent three-dimensional point cloud data in the target space;
and determining the conversion ratio of the three-dimensional house model and the target space based on the ratio of the difference of the target three-dimensional coordinate values to the actual distance.
According to the three-dimensional house model determining method provided by the invention, the method further comprises the following steps:
under the condition that the three-dimensional house model is determined, determining a three-dimensional sub model corresponding to the house configuration component in scanning equipment;
determining an operation instruction based on the scanning hand action of the scanning equipment;
and matching the three-dimensional house model based on the operation instruction and the three-dimensional sub-model to obtain a three-dimensional design model.
According to the three-dimensional house model determining method provided by the invention, the method further comprises the following steps:
determining a house plane house type graph and a measurement area corresponding to the house plane house type graph based on the three-dimensional house model;
and switching and displaying the house plane house type graph, the measuring area, the three-dimensional house model and the three-dimensional design model.
The present invention also provides a three-dimensional house model determining apparatus, including:
the system comprises an acquisition module, a detection module and a display module, wherein the acquisition module is used for acquiring three-dimensional point cloud data under at least two visual angles of a target space, and the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space;
the modeling module is used for carrying out three-dimensional modeling on the basis of the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space;
the determining module is used for deleting the three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model under the condition that at least one obstacle exists in the initial three-dimensional model to obtain a three-dimensional missing model, wherein the obstacle is an object for shielding a boundary line of the target space;
and the color filling module is used for determining target color information in a threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain a three-dimensional house model, wherein the missing pixel point lacks color information.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor executes the program to implement the three-dimensional house model determining method according to any one of the above.
The invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of determining a three-dimensional house model as described in any one of the above.
According to the three-dimensional house model determining method, the three-dimensional house model determining device, the electronic equipment and the storage medium, the space range and the object outline of the target space are determined by obtaining the three-dimensional point cloud data corresponding to the target space, the three-dimensional modeling is carried out through the three-dimensional point cloud data to obtain the initial three-dimensional model, the three-dimensional point cloud data corresponding to at least one obstacle which shields the boundary line of the target space in the initial three-dimensional model is deleted, the missing pixel points are filled with the target color information in the threshold range of the missing pixel points, the complete three-dimensional house model is obtained, the house information is rapidly determined, manpower and material resources are saved, and the display effect of the three-dimensional house model and the experience of a user are improved while the accuracy of rapid measurement of the target space is ensured.
Drawings
In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart of a method for determining a three-dimensional house model according to the present invention;
FIG. 2 is one of the exemplary diagrams of color fill provided by the present invention;
FIG. 3 is a second exemplary illustration of color fill provided by the present invention;
FIG. 4 is a schematic structural diagram of a three-dimensional house model determining apparatus provided by the present invention;
fig. 5 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Aiming at the problems of large labor cost and time cost and low efficiency in determining house information in the prior art, the embodiment of the invention provides a three-dimensional house model determining method, fig. 1 is a flow schematic diagram of the three-dimensional house model determining method provided by the invention, and as shown in fig. 1, the method comprises the following steps:
and 110, acquiring three-dimensional point cloud data under at least two visual angles of a target space, wherein the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space.
And 120, performing three-dimensional modeling based on the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space.
And step 130, under the condition that at least one obstacle exists in the initial three-dimensional model, deleting the three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model to obtain a three-dimensional missing model, wherein the obstacle is an object for shielding a boundary line of the target space.
Specifically, in the prior art, the efficiency of acquiring the house information through the traditional measuring tool is low, and the investment of labor cost and time cost is high, so in the embodiment of the invention, the target space can be scanned in multiple visual angles by wearing the AR glasses, the target space and objects in the target space are labeled based on the three-dimensional point cloud technology to obtain a plurality of three-dimensional point cloud data, and the more visual angle pictures obtained by scanning are, the more accurate the three-dimensional model obtained when the three-dimensional modeling is performed on the target space is. Meanwhile, after the three-dimensional modeling is carried out through the three-dimensional point cloud data, and after the initial three-dimensional model is determined, the boundary lines of the target space may be shielded by obstacles in the target space, and the efficiency and the accuracy of the target space measurement are further influenced.
It should be noted that, in a single-view-angle picture, the data amount of three-dimensional point cloud labeling is small, and the error rate is high, so that when a target space is scanned, the more view-angle pictures are obtained by scanning, the more labeling data are obtained, and the more accurate the initial three-dimensional model obtained by modeling is, and the more practical the model is.
Optionally, the laser radar ray is emitted to the surface of an object in the target space, the three-dimensional point cloud data is obtained through reflection of the surface of the object, the spatial range in the target space is determined through three-dimensional coordinate values in the three-dimensional point cloud data under different viewing angles, and the contour of the object in the target space is further obtained through rendering according to the density of the three-dimensional point cloud data.
Optionally, after obtaining the three-dimensional point cloud data, the obtained three-dimensional point cloud data may be input into modeling software, and an initial three-dimensional model corresponding to the target space is automatically generated, where the modeling software may be: autoCAD, three-dimensional MAX, arcGIS, maya, to which embodiments of the present invention are not limited.
Optionally, the obstacle may be a home device in the target space, and the home device blocks a boundary line in the target space, which affects measurement of the target space. The household equipment can be a sofa, a table, a tea table and the like.
Optionally, the three-dimensional point cloud data comprises three-dimensional coordinate values, color information and reflection intensity;
the method for acquiring the three-dimensional point cloud data under at least two visual angles of the target space further comprises the following steps:
converting coordinate systems corresponding to the three-dimensional point cloud data under the visual angles into the same world coordinate system;
determining a target three-dimensional coordinate value corresponding to each three-dimensional point cloud data in the world coordinate system;
determining the difference between the target three-dimensional coordinate values corresponding to two adjacent three-dimensional point cloud data and the actual distance corresponding to two adjacent three-dimensional point cloud data in the target space;
and determining the conversion ratio of the three-dimensional house model and the target space based on the ratio of the difference of the target three-dimensional coordinate values to the actual distance.
Specifically, a three-dimensional coordinate system is established at each view angle, so that three-dimensional coordinate values of three-dimensional point cloud data at corresponding view angles in the three-dimensional coordinate system are obtained, in order to facilitate measurement of a house, after the three-dimensional point cloud data are obtained, different three-dimensional coordinate systems are converted to the same world coordinate system, the three-dimensional coordinate values corresponding to the three-dimensional point cloud data are converted to obtain target three-dimensional coordinate values, and meanwhile, the conversion proportion of a three-dimensional house model and a target space is determined by determining the difference between the target coordinate values corresponding to two adjacent three-dimensional point cloud data and the actual distance in the house.
Alternatively, the color information may be RGB colors, i.e., colors representing three channels of Red (Red), green (Green), and Blue (Blue). Colors can also be characterized for HIS mode colors, i.e. by three basic characteristic quantities, hue (Hue), saturation (Saturation) and brightness (Intensity). But may also be grey scale values.
Optionally, when the three-dimensional coordinate system is converted, a top view of the initial three-dimensional model is determined, a position corresponding to an origin of a coordinate system in each three-dimensional coordinate system is marked in the top view, the origin of the world coordinate system is determined in the target space, each three-dimensional coordinate system is converted into the world coordinate system according to a position relationship between the origin of the coordinate system and the origin of the world coordinate system, each three-dimensional coordinate value is further converted into the world coordinate system, and then the target three-dimensional coordinate value is obtained.
Optionally, the determining target color information within a threshold range of at least one missing pixel in the three-dimensional missing model, and filling each missing pixel based on the target color information to obtain a three-dimensional house model includes:
under the condition that the three-dimensional missing model has at least one missing pixel point, determining at least one plane view based on the three-dimensional missing model, wherein the plane view has at least one missing pixel point;
determining a missing boundary of the plane view, wherein the missing boundary divides the plane view into a missing region and a complete region, and at least one missing pixel point exists in the missing region;
determining target color information corresponding to the pixel points within the threshold range of the missing pixel points;
and determining the target color information as the color information of the missing pixel points.
Specifically, if an obstacle exists in the initial three-dimensional model, the initial three-dimensional model is divided in the direction of six views, that is, internal six views, such as an internal front view, an internal back view, an internal left view, an internal right view, an internal top view and an internal bottom view, are obtained from the inside of the initial three-dimensional model, at least one internal view corresponding to a missing pixel point lacking color information exists in the internal six views is further determined, and the internal view is further determined as a plane view, wherein color information exists in a part of regions in the plane view, and is called as a complete region, and color information does not exist in the other part of regions, and is called as a missing region. Furthermore, target color information within a threshold range of the missing pixel points in the missing region can be sequentially determined, and the missing pixel points are subjected to color filling through the target color information, so that color supplement of the missing region is realized, and the display effect of the finally generated three-dimensional house model is improved.
Optionally, the threshold range may be a plurality of pixel points adjacent to the missing pixel point, for example, taking the missing pixel point as a center, 8 pixel points outside the missing pixel point are the threshold range of the missing pixel point, in the threshold range, a part of the pixel points are in a complete region and have color information, and another part of the pixel points are in the missing region and are all missing pixel points and do not have color information. The size of the threshold range is not limited in the embodiment of the invention, and can be determined according to actual conditions.
Optionally, the determining target color information corresponding to a pixel point within the threshold range of the missing pixel point includes:
and under the condition that the color information in the complete area is consistent, determining the color information of any one pixel point in the complete area as target color information.
Specifically, under the condition that the target space is a house, the determined plane view is any one of a wall, a roof and a floor, and therefore, if the color information of the complete area in the plane view is consistent, that is, the complete area in the plane view is a pure color, the color information of any one pixel point in the complete area is determined as the target color information based on the consideration of color matching consistency, so that color filling is performed on each missing pixel point in the missing area through the target color information.
Optionally, the determining target color information corresponding to a pixel point within the threshold range of the missing pixel point further includes:
determining a first color change boundary of the color information change in the complete area in the case that there is a change in the color information in the complete area;
predicting a second color change boundary of the first color change boundary extending to the missing region based on the shape characteristics corresponding to the first color change boundary and the first color change boundary;
determining a threshold range corresponding to each missing pixel point based on the first color change boundary and the second color change boundary;
and determining the color information of each pixel point in the threshold range as target color information.
Specifically, if the color information of the complete area in the plane view changes, that is, at least two kinds of color information exist in the complete area of the plane view, a first color change boundary where the color information changes is determined, and a second color change boundary where the first color change boundary extends to the missing area is predicted according to the three-dimensional coordinate value corresponding to each pixel point on the first color change boundary and the shape feature corresponding to the first color change boundary, and the missing area is divided into at least two areas by the second color change boundary, and the two areas have different color information, so that the color filling of the missing area is prevented from being abrupt. Meanwhile, after the first color change boundary and the second color change boundary are determined, the threshold range corresponding to the missing pixel points is determined, the first color change boundary and the second color change boundary can affect the size of the threshold range, target color information corresponding to the pixel points in the threshold range is further determined, and color filling is carried out on the missing pixel points through the target color information, so that the display effect is improved.
Optionally, the three-dimensional coordinate value corresponding to the missing pixel point corresponding to the second color change boundary may also be predicted by determining the curvature value and the three-dimensional coordinate value corresponding to the first color change boundary.
Optionally, a reasonable complete shape may be predicted by determining shape features corresponding to the first color change boundary and color information of each pixel point in an area formed by the first color change boundary and the missing boundary, and determining an edge line of the complete shape in the missing area as the second color change boundary.
Exemplarily, fig. 2 is one of exemplary schematic diagrams of color filling provided by the present invention, as shown in fig. 2, a missing region exists in a plan view, and the missing region is a sum of a region B1 and a region B2, the region A1 and the region A2 in the plan view form a complete region, color information corresponding to the region A1 and the region A2 is different, the color information in the region A1 is consistent, the color information in the region A2 is consistent, a first color change boundary between the region A1 and the region A2 is in a wave shape, the first color change boundary is further extended to the missing region by determining a three-dimensional coordinate value and a curvature value of each pixel point on the first color change boundary, or by determining an amplitude value corresponding to the first color change boundary in the wave shape, so as to obtain a second color change boundary, and the missing region is divided into the region B1 and the region B2 by the second color change boundary, that is, the region B1 and the region B2 are color filled with different color information respectively. Taking missing pixel points C and missing pixel points D in the missing region as an example, the color filling of the missing pixel points C and the missing pixel points D includes the following steps:
(1) And determining 8 pixel points adjacent to the missing pixel point C, wherein 4 pixel points are located in the area A1 and have color information, and 4 pixel points are located in the area B1 and are all the missing pixel points, so that the color information corresponding to the 4 pixel points in the area A1 is determined as target color information, and the missing pixel point C is subjected to color filling through the target color information.
(2) Determining 8 pixel points adjacent to a missing pixel point D, wherein 1 pixel point is located in a region A2 and has color information, 2 pixel points are located on a missing boundary, color filling is performed based on the color information corresponding to the pixel points in the region A2, 4 pixel points are located in a region B2 and are all missing pixel points and do not have color information, meanwhile, a second color change boundary penetrates through 1 pixel point at the upper left corner, therefore, the 1 pixel point at the upper left corner is excluded from a threshold range corresponding to the missing pixel point D, only 3 pixel points have color information in the determined threshold range, and the colors of the 3 pixel points are consistent, therefore, the color information corresponding to any one pixel point in the 3 pixel points is determined as target color information, and the missing pixel point D is color filled through the target color information.
Exemplarily, fig. 3 is a second exemplary schematic diagram of color filling provided by the present invention, as shown in fig. 3, a region A3 and a region A4 in a plan view form a complete region, color information corresponding to the region A3 and the region A4 is different, color information in the region A3 is consistent, color information in the region A4 is consistent, a first color change boundary between the region A3 and the region A4 is determined, and a second color change boundary of the first color change boundary in a missing region is reasonably predicted based on a shape formed by the first color change boundary and the missing boundary and the color information of the region A3, and the shape formed by the first color change boundary and the second color change boundary is a petal shape, that is, the color information of the second color change boundary is different from the color information of the region B3 in the missing region and the region B4 other than the region B3 in the missing region, and the missing pixel point E in the region B3 is taken as an example, the color filling of the missing pixel point E includes the following steps:
determining 8 pixel points adjacent to the missing pixel point E, wherein 3 pixel points are located in the region B3 and are all the missing pixel points, and performing color filling based on color information corresponding to the missing pixel points in the region B3, and meanwhile, the second color change boundary passes through the 5 pixel points on the left side, so that the 5 pixel points on the left side are excluded from the threshold range corresponding to the missing pixel point E, namely the threshold range only contains 3 pixel points, and the 3 pixel points in the determined threshold range all have color information, and the colors of the 3 pixel points are consistent, therefore, the color information corresponding to any one pixel point in the 3 pixel points is determined as target color information, and the missing pixel point E is subjected to color filling through the target color information.
Optionally, the method further comprises:
under the condition that the three-dimensional house model is determined, determining a three-dimensional sub model corresponding to the house configuration component in scanning equipment;
determining an operation instruction based on the scanning hand action of the scanning equipment;
and matching the three-dimensional house model based on the operation instruction and the three-dimensional sub-model to obtain a three-dimensional design model.
Specifically, after the three-dimensional house model is obtained, a three-dimensional sub model corresponding to a house configuration component stored in the equipment can be determined in scanning equipment, or a three-dimensional sub model corresponding to the house configuration component is determined through a network, an operation instruction is further obtained through scanning hand actions, indoor design is performed on the three-dimensional house model through the operation instruction, and the display effect of the three-dimensional design model is improved.
Optionally, the scanning device may be AR glasses; the operation instruction may include: and the three-dimensional submodel corresponding to the house configuration part can be dragged into the three-dimensional house model through the actions of a scanning hand, and is further arranged to obtain a corresponding three-dimensional design model.
In addition, after modeling is carried out based on the three-dimensional point cloud data, the three-dimensional model corresponding to the obstacle can be dragged through scanning hand actions, and therefore the obstacle can be deleted.
Optionally, the method further comprises:
determining a house plane house type graph and a measurement area corresponding to the house plane house type graph based on the three-dimensional house model;
and switching and displaying the house plane house type graph, the measuring area, the three-dimensional house model and the three-dimensional design model.
Specifically, after the three-dimensional house model is obtained, an internal top view corresponding to the three-dimensional house model can be determined as a house plane house type graph, the measurement area of the house plane house type graph is determined through conversion proportion and uploaded to a cloud end or a cloud database platform, and meanwhile, the house plane house type graph, the measurement area, the three-dimensional house model and the three-dimensional design model can be switched and displayed through the carousel component.
In addition, when showing the measurement area, still can connect high in the clouds or cloud database platform and further confirm that detailed address information, community information, near configuration information etc. that three-dimensional house model corresponds show jointly, be convenient for rent a house intermediary or real estate sales personnel at the during operation, accessible AR glasses carry out actual measurement, ensure to measure the authenticity, still can let the user wear AR glasses simultaneously and carry out indoor design etc. improve user experience and feel.
The three-dimensional house model determining method provided by the invention comprises the steps of determining the space range and the object outline of a target space by obtaining three-dimensional point cloud data corresponding to the target space, carrying out three-dimensional modeling through the three-dimensional point cloud data to obtain an initial three-dimensional model, deleting the three-dimensional point cloud data corresponding to at least one obstacle which shields the boundary line of the target space in the initial three-dimensional model, and filling missing pixel points with target color information in the threshold range of the missing pixel points to obtain a complete three-dimensional house model, so that the house information is rapidly determined, manpower and material resources are saved, and the display effect of the three-dimensional house model and the experience of a user are improved while the accuracy of rapid measurement of the target space is ensured.
The following describes the three-dimensional house model determining apparatus provided by the present invention, and the three-dimensional house model determining apparatus described below and the three-dimensional house model determining method described above may be referred to in correspondence with each other.
Fig. 4 is a schematic structural diagram of a three-dimensional house model determining apparatus provided by the present invention, and as shown in fig. 4, the three-dimensional house model determining apparatus 400 includes: an obtaining module 400, a modeling module 402, a determining module 403, and a color filling module 404, wherein:
an obtaining module 400, configured to obtain three-dimensional point cloud data in at least two viewing angles of a target space, where the three-dimensional point cloud data is used to determine a spatial range of the target space and a contour of an object in the target space;
a modeling module 402, configured to perform three-dimensional modeling based on the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space;
a determining module 403, configured to delete the three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model when at least one obstacle exists in the initial three-dimensional model, to obtain a three-dimensional missing model, where the obstacle is an object that blocks a boundary line of the target space;
a color filling module 404, configured to determine target color information within a threshold range of at least one missing pixel in the three-dimensional missing model, and fill each missing pixel based on the target color information to obtain a three-dimensional house model, where the missing pixel lacks color information.
The three-dimensional house model determining device provided by the invention determines the space range and the object outline of the target space by acquiring the three-dimensional point cloud data corresponding to the target space, performs three-dimensional modeling through the three-dimensional point cloud data to obtain the initial three-dimensional model, deletes the three-dimensional point cloud data corresponding to at least one obstacle which shields the boundary line of the target space in the initial three-dimensional model, and fills the missing pixel points with the target color information in the threshold range of the missing pixel points to obtain the complete three-dimensional house model, thereby realizing the rapid determination of the house information, saving manpower and material resources, and improving the display effect of the three-dimensional house model and the experience of a user while ensuring the accuracy of rapid measurement of the target space.
Optionally, the three-dimensional point cloud data includes three-dimensional coordinate values, color information, and reflection intensity.
Optionally, the obtaining module 400 is specifically configured to:
converting coordinate systems corresponding to the three-dimensional point cloud data under the visual angles into the same world coordinate system;
determining a target three-dimensional coordinate value corresponding to each three-dimensional point cloud data in the world coordinate system;
determining the difference between the target three-dimensional coordinate values corresponding to two adjacent three-dimensional point cloud data and the actual distance corresponding to two adjacent three-dimensional point cloud data in the target space;
and determining the conversion ratio of the three-dimensional house model and the target space based on the ratio of the difference of the target three-dimensional coordinate values to the actual distance.
Optionally, the color filling module 404 is specifically configured to:
determining at least one plane view based on the three-dimensional missing model under the condition that the three-dimensional missing model has at least one missing pixel point, wherein the plane view has at least one missing pixel point;
determining a missing boundary of the plane view, wherein the missing boundary divides the plane view into a missing region and a complete region, and at least one missing pixel point exists in the missing region;
determining target color information corresponding to the pixel points in the threshold range of the missing pixel points;
and determining the target color information as the color information of the missing pixel point.
Optionally, the color filling module 404 is specifically configured to:
and under the condition that the color information in the complete area is consistent, determining the color information of any one pixel point in the complete area as target color information.
Optionally, the color filling module 404 is specifically configured to:
determining a first color change boundary where color information changes in the full area in a case where there is a change in the color information in the full area;
predicting a second color change boundary of the first color change boundary extending to the missing region based on the shape characteristics corresponding to the first color change boundary and the first color change boundary;
determining a threshold range corresponding to each missing pixel point based on the first color change boundary and the second color change boundary;
and determining the color information of each pixel point in the threshold range as target color information.
Optionally, the three-dimensional house model determining apparatus 400 further includes: match processing module and show module, wherein:
the matching processing module is specifically configured to:
under the condition that the three-dimensional house model is determined, determining a three-dimensional sub model corresponding to the house configuration component in scanning equipment;
determining an operation instruction based on the scanning hand action of the scanning equipment;
and matching the three-dimensional house model based on the operation instruction and the three-dimensional submodel to obtain a three-dimensional design model.
The display module is specifically used for:
determining a house plane house type graph and a measurement area corresponding to the house plane house type graph based on the three-dimensional house model;
and switching and displaying the house plane house type graph, the measuring area, the three-dimensional house model and the three-dimensional design model.
Fig. 5 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 5, the electronic device may include: a processor (processor) 510, a communication Interface (Communications Interface) 520, a memory (memory) 530, and a communication bus 540, wherein the processor 510, the communication Interface 520, and the memory 530 communicate with each other via the communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a three-dimensional house model determination method comprising:
acquiring three-dimensional point cloud data under at least two visual angles of a target space, wherein the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space;
performing three-dimensional modeling based on the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space;
deleting three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model under the condition that at least one obstacle exists in the initial three-dimensional model to obtain a three-dimensional missing model, wherein the obstacle is an object for shielding a boundary line of the target space;
and determining target color information in a threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain a three-dimensional house model, wherein the missing pixel point lacks color information.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being storable on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer being capable of executing the three-dimensional house model determining method provided by the above methods, the method including:
acquiring three-dimensional point cloud data under at least two visual angles of a target space, wherein the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space;
performing three-dimensional modeling based on the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space;
deleting three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model under the condition that at least one obstacle exists in the initial three-dimensional model to obtain a three-dimensional missing model, wherein the obstacle is an object for shielding a boundary line of the target space;
and determining target color information within a threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain a three-dimensional house model, wherein the missing pixel point lacks color information.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the three-dimensional house model determining method provided by the above methods, the method comprising:
acquiring three-dimensional point cloud data under at least two visual angles of a target space, wherein the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space;
performing three-dimensional modeling based on the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space;
under the condition that at least one obstacle exists in the initial three-dimensional model, deleting three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model to obtain a three-dimensional missing model, wherein the obstacle is an object for shielding a boundary line of the target space;
and determining target color information in a threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain a three-dimensional house model, wherein the missing pixel point lacks color information.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for determining a three-dimensional house model, comprising:
acquiring three-dimensional point cloud data under at least two visual angles of a target space, wherein the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space;
performing three-dimensional modeling based on the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space;
deleting three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model under the condition that at least one obstacle exists in the initial three-dimensional model to obtain a three-dimensional missing model, wherein the obstacle is an object for shielding a boundary line of the target space;
and determining target color information within a threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain a three-dimensional house model, wherein the missing pixel point lacks color information.
2. The method for determining the three-dimensional house model according to claim 1, wherein the determining target color information within a threshold range of at least one missing pixel in the three-dimensional missing model, and filling each missing pixel based on the target color information to obtain the three-dimensional house model comprises:
under the condition that the three-dimensional missing model has at least one missing pixel point, determining at least one plane view based on the three-dimensional missing model, wherein the plane view has at least one missing pixel point;
determining a missing boundary of the plane view, wherein the missing boundary divides the plane view into a missing region and a complete region, and at least one missing pixel point exists in the missing region;
determining target color information corresponding to the pixel points within the threshold range of the missing pixel points;
and determining the target color information as the color information of the missing pixel point.
3. The method of claim 2, wherein the determining the target color information corresponding to the pixel points within the threshold range of the missing pixel points comprises:
and under the condition that the color information in the complete area is consistent, determining the color information of any one pixel point in the complete area as target color information.
4. The method of claim 2, wherein the determining the target color information corresponding to the pixel points within the threshold range of the missing pixel point further comprises:
determining a first color change boundary where color information changes in the full area in a case where there is a change in the color information in the full area;
predicting a second color change boundary of the first color change boundary extending to the missing region based on the shape characteristics corresponding to the first color change boundary and the first color change boundary;
determining a threshold range corresponding to each missing pixel point based on the first color change boundary and the second color change boundary;
and determining the color information of each pixel point in the threshold range as target color information.
5. The three-dimensional house model determination method according to any one of claims 2 to 4, wherein the three-dimensional point cloud data includes three-dimensional coordinate values, color information, and reflection intensity;
the method for acquiring the three-dimensional point cloud data under at least two visual angles of the target space further comprises the following steps:
converting coordinate systems corresponding to the three-dimensional point cloud data under the visual angles into the same world coordinate system;
determining a target three-dimensional coordinate value corresponding to each three-dimensional point cloud data in the world coordinate system;
determining the difference between the target three-dimensional coordinate values corresponding to two adjacent three-dimensional point cloud data and the actual distance corresponding to two adjacent three-dimensional point cloud data in the target space;
and determining the conversion ratio of the three-dimensional house model and the target space based on the ratio of the difference of the target three-dimensional coordinate values to the actual distance.
6. The method of determining a three-dimensional house model of claim 5, further comprising:
under the condition that the three-dimensional house model is determined, determining a three-dimensional sub-model corresponding to the house configuration part in the scanning equipment;
determining an operation instruction based on the scanning hand action of the scanning equipment;
and matching the three-dimensional house model based on the operation instruction and the three-dimensional sub-model to obtain a three-dimensional design model.
7. The method of determining a three-dimensional house model of claim 6, further comprising:
determining a house plane house type graph and a measurement area corresponding to the house plane house type graph based on the three-dimensional house model;
and switching and displaying the house plane house type graph, the measuring area, the three-dimensional house model and the three-dimensional design model.
8. A three-dimensional house model determining apparatus, comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring three-dimensional point cloud data under at least two visual angles of a target space, and the three-dimensional point cloud data is used for determining the space range of the target space and the outline of an object in the target space;
the modeling module is used for carrying out three-dimensional modeling on the basis of the three-dimensional point cloud data to obtain an initial three-dimensional model corresponding to the target space;
the determining module is used for deleting the three-dimensional point cloud data corresponding to each obstacle in the initial three-dimensional model under the condition that at least one obstacle exists in the initial three-dimensional model to obtain a three-dimensional missing model, wherein the obstacle is an object for shielding a boundary line of the target space;
and the color filling module is used for determining target color information in a threshold range of at least one missing pixel point in the three-dimensional missing model, and filling each missing pixel point based on the target color information to obtain a three-dimensional house model, wherein the missing pixel point lacks color information.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the three-dimensional house model determination method according to any one of claims 1 to 7 when executing the program.
10. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the three-dimensional house model determination method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211493718.XA CN115761138A (en) | 2022-11-25 | 2022-11-25 | Three-dimensional house model determining method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211493718.XA CN115761138A (en) | 2022-11-25 | 2022-11-25 | Three-dimensional house model determining method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115761138A true CN115761138A (en) | 2023-03-07 |
Family
ID=85338337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211493718.XA Pending CN115761138A (en) | 2022-11-25 | 2022-11-25 | Three-dimensional house model determining method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115761138A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152391A (en) * | 2023-09-05 | 2023-12-01 | 赫红建筑设计(广东)有限公司 | Fitment overall arrangement intelligent management system based on virtual reality |
-
2022
- 2022-11-25 CN CN202211493718.XA patent/CN115761138A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152391A (en) * | 2023-09-05 | 2023-12-01 | 赫红建筑设计(广东)有限公司 | Fitment overall arrangement intelligent management system based on virtual reality |
| CN117152391B (en) * | 2023-09-05 | 2024-04-12 | 赫红建筑设计(广东)有限公司 | Fitment overall arrangement intelligent management system based on virtual reality |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107194983B (en) | A kind of three-dimensional visualization method and system based on a cloud and image data | |
| CN111325779B (en) | Point cloud registration method and device, electronic equipment and storage medium | |
| EP3108449B1 (en) | View independent 3d scene texturing | |
| JP6725110B2 (en) | Image rendering of laser scan data | |
| CN107154032B (en) | A kind of image processing method and device | |
| US9922443B2 (en) | Texturing a three-dimensional scanned model with localized patch colors | |
| CN111080662A (en) | Lane line extraction method and device and computer equipment | |
| US6970174B2 (en) | Texture mapping method and apparatus | |
| CN107610225B (en) | Method for unitizing three-dimensional oblique photography live-action model | |
| US20210209776A1 (en) | Method and device for depth image fusion and computer-readable storage medium | |
| CN113223159B (en) | Single remote sensing image three-dimensional modeling method based on target texture virtualization processing | |
| CN115761138A (en) | Three-dimensional house model determining method and device, electronic equipment and storage medium | |
| US20210312647A1 (en) | Detecting device, information processing device, detecting method, and information processing program | |
| CN108510558B (en) | Compression method, device and the terminal of point cloud data | |
| CN115375823A (en) | Three-dimensional virtual clothing generation method, device, equipment and storage medium | |
| CN111638497A (en) | Radar data processing method, device, equipment and storage medium | |
| Liu et al. | Creating simplified 3D models with high quality textures | |
| CN114782357A (en) | Self-adaptive segmentation system and method for transformer substation scene | |
| CN106360941A (en) | Method for locating fingernails and manicure equipment | |
| EP4202858A1 (en) | Method and device for cargo counting, computer equipment, and storage medium | |
| CN114170367B (en) | Method, apparatus, storage medium, and device for infinite-line-of-sight pyramidal heatmap rendering | |
| CN116801115A (en) | Sparse array camera deployment method | |
| CN117745969A (en) | Building singulation method, device and related equipment | |
| CN115375816A (en) | Micro-rendering method, device, electronic equipment and storage medium | |
| US5821942A (en) | Ray tracing through an ordered array |
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 |