CN114596416A - Three-dimensional ground object model repairing method, system, equipment and storage medium - Google Patents
Three-dimensional ground object model repairing method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN114596416A CN114596416A CN202210489638.0A CN202210489638A CN114596416A CN 114596416 A CN114596416 A CN 114596416A CN 202210489638 A CN202210489638 A CN 202210489638A CN 114596416 A CN114596416 A CN 114596416A
- Authority
- CN
- China
- Prior art keywords
- patches
- segmentation
- triangular
- patch
- boundary
- 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
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
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
- G06T17/205—Re-meshing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides a three-dimensional ground object model repairing method, a system, equipment and a storage medium, which relate to three-dimensional grid model deformation and comprise the following steps: the method comprises the steps of respectively calibrating a distortion boundary with a starting position and a stopping position and a plurality of distortion triangular patches on a three-dimensional ground object model with local deformation, respectively constructing a model calibration boundary and a segmentation patch where the model calibration boundary is located according to the starting position, the stopping position and two distortion triangular patches where the model calibration boundary and the segmentation patch are located, triangulating all the distortion triangular patches according to the junctions of the distortion triangular patches and the segmentation patches, calibrating all the segmented distortion triangular patches to the model calibration boundary, deleting the segmentation patches, enabling the three-dimensional ground object model to be in a calibrated shape based on an original topological structure, truly repairing the distorted part of the three-dimensional ground object model with local deformation, simplifying a repairing mode, preventing the three-dimensional ground object model from flickering due to the fact that the distorted part is shielded when the three-dimensional ground object model is displayed, and considering repairing efficiency and stability.
Description
Technical Field
The invention relates to the technical field of three-dimensional grid model deformation, in particular to a three-dimensional ground object model repairing method, a three-dimensional ground object model repairing system, three-dimensional ground object model repairing equipment and a storage medium.
Background
The method is dependent on the technical development of synthesizing images by computing equipment, carries out three-dimensional visual modeling on the images, enables objects in the real world to be presented electronically, is popularized to a plurality of application scenes such as home theaters, operation treatment, home theaters, surveying and mapping and provides a plurality of conveniences for life production.
At present, due to the limitation of a plurality of factors such as camera shooting conditions, imaging performance, modeling technology adaptability and the like, some three-dimensional modeling technologies are difficult to make a three-dimensional ground object model truly and accurately reflect a real ground object in shape, so that the three-dimensional ground object model is easy to distort, for example, in a three-dimensional city model, a part which is characterized as a horizontal road surface is in an uneven shape, or/and a part which is characterized as a building wall line or an eave is staggered, so that the three-dimensional visualization effect is seriously reduced.
The distortion part is visually shielded on the three-dimensional ground object model due to excessive dependence on human-computer interaction operation, distortion repair is not really carried out on the three-dimensional ground object model, and the efficiency is low.
Disclosure of Invention
The present invention is directed to solving the technical problems of the related art, at least to some extent, and in order to achieve the above objects, the present invention provides a three-dimensional terrain model restoration method, system, device, and storage medium.
In a first aspect, the present invention provides a method for repairing a three-dimensional feature model, including:
respectively calibrating a distortion boundary which is characterized by being bent in an annular shape from a starting position to an ending position and a plurality of distortion triangular patches passing through the distortion boundary on a three-dimensional terrain model of local deformation;
constructing a model calibration boundary which is from the starting position to the ending position, performing normal detection on two discrete distorted triangular patches which pass through the starting position and the ending position respectively, and performing angular bisection detection on normal vectors of the two detected patches which are not collinear according to the model calibration boundary;
constructing segmentation patches intersected with all the distorted triangular patches through the detected angular bisector vectors and the model calibration boundary, and triangulating all the distorted triangular patches according to the junctions of the distorted triangular patches and the segmentation patches respectively;
and after all the segmented distorted triangular patches are calibrated to the model calibration boundary, deleting the segmented patches to enable the three-dimensional ground object model to be in a calibrated shape based on the original topological structure.
In a second aspect, the present invention provides a three-dimensional terrain model repairing system, comprising:
the model marking module is used for respectively marking a distortion boundary which is characterized by being bent in an annular shape from a starting position to an ending position and a plurality of distortion triangular patches passing through the distortion boundary on a three-dimensional ground object model with local deformation;
the vector positioning module is used for constructing a model calibration boundary which is from the starting position to the ending position, respectively carrying out normal detection on two discrete distorted triangular patches which pass through the starting position and the ending position, and carrying out angular bisector detection on normal vectors of the two detected patches which are not collinear according to the model calibration boundary;
the patch segmentation module is used for constructing segmentation patches intersected with all the distorted triangular patches through the detected angular bisector vectors and the model calibration boundary, and carrying out triangularization segmentation on all the distorted triangular patches according to the junctions of the distorted triangular patches and the segmentation patches respectively;
and the model calibration module is used for calibrating all the divided distorted triangular patches to the model calibration boundary, and then deleting the divided patches to enable the three-dimensional ground object model to be calibrated in shape based on the original topological structure.
In a third aspect, the invention provides a computing device comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the three-dimensional terrain model repairing method according to the first aspect.
In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the three-dimensional terrain model restoration method according to the first aspect.
By using the three-dimensional ground object model repairing method, the system, the computing equipment and the non-temporary computer readable storage medium, aiming at a distortion part which is positioned on a three-dimensional ground object model and has local deformation compared with a real ground object, firstly, a distortion boundary which has no annular bending and a plurality of distortion triangular patches passing through the distortion boundary are respectively marked so as to avoid a fidelity part which is positioned on the three-dimensional ground object model and is consistent with the real ground object, then, a model calibration boundary which is in a straight line and two patch normal vectors which are respectively positioned at the two positions are respectively generated by utilizing the initial position and the end position of the distortion boundary, the model calibration boundary is sequentially used as a basis for generating an angular bisector vector together with the two patch normal vectors and as a basis for generating segmentation patches together with the angular bisector vector, and the reusability of the two positions and the model calibration boundary is improved, finally, after the corresponding distorted triangular patches are divided according to the junctions of the distorted triangular patches and the dividing patches, the corresponding distorted triangular patches are calibrated to model calibration boundaries, so that the distorted parts are really repaired, and the fidelity parts are kept unchanged.
Drawings
FIG. 1 is a schematic flow chart of a three-dimensional terrain model repairing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an embodiment of the invention, in which a model calibration boundary is used to perform an angle bisection detection on normal vectors of two patches to form an angle bisection line vector;
FIG. 3 is a schematic diagram of a distorted triangular patch intersecting a segmented patch according to an embodiment of the present invention;
fig. 4 is a schematic diagram of another triangular patch intersecting a split patch according to an embodiment of the present invention;
FIG. 5 is a schematic view of a three-dimensional building model showing a partial recess according to an embodiment of the present invention;
FIG. 6 is a schematic view of a portion of the three-dimensional building model of FIG. 5 being straightened for wall section;
fig. 7 is a schematic structural diagram of a three-dimensional terrain model repairing apparatus according to an embodiment of the present invention.
Detailed Description
Embodiments of the invention will now be described in detail with reference to the drawings, wherein like reference numerals designate identical or similar elements throughout the different views unless otherwise indicated. It is to be noted that the embodiments described in the following exemplary embodiments do not represent all embodiments of the present invention. They are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the claims, and the scope of the present disclosure is not limited in these respects. Features of the various embodiments of the invention may be combined with each other without departing from the scope of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Referring to fig. 1, a three-dimensional feature model repairing method according to an embodiment of the present invention includes S1 to S4.
And S1, respectively calibrating a distortion boundary which is characterized in that the distortion boundary is not annularly bent from the initial position to the end position and a plurality of distortion triangular patches passing through the distortion boundary on the three-dimensional ground object model of the local deformation.
In the embodiment of the invention, aiming at a distortion part which is positioned in a three-dimensional ground object model and has local deformation compared with a real ground object, a server can automatically detect the shape of the three-dimensional ground object model through a convolutional neural network or a Mesh R-CNN and other machine learning algorithms to obtain a distortion boundary which is in a curve shape and a plurality of distortion triangular patches; alternatively, the user may interact with a display device such as a desktop computer, a notebook computer, or an ipad through a peripheral such as a mouse or a capacitance pen, input an operation of selecting the distortion boundary and the plurality of distorted triangular patches on the three-dimensional terrain model displayed on the display device, and in response to the operation, the display device may mark the selected distortion boundary and the plurality of distorted triangular patches with colors, for example, mark the distortion boundary from black to white, avoid a fidelity portion that is on the three-dimensional terrain model and corresponds to the real terrain, and maintain the distortion portion unchanged.
S2, constructing a model calibration boundary from the starting position to the ending position, performing normal detection on two discrete distorted triangular patches passing through the starting position and the ending position respectively, and performing angular bisection detection on normal vectors of the two detected patches which are not collinear according to the model calibration boundary.
And S3, constructing the segmentation patches intersected with all the distorted triangular patches through the detected angular bisector vectors and the model calibration boundaries, and carrying out triangularization segmentation processing on all the distorted triangular patches according to the junctions of the distorted triangular patches and the segmentation patches respectively.
In the embodiment of the invention, aiming at the starting and ending positions of the distortion boundary and two distortion triangular patches passing through the two positions, the display control equipment can perform automatic processing through a MeshLab three-dimensional modeling tool or a machine learning algorithm, respectively generate a linear model calibration boundary and two patch normal vectors respectively positioned at the two positions by utilizing the starting position and the ending position of the distortion boundary, regarding the model calibration boundary, the model calibration boundary and the two patch normal vectors are firstly used as a basis for generating an angular bisector vector and then are used as a basis for generating a segmentation patch together with the angular bisector vector, and the reusability of the two positions and the model calibration boundary is improved.
And S4, after all the distorted triangular patches which are divided are calibrated to the model calibration boundary, deleting the divided patches to enable the three-dimensional ground object model to be in a calibrated shape based on the original topological structure.
In the embodiment of the invention, after the display and control device can automatically segment the distorted triangular patch through a mesh division algorithm such as Delaunay or Hypermesh or MeshCNN and the like, the segmented distorted triangular patch can be stretched or compressed based on geometric deformation through an algorithm with mesh geometric deformation performance such as Laplacian to be connected with a model calibration boundary, so that the three-dimensional terrain model is calibrated in shape on the basis of maintaining the original topological structure, the distorted part is really repaired, and the fidelity part is also maintained unchanged.
Compared with the method for reconstructing the new three-dimensional ground object model through excessive human-computer interaction to replace the original three-dimensional ground object model, the method for repairing the three-dimensional ground object model simplifies the repairing mode, prevents the three-dimensional ground object model from flickering due to the fact that the distortion part is shielded when the three-dimensional ground object model is displayed, not only helps to reduce storage loss, but also helps to consider repairing efficiency and stability.
Optionally, S2 includes: calibrating a reference position on a model calibration boundary; respectively translating the normal vectors of the two surface patches to reference positions; respectively carrying out normalization processing on normal vectors of two surface patches intersected at a reference position to obtain two corresponding unit vectors; and according to a parallelogram rule, carrying out angular bisector measurement processing on the two unit vectors to obtain angular bisector vectors which intersect at the reference position.
In the embodiment of the present invention, referring to fig. 2, on the model calibration boundary, a patch vector is obtained from the start position P by using the center position O as the reference positionsIs shifted to the center position O, and the other patch vector is moved from the start position PtThe position is translated to a central position O, and after normalization processing is respectively carried out on the vectors of the two surface patches, the vectors of the two surface patches are intersected at the central positionThe unit vector OA and the unit vector OB at the position O, and the angular bisector vector OC are on the angular bisector between the unit vector OA and the unit vector OB, so that the angular bisector vector can be simply and reliably measured, and the vector detection efficiency is improved.
Optionally, S3 includes: and dividing the distorted triangular patch to which the distorted triangular patch belongs into a plurality of sub-triangular patches with complementarity according to the updated array, wherein the two corresponding segmentation points of the segmentation point position pairs are represented as discrete distribution on the boundary of the corresponding distorted triangular patch.
In the embodiment of the present invention, for example, the original arrays to which the four distorted triangular patches belong are Over1, Over2, Over3 and Over4, and Over4 represents [ V [1，V2，V3]For example, wherein V1、V2And V3Respectively representing the original three vertex coordinates, I, of the fourth distorted triangular patch1To be represented from V1Connection V2Is intersected with a division point coordinate of the division patch, I2To be represented from V2Connection V3The boundary of the division patch intersects with the other division point coordinate of the division patch, the two division point coordinates form a corresponding division point pair together, an array with the length larger than Over4 is newly established, and the newly established array is Uver4= [ V ] V1，V2，V3，I1，I3]Thereafter, Over4 is removed, e.g., the split patch may be quadrilateral, with its four vertex coordinates represented as [ V ]4，V5，V6，V7]See fig. 3.
In the process of traversing all the distorted triangular patches, all the segmentation point pairs and the corresponding original arrays are merged together so as to prevent any segmentation point pair and the merged original array from being omitted, delete the original array in time, release the storage space occupied by the original array and contribute to improving the reliability of patch segmentation.
Optionally, dividing the distorted triangular patch to which the distorted triangular patch belongs into a plurality of sub-triangular patches with complementarity according to the update array, including: according to the segmentation point pairs in the updated array, constructing a linear segmentation boundary along the segmentation surface patch, so that the distorted triangular surface patch where the segmentation boundary is located is divided into two sub surface patches, and each sub surface patch is in a triangular shape or a quadrilateral shape; checking whether the original vertex coordinates which are repeated with the division point position pairs exist in the updated array; if so, respectively determining the two sub-patches as sub-triangular patches; if not, determining the triangular sub-patch as a sub-triangular patch, and dividing the quadrilateral sub-patch into another two sub-triangular patches.
In one embodiment of the invention, referring to FIG. 3, the segmentation boundary represents the Slave I1Connection I2Straight line of (2) due to1And I2None of them is linked to V1、V2And V3Any of which coincide along the slave I1Connection I2Will have three vertices V1、V2And V3The distorted triangular patch is divided into a triangular sub-patch and a quadrilateral sub-patch, and the quadrilateral sub-patch can be further divided along the V-axis1Connection I2Straight line of or from V2Straight-line connection I1The straight line of (a) divides it into two triangular sub-patches.
In another embodiment of the present invention, see FIG. 4, since I1And V1Coincide along the slave axis I1Connection I2Will have three vertices V1、V2And V3The represented distorted triangular patch is divided into two sub-patches each having a triangular shape.
The method comprises the steps of utilizing a segmentation boundary represented by a segmentation point position pair to partition a distorted triangular patch to which the segmentation boundary belongs, reflecting that the segmentation boundary passes through one vertex position of the distorted triangular patch under the condition that an original vertex coordinate and the segmentation point position pair are repeated, reflecting that two sub-patches are in triangular shapes at the moment, avoiding further patch partitioning operation to reduce the number of patch partitioning times and helping to ensure patch segmentation efficiency, reflecting that the segmentation boundary does not pass through any vertex position of the distorted triangular patch but passes through two boundaries of the distorted triangular patch under the condition that the original vertex coordinate and the segmentation point position pair are not repeated, further partitioning the sub-patches in the quadrilateral shape at the moment to prevent the sub-patches which do not conform to the triangular shape from being missed to be segmented and helping to improve the reliability of patch segmentation, helping to prevent the control patch from being over-segmented.
Optionally, S4 includes: traversing all the segmentation point pairs; respectively shifting two corresponding segmentation points to the model calibration boundary along a direction perpendicular to the model calibration boundary according to the currently traversed segmentation point position pair, so that the corresponding distorted triangular patch is stretched or compressed and deformed along with the shifting of the two segmentation points on the distorted triangular patch to form a calibrated triangular patch; and when the traversal is finished, performing side-by-side smoothing processing on each calibration triangular patch by taking the divided patch as a reference.
In the embodiment of the invention, see FIG. 3, I1Is translated to I at the model calibration boundary1 'Position, I2Is translated to I at the model calibration boundary2 'Position, then, the regularized triangular patch may be subjected to side-splitting smoothing based on both sides of the segmentation patch by, for example, a laplacian smoothing algorithm to prevent the regularized triangular patch as a whole from being smoothed out of the segmentation points.
In the embodiment of the invention, referring to fig. 5, taking a three-dimensional building model as an example, one side of the three-dimensional building model shows that a part of a wall line is straightened and is sunken inwards, after the three-dimensional ground object model is processed by the three-dimensional ground object model repairing method, the inwards sunken part is straightened to the same straight line, and is restored to a shape which is consistent with a real building, as shown in fig. 6.
Referring to fig. 7, a three-dimensional terrain model restoration system according to another embodiment of the present invention includes: the device comprises a model difference module, a vector positioning module, a patch segmentation module and a model calibration module.
And the model marking module is used for respectively marking a distortion boundary which is characterized by being bent in an acyclic shape from the starting position to the ending position and a plurality of distortion triangular patches passing through the distortion boundary on the three-dimensional ground object model with local deformation.
And the vector positioning module is used for constructing a model calibration boundary from the starting position to the ending position, respectively carrying out normal detection on two discrete distorted triangular patches passing through the starting position and the ending position, and carrying out angular bisection detection on normal vectors of the two detected patches which are not collinear according to the model calibration boundary.
And the patch segmentation module is used for constructing segmentation patches intersected with all the distorted triangular patches through the detected angular bisector vectors and the model calibration boundary, and performing triangularization segmentation processing on all the distorted triangular patches according to the junctions of the distorted triangular patches and the segmentation patches respectively.
And the model calibration module is used for deleting the segmented patches after calibrating all the segmented distorted triangular patches to model calibration boundaries, so that the three-dimensional ground object model is calibrated in shape based on the original topological structure.
Optionally, the vector positioning module is specifically configured to: calibrating a reference position on a model calibration boundary; respectively translating the normal vectors of the two surface patches to reference positions; respectively carrying out normalization processing on normal vectors of two surface patches intersected at a reference position to obtain two corresponding unit vectors; and according to a parallelogram rule, carrying out angular bisector measurement processing on the two unit vectors to obtain angular bisector vectors which intersect at the reference position.
Optionally, the patch dividing module is specifically configured to: and dividing the distorted triangular patch to which the distorted triangular patch belongs into a plurality of sub-triangular patches with complementarity according to the updated array, wherein the two corresponding segmentation points of the segmentation point position pairs are represented as discrete distribution on the boundary of the corresponding distorted triangular patch.
Optionally, the patch segmentation module is specifically configured to: according to the segmentation point pairs in the updated array, straight segmentation boundaries are constructed along the segmentation surface patches, so that the distortion triangular surface patches where the segmentation boundaries are located are divided into two sub-surface patches by the segmentation boundaries, and each sub-surface patch is in a triangular shape or a quadrilateral shape; checking whether the original vertex coordinates which are repeated with the division point position pairs exist in the updated array; if so, respectively determining the two sub-patches as sub-triangular patches; if not, determining the triangular sub-patch as a sub-triangular patch, and dividing the quadrilateral sub-patch into another two sub-triangular patches.
Optionally, the model calibration module is specifically configured to: traversing all the segmentation point pairs; according to the traversed segmentation point position pair, respectively shifting the two corresponding segmentation points to the model calibration boundary along the direction vertical to the model calibration boundary, so that the corresponding distorted triangular patch is stretched or compressed and deformed along with the shifting of the two segmentation points on the distorted triangular patch to form a calibrated triangular patch; and when the traversal is finished, performing side-by-side smoothing processing on each calibration triangular patch by taking the divided patch as a reference.
A computing device according to another embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the three-dimensional terrain model repairing method. It will be appreciated that the aforementioned computing device may be a server or a terminal device, wherein the processor may be connected to the memory via a universal serial control bus.
A non-transitory computer-readable storage medium according to another embodiment of the present invention has a computer program stored thereon, and when executed by a processor, implements the three-dimensional terrain model restoration method as mentioned above.
Generally, computer instructions for carrying out the methods of the present invention may be carried using any combination of one or more computer-readable storage media. Non-transitory computer readable storage media may include any computer readable medium except for the signal itself, which is temporarily propagating.
A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages, and in particular may employ Python languages suitable for neural network computing and TensorFlow, PyTorch-based platform frameworks. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
For the three-dimensional terrain model restoration apparatus, the computing device and the non-transitory computer-readable storage medium, reference may be made to the detailed description of the three-dimensional terrain model restoration method and the beneficial effects thereof, which is not described herein again.
Although embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are illustrative and not to be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A three-dimensional ground object model repairing method is characterized by comprising the following steps:
respectively calibrating a distortion boundary which is characterized by being bent in an annular shape from a starting position to an ending position and a plurality of distortion triangular patches passing through the distortion boundary on a three-dimensional terrain model of local deformation;
constructing a model calibration boundary which is from the starting position to the ending position, performing normal detection on two discrete distorted triangular patches which pass through the starting position and the ending position respectively, and performing angular bisection detection on normal vectors of the two detected patches which are not collinear according to the model calibration boundary;
constructing segmentation patches intersected with all the distorted triangular patches through the detected angular bisector vectors and the model calibration boundaries, and triangulating all the distorted triangular patches according to the junctions of the distorted triangular patches and the segmentation patches respectively;
and after all the divided distorted triangular patches are calibrated to the model calibration boundary, deleting the divided patches to enable the three-dimensional ground object model to be in a calibrated shape based on the original topological structure.
2. The method of repairing a three-dimensional feature model according to claim 1, wherein the performing angular bisection detection on the detected two patch normal vectors that are not collinear according to the model calibration boundary comprises:
calibrating a reference position on the model calibration boundary;
respectively translating the two surface patch normal vectors to the reference position;
respectively carrying out normalization processing on the normal vectors of the two surface patches intersected at the reference position to obtain two corresponding unit vectors;
and according to a parallelogram rule, carrying out angular bisector measurement processing on the two unit vectors to obtain the angular bisector vector intersected at the reference position.
3. The method of repairing a three-dimensional feature model according to claim 1, wherein the triangulating all the distorted triangular patches according to their respective junctions with the segmentation patch comprises:
the method comprises the steps of detecting the positions of the boundary of each distorted triangular patch and the boundary intersection of the divided patches one by one, merging original arrays of the three original vertex positions of the distorted triangular patches corresponding to the divided point pair and characterization into an updated array when the corresponding divided point pair is detected, deleting the original array, dividing the distorted triangular patches to which the distorted triangular patches belong into a plurality of sub-triangular patches with complementarity according to the updated array, wherein the divided point pair is characterized in that the two corresponding divided points are discretely distributed on the boundary of the corresponding distorted triangular patches.
4. The method of repairing a three-dimensional feature model of claim 3, wherein the dividing the distorted triangular patch to which the distorted triangular patch belongs into a plurality of sub-triangular patches having complementarity according to the updated array comprises:
according to the segmentation point position pairs in the updating array, straight segmentation boundaries are constructed along the segmentation surface patches, so that the distortion triangular surface patches where the segmentation boundaries are located are divided into two sub surface patches by the segmentation boundaries, and each sub surface patch is in a triangular shape or a quadrilateral shape;
checking whether an original vertex coordinate which is repeated with the segmentation point pair exists in the updated array;
if so, respectively determining the two sub-patches as the sub-triangular patches;
if not, determining the triangular sub-patch as one sub-triangular patch, and dividing the quadrilateral sub-patch into another two sub-triangular patches.
5. The method of repairing a three-dimensional feature model according to claim 3, wherein the calibrating all the distorted triangular patches after the segmentation to the model calibration boundary comprises:
traversing all the segmentation point pairs;
according to the currently traversed segmentation point position pair, respectively shifting the two corresponding segmentation points to the model calibration boundary along a direction perpendicular to the model calibration boundary, so that the corresponding distorted triangular patch is stretched or compressed and deformed along with the shifting of the two segmentation points on the distorted triangular patch to form a calibrated triangular patch;
and when the traversal is finished, respectively carrying out side-dividing smoothing processing on each calibration triangular patch by taking the segmentation patch as a reference.
6. A three-dimensional terrain model restoration system, comprising:
the model marking module is used for respectively marking a distortion boundary which is characterized by being bent in an annular shape from a starting position to an ending position and a plurality of distortion triangular patches passing through the distortion boundary on a three-dimensional ground object model with local deformation;
the vector positioning module is used for constructing a model calibration boundary which is from the starting position to the ending position, respectively carrying out normal detection on two discrete distorted triangular patches which pass through the starting position and the ending position, and carrying out angular bisector detection on normal vectors of the two detected patches which are not collinear according to the model calibration boundary;
the patch segmentation module is used for constructing segmentation patches intersected with all the distorted triangular patches through the detected angular bisector vectors and the model calibration boundary, and carrying out triangularization segmentation on all the distorted triangular patches according to the junctions of the distorted triangular patches and the segmentation patches respectively;
and the model calibration module is used for calibrating all the divided distorted triangular patches to the model calibration boundary, and then deleting the divided patches to enable the three-dimensional ground object model to be calibrated in shape based on the original topological structure.
7. The three-dimensional terrain model restoration system of claim 6, wherein the patch segmentation module is specifically configured to:
the method comprises the steps of detecting the positions of the boundary of each distorted triangular patch and the boundary intersection of the divided patches one by one, merging original arrays of the three original vertex positions of the distorted triangular patches corresponding to the divided point pair and characterization into an updated array when the corresponding divided point pair is detected, deleting the original array, dividing the distorted triangular patches to which the distorted triangular patches belong into a plurality of sub-triangular patches with complementarity according to the updated array, wherein the divided point pair is characterized in that the two corresponding divided points are discretely distributed on the boundary of the corresponding distorted triangular patches.
8. The three-dimensional terrain model restoration system of claim 7, wherein the patch segmentation module is specifically configured to:
according to the segmentation point position pairs in the updating array, straight segmentation boundaries are constructed along the segmentation surface patches, so that the distortion triangular surface patches where the segmentation boundaries are located are divided into two sub surface patches by the segmentation boundaries, and each sub surface patch is in a triangular shape or a quadrilateral shape;
checking whether an original vertex coordinate which is repeated with the segmentation point pair exists in the updated array;
if so, respectively determining the two sub-patches as the sub-triangular patches;
if not, determining the triangular sub-patch as one sub-triangular patch, and dividing the quadrilateral sub-patch into another two sub-triangular patches.
9. A computing device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements the three-dimensional terrain model repairing method according to any one of claims 1-5.
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 terrain model restoration method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210489638.0A CN114596416B (en) | 2022-05-07 | 2022-05-07 | Three-dimensional ground object model repairing method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210489638.0A CN114596416B (en) | 2022-05-07 | 2022-05-07 | Three-dimensional ground object model repairing method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114596416A true CN114596416A (en) | 2022-06-07 |
| CN114596416B CN114596416B (en) | 2022-07-08 |
Family
ID=81813453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210489638.0A Active CN114596416B (en) | 2022-05-07 | 2022-05-07 | Three-dimensional ground object model repairing method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114596416B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5319744A (en) * | 1991-04-03 | 1994-06-07 | General Electric Company | Polygon fragmentation method of distortion correction in computer image generating systems |
| CN101867703A (en) * | 2009-04-16 | 2010-10-20 | 辉达公司 | The system and method that is used for correcting image |
| CN103617603A (en) * | 2013-12-06 | 2014-03-05 | 南京大学 | Automatic restoration method of three-dimensional digital geometric grid model structure |
| CN108154479A (en) * | 2016-12-02 | 2018-06-12 | 航天星图科技（北京）有限公司 | A kind of method that remote sensing images are carried out with image rectification |
| CN108182699A (en) * | 2017-12-28 | 2018-06-19 | 北京天睿空间科技股份有限公司 | Three-dimensional registration method based on two dimensional image local deformation |
| WO2019036347A1 (en) * | 2017-08-13 | 2019-02-21 | Frederick Amy Louise | Process for customized wall and surface repair patches |
-
2022
- 2022-05-07 CN CN202210489638.0A patent/CN114596416B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5319744A (en) * | 1991-04-03 | 1994-06-07 | General Electric Company | Polygon fragmentation method of distortion correction in computer image generating systems |
| CN101867703A (en) * | 2009-04-16 | 2010-10-20 | 辉达公司 | The system and method that is used for correcting image |
| CN103617603A (en) * | 2013-12-06 | 2014-03-05 | 南京大学 | Automatic restoration method of three-dimensional digital geometric grid model structure |
| CN108154479A (en) * | 2016-12-02 | 2018-06-12 | 航天星图科技（北京）有限公司 | A kind of method that remote sensing images are carried out with image rectification |
| WO2019036347A1 (en) * | 2017-08-13 | 2019-02-21 | Frederick Amy Louise | Process for customized wall and surface repair patches |
| CN108182699A (en) * | 2017-12-28 | 2018-06-19 | 北京天睿空间科技股份有限公司 | Three-dimensional registration method based on two dimensional image local deformation |
Non-Patent Citations (1)
| Title |
|---|
| 张培峰等: "基于Barista软件的高分辨率遥感影像中建筑物3D信息的提取", 《应用生态学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114596416B (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110307838B (en) | Robot repositioning method and device, computer-readable storage medium and robot | |
| Zhou et al. | Canny-vo: Visual odometry with rgb-d cameras based on geometric 3-d–2-d edge alignment | |
| AU2013326865B2 (en) | Determining image transforms without using image acquisition metadata | |
| JP4635392B2 (en) | 3D object surface shape modeling apparatus and program | |
| US7272264B2 (en) | System and method for hole filling in 3D models | |
| US10810718B2 (en) | Method and device for three-dimensional reconstruction | |
| CN112233249B (en) | B spline surface fitting method and device based on dense point cloud | |
| US6820043B2 (en) | Modeling continuous properties on discontinuous surfaces | |
| Guo et al. | A geometry-and texture-based automatic discontinuity trace extraction method for rock mass point cloud | |
| CN109615702B (en) | Grid hole filling method, image processing equipment and device with storage function | |
| CN113393577B (en) | Oblique photography terrain reconstruction method | |
| CN110838129A (en) | Three-dimensional building model contour characteristic line extraction method based on oblique photogrammetry | |
| CN114638795A (en) | Multi-structure light measurement unit online measurement method and system | |
| CN114596416B (en) | Three-dimensional ground object model repairing method, system, equipment and storage medium | |
| JPWO2015151553A1 (en) | Change detection support device, change detection support method, and program | |
| CN108961391B (en) | Surface reconstruction method based on curvature filtering | |
| CN112967396B (en) | Mirror reflection-based 3D model sphere protection area parameterization method and system | |
| KR20190113669A (en) | Apparatus and method for data management for reconstruct in 3d object surface | |
| JP2002183227A (en) | Method and device for creating free-form surface directly from group data | |
| CN116524149A (en) | Curved surface graph mapping method, device, equipment and storage medium | |
| CN117910184B (en) | Method and system for converting spline curve into road plane design parameter | |
| CN116625242B (en) | Path planning method and system for optical three-coordinate measuring machine, electronic equipment and medium | |
| Wang et al. | Spatial virtual recovery design technology of ancient buildings based on 3D laser scanning technology | |
| Liu et al. | A Quantitative Texture Feature Preserving Method for Simplifying 3D Building Models | |
| CN115588048A (en) | Target ranging method, device, electronic equipment and computer readable storage medium |
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 |