Model similarity determination method and device, equipment and storage medium
By generating two-dimensional point cloud data and constructing a set of triangles, the similarity of the triangles is used to determine the similarity of the models, which solves the problem of high computational cost in the existing technology and realizes efficient computation for model similarity judgment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GEER TECH CO LTD
- Filing Date
- 2024-11-18
- Publication Date
- 2026-05-29
AI Technical Summary
Existing technologies for determining model similarity are computationally expensive, resulting in low efficiency.
By acquiring the 3D point cloud data of the model to be judged, determining the distribution direction vector, generating 2D point cloud data, and constructing a set of triangles, the similarity of the models is judged by the similarity of the triangles, and dimensionality reduction is performed to reduce the amount of computation.
It effectively reduces the computational cost of model similarity judgment and improves judgment efficiency.
Smart Images
Figure CN122115902A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer vision technology, and in particular to methods, apparatus, devices and storage media for model similarity judgment. Background Technology
[0002] In the field of computer vision, model similarity assessment is indispensable. For example, determining whether a ground truth model is similar to a standard or reference ground truth model. Currently, a common method for judging model similarity is to perform coarse matching based on the model's 3D feature points, and then calculate the matching error using classic fine matching algorithms such as ICP (Iterative Closest Point). This matching error is then used to determine model similarity. However, calculating 3D feature points and using the ICP algorithm to calculate the matching error requires significant computational resources. Therefore, the above method for judging model similarity is computationally expensive.
[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention
[0004] The main purpose of this application is to provide a method, apparatus, device and storage medium for judging model similarity, which aims to solve the technical problem that the computational cost of judging model similarity in the prior art is high.
[0005] To achieve the above objectives, this application proposes a model similarity judgment method, the method comprising:
[0006] Obtain the 3D point cloud data of the model to be judged, and determine the distribution direction vectors based on the 3D point cloud data;
[0007] Two-dimensional point cloud data is generated based on the distribution direction vectors and the three-dimensional point cloud data.
[0008] A set of triangles for the model to be judged is generated based on each of the aforementioned two-dimensional point cloud data;
[0009] If a triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model.
[0010] In one embodiment, the step of generating two-dimensional point cloud data based on the respective distribution direction vectors and the three-dimensional point cloud data includes:
[0011] Determine the target's geometric centroid based on the three-dimensional point cloud data;
[0012] A local coordinate system for the three-dimensional model is constructed with the target's geometric centroid as the origin and the various distribution direction vectors as coordinate axes.
[0013] Multiple coordinate planes are determined based on the local coordinate system of the three-dimensional model;
[0014] The three-dimensional point cloud data is projected onto the multiple coordinate planes to obtain two-dimensional point cloud data.
[0015] In one embodiment, the step of generating a set of triangles for the model to be judged based on each of the two-dimensional point cloud data includes:
[0016] Calculate the corresponding current two-dimensional convex hull based on each of the aforementioned two-dimensional point cloud data;
[0017] Obtain the two-dimensional convex hulls of the target model;
[0018] Calculate the area ratio of each current two-dimensional convex hull to each two-dimensional convex hull of the target model;
[0019] If multiple area ratios are all within a preset range, then a set of triangles for the model to be judged is generated based on each current two-dimensional convex hull.
[0020] In one embodiment, the step of generating a set of triangles for the model to be judged based on each of the current two-dimensional convex hulls if all of the multiple area ratios are within a preset range includes:
[0021] If all of the area ratios are within a preset range, then the vertices of each of the current two-dimensional convex hulls are obtained;
[0022] Identify multiple target vertices that have a direct connection with the stated vertex;
[0023] Generate the current triangle based on the vertex and the multiple target vertices directly connected to the vertex;
[0024] Generate a set of triangles for the model to be judged based on each of the current triangles.
[0025] In one embodiment, the step of determining that the model to be judged is similar to the target model if a triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the target model includes:
[0026] Determine multiple projection directions and the projection order of the multiple projection directions;
[0027] According to the projection order, triangle searches are performed in the triangle set of the target model according to the multiple projection directions;
[0028] If a triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model.
[0029] In one embodiment, after the step of generating a set of triangles for the model to be judged based on each of the two-dimensional point cloud data, the method further includes:
[0030] If no triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the model to be judged, then the model to be judged is determined to be dissimilar to the target model.
[0031] In one embodiment, the step of acquiring the three-dimensional point cloud data of the model to be judged and determining the distribution direction vectors based on the three-dimensional point cloud data includes:
[0032] Obtain the 3D point cloud data of the model to be judged, and perform standardization processing on the 3D point cloud data;
[0033] Principal component analysis was performed on the standardized 3D point cloud data to obtain the important eigenvalues and eigenvectors of the principal components.
[0034] Each distribution direction vector is determined based on the principal component important eigenvalues and the eigenvectors.
[0035] Furthermore, to achieve the above objectives, this application also proposes a model similarity determination device, which includes:
[0036] The acquisition module is used to acquire the three-dimensional point cloud data of the model to be judged, and to determine the distribution direction vectors based on the three-dimensional point cloud data.
[0037] The generation module is used to generate two-dimensional point cloud data based on the distribution direction vectors and the three-dimensional point cloud data;
[0038] The generation module is also used to generate a set of triangles for the model to be judged based on each of the two-dimensional point cloud data.
[0039] The judgment module is used to determine that the model to be judged is similar to the target model if a triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model.
[0040] In addition, to achieve the above objectives, this application also proposes a model similarity judgment device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the model similarity judgment method as described above.
[0041] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the model similarity judgment method as described above.
[0042] One or more technical solutions proposed in this application have at least the following technical effects: by acquiring the three-dimensional point cloud data of the model to be judged, determining each distribution direction vector based on the three-dimensional point cloud data; generating two-dimensional point cloud data based on the each distribution direction vector and the three-dimensional point cloud data; generating a set of triangles for the model to be judged based on each of the two-dimensional point cloud data; if a triangle similar to each triangle in the set of triangles of the model to be judged is found in the set of triangles of the target model, then it is determined that the model to be judged is similar to the target model; through the above method, after determining each distribution direction vector, the three-dimensional point cloud data is reduced in dimensionality using a local coordinate system of the three-dimensional model constructed with each distribution direction vector as the coordinate axis direction, so as to reduce the amount of data calculation and improve the calculation efficiency. Then, the similarity between models is judged by the similarity of triangles, thereby effectively reducing the calculation cost of judging the similarity of models and improving the efficiency of judging the similarity of models. Attached Figure Description
[0043] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0045] Figure 1 This is a flowchart illustrating an embodiment of the model similarity determination method in this application.
[0046] Figure 2 This is a flowchart illustrating Embodiment 2 of the model similarity judgment method of this application;
[0047] Figure 3 This is a schematic diagram of the module structure of the model similarity judgment device in an embodiment of this application;
[0048] Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the model similarity judgment method in this application embodiment.
[0049] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0050] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or model similarity judgment device capable of performing the above functions. The following description uses a model similarity judgment device as an example to illustrate this embodiment and the subsequent embodiments.
[0051] Based on this, embodiments of this application provide a method for judging model similarity, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the model similarity judgment method of this application.
[0052] In this embodiment, the model similarity judgment method includes steps S10 to S40:
[0053] Step S10: Obtain the three-dimensional point cloud data of the model to be judged, and determine the distribution direction vectors based on the three-dimensional point cloud data.
[0054] It should be noted that the model to be judged refers to the model that needs to be judged for model similarity. The 3D point cloud data of the model to be judged can be obtained by scanning or image reconstruction. The number of distribution direction vectors can be three, which are represented as F1, F2 and F3 respectively.
[0055] Further, step S10 includes: acquiring three-dimensional point cloud data of the model to be judged, and performing standardization processing on the three-dimensional point cloud data; performing principal component analysis on the standardized three-dimensional point cloud data to obtain important eigenvalues and eigenvectors of the principal components; and determining each distribution direction vector based on the important eigenvalues and eigenvectors of the principal components.
[0056] It should be understood that after obtaining the three-dimensional point cloud data of the model to be judged, the three-dimensional point cloud data is standardized to eliminate the influence of scale between different dimensions. The principal component important eigenvalues represent the importance of the principal components of the three-dimensional point cloud data. These principal component important eigenvalues can be obtained by performing principal component analysis on the standardized three-dimensional point cloud data.
[0057] Step S20: Generate two-dimensional point cloud data based on the distribution direction vectors and the three-dimensional point cloud data.
[0058] It is understandable that two-dimensional point cloud data refers to point cloud data after dimensionality reduction processing of three-dimensional point cloud data through projection. For example, three 2D point cloud data are P1, P2 and P3.
[0059] Further, step S20 includes: determining the target geometric centroid based on the three-dimensional point cloud data; constructing a local coordinate system of the three-dimensional model with the target geometric centroid as the origin and the various distribution direction vectors as coordinate axes; determining multiple coordinate planes based on the local coordinate system of the three-dimensional model; and projecting the three-dimensional point cloud data onto the multiple coordinate planes respectively to obtain two-dimensional point cloud data.
[0060] It should be understood that the target geometric centroid refers to the geometric centroid of the three-dimensional point cloud. After determining the target geometric centroid and each distribution direction vector, a local coordinate system of the three-dimensional model is constructed with the target geometric centroid as the origin and each distribution direction vector as the coordinate axis. The type of the local coordinate system of the three-dimensional model can be a spatial coordinate system.
[0061] It is understandable that for a local coordinate system of a 3D model, there can be multiple coordinate planes, such as the O-F1-F2 coordinate plane, the O-F1-F3 coordinate plane, and the O-F2-F3 coordinate plane. After determining multiple coordinate planes, the 3D point cloud data is projected onto the multiple coordinate planes respectively to obtain three 2D point cloud data after projection, that is, two-dimensional point cloud data.
[0062] Step S30: Generate a set of triangles for the model to be judged based on each of the two-dimensional point cloud data.
[0063] It should be understood that the triangle set refers to the set of triangles generated using the various two-dimensional point cloud data of the model to be judged. After obtaining the two-dimensional point cloud data projected onto each coordinate plane, the triangle set of the model to be judged is generated based on the various two-dimensional point cloud data.
[0064] Furthermore, after step S30, the method further includes: if no triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the target model, then it is determined that the model to be judged is not similar to the target model.
[0065] Understandably, the target model can be a reference model or a standard model. After generating the triangle set of the model to be judged, under the same projection relationship, a triangle search is performed in the triangle set of the target model. If no triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model, for example, if triangles similar to triangles A and B are found in the triangle set of the target model, but no triangle similar to triangle C is found, then it is determined that the model to be judged and the target model are not similar, that is, there is no similarity relationship between the model to be judged and the target model.
[0066] Step S40: If a triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model.
[0067] It should be noted that if a triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model, for example, if triangles similar to triangles A, B, and C are found in the triangle set of the target model, it indicates that all triangles are similar. In this case, it is determined that the model to be judged is similar to the target model, that is, the model to be judged and the target model have a similarity relationship.
[0068] Further, step S40 includes: determining multiple projection directions and the projection order of the multiple projection directions; performing triangle searches in the triangle set of the target model according to the projection order and the multiple projection directions respectively; if a triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model.
[0069] Understandably, in order to effectively improve the accuracy of judging model similarity, this embodiment performs triangle search from multiple projection directions. Since there are multiple projection directions, it is necessary to determine the projection order of the multiple projection directions before performing the search. At this time, according to the projection order, triangle search is performed in the triangle set of the target model according to the multiple projection directions. Then, it is determined whether a triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model. If so, it is determined that the model to be judged is similar to the target model. If not, it is determined that the model to be judged is not similar to the target model.
[0070] This embodiment acquires 3D point cloud data of the model to be judged, determines various distribution direction vectors based on the 3D point cloud data, generates 2D point cloud data based on the various distribution direction vectors and the 3D point cloud data, and generates a set of triangles for the model to be judged based on the various 2D point cloud data. If a triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model. Through the above method, after determining various distribution direction vectors, the 3D point cloud data is dimensionality-reduced using a local coordinate system of the 3D model constructed with the various distribution direction vectors as coordinate axes, thereby reducing the amount of data computation and improving computational efficiency. Then, the similarity between models is judged by the similarity of triangles, which can effectively reduce the computational cost of judging model similarity and thus improve the efficiency of judging model similarity.
[0071] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S30 includes steps S301 to S304:
[0072] Step S301: Calculate the corresponding current two-dimensional convex hull based on each of the two-dimensional point cloud data.
[0073] It should be noted that the current 2D convex hull refers to the convex hull corresponding to the 2D point cloud data. For example, the current 2D convex hull corresponding to 2D point cloud data P1 is C1, the current 2D convex hull corresponding to 2D point cloud data P2 is C2, and the current 2D convex hull corresponding to 2D point cloud data P3 is C3. Since each 2D point cloud data is obtained through principal component analysis, the current 2D convex hull corresponding to the 2D point cloud data can reflect the shape of the original 3D model from multiple different perspectives.
[0074] Step S302: Obtain each two-dimensional convex hull of the target model.
[0075] Step S303: Calculate the area ratio of each current two-dimensional convex hull to each two-dimensional convex hull of the target model.
[0076] It should be understood that after obtaining each current two-dimensional convex hull of the model to be judged, the area of each current two-dimensional convex hull, such as M1, M2, and M3, is further calculated; and after obtaining each two-dimensional convex hull of the target model, the area of each two-dimensional convex hull, such as M1', M2', and M3', is further calculated, and then the area ratios of each current two-dimensional convex hull and each two-dimensional convex hull of the target model are calculated, such as M1 / M1', M2 / M2', and M3 / M3'.
[0077] Step S304: If multiple area ratios are all within a preset range, then generate a set of triangles for the model to be judged based on each current two-dimensional convex hull.
[0078] Understandably, after obtaining multiple area ratios, it is necessary to determine whether each area ratio is within a preset range. If all are within the preset range, a set of triangles for the model to be judged is generated. The preset range can be set to [0.8, 1.2] and can also be adjusted adaptively according to actual needs.
[0079] Further, step S304 includes: if multiple area ratios are all within a preset range, then obtaining the vertices of each current two-dimensional convex hull; determining multiple target vertices that have a direct relationship with the vertices; generating a current triangle based on the vertices and the multiple target vertices that have a direct relationship with the vertices; and generating a triangle set of the model to be judged based on each current triangle.
[0080] It should be understood that the vertices of the current two-dimensional convex hull refer to the points that constitute the boundary of the current two-dimensional convex hull. After obtaining the vertices of each current two-dimensional convex hull, starting from any vertex, select multiple target vertices that have a direct relationship with it. This direct relationship is represented by the target vertex that is closest to the vertex of the current two-dimensional convex hull. Then, generate the current triangle based on the vertex and the multiple target vertices that have a direct relationship with it, and further generate the triangle set of the model to be judged.
[0081] This embodiment calculates the corresponding current two-dimensional convex hull based on each of the two-dimensional point cloud data; obtains each of the two-dimensional convex hulls of the target model; calculates the area ratio of each of the current two-dimensional convex hulls to each of the two-dimensional convex hulls of the target model; if multiple area ratios are all within a preset range, then a triangle set of the model to be judged is generated based on each of the current two-dimensional convex hulls; by the above method, the area of each of the two-dimensional convex hulls of the target model and the area of each of the current two-dimensional convex hulls are calculated respectively, and the area ratio is further calculated. Then it is determined that multiple area ratios are all within a preset range. If so, it indicates that the requirements for executing the next step are met. At this time, the triangle set of the model to be judged is generated using the vertices of each of the current two-dimensional convex hulls and multiple target vertices, thereby effectively improving the accuracy of generating the triangle set of the model to be judged.
[0082] This application also provides a model similarity judgment device, please refer to... Figure 3 The model similarity determination device includes:
[0083] The acquisition module 10 is used to acquire the three-dimensional point cloud data of the model to be judged, and to determine the distribution direction vectors based on the three-dimensional point cloud data.
[0084] The generation module 20 is used to generate two-dimensional point cloud data based on the various distribution direction vectors and the three-dimensional point cloud data.
[0085] The generation module 20 is also used to generate a set of triangles for the model to be judged based on each of the two-dimensional point cloud data.
[0086] The judgment module 30 is used to determine that the model to be judged is similar to the target model if a triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model.
[0087] This embodiment acquires 3D point cloud data of the model to be judged, determines various distribution direction vectors based on the 3D point cloud data, generates 2D point cloud data based on the various distribution direction vectors and the 3D point cloud data, and generates a set of triangles for the model to be judged based on the various 2D point cloud data. If a triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model. Through the above method, after determining various distribution direction vectors, the 3D point cloud data is dimensionality-reduced using a local coordinate system of the 3D model constructed with the various distribution direction vectors as coordinate axes, thereby reducing the amount of data computation and improving computational efficiency. Then, the similarity between models is judged by the similarity of triangles, which can effectively reduce the computational cost of judging model similarity and thus improve the efficiency of judging model similarity.
[0088] The model similarity determination device provided in this application, employing the model similarity determination method in the above embodiments, can solve the technical problem of high computational cost in judging model similarity in the prior art. Compared with the prior art, the beneficial effects of the model similarity determination device provided in this application are the same as those of the model similarity determination method provided in the above embodiments, and other technical features in the model similarity determination device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0089] In one embodiment, the acquisition module 10 is further configured to acquire three-dimensional point cloud data of the model to be judged, perform standardization processing on the three-dimensional point cloud data, perform principal component analysis on the standardized three-dimensional point cloud data to obtain principal component important eigenvalues and eigenvectors, and determine each distribution direction vector based on the principal component important eigenvalues and eigenvectors.
[0090] In one embodiment, the generation module 20 is further configured to determine the target geometric centroid based on the three-dimensional point cloud data; construct a local coordinate system of the three-dimensional model with the target geometric centroid as the origin and the various distribution direction vectors as coordinate axes; determine multiple coordinate planes based on the local coordinate system of the three-dimensional model; and project the three-dimensional point cloud data onto the multiple coordinate planes respectively to obtain two-dimensional point cloud data.
[0091] In one embodiment, the generation module 20 is further configured to calculate the corresponding current two-dimensional convex hull based on each of the two-dimensional point cloud data; obtain each of the two-dimensional convex hulls of the target model; calculate the area ratio of each of the current two-dimensional convex hulls to each of the two-dimensional convex hulls of the target model; and if multiple area ratios are all within a preset range, generate a set of triangles of the model to be judged based on each of the current two-dimensional convex hulls.
[0092] In one embodiment, the generation module 20 is further configured to: if multiple area ratios are all within a preset range, obtain the vertices of each current two-dimensional convex hull; determine multiple target vertices that have a direct relationship with the vertices; generate a current triangle based on the vertices and the multiple target vertices that have a direct relationship with the vertices; and generate a triangle set of the model to be judged based on each current triangle.
[0093] In one embodiment, the judgment module 30 is further configured to determine that the model to be judged is not similar to the target model if no triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the target model.
[0094] In one embodiment, the judgment module 30 is further configured to determine multiple projection directions and the projection order of the multiple projection directions; perform triangle searches in the triangle set of the target model according to the projection order and the multiple projection directions respectively; if a triangle similar to each triangle in the triangle set of the model to be judged is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model.
[0095] This application provides a model similarity determination device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the model similarity determination method in the above embodiment 1.
[0096] The following is for reference. Figure 4 The diagram illustrates a structural schematic suitable for implementing the model similarity determination device in the embodiments of this application. The model similarity determination device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The model similarity determination device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0097] like Figure 4As shown, the model similarity determination device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the model similarity determination device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the model similarity determination device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows model similarity determination devices with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.
[0098] Specifically, according to the embodiments disclosed in this application, the process described above with reference to the flowcharts can be implemented as a computer software program. This computer program includes program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0099] The model similarity determination device provided in this application, employing the model similarity determination method in the above embodiments, can solve the technical problem of high computational cost in judging model similarity in the prior art. Compared with the prior art, the beneficial effects of the model similarity determination device provided in this application are the same as those of the model similarity determination method provided in the above embodiments, and other technical features in this model similarity determination device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.
[0100] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0101] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0102] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the model similarity judgment method in the above embodiments.
[0103] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0104] The aforementioned computer-readable storage medium may be included in the model similarity determination device; or it may exist independently and not be assembled into the model similarity determination device.
[0105] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0107] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0108] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described model similarity judgment method, thereby solving the technical problem of high computational cost in judging model similarity in the prior art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the model similarity judgment method provided in the above embodiments, and will not be repeated here.
[0109] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A method for judging model similarity, characterized in that, The method includes: Obtain the 3D point cloud data of the model to be judged, and determine the distribution direction vectors based on the 3D point cloud data; Two-dimensional point cloud data is generated based on the distribution direction vectors and the three-dimensional point cloud data. A set of triangles for the model to be judged is generated based on each of the aforementioned two-dimensional point cloud data; If a triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model.
2. The method as described in claim 1, characterized in that, The step of generating two-dimensional point cloud data based on the distribution direction vectors and the three-dimensional point cloud data includes: Determine the target's geometric centroid based on the three-dimensional point cloud data; A local coordinate system for the three-dimensional model is constructed with the target's geometric centroid as the origin and the various distribution direction vectors as coordinate axes. Multiple coordinate planes are determined based on the local coordinate system of the three-dimensional model; The three-dimensional point cloud data is projected onto the multiple coordinate planes to obtain two-dimensional point cloud data.
3. The method as described in claim 1, characterized in that, The step of generating a set of triangles for the model to be judged based on each of the two-dimensional point cloud data includes: Calculate the corresponding current two-dimensional convex hull based on each of the aforementioned two-dimensional point cloud data; Obtain the two-dimensional convex hulls of the target model; Calculate the area ratio of each current two-dimensional convex hull to each two-dimensional convex hull of the target model; If multiple area ratios are all within a preset range, then a set of triangles for the model to be judged is generated based on each current two-dimensional convex hull.
4. The method as described in claim 3, characterized in that, The step of generating a set of triangles for the model to be judged based on each current two-dimensional convex hull if multiple area ratios are all within a preset range includes: If all of the area ratios are within a preset range, then the vertices of each of the current two-dimensional convex hulls are obtained; Identify multiple target vertices that have a direct connection with the stated vertex; Generate the current triangle based on the vertex and the multiple target vertices directly connected to the vertex; Generate a set of triangles for the model to be judged based on each of the current triangles.
5. The method according to any one of claims 1 to 4, characterized in that, The step of determining that the model to be judged is similar to the target model if a triangle similar to every triangle in the triangle set of the model to be judged is found in the triangle set of the target model includes: Determine multiple projection directions and the projection order of the multiple projection directions; According to the projection order, triangle searches are performed in the triangle set of the target model according to the multiple projection directions; If a triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the target model, then the model to be judged is determined to be similar to the target model.
6. The method as described in claim 1, characterized in that, After the step of generating a set of triangles for the model to be judged based on each of the two-dimensional point cloud data, the method further includes: If no triangle similar to all triangles in the triangle set of the target model is found in the triangle set of the model to be judged, then the model to be judged is determined to be dissimilar to the target model.
7. The method as described in claim 1, characterized in that, The step of acquiring the 3D point cloud data of the model to be judged and determining the distribution direction vectors based on the 3D point cloud data includes: Obtain the 3D point cloud data of the model to be judged, and perform standardization processing on the 3D point cloud data; Principal component analysis was performed on the standardized 3D point cloud data to obtain the important eigenvalues and eigenvectors of the principal components. Each distribution direction vector is determined based on the principal component important eigenvalues and the eigenvectors.
8. A model similarity judgment device, characterized in that, The device includes: The acquisition module is used to acquire the three-dimensional point cloud data of the model to be judged, and to determine the distribution direction vectors based on the three-dimensional point cloud data. The generation module is used to generate two-dimensional point cloud data based on the distribution direction vectors and the three-dimensional point cloud data; The generation module is also used to generate a set of triangles for the model to be judged based on each of the two-dimensional point cloud data. The judgment module is used to determine that the model to be judged is similar to the target model if a triangle similar to all triangles in the triangle set of the model to be judged is found in the triangle set of the target model.
9. A model similarity judgment device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the model similarity determination method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the model similarity judgment method as described in any one of claims 1 to 7.