Scanning cap positioning method and apparatus, terminal device, and computer-readable storage medium

Abstract

Embodiments of the present application provide a scanning cap positioning method and device, terminal equipment and computer readable storage medium, relating to the technical field of data processing. At least one candidate scanning cap point cloud cluster is determined based on point cloud data; a top plane equation is determined based on the candidate scanning cap point cloud cluster, and a top plane point cloud of the candidate scanning cap top plane is screened based on the top plane equation; a transformation matrix between the candidate scanning cap point cloud cluster and a scanning cap point cloud model is determined according to the top plane point cloud and a top plane model of a pre-generated scanning cap point cloud model, and the scanning cap point cloud model and the candidate scanning cap point cloud cluster are spatially mapped based on the transformation matrix; in the case that the matching degree between the spatially mapped scanning cap point cloud model and the candidate scanning cap point cloud cluster is greater than a preset matching threshold, the candidate scanning cap point cloud cluster is determined as a point cloud cluster corresponding to a target scanning cap, so as to reduce scanning time consumption and improve the clinical diagnosis and treatment experience and diagnosis and treatment efficiency of users.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a scanning cap positioning method, apparatus, terminal device, and computer-readable storage medium. Background Technology

[0002] In the clinical practice of digital implant restoration for edentulous jaws, the positioning of the scanning cap is a crucial step. The scanning cap is a marking component that is fitted over the scanning bar. Its core function is to provide three-dimensional spatial information such as soft tissue morphology, gingival cuff structure, and occlusal relationship during intraoral scanning, which is essential for subsequent restoration design. The positioning of the scanning cap directly affects the accuracy of the subsequent restoration design, as well as the placement accuracy, occlusal function, and aesthetics of the restoration after insertion.

[0003] In related technologies, the positioning and registration of the scanning cap often relies on the complete optical capture of the overall shape of the scanning cap, requiring the scanning data to have an overlap rate of more than 70% with the standard model. Therefore, it is necessary to capture the 360° full surface information of the scanning cap, which not only leads to a longer scanning time, but also reduces the patient's clinical diagnosis and treatment experience and the efficiency of diagnosis and treatment. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a scanning cap positioning method, device, terminal equipment, and computer-readable storage medium to reduce scanning time and improve the user's clinical diagnosis and treatment experience and efficiency.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, this application provides a method for locating a scanning cap, the method comprising: Acquire point cloud data of the user's edentulous jaw region, and determine at least one candidate scan cap point cloud cluster based on the point cloud data; The top plane equation is determined based on the candidate scan cap point cloud cluster, and the top plane point cloud of the candidate scan cap top plane is selected from the candidate scan cap point cloud cluster based on the top plane equation. Based on the top plane point cloud and the top plane model of the pre-generated scan cap point cloud model, the transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model is determined, and the scan cap point cloud model and the candidate scan cap point cloud cluster are spatially mapped based on the transformation matrix. If the degree of matching between the spatially mapped scan cap point cloud model and the candidate scan cap point cloud cluster is greater than a preset matching threshold, the candidate scan cap point cloud cluster is determined to be the point cloud cluster corresponding to the target scan cap.

[0006] In an optional implementation, determining at least one candidate scan cap point cloud cluster based on the point cloud data includes: Euclidean clustering is performed on the point cloud data based on the Euclidean distance between the point cloud data to obtain multiple point cloud clusters; For each of the point cloud clusters, determine whether the number of point cloud data in the point cloud cluster is within a preset range; If the number of point cloud data is within the preset range, then the point cloud cluster is determined as the candidate scan cap point cloud cluster.

[0007] In an optional implementation, the step of determining the top plane equation based on the candidate scan cap point cloud cluster, and filtering the top plane point cloud of the top of the candidate scan cap from the candidate scan cap point cloud cluster based on the top plane equation, includes: The top plane equation is obtained by performing plane fitting on the point cloud data in the candidate scan cap point cloud cluster using the RANSAC algorithm. The distance between each point cloud data in the candidate scan cap point cloud cluster and the top plane of the candidate scan cap is calculated according to the top plane equation, and the top plane point cloud is selected from the candidate scan cap point cloud cluster according to the distance.

[0008] In an optional implementation, determining the transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model based on the top plane point cloud and the top plane model of the pre-generated scan cap point cloud model includes: Using a global registration algorithm, based on the top plane point cloud and the top plane model, the initial transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model is calculated, and the first average normal vector of the top plane of the candidate scan cap is calculated based on the top plane point cloud. The second average normal vector of the top plane model is transformed based on the initial transformation matrix to determine whether the orientation of the transformed second average normal vector is consistent with that of the first average normal vector. When the orientations are consistent, the initial transformation matrix is ​​determined as the transformation matrix; In the case of inconsistent orientation, the initial transformation matrix is ​​normalized based on the top plane model to obtain the transformation matrix.

[0009] In an optional implementation, the step of performing normal correction on the initial transformation matrix based on the top plane model to obtain the transformation matrix includes: The symmetry axis and symmetry center of the top plane model are transformed based on the initial transformation matrix, and a flip matrix is ​​constructed based on the transformed symmetry axis. The normal correction parameter is calculated based on the transformed symmetry center and the flip matrix. The transformation matrix is ​​calculated based on the normal correction parameters and the initial transformation matrix.

[0010] In an optional implementation, the spatial mapping of the scanned hat point cloud model and the candidate scanned hat point cloud clusters based on the transformation matrix includes: The scanning cap point cloud model is transformed based on the transformation matrix to map the scanning cap point cloud model to the user's edentulous jaw region; The method further includes: Calculate the degree of matching between the mapped scan cap point cloud model and the candidate scan cap point cloud cluster.

[0011] Secondly, this application provides a scanning cap positioning device, the device comprising: The acquisition module is used to acquire point cloud data of the user's edentulous jaw region and determine at least one candidate scan cap point cloud cluster based on the point cloud data; The positioning module is used to determine the top plane equation based on the candidate scan cap point cloud cluster, and to filter out the top plane point cloud of the candidate scan cap top plane from the candidate scan cap point cloud cluster based on the top plane equation. The positioning module is further configured to determine the transformation matrix between the candidate scanning hat point cloud cluster and the scanning hat point cloud model based on the top plane point cloud and the top plane model of the pre-generated scanning hat point cloud model, and to perform spatial mapping between the scanning hat point cloud model and the candidate scanning hat point cloud cluster based on the transformation matrix. The positioning module is further configured to determine the candidate scanning cap point cloud cluster as the scanning cap point cloud cluster of the target scanning cap when the degree of matching between the spatially mapped scanning cap point cloud model and the candidate scanning cap point cloud cluster is greater than a preset matching threshold.

[0012] In an optional implementation, the acquisition module is further configured to perform Euclidean clustering on the point cloud data based on the Euclidean distance between the point cloud data to obtain multiple point cloud clusters; for each point cloud cluster, determine whether the number of point cloud data in the point cloud cluster is within a preset number range; if the number of point cloud data is within the preset number range, then determine the point cloud cluster as the candidate scan cap point cloud cluster.

[0013] Thirdly, this application provides a terminal device including a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the method described in any of the foregoing embodiments.

[0014] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the foregoing embodiments.

[0015] The scanning cap positioning method, apparatus, terminal device, and computer-readable storage medium provided in this application embodiment allow the terminal device to acquire point cloud data of the user's edentulous jaw region, determine at least one candidate scanning cap point cloud cluster based on the point cloud data, and determine the top plane point cloud of the top plane of the candidate scanning cap based on the candidate scanning cap point cloud cluster. Then, based on the top plane point cloud and the top plane model of the pre-generated scanning cap point cloud model, a transformation matrix between the candidate scanning cap point cloud cluster and the scanning cap point cloud model is determined. Based on the transformation matrix, the scanning cap point cloud model and the candidate scanning cap point cloud cluster are spatially mapped, and the matching degree between the two after mapping is used to determine whether the target scanning cap is successfully matched. In this way, the transformation matrix can be determined and the spatial mapping between the scanning cap point cloud model and the candidate scanning cap point cloud cluster can be realized by using the top plane model of the pre-calibrated scanning cap point cloud model and the top plane point cloud in the scanned point cloud cluster. Thus, the positioning of the scanning cap can be determined based on the degree of matching of the mapped point cloud. In this way, it is not necessary to capture the full surface information of the scanning cap. Only the top area of ​​the scanning cap and a small amount of low overlap data of the sides need to be obtained to achieve the positioning and registration of the scanning cap. Therefore, the scanning time can be reduced, and the clinical diagnosis and treatment experience and efficiency of the user can be improved.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This diagram illustrates point cloud data from a scanning cap in the relevant technology. Figure 2 A schematic diagram of the scan cap registration result in the related technology is shown; Figure 3 A schematic diagram of the positioning system is shown; Figure 4 A block diagram of a terminal device provided in an embodiment of this application is shown; Figure 5 This paper illustrates a flowchart of a scanning cap positioning method provided in an embodiment of this application. Figure 6 This diagram illustrates a candidate scan cap point cloud cluster obtained through the scan cap localization method provided in this application embodiment; Figure 7 This diagram illustrates the scan cap registration result achieved by the scan cap positioning method provided in this application embodiment; Figure 8 This paper illustrates a functional block diagram of a scanning cap positioning device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0021] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0022] In related technologies, scanning caps with highly symmetrical geometric structures such as cylinders or cones are commonly used. The shape characteristics of these scanning caps often lack directional identification, making it difficult to determine the spatial orientation and rotation angle of the scanning cap based on local data. Therefore, scanning cap positioning and registration often rely on the complete optical capture of the overall shape of the scanning cap.

[0023] Figure 1 This is a schematic diagram of point cloud data for a scanning cap in related technologies. Figure 2 For a schematic diagram of the scan cap registration result in related technologies, please refer to [link / reference]. Figures 1-2 In order to achieve accurate registration of the scanning cap, the relevant technical requirements are that the intraoral scanner must capture all surface information of the scanning cap from 360°, ensuring that the scanning data covers the top of the scanning cap, the entire side surface, and the edge contour at the junction with the gum line.

[0024] This mandatory circumferential scanning method presents significant technical challenges: Firstly, doctors need to repeatedly adjust the probe angle within the patient's mouth, performing multiple circumferential scans around each scanning cap. For edentulous patients with 4 to 6 implants, dozens of such high-precision circumferential scans are required in a single treatment, greatly increasing the complexity of the procedure and the physical burden on the doctor. Secondly, the prolonged and extensive intraoral probe movement extends the total scanning time, exacerbating patient discomfort and easily inducing pharyngeal reflexes, nausea, or even vomiting. This is particularly pronounced in elderly patients with limited mouth opening or sensitive pharyngeal reflexes, leading to scan interruptions and frequent rescans, ultimately affecting overall treatment efficiency and clinical success rates.

[0025] Based on this, embodiments of this application provide a scanning cap positioning method, apparatus, terminal device, and computer-readable storage medium to solve the above-mentioned problems.

[0026] Specifically, Figure 3 For a schematic diagram of the positioning system, please refer to [link / reference]. Figure 3 The positioning system includes a terminal device and a scanning device, and the terminal device and the scanning device are communicatively connected. The scanning device is used to scan three-dimensional point cloud data of the patient's edentulous jaw area and sends the point cloud data to the terminal device for processing. The terminal device is then used to locate the scanning cap based on the point cloud data sent by the scanning device.

[0027] exist Figure 3 On this basis, Figure 4 Please refer to the block diagram of the terminal device provided in the embodiments of this application. Figure 4 The terminal device includes a memory, a processor, and a communication module. These components are electrically connected directly or indirectly to enable data transmission or interaction. For example, they can be electrically connected via one or more communication buses or signal lines.

[0028] Memory is used to store computer programs or data that can be executed by a processor. Memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc.

[0029] The processor is used to read / write data or computer programs stored in the memory, and execute the computer program to implement the scanning cap positioning method provided in the embodiments of this application.

[0030] The communication module is used to establish communication connections between the terminal device and other communication terminals via the network, and to send and receive data via the network.

[0031] It should be understood that, Figure 4 The structure shown is only a schematic diagram of the terminal device; the terminal device may also include components that are larger than those shown. Figure 4 The more or fewer components shown, or having the same Figure 3 The different configurations shown. Figure 4 The components shown can be implemented using hardware, software, or a combination thereof.

[0032] The following is based on the above. Figure 3 The terminal device in this application is the execution subject. The scanning cap positioning method provided in the embodiments of this application is described by way of example in conjunction with the flowchart.

[0033] Specifically, Figure 5 For a flowchart illustrating the scanning cap positioning method provided in this application embodiment, please refer to [link / reference]. Figure 5 The method includes: Step S20: Obtain point cloud data of the user's edentulous jaw region, and determine at least one candidate scan cap point cloud cluster based on the point cloud data.

[0034] Step S21: Determine the top plane equation based on the candidate scan cap point cloud cluster, and select the top plane point cloud of the candidate scan cap top plane from the candidate scan cap point cloud cluster based on the top plane equation.

[0035] In this embodiment, the scanning device can perform optical three-dimensional acquisition of the maxillary or mandibular region of the patient's missing teeth, thereby obtaining three-dimensional point cloud data, and send the point cloud data to the terminal device in real time. The terminal device can analyze the point cloud data to identify at least one candidate scan cap point cloud cluster that is suspected to be a scan cap pair.

[0036] Understandably, each candidate scan cap point cloud cluster contains multiple point cloud data.

[0037] In this embodiment, the top of each scanning cap is a planar region with a clear geometric boundary. The terminal device can fit the top plane equation for each scanning cap point cloud cluster, thereby filtering out the top plane point clouds that may belong to the top plane.

[0038] Understandably, in addition to the top planar point cloud, the candidate scan cap point cloud cluster may also include other point clouds that can characterize the side morphology of the scan cap.

[0039] Step S22: Based on the top plane point cloud and the top plane model of the pre-generated scan cap point cloud model, determine the transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model, and perform spatial mapping on the scan cap point cloud model and the candidate scan cap point cloud cluster based on the transformation matrix.

[0040] Step S23: If the matching degree between the spatially mapped scan cap point cloud model and the candidate scan cap point cloud cluster is greater than the preset matching threshold, the candidate scan cap point cloud cluster is determined to be the point cloud cluster corresponding to the target scan cap.

[0041] Understandably, after the terminal device determines the candidate scanning cap point cloud cluster, it also needs to determine the spatial relationship between the candidate scanning cap point cloud cluster and the standard model. By spatially mapping the scanning cap point cloud model and the candidate scanning cap point cloud cluster, it is convenient to perform subsequent point cloud matching and comparison, and at the same time, it is convenient to determine the pose of the scanning cap in the user's edentulous jaw area.

[0042] In one possible implementation, the scanning cap point cloud model can be generated in advance, and the top plane region point cloud in the scanning cap point cloud model can be obtained by means of manual cropping, etc., and stored as the top plane model.

[0043] In this embodiment, the transformation matrix may include two parts: rotation and translation. The terminal device can perform spatial mapping on the scanned cap point cloud model and the candidate scanned cap point cloud cluster based on the transformation matrix.

[0044] In one possible implementation, the terminal device can perform coordinate transformation on the scanning cap point cloud model based on the transformation matrix, so that its posture and position are consistent with the actual candidate scanning cap point cloud cluster in the patient's mouth, thereby mapping the virtual model to the edentulous area inside the real oral cavity.

[0045] In another possible implementation, the terminal device can also transform the candidate scan cap point cloud cluster to the reference coordinate system where the scan cap point cloud model is located based on the transformation matrix, so that the two are in the same mathematical space, which is convenient for subsequent comparison.

[0046] Subsequently, the terminal device can determine the degree of matching between the scan cap point cloud model and the candidate scan cap point cloud clusters based on the spatial mapping. This degree of matching can be the geometric overlap between the spatially mapped scan cap point cloud model and the candidate scan cap point cloud clusters. When this degree of matching is greater than a preset matching threshold, it can be determined that the current candidate scan cap point cloud cluster and the standard scan cap model have achieved sufficient consistency in spatial position and orientation, thereby confirming that the point cloud cluster is indeed the scan data corresponding to a certain real scan cap, thus completing the localization and registration of a single scan cap.

[0047] Figure 6 This is a schematic diagram of a candidate scan cap point cloud cluster obtained by the scan cap localization method provided in the embodiments of this application. Figure 7 For a schematic diagram of the scan cap registration result achieved by the scan cap positioning method provided in this application embodiment, please refer to [link / reference]. Figures 6-7 With the scanning cap positioning method provided in this application embodiment, the terminal device only needs to obtain point cloud data of the top area of ​​the scanning cap and a small amount of low overlap point cloud data of the side to achieve accurate positioning and registration of the scanning cap.

[0048] The scanning cap positioning method provided in this application embodiment allows the terminal device to acquire point cloud data of the user's edentulous jaw region, determine at least one candidate scanning cap point cloud cluster based on the point cloud data, and determine the top plane point cloud of the top plane of the candidate scanning cap based on the candidate scanning cap point cloud cluster. Then, based on the top plane point cloud and the top plane model of the pre-generated scanning cap point cloud model, a transformation matrix between the candidate scanning cap point cloud cluster and the scanning cap point cloud model is determined. Based on the transformation matrix, the scanning cap point cloud model and the candidate scanning cap point cloud cluster are spatially mapped, and the matching degree between the two after mapping is used to determine whether the target scanning cap is successfully matched. In this way, the transformation matrix can be determined and the spatial mapping between the scanning cap point cloud model and the candidate scanning cap point cloud cluster can be realized by using the top plane model of the pre-calibrated scanning cap point cloud model and the top plane point cloud in the scanned point cloud cluster. Thus, the positioning of the scanning cap can be determined based on the degree of matching of the mapped point cloud. In this way, it is not necessary to capture the full surface information of the scanning cap. Only the top area of ​​the scanning cap and a small amount of low overlap data of the sides need to be obtained to achieve the positioning and registration of the scanning cap. Therefore, the scanning time can be reduced, and the clinical diagnosis and treatment experience and efficiency of the user can be improved.

[0049] The following provides a possible implementation method for determining at least one candidate scan cap point cloud cluster based on point cloud data.

[0050] In this embodiment, the terminal device may perform Euclidean clustering on the point cloud data according to the Euclidean distance between the point cloud data to obtain a plurality of point cloud clusters; for each point cloud cluster respectively, determine whether the number of point cloud data in the point cloud cluster is within a preset number range; if the number of point cloud data is within the preset number range, determine the point cloud cluster as a candidate scan cap point cloud cluster.

[0051] In this embodiment, considering that the original point cloud data obtained by intraoral scanning of edentulous patients has the characteristics of high density, mixed noise, and serious local overlap, direct clustering analysis on the original point cloud will lead to excessive calculation burden and is easily interfered by noise points, which affects the subsequent recognition accuracy. Therefore, the terminal device may first perform voxel filtering downsampling on the three-dimensional point cloud data of the patient's edentulous area obtained by the scanning device.

[0052] This operation can divide the space into a number of cubic voxel grids with fixed side lengths, and only retain one representative point in each voxel—usually the coordinate mean of all points in the voxel or the point closest to the center, so that the point cloud density can be significantly reduced on the premise of substantially maintaining the geometric structure, and the downsampled point cloud data can be obtained.

[0053] Thereafter, the terminal device may use the Euclidean clustering algorithm to perform a clustering operation on the downsampled point cloud data, that is, determine whether points belong to the same cluster according to the Euclidean distance between points. Specifically, for any two points Point i and Point j , if their Euclidean distance satisfies ||Point i -Point j ||<D, that is, the distance between the two points is less than the preset clustering distance threshold D, then the two points are considered to belong to the same cluster, thereby dividing the plurality of point cloud data into a plurality of point cloud clusters, and each point cloud cluster includes a plurality of point cloud data.

[0054] It should be noted that this clustering is not based on the global geometric shape as the criterion, but completely depends on the spatial relationship in the local neighborhood, so it is robust to common clinical situations such as possible occlusion, tilt or partial missing of the scan cap in the mouth.

[0055] On this basis, the terminal device may, for each point cloud cluster respectively, count the number of point cloud data contained therein, and determine whether the number falls within a preset number range [Nmin,Nmax], wherein Nmin and Nmax are integer thresholds, and their values can be adaptively determined according to actual application scenarios or empirical values. In one example, the number of point clouds corresponding to the scan cap point cloud model may be 5000, based on which Nmin can be 2000 and Nmax can be 20000.

[0056] Understandably, if the number of point cloud data contained in a certain point cloud cluster falls within this range, then the point cloud cluster can be determined as a candidate scan hat point cloud cluster, and subsequent operations can be performed on it.

[0057] In one possible implementation, after obtaining the candidate scan cap point cloud cluster, the terminal device can perform plane fitting on the point cloud data in the candidate scan cap point cloud cluster using the RANSAC algorithm to obtain the top plane equation; calculate the distance between each point cloud data in the candidate scan cap point cloud cluster and the top plane of the candidate scan cap based on the top plane equation, and filter out the top plane point cloud from the candidate scan cap point cloud cluster based on the distance.

[0058] In this embodiment, the terminal device can execute the RANSAC algorithm on the candidate scan cap point cloud cluster to achieve plane fitting through iterative random sampling and consistency verification mechanism, and obtain the top plane equation ax+by+cz+d=0 of the candidate scan cap top plane.

[0059] Subsequently, the terminal device can use the formula Calculate the vertical distance from each point cloud in the candidate scan cap point cloud cluster to the top plane of the candidate scan cap. The system identifies target point clouds with vertical distances less than a preset distance threshold, and then designates these target point clouds as the top plane point cloud. , , These are the x-axis, y-axis, and z-axis coordinates of point cloud i, respectively.

[0060] Thus, the top plane in the candidate scan cap point cloud cluster can be calculated by relying only on the local point cloud distribution, without relying on the complete cylindrical surface information.

[0061] Subsequently, the terminal device can use a global registration algorithm to calculate the initial transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model based on the top plane point cloud and the top plane model.

[0062] In this embodiment, the terminal device can process the top plane point cloud and the top plane model using a global registration algorithm to calculate the initial transformation matrix. This initial transformation matrix T can be characterized as... , where R is the rotation matrix and t is the translation vector.

[0063] However, considering that the scanning cap has a clear orientation inside the user's mouth, and that three-dimensional registration cannot be achieved by relying solely on planar geometric matching, this can lead to ambiguity in the orientation of the plane. Therefore, it is necessary to introduce a planar normal vector to determine the orientation.

[0064] Specifically, the terminal device can compute the first average normal vector of the top plane of the candidate scanning cap based on the top plane point cloud, and then transform the second average normal vector of the top plane model based on the initial transformation matrix to determine whether the orientation of the transformed second average normal vector is consistent with that of the first average normal vector.

[0065] In practical applications, the terminal device can first accumulate and normalize the normal vectors of all top plane point clouds of the candidate scanned cap point cloud cluster to obtain the first average normal vector, which is used to characterize the true orientation of the top plane obtained by the actual scan.

[0066] In addition, the terminal device can perform the same operation on the top plane model of the scanning cap point cloud model in advance to obtain the second plane normal vector for storage, which is used to characterize the design orientation of the top plane of the scanning cap under ideal conditions.

[0067] In one possible implementation, the terminal device can perform an inverse transformation on the normal vector of the second plane based on the initial transformation matrix, calculated as follows: This allows us to obtain the normal orientation of the transformed top plane model in the current coordinate system. This is the transformed second average normal vector. Let R be the second average normal vector, and R be the rotation matrix in the initial transformation matrix.

[0068] Next, the terminal device can determine whether the orientation of the transformed second average normal vector is consistent with that of the first average normal vector through dot product operation. That is, if Then it can be determined that the orientation is consistent. If so, it can be determined that the orientations are inconsistent. This is the first average normal vector.

[0069] In this embodiment, if the orientations are inconsistent, it indicates that the orientations of the actual candidate scan cap point cloud clusters and the standard scan cap point cloud model have been flipped when the initial transformation matrix is ​​involved in the transformation. Therefore, the initial transformation matrix needs to be corrected.

[0070] Understandably, when the orientations are consistent, the terminal device can determine the initial transformation matrix as the transformation matrix; while when the orientations are inconsistent, the terminal device can perform normal correction on the initial transformation matrix based on the top plane model to obtain the transformation matrix.

[0071] Understandably, normal correction of the initial transformation matrix does not refer to simply adjusting the rotation angle, but rather to performing a flip operation based on the inherent geometric symmetry of the top plane model of the scan cap through its axis of symmetry and center of symmetry, thereby eliminating the ambiguity of normal orientation caused by relying solely on registration of two planes.

[0072] In one possible implementation, the terminal device can transform the axis of symmetry and the center of symmetry of the top plane model based on the initial transformation matrix, construct a flip matrix based on the transformed axis of symmetry, calculate the normal correction parameter based on the transformed center of symmetry and the flip matrix, and calculate the transformation matrix based on the normal correction parameter and the initial transformation matrix.

[0073] In this embodiment, the terminal device can first pre-calibrate the axis of symmetry of the top plane model. and center of symmetry The coordinate transformations are performed according to the rotation matrix R and translation vector t in the initial transformation matrix T to obtain the transformed axis of symmetry. With the transformed center of symmetry .in, , .in, The four-dimensional homogeneous coordinate system is centered.

[0074] Subsequently, the terminal device can Let the direction vector (x, y, z) be the rotation axis. Construct a flip matrix R that rotates the vector by 180 degrees around this axis. 180 Its mathematical expression is , where the identity matrix Antisymmetric matrix .

[0075] Based on this, the terminal device can incorporate the transformed center of symmetry. The correction parameter Tcorr is constructed using the flip matrix R180, and its mathematical expression is as follows: The correction parameter Tcorr is then multiplied by the initial transformation matrix T to obtain the transformation matrix. ,Right now .

[0076] Next, the terminal device can transform the scanning cap point cloud model based on the transformation matrix to map the scanning cap point cloud model to the user's edentulous jaw region, and calculate the degree of matching between the mapped scanning cap point cloud model and the candidate scanning cap point cloud clusters, thereby determining whether the scanning cap has been successfully positioned and registered based on the degree of matching.

[0077] In this embodiment, the terminal device can transform the pre-built standard scanning cap point cloud model into a spatial coordinate system according to the solved transformation matrix, so that the model is aligned with the candidate scanning cap point cloud cluster actually collected in the patient's mouth in three-dimensional space, thereby realizing the spatial correspondence between the virtual model and the real scanning data under a unified coordinate system.

[0078] In practical applications, this transformation process includes two basic operations: translation and rotation. After the mapping is completed, the terminal device can determine the geometric consistency between the transformed model and the real point cloud, thereby determining the degree of matching between the model and the real point cloud. When the degree of matching is greater than a preset matching threshold, the terminal device can determine that the candidate point cloud cluster is indeed the point cloud corresponding to the real scanning cap, thus completing the localization confirmation of a single scanning cap.

[0079] In this way, relying only on limited scanning data from the top planar region, the accurate position of the scanning cap in the patient's mouth can be identified through spatial mapping and matching verification, avoiding the operational redundancy caused by the requirement to cover the entire cylindrical surface in traditional methods.

[0080] To perform the corresponding steps in the above embodiments and various possible methods, an implementation of a scanning cap positioning device is given below. Optionally, the scanning cap positioning device can adopt the above-described... Figure 4 The device structure of the terminal device is shown. Further, please refer to... Figure 8 , Figure 8 This is a functional block diagram of a scanning cap positioning device provided in an embodiment of this application. It should be noted that the basic principle and technical effects of the scanning cap positioning device provided in this embodiment are the same as those in the above embodiments. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above embodiments. The scanning cap positioning device includes: an acquisition module and a positioning module.

[0081] The acquisition module is used to acquire point cloud data of the user's edentulous jaw region and determine at least one candidate scan cap point cloud cluster based on the point cloud data.

[0082] Understandably, this acquisition module can be used to perform the above step S20.

[0083] The localization module is used to determine the top plane equation based on the candidate scan cap point cloud cluster, and to filter out the top plane point cloud of the candidate scan cap top plane from the candidate scan cap point cloud cluster based on the top plane equation. The localization module is also used to determine the transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model based on the top plane point cloud and the top plane model of the pre-generated scan cap point cloud model, and to perform spatial mapping between the scan cap point cloud model and the candidate scan cap point cloud cluster based on the transformation matrix. The localization module is also used to determine the candidate scanning cap point cloud cluster as the scanning cap point cloud cluster of the target scanning cap when the degree of matching between the spatially mapped scanning cap point cloud model and the candidate scanning cap point cloud cluster is greater than a preset matching threshold.

[0084] Understandably, this positioning module can be used to perform the above steps S21 to S23.

[0085] Optionally, the acquisition module is further configured to perform Euclidean clustering on the point cloud data based on the Euclidean distance between the point cloud data to obtain multiple point cloud clusters; for each point cloud cluster, determine whether the number of point cloud data in the point cloud cluster is within a preset range; if the number of point cloud data is within the preset range, then the point cloud cluster is determined as a candidate scan cap point cloud cluster.

[0086] Optionally, the positioning module is also used to perform plane fitting on the point cloud data in the candidate scan cap point cloud cluster using the RANSAC algorithm to obtain the top plane equation; calculate the distance between each point cloud data in the candidate scan cap point cloud cluster and the top plane of the candidate scan cap according to the top plane equation, and filter out the top plane point cloud from the candidate scan cap point cloud cluster according to the distance.

[0087] Optionally, the positioning module is further configured to calculate, using a global registration algorithm, an initial transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model based on the top plane point cloud and the top plane model, and to calculate the first average normal vector of the top plane of the candidate scan cap based on the top plane point cloud; to transform the second average normal vector of the top plane model based on the initial transformation matrix, and to determine whether the orientation of the transformed second average normal vector is consistent with that of the first average normal vector; if the orientation is consistent, the initial transformation matrix is ​​determined as the transformation matrix; if the orientation is inconsistent, the initial transformation matrix is ​​normalized based on the top plane model to obtain the transformation matrix.

[0088] Optionally, the positioning module is also used to transform the axis of symmetry and the center of symmetry of the top plane model based on the initial transformation matrix, construct a flip matrix based on the transformed axis of symmetry, calculate the normal correction parameter based on the transformed center of symmetry and the flip matrix, and calculate the transformation matrix based on the normal correction parameter and the initial transformation matrix.

[0089] Optionally, the positioning module is also used to transform the scanning cap point cloud model based on the transformation matrix to map the scanning cap point cloud model to the user's edentulous jaw region.

[0090] Optionally, the localization module is also used to calculate the degree of matching between the mapped scan cap point cloud model and the candidate scan cap point cloud clusters.

[0091] Optionally, the above modules can be stored in the form of software or firmware. Figure 4 The memory shown is either stored in or embedded in the operating system (OS) of the terminal device, and can be used by... Figure 4 The processor executes the commands. Meanwhile, the data and program code required to execute these modules can be stored in memory.

[0092] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, can implement the scanning cap positioning method provided in this application.

[0093] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products 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, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive 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 a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0094] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0095] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0096] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for locating a scanning cap, characterized in that, The method includes: Acquire point cloud data of the user's edentulous jaw region, and determine at least one candidate scan cap point cloud cluster based on the point cloud data; The top plane equation is determined based on the candidate scan cap point cloud cluster, and the top plane point cloud of the candidate scan cap top plane is selected from the candidate scan cap point cloud cluster based on the top plane equation. Based on the top plane point cloud and the top plane model of the pre-generated scan cap point cloud model, the transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model is determined, and the scan cap point cloud model and the candidate scan cap point cloud cluster are spatially mapped based on the transformation matrix. If the degree of matching between the spatially mapped scan cap point cloud model and the candidate scan cap point cloud cluster is greater than a preset matching threshold, the candidate scan cap point cloud cluster is determined to be the point cloud cluster corresponding to the target scan cap.

2. The method according to claim 1, characterized in that, The step of determining at least one candidate scan cap point cloud cluster based on the point cloud data includes: Euclidean clustering is performed on the point cloud data based on the Euclidean distance between the point cloud data to obtain multiple point cloud clusters; For each of the point cloud clusters, determine whether the number of point cloud data in the point cloud cluster is within a preset range; If the number of point cloud data is within the preset range, then the point cloud cluster is determined as the candidate scan cap point cloud cluster.

3. The method according to claim 1, characterized in that, The step of determining the top plane equation based on the candidate scan cap point cloud cluster, and filtering the top plane point cloud of the top of the candidate scan cap from the candidate scan cap point cloud cluster based on the top plane equation, includes: The top plane equation is obtained by performing plane fitting on the point cloud data in the candidate scan cap point cloud cluster using the RANSAC algorithm. The distance between each point cloud data in the candidate scan cap point cloud cluster and the top plane of the candidate scan cap is calculated according to the top plane equation, and the top plane point cloud is selected from the candidate scan cap point cloud cluster according to the distance.

4. The method according to claim 1, characterized in that, The step of determining the transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model based on the top plane point cloud and the top plane model of the pre-generated scan cap point cloud model includes: Using a global registration algorithm, based on the top plane point cloud and the top plane model, the initial transformation matrix between the candidate scan cap point cloud cluster and the scan cap point cloud model is calculated, and the first average normal vector of the top plane of the candidate scan cap is calculated based on the top plane point cloud. The second average normal vector of the top plane model is transformed based on the initial transformation matrix to determine whether the orientation of the transformed second average normal vector is consistent with that of the first average normal vector. When the orientations are consistent, the initial transformation matrix is ​​determined as the transformation matrix; In the case of inconsistent orientation, the initial transformation matrix is ​​normalized based on the top plane model to obtain the transformation matrix.

5. The method according to claim 4, characterized in that, The step of performing normal correction on the initial transformation matrix based on the top plane model to obtain the transformation matrix includes: The symmetry axis and symmetry center of the top plane model are transformed based on the initial transformation matrix, and a flip matrix is ​​constructed based on the transformed symmetry axis. The normal correction parameter is calculated based on the transformed symmetry center and the flip matrix. The transformation matrix is ​​calculated based on the normal correction parameters and the initial transformation matrix.

6. The method according to claim 1, characterized in that, The spatial mapping of the scanned hat point cloud model and the candidate scanned hat point cloud clusters based on the transformation matrix includes: The scanning cap point cloud model is transformed based on the transformation matrix to map the scanning cap point cloud model to the user's edentulous jaw region; The method further includes: Calculate the degree of matching between the mapped scan cap point cloud model and the candidate scan cap point cloud cluster.

7. A scanning cap positioning device, characterized in that, The device includes: The acquisition module is used to acquire point cloud data of the user's edentulous jaw region and determine at least one candidate scan cap point cloud cluster based on the point cloud data; The positioning module is used to determine the top plane equation based on the candidate scan cap point cloud cluster, and to filter out the top plane point cloud of the candidate scan cap top plane from the candidate scan cap point cloud cluster based on the top plane equation. The positioning module is further configured to determine the transformation matrix between the candidate scanning hat point cloud cluster and the scanning hat point cloud model based on the top plane point cloud and the top plane model of the pre-generated scanning hat point cloud model, and to perform spatial mapping between the scanning hat point cloud model and the candidate scanning hat point cloud cluster based on the transformation matrix. The positioning module is further configured to determine the candidate scanning cap point cloud cluster as the scanning cap point cloud cluster of the target scanning cap when the degree of matching between the spatially mapped scanning cap point cloud model and the candidate scanning cap point cloud cluster is greater than a preset matching threshold.

8. The apparatus according to claim 7, characterized in that, The acquisition module is further configured to perform Euclidean clustering on the point cloud data according to the Euclidean distance between the point cloud data to obtain multiple point cloud clusters; for each point cloud cluster, determine whether the number of point cloud data in the point cloud cluster is within a preset number range; if the number of point cloud data is within the preset number range, then determine the point cloud cluster as the candidate scan cap point cloud cluster.

9. A terminal device, characterized in that, It includes a processor and a memory, the memory storing a computer program executable by the processor, the processor being able to execute the computer program to implement the method of any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-6.

Images