3D data registration method, device, equipment and medium for oral scanning

Abstract

The present application relates to oral cavity 3D data scanning technology, and discloses a 3D data registration method for oral cavity scanning, comprising: constructing a voxel model based on real-time oral cavity scanning point cloud data, frame-by-frame registering real-time oral cavity to-be-registered point cloud data and the voxel model, if the real-time oral cavity to-be-registered point cloud data and the voxel model fail to be registered for a continuous preset number of frames, selecting a to-be-registered voxel set from the voxel model through a pre-constructed repositioning method, if the real-time oral cavity to-be-registered point cloud data and the voxel model fail to be registered for a continuous preset number of frames, selecting a to-be-registered voxel set from the voxel model through a pre-constructed positioning method, performing point cloud coarse registration processing and point cloud fine registration processing on the real-time oral cavity to-be-registered point cloud data and the to-be-registered voxel set, and obtaining a registration result. The present application also proposes a 3D data registration device and equipment for oral cavity scanning and a storage medium. The present application can improve the speed and accuracy of oral cavity scanning data registration.

Description

Technical Field

[0001] This invention relates to the field of oral 3D data scanning technology, and in particular to a 3D data registration method, apparatus, electronic device, and computer-readable storage medium for oral scanning. Background Technology

[0002] With the increasing use of intraoral scanners, users have placed higher demands on scanning speed and accuracy. During intraoral data scanning, a "voxel" structure is typically used to store the scan data for easier management. For example, multiple voxels can be used to store and manage multi-frame point clouds representing the current three-dimensional morphology of a tooth. Simultaneously, when using a scanner to acquire images intraorally, to obtain more accurate imaging data, each time new scan data ("point cloud to be registered") is input, the point cloud to be registered is registered with multiple existing voxel data to find its position in the current imaging model, completing data registration and fusion.

[0003] However, in actual real-time scanning applications, there are continuous scanning scenarios and non-continuous scanning scenarios (due to the limitations of the scanning environment, it is not possible to use the scanner for continuous scanning. After the scanning is interrupted, it is necessary to continue scanning from any position of the already scanned model). In the existing technology, for any scenario, when new scanning data is input each time, the new scanning data is registered with all current voxels. Due to the large number of voxels, the speed and accuracy of data registration are not high. Summary of the Invention

[0004] This invention provides a 3D data registration method, apparatus, electronic device, and readable storage medium for oral scans, the main purpose of which is to improve the speed and accuracy of oral scan data registration.

[0005] To achieve the above objectives, the present invention provides a 3D data registration method for oral cavity scanning, comprising:

[0006] Acquire real-time oral cavity scanning point cloud data, and construct a voxel model based on the real-time oral cavity scanning point cloud data;

[0007] Acquire real-time oral cavity point cloud data to be registered, and perform frame-by-frame registration between the real-time oral cavity point cloud data to be registered and the voxel model;

[0008] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, then it is determined that the frame-by-frame registration has failed, and a set of voxels to be registered is selected from the voxel model through a pre-constructed relocation method.

[0009] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a number of consecutive preset frames, then the frame-by-frame registration is determined to be successful, and the set of voxels to be registered is selected from the voxel model using a pre-constructed localization method.

[0010] The real-time oral cavity point cloud data to be registered and the set of voxels to be registered are subjected to coarse point cloud registration processing and fine point cloud registration processing to obtain the registration result.

[0011] Optionally, constructing a voxel model based on the real-time oral cavity scanning point cloud data includes: arranging the voxels in the real-time oral cavity scanning point cloud data in a temporal sequence according to the scanning time of the real-time oral cavity scanning point cloud data to obtain a voxel model.

[0012] Optionally, the step of performing frame-by-frame registration between the real-time oral cavity point cloud data to be registered and the voxel model includes:

[0013] Point cloud data of a consecutive preset number of frames are selected from the real-time oral cavity point cloud data to be registered and registered with the voxel with the closest temporal sequence in the voxel model.

[0014] Optionally, the step of selecting the set of voxels to be registered from the voxel model using a pre-built relocation method includes:

[0015] According to the principle of closest temporal sequence, a first preset number of voxels are selected from the voxel model as voxels to be registered;

[0016] A second preset number of voxels are selected from the voxel model according to the random selection principle as voxels to be registered;

[0017] The set of voxels to be registered is obtained by summing all voxels selected based on the principle of closest temporal sequence and the principle of random selection.

[0018] Optionally, the step of selecting the set of voxels to be registered from the voxel model using a pre-built localization method includes:

[0019] According to the principle of closest temporal sequence, a third preset number of voxels are selected from the voxel model as voxels to be registered;

[0020] According to the spatial priority principle, a fourth preset number of voxels are selected from the voxel model as voxels to be registered;

[0021] The set of voxels to be registered is obtained by summing all voxels selected based on the principle of closest temporal sequence and the principle of spatial priority.

[0022] Optionally, the step of selecting a fourth preset number of voxels from the voxel model as voxels to be registered according to the spatial priority principle includes:

[0023] The centroid coordinates of the voxel with the closest temporal sequence in the voxel model are used as the center, and a neighborhood space is constructed with a preset neighborhood radius.

[0024] The fourth preset number of voxels are selected from the neighborhood space as voxels to be registered.

[0025] Optionally, after performing coarse and fine registration processing on the real-time oral cavity point cloud data to be registered and the set of voxels to be registered to obtain the registration result, the method further includes:

[0026] If the registration result is that the point cloud registration is successful, the voxel model is updated using the real-time oral cavity point cloud data to be registered, and the steps of obtaining the real-time oral cavity point cloud data to be registered and registering the real-time oral cavity point cloud data with the voxel model frame by frame are returned until the voxel model meets the preset accuracy requirements or a stop registration command is received.

[0027] If the registration result is a point cloud registration failure, return to the step of obtaining real-time oral cavity point cloud data to be registered and performing frame-by-frame registration of the real-time oral cavity point cloud data to be registered with the voxel model.

[0028] To address the aforementioned problems, the present invention also provides a 3D data registration device for oral cavity scanning, the device comprising:

[0029] The voxel model construction module is used to acquire real-time oral cavity scanning point cloud data and construct a voxel model based on the real-time oral cavity scanning point cloud data.

[0030] The frame-by-frame registration module is used to acquire real-time oral cavity point cloud data to be registered and to perform frame-by-frame registration between the real-time oral cavity point cloud data to be registered and the voxel model.

[0031] The voxel selection module is used to determine frame-by-frame registration failure if the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, and select a set of voxels to be registered from the voxel model using a pre-built relocalization method; if the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, it is determined that frame-by-frame registration is successful, and a set of voxels to be registered is selected from the voxel model using a pre-built localization method.

[0032] The voxel registration module is used to perform coarse point cloud registration processing and fine point cloud registration processing on the real-time oral cavity point cloud data to be registered and the set of voxels to be registered, so as to obtain the registration result.

[0033] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0034] Memory, storing at least one computer program; and

[0035] The processor executes the computer program stored in the memory to implement the 3D data registration method for oral scanning described above.

[0036] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the 3D data registration method for oral scanning described above.

[0037] This embodiment performs frame-by-frame registration of real-time oral cavity point cloud data to be registered with a voxel model. When frame-by-frame registration fails, a pre-built relocation method is used to select the set of voxels to be registered from the voxel model. When frame-by-frame registration succeeds, a pre-built localization method is used to select the set of voxels to be registered from the voxel model. During intraoral scanning, the two registration methods, "localization" and "relocation," are automatically switched according to the actual scanning situation, ensuring both the accuracy and smoothness of real-time continuous scanning, as well as the response speed and accuracy of resuming scanning after a break. Therefore, the 3D data registration method, device, electronic device, and computer-readable storage medium for oral scanning proposed in this invention can improve the speed and accuracy of oral scanning data registration. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating a 3D data registration method for oral cavity scanning provided in an embodiment of the present invention.

[0039] Figure 2 This is a functional block diagram of a 3D data registration device for oral cavity scanning provided in an embodiment of the present invention;

[0040] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the 3D data registration method for oral scanning, according to an embodiment of the present invention.

[0041] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0042] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0043] This application provides a 3D data registration method for oral cavity scanning. The execution entity of the 3D data registration method for oral cavity scanning includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the 3D data registration method for oral cavity scanning can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0044] Reference Figure 1 The diagram shown is a flowchart illustrating a 3D data registration method for oral cavity scanning according to an embodiment of the present invention. In this embodiment, the 3D data registration method for oral cavity scanning includes:

[0045] S1. Acquire real-time oral cavity scanning point cloud data, and construct a voxel model based on the real-time oral cavity scanning point cloud data.

[0046] In this embodiment of the invention, the real-time oral scanning point cloud data refers to three-dimensional point cloud data obtained by scanning the object under test using an intraoral scanner. This includes the external and internal three-dimensional density data of the object under test. The data's constituent unit is called a voxel, which contains not only location information but also information such as density and size. For example, multiple frames of point cloud data of the three-dimensional morphology of teeth obtained by an intraoral scanner can be stored and managed using multiple voxels.

[0047] In an optional embodiment of the present invention, the step of constructing a voxel model based on the real-time oral cavity scanning point cloud data includes: arranging the voxels in the real-time oral cavity scanning point cloud data in a temporal sequence according to the scanning time of the real-time oral cavity scanning point cloud data to obtain a voxel model.

[0048] S2. Obtain real-time oral cavity point cloud data to be registered, and perform frame-by-frame registration between the real-time oral cavity point cloud data to be registered and the voxel model.

[0049] In this embodiment of the invention, the real-time oral registration point cloud data refers to the new scanning data (i.e., the registration point cloud) input by the intraoral scanner. The registration point cloud will be registered with multiple voxels in the voxel model to find the position of the registration point cloud in the current voxel model and complete the data registration and fusion.

[0050] Specifically, the frame-by-frame registration of the real-time oral cavity point cloud data to be registered with the voxel model includes:

[0051] Point cloud data of a consecutive preset number of frames are selected from the real-time oral cavity point cloud data to be registered and registered with the voxel with the closest temporal sequence in the voxel model.

[0052] In one optional embodiment of the present invention, during actual oral cavity scanning, there are continuous scanning scenarios ("localization" scenarios) and non-continuous scanning scenarios ("relocalization" scenarios). By registering the point cloud data to be registered with the voxel model with the closest time sequence for a preset number of consecutive frames, that is, registering the input point cloud data to be registered with the point cloud with the greatest correlation in the previous scan, the scanning scenario can be accurately identified and the accuracy of data registration can be improved.

[0053] In one optional embodiment of the present invention, the consecutive preset number of frames can be 3 consecutive frames.

[0054] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, then it is determined that the frame-by-frame registration has failed, and S3 is executed to select a set of voxels to be registered from the voxel model through a pre-constructed relocation method.

[0055] In this embodiment of the invention, if frame-by-frame registration fails, it is determined to be a non-continuous scan. The voxel to be registered is found through a relocation method, thereby effectively ensuring that the scan can quickly return to the user-specified position after it is interrupted.

[0056] Specifically, the step of selecting the set of voxels to be registered from the voxel model using a pre-built relocation method includes:

[0057] According to the principle of closest temporal sequence, a first preset number of voxels are selected from the voxel model as voxels to be registered;

[0058] A second preset number of voxels are selected from the voxel model according to the random selection principle as voxels to be registered;

[0059] The set of voxels to be registered is obtained by summing all voxels selected based on the principle of closest temporal sequence and the principle of random selection.

[0060] In an optional embodiment of the present invention, in the voxel model obtained by real-time scanning, the update time of each voxel is recorded, and the voxels are sorted from oldest to newest according to the update time. J voxels at the end of the queue (a first preset number) are selected as registration voxels according to the "time-nearest principle". The voxels selected according to the "time-nearest principle" are called submap_1. Then, based on the "random selection principle", K voxels are randomly selected from all voxels in the voxel model as registration voxels. The voxels selected according to the "random selection principle" are called submap_2. The resulting J voxel submap_1 and K voxel submap_2 are used as the registration voxel set for the "relocalization" scenario.

[0061] In this embodiment of the invention, for the "relocation" operation of rescanning after a scan is interrupted, voxels are first screened according to the "time-nearest principle" and then the voxels to be registered are searched according to the "random selection principle". This effectively ensures the speed at which the scan returns to the user-specified position after the scan is interrupted and improves the data registration speed.

[0062] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, then the frame-by-frame registration is determined to be successful, and S4 is executed to select the set of voxels to be registered from the voxel model using a pre-constructed localization method.

[0063] Specifically, the step of selecting the set of voxels to be registered from the voxel model using a pre-built localization method includes:

[0064] According to the principle of closest temporal sequence, a third preset number of voxels are selected from the voxel model as voxels to be registered;

[0065] According to the spatial priority principle, a fourth preset number of voxels are selected from the voxel model as voxels to be registered;

[0066] The set of voxels to be registered is obtained by summing all voxels selected based on the principle of closest temporal sequence and the principle of spatial priority.

[0067] In this embodiment of the invention, when frame-by-frame registration is successful, it is determined to be a continuous scan. The voxels to be registered are searched by the positioning method. The voxels at the end of N queues (a third preset number) are selected as the voxels to be registered by the "temporal nearest principle". Similarly, the voxels selected according to the "temporal nearest principle" are called submap_1.

[0068] Specifically, the step of selecting a fourth preset number of voxels from the voxel model as voxels to be registered according to the spatial priority principle includes:

[0069] The centroid coordinates of the voxel with the closest temporal sequence in the voxel model are used as the center, and a neighborhood space is constructed with a preset neighborhood radius.

[0070] The fourth preset number of voxels are selected from the neighborhood space as voxels to be registered.

[0071] In an optional embodiment of the present invention, the centroid coordinates of the last updated voxel in the voxel model are used as the center, and voxels falling within a preset radius are searched as neighboring voxels. Simultaneously, in actual scanning, since the number of neighboring voxels is large, M voxels (a fourth preset number) are randomly selected from the neighboring voxels as voxels to be registered. The voxels selected according to the "spatial priority principle" are called submap_3. By selecting the neighboring voxels of the last updated voxel, while ensuring a higher registration success rate, a sufficient number of reliable registration relationships between voxels can be provided for purposes such as cumulative error calibration. The resulting N voxel submap_1 and M voxel submap_3 are used as the set of voxels to be registered in the "localization" scenario.

[0072] S5. Perform coarse point cloud registration processing and fine point cloud registration processing on the real-time oral cavity point cloud data to be registered and the set of voxels to be registered to obtain the registration result.

[0073] In this embodiment of the invention, the difference between the two scenarios of "localization" and "relocalization" lies in the different ways of selecting the voxel to be registered. The methods used when registering the point cloud to be registered and the voxel to be registered are the same, both of which are achieved through two methods: coarse registration and fine registration of the point cloud. The coarse registration of the point cloud includes a registration method based on exhaustive search and a registration method based on feature matching. The fine registration of the point cloud includes the ICP (Iterative Closest Point) algorithm and derivative algorithms based on ICP.

[0074] In another optional embodiment of the present invention, after performing coarse and fine registration processing on the real-time oral cavity point cloud data to be registered and the set of voxels to be registered to obtain the registration result, the method further includes:

[0075] If the registration result is that the point cloud registration is successful, the voxel model is updated using the real-time oral cavity point cloud data to be registered, and the steps of obtaining the real-time oral cavity point cloud data to be registered and registering the real-time oral cavity point cloud data with the voxel model frame by frame are returned until the voxel model meets the preset accuracy requirements or a stop registration command is received.

[0076] If the registration result is a point cloud registration failure, return to the step of obtaining real-time oral cavity point cloud data to be registered and performing frame-by-frame registration of the real-time oral cavity point cloud data to be registered with the voxel model.

[0077] In this embodiment of the invention, the registration result includes successful point cloud registration and failed point cloud registration. When point cloud registration is successful, the voxel model is updated using the successfully registered real-time oral cavity point cloud data to be registered. When point cloud registration fails, the real-time oral cavity point cloud data to be registered is reacquired for data registration.

[0078] This embodiment performs frame-by-frame registration of real-time oral cavity point cloud data to be registered with a voxel model. When frame-by-frame registration fails, a pre-built relocalization method is used to select the set of voxels to be registered from the voxel model. When frame-by-frame registration succeeds, a pre-built localization method is used to select the set of voxels to be registered from the voxel model. During intraoral scanning, the two registration methods, "localization" and "relocalization," are automatically switched according to the actual scanning situation. This ensures both the accuracy and smoothness of real-time continuous scanning, as well as the response speed and accuracy of resuming scanning after a break. Therefore, the 3D data registration method for oral cavity scanning proposed in this invention can improve the speed and accuracy of oral cavity scanning data registration.

[0079] like Figure 2 The diagram shown is a functional block diagram of a 3D data registration device for oral cavity scanning provided in an embodiment of the present invention.

[0080] The 3D data registration device 100 for oral cavity scanning described in this invention can be installed in an electronic device. Depending on the functions implemented, the 3D data registration device 100 for oral cavity scanning may include a voxel model construction module 101, a frame-by-frame registration module 102, a voxel selection module 103, and a voxel registration module 104. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0081] In this embodiment, the functions of each module / unit are as follows:

[0082] The voxel model construction module 101 is used to acquire real-time oral cavity scanning point cloud data and construct a voxel model based on the real-time oral cavity scanning point cloud data.

[0083] The frame-by-frame registration module 102 is used to acquire real-time oral cavity point cloud data to be registered and to perform frame-by-frame registration between the real-time oral cavity point cloud data to be registered and the voxel model.

[0084] The voxel selection module 103 is used to determine frame-by-frame registration failure if the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, and select a set of voxels to be registered from the voxel model using a pre-built relocation method; if the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, it is determined that frame-by-frame registration is successful, and select a set of voxels to be registered from the voxel model using a pre-built localization method.

[0085] The voxel registration module 104 is used to perform coarse point cloud registration processing and fine point cloud registration processing on the real-time oral cavity point cloud data to be registered and the set of voxels to be registered, so as to obtain the registration result.

[0086] In detail, the specific implementation methods of each module of the 3D data registration device 100 for oral cavity scanning are as follows:

[0087] Step 1: Acquire real-time oral cavity scanning point cloud data, and construct a voxel model based on the real-time oral cavity scanning point cloud data.

[0088] In this embodiment of the invention, the real-time oral scanning point cloud data refers to three-dimensional point cloud data obtained by scanning the object under test using an intraoral scanner. This includes the external and internal three-dimensional density data of the object under test. The data's constituent unit is called a voxel, which contains not only location information but also information such as density and size. For example, multiple frames of point cloud data of the three-dimensional morphology of teeth obtained by an intraoral scanner can be stored and managed using multiple voxels.

[0089] In an optional embodiment of the present invention, the step of constructing a voxel model based on the real-time oral cavity scanning point cloud data includes: arranging the voxels in the real-time oral cavity scanning point cloud data in a temporal sequence according to the scanning time of the real-time oral cavity scanning point cloud data to obtain a voxel model.

[0090] Step 2: Obtain real-time oral cavity point cloud data to be registered, and perform frame-by-frame registration between the real-time oral cavity point cloud data to be registered and the voxel model.

[0091] In this embodiment of the invention, the real-time oral registration point cloud data refers to the new scanning data (i.e., the registration point cloud) input by the intraoral scanner. The registration point cloud will be registered with multiple voxels in the voxel model to find the position of the registration point cloud in the current voxel model and complete the data registration and fusion.

[0092] Specifically, the frame-by-frame registration of the real-time oral cavity point cloud data to be registered with the voxel model includes:

[0093] Point cloud data of a consecutive preset number of frames are selected from the real-time oral cavity point cloud data to be registered and registered with the voxel with the closest temporal sequence in the voxel model.

[0094] In one optional embodiment of the present invention, during actual oral cavity scanning, there are continuous scanning scenarios ("localization" scenarios) and non-continuous scanning scenarios ("relocalization" scenarios). By registering the point cloud data to be registered with the voxel model with the closest time sequence for a preset number of consecutive frames, that is, registering the input point cloud data to be registered with the point cloud with the greatest correlation in the previous scan, the scanning scenario can be accurately identified and the accuracy of data registration can be improved.

[0095] In one optional embodiment of the present invention, the consecutive preset number of frames can be 3 consecutive frames.

[0096] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, then it is determined that the frame-by-frame registration has failed, and step three is executed: select the set of voxels to be registered from the voxel model through a pre-constructed relocation method.

[0097] In this embodiment of the invention, if frame-by-frame registration fails, it is determined to be a non-continuous scan. The voxel to be registered is found through a relocation method, thereby effectively ensuring that the scan can quickly return to the user-specified position after it is interrupted.

[0098] Specifically, the step of selecting the set of voxels to be registered from the voxel model using a pre-built relocation method includes:

[0099] According to the principle of closest temporal sequence, a first preset number of voxels are selected from the voxel model as voxels to be registered;

[0100] A second preset number of voxels are selected from the voxel model according to the random selection principle as voxels to be registered;

[0101] The set of voxels to be registered is obtained by summing all voxels selected based on the principle of closest temporal sequence and the principle of random selection.

[0102] In an optional embodiment of the present invention, in the voxel model obtained by real-time scanning, the update time of each voxel is recorded, and the voxels are sorted from oldest to newest according to the update time. J voxels at the end of the queue (a first preset number) are selected as registration voxels according to the "time-nearest principle". The voxels selected according to the "time-nearest principle" are called submap_1. Then, based on the "random selection principle", K voxels are randomly selected from all voxels in the voxel model as registration voxels. The voxels selected according to the "random selection principle" are called submap_2. The resulting J voxel submap_1 and K voxel submap_2 are used as the registration voxel set for the "relocalization" scenario.

[0103] In this embodiment of the invention, for the "relocation" operation of rescanning after a scan is interrupted, voxels are first screened according to the "time-nearest principle" and then the voxels to be registered are searched according to the "random selection principle". This effectively ensures the speed at which the scan returns to the user-specified position after the scan is interrupted and improves the data registration speed.

[0104] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, then the frame-by-frame registration is determined to be successful, and step four is executed: select the set of voxels to be registered from the voxel model using a pre-constructed localization method.

[0105] Specifically, the step of selecting the set of voxels to be registered from the voxel model using a pre-built localization method includes:

[0106] According to the principle of closest temporal sequence, a third preset number of voxels are selected from the voxel model as voxels to be registered;

[0107] According to the spatial priority principle, a fourth preset number of voxels are selected from the voxel model as voxels to be registered;

[0108] The set of voxels to be registered is obtained by summing all voxels selected based on the principle of closest temporal sequence and the principle of spatial priority.

[0109] In this embodiment of the invention, when frame-by-frame registration is successful, it is determined to be a continuous scan. The voxels to be registered are searched by the positioning method. The voxels at the end of N queues (a third preset number) are selected as the voxels to be registered by the "temporal nearest principle". Similarly, the voxels selected according to the "temporal nearest principle" are called submap_1.

[0110] Specifically, the step of selecting a fourth preset number of voxels from the voxel model as voxels to be registered according to the spatial priority principle includes:

[0111] The centroid coordinates of the voxel with the closest temporal sequence in the voxel model are used as the center, and a neighborhood space is constructed with a preset neighborhood radius.

[0112] The fourth preset number of voxels are selected from the neighborhood space as voxels to be registered.

[0113] In an optional embodiment of the present invention, the centroid coordinates of the last updated voxel in the voxel model are used as the center, and voxels falling within a preset radius are searched as neighboring voxels. Simultaneously, in actual scanning, since the number of neighboring voxels is large, M voxels (a fourth preset number) are randomly selected from the neighboring voxels as voxels to be registered. The voxels selected according to the "spatial priority principle" are called submap_3. By selecting the neighboring voxels of the last updated voxel, while ensuring a higher registration success rate, a sufficient number of reliable registration relationships between voxels can be provided for purposes such as cumulative error calibration. The resulting N voxel submap_1 and M voxel submap_3 are used as the set of voxels to be registered in the "localization" scenario.

[0114] Step 5: Perform coarse point cloud registration processing and fine point cloud registration processing on the real-time oral cavity point cloud data to be registered and the set of voxels to be registered to obtain the registration result.

[0115] In this embodiment of the invention, the difference between the two scenarios of "localization" and "relocalization" lies in the different ways of selecting the voxel to be registered. The methods used when registering the point cloud to be registered and the voxel to be registered are the same, both of which are achieved through two methods: coarse registration and fine registration of the point cloud. The coarse registration of the point cloud includes a registration method based on exhaustive search and a registration method based on feature matching. The fine registration of the point cloud includes the ICP (Iterative Closest Point) algorithm and derivative algorithms based on ICP.

[0116] In another optional embodiment of the present invention, after performing coarse and fine registration processing on the real-time oral cavity point cloud data to be registered and the set of voxels to be registered to obtain the registration result, the method further includes:

[0117] If the registration result is that the point cloud registration is successful, the voxel model is updated using the real-time oral cavity point cloud data to be registered, and the steps of obtaining the real-time oral cavity point cloud data to be registered and registering the real-time oral cavity point cloud data with the voxel model frame by frame are returned until the voxel model meets the preset accuracy requirements or a stop registration command is received.

[0118] If the registration result is a point cloud registration failure, return to the step of obtaining real-time oral cavity point cloud data to be registered and performing frame-by-frame registration of the real-time oral cavity point cloud data to be registered with the voxel model.

[0119] In this embodiment of the invention, the registration result includes successful point cloud registration and failed point cloud registration. When point cloud registration is successful, the voxel model is updated using the successfully registered real-time oral cavity point cloud data to be registered. When point cloud registration fails, the real-time oral cavity point cloud data to be registered is reacquired for data registration.

[0120] This embodiment performs frame-by-frame registration of real-time oral cavity point cloud data to be registered with a voxel model. When frame-by-frame registration fails, a pre-built relocalization method is used to select the set of voxels to be registered from the voxel model. When frame-by-frame registration succeeds, a pre-built localization method is used to select the set of voxels to be registered from the voxel model. During intraoral scanning, the two registration methods, "localization" and "relocalization," are automatically switched according to the actual scanning situation. This ensures both the accuracy and smoothness of real-time continuous scanning, as well as the response speed and accuracy of resuming scanning after a break. Therefore, the 3D data registration device for oral cavity scanning proposed in this invention can improve the speed and accuracy of oral cavity scanning data registration.

[0121] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing the 3D data registration method for oral scanning according to an embodiment of the present invention.

[0122] The electronic device may include a processor 10, a memory 11, a communication interface 12 and a bus 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a 3D data registration program for oral scanning.

[0123] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as code for 3D data registration programs used for oral scans, but also to temporarily store data that has been output or will be output.

[0124] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., 3D data registration programs for oral scans) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0125] The communication interface 12 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0126] The bus 13 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 13 can be divided into an address bus, a data bus, a control bus, etc. The bus 13 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0127] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0128] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0129] Furthermore, the electronic device may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device and other electronic devices.

[0130] Optionally, the electronic device may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0131] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0132] The 3D data registration program for oral cavity scanning stored in the memory 11 of the electronic device is a combination of multiple instructions that, when run in the processor 10, can achieve the following:

[0133] Acquire real-time oral cavity scanning point cloud data, and construct a voxel model based on the real-time oral cavity scanning point cloud data;

[0134] Acquire real-time oral cavity point cloud data to be registered, and perform frame-by-frame registration between the real-time oral cavity point cloud data to be registered and the voxel model;

[0135] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, then it is determined that the frame-by-frame registration has failed, and a set of voxels to be registered is selected from the voxel model through a pre-constructed relocation method.

[0136] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a number of consecutive preset frames, then the frame-by-frame registration is determined to be successful, and the set of voxels to be registered is selected from the voxel model using a pre-constructed localization method.

[0137] The real-time oral cavity point cloud data to be registered and the set of voxels to be registered are subjected to coarse point cloud registration processing and fine point cloud registration processing to obtain the registration result.

[0138] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0139] Furthermore, if the modules / units integrated into the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0140] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0141] Acquire real-time oral cavity scanning point cloud data, and construct a voxel model based on the real-time oral cavity scanning point cloud data;

[0142] Acquire real-time oral cavity point cloud data to be registered, and perform frame-by-frame registration between the real-time oral cavity point cloud data to be registered and the voxel model;

[0143] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a consecutive preset number of frames, then it is determined that the frame-by-frame registration has failed, and a set of voxels to be registered is selected from the voxel model through a pre-constructed relocation method.

[0144] If the real-time oral cavity point cloud data to be registered fails to register with the voxel model for a number of consecutive preset frames, then the frame-by-frame registration is determined to be successful, and the set of voxels to be registered is selected from the voxel model using a pre-constructed localization method.

[0145] The real-time oral cavity point cloud data to be registered and the set of voxels to be registered are subjected to coarse point cloud registration processing and fine point cloud registration processing to obtain the registration result.

[0146] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0147] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0148] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0149] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0150] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0151] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0152] Foundational artificial intelligence technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0153] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The term "second class" is used to indicate names and does not indicate any specific order.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A 3D data registration method for an oral scan, characterized in that, The method comprises: acquiring real-time oral cavity scanning point cloud data, and constructing a voxel model based on the real-time oral cavity scanning point cloud data; acquiring real-time oral cavity point cloud data to be registered, and performing frame-by-frame registration on the real-time oral cavity point cloud data to be registered and the voxel model; if the real-time oral cavity point cloud data to be registered and the voxel model fail to be registered for a continuous preset number of frames, determining that the frame-by-frame registration fails, and selecting a voxel set to be registered from the voxel model by using a pre-constructed repositioning method; if the real-time oral cavity point cloud data to be registered and the voxel model do not fail to be registered for a continuous preset number of frames, determining that the frame-by-frame registration succeeds, and selecting a voxel set to be registered from the voxel model by using a pre-constructed positioning method; performing point cloud coarse registration processing and point cloud fine registration processing on the real-time oral cavity point cloud data to be registered and the voxel set to be registered, to obtain a registration result; wherein the selecting of the voxel set to be registered from the voxel model by using the pre-constructed repositioning method comprises: selecting a first preset number of voxels from the voxel model as voxels to be registered according to a time sequence nearest principle; selecting a second preset number of voxels from the voxel model as voxels to be registered according to a random selection principle; obtaining the voxel set to be registered by aggregating all the voxels to be registered selected according to the time sequence nearest principle and the random selection principle; wherein the selecting of the voxel set to be registered from the voxel model by using the pre-constructed positioning method comprises: selecting a third preset number of voxels from the voxel model as voxels to be registered according to a time sequence nearest principle; selecting a fourth preset number of voxels from the voxel model as voxels to be registered according to a space priority principle; obtaining the voxel set to be registered by aggregating all the voxels to be registered selected according to the time sequence nearest principle and the space priority principle.

2. The 3D data registration method for an intraoral scan as claimed in claim 1, characterized in that, The constructing of the voxel model based on the real-time oral cavity scanning point cloud data comprises: performing time sequence arrangement on voxels in the real-time oral cavity scanning point cloud data according to scanning time of the real-time oral cavity scanning point cloud data, to obtain a voxel model.

3. The 3D data registration method for an intraoral scan of claim 1, wherein, The performing of the frame-by-frame registration on the real-time oral cavity point cloud data to be registered and the voxel model comprises: selecting point cloud data of a continuous preset number of frames from the real-time oral cavity point cloud data to be registered and performing registration on the voxel closest in time sequence in the voxel model.

4. The 3D data registration method for an intraoral scan of claim 1, wherein, The selecting of the fourth preset number of voxels from the voxel model as voxels to be registered according to the space priority principle comprises: taking a gravity center coordinate of the voxel closest in time sequence in the voxel model as a center, and constructing a neighborhood space with a preset neighborhood radius; selecting the fourth preset number of voxels from the neighborhood space as voxels to be registered.

5. The 3D data registration method for an intraoral scan according to any one of claims 1 to 4, characterized in that, After the performing of the point cloud coarse registration processing and the point cloud fine registration processing on the real-time oral cavity point cloud data to be registered and the voxel set to be registered, to obtain a registration result, the method further comprises: if the registration result is point cloud registration success, updating the voxel model by using the real-time oral cavity point cloud data to be registered, returning to the acquiring of the real-time oral cavity point cloud data to be registered, and performing the frame-by-frame registration on the real-time oral cavity point cloud data to be registered and the voxel model, until the voxel model meets a preset accuracy requirement or a stop registration instruction is received; If the registration result is a point cloud registration failure, the real-time oral cavity to-be-registered point cloud data is returned to the step of frame-by-frame registration of the real-time oral cavity to-be-registered point cloud data and the voxel model.

6. A 3D data registration apparatus for an oral scan, characterized in that The device comprises: A voxel model construction module is configured to acquire real-time oral cavity scanning point cloud data, and construct a voxel model based on the real-time oral cavity scanning point cloud data; A frame-by-frame registration module is configured to acquire real-time oral cavity to-be-registered point cloud data, and perform frame-by-frame registration of the real-time oral cavity to-be-registered point cloud data and the voxel model; A to-be-registered voxel selection module is configured to, if the real-time oral cavity to-be-registered point cloud data and the voxel model fail to be registered for a continuous preset number of frames, determine that the frame-by-frame registration fails, select a to-be-registered voxel set from the voxel model by using a pre-constructed repositioning method, and if the real-time oral cavity to-be-registered point cloud data and the voxel model do not fail to be registered for a continuous preset number of frames, determine that the frame-by-frame registration is successful, and select a to-be-registered voxel set from the voxel model by using a pre-constructed positioning method. The method comprises the following steps: selecting a first preset number of voxels from the voxel model as to-be-registered voxels according to a time sequence nearest principle; selecting a second preset number of voxels from the voxel model as to-be-registered voxels according to a random selection principle; obtaining a to-be-registered voxel set by aggregating all to-be-registered voxels selected based on the time sequence nearest principle and the random selection principle; The method comprises the following steps: selecting a third preset number of voxels from the voxel model as to-be-registered voxels according to a time sequence nearest principle; selecting a fourth preset number of voxels from the voxel model as to-be-registered voxels according to a space priority principle; obtaining a to-be-registered voxel set by aggregating all to-be-registered voxels selected based on the time sequence nearest principle and the space priority principle; A voxel registration module is configured to perform point cloud coarse registration processing and point cloud fine registration processing on the real-time oral cavity to-be-registered point cloud data and the to-be-registered voxel set, and obtain a registration result.

7. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the 3D data registration method for oral cavity scanning according to any one of claims 1 to 5.

8. A computer readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the 3D data registration method for oral cavity scanning according to any one of claims 1 to 5.

Images