WO2023241704A1 - 牙齿模型的获取方法、装置、设备及介质 - Google Patents

牙齿模型的获取方法、装置、设备及介质 Download PDF

Info

Publication number
WO2023241704A1
WO2023241704A1 PCT/CN2023/100826 CN2023100826W WO2023241704A1 WO 2023241704 A1 WO2023241704 A1 WO 2023241704A1 CN 2023100826 W CN2023100826 W CN 2023100826W WO 2023241704 A1 WO2023241704 A1 WO 2023241704A1
Authority
WO
WIPO (PCT)
Prior art keywords
point cloud
cloud data
model
preset
tooth model
Prior art date
Application number
PCT/CN2023/100826
Other languages
English (en)
French (fr)
Inventor
孙博
章惠全
马超
贾勇杰
Original Assignee
先临三维科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 先临三维科技股份有限公司 filed Critical 先临三维科技股份有限公司
Publication of WO2023241704A1 publication Critical patent/WO2023241704A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
    • A61C9/00—Impression cups, i.e. impression trays; Impression methods
    • A61C9/004—Means or methods for taking digitized impressions
    • A61C9/0046—Data acquisition means or methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30036—Dental; Teeth

Definitions

  • the present disclosure relates to the technical field of three-dimensional modeling, and in particular to a method, device, equipment and medium for obtaining a dental model.
  • intraoral scanners With the continuous maturity and practical application of oral digitization and chairside restoration technology, the use of intraoral scanners continues to increase, and more clinics use intraoral scanners to scan and obtain three-dimensional data models of the teeth in the patient's mouth. Since intraoral scanning requires the intraoral scanner to be inserted into the patient's mouth for scanning and acquisition, the scanning head is generally relatively small, and its imaging window is generally about 15mm. Therefore, the three-dimensional data of the teeth in the entire oral cavity cannot be directly obtained, and needs to be moved through And change the position and orientation of the intraoral scanner to obtain three-dimensional data of teeth in different areas of the oral cavity, and then through tracking and splicing during scanning and subsequent optimization processes, a consistent and complete three-dimensional data model of teeth is finally obtained.
  • the intraoral scanner moves and scans.
  • Point cloud data frames of teeth in the mouth, and tracking splicing technology is used to determine the splicing position of the point cloud data frames of newly scanned teeth. According to the splicing position, the point cloud data frames of the currently scanned teeth are spliced to obtain a tooth model.
  • the present disclosure provides a method, device, equipment and medium for obtaining a tooth model, whereby the generation and display of the tooth model and the global optimization of the tooth model are processed in parallel, And update the tooth model based on the global optimization results at the appropriate time, avoiding the problem that the tooth model has a large error and cannot continue to collect the point cloud data frame of the tooth, thereby affecting the completeness of the tooth model acquisition, and ensures that the tooth model is based on the point cloud data frame.
  • the cloud data frame can display the tooth model in real time, achieving the completeness and accuracy of the acquired tooth model.
  • An embodiment of the present disclosure provides a method for obtaining a tooth model.
  • the method includes: in response to the collected current point cloud data frame of the tooth, generating and displaying the current point cloud data frame according to a preset tracking splicing algorithm and the current point cloud data frame.
  • Tooth model store the current point cloud data frame in a preset database, and determine whether the preset model update conditions are met based on all point cloud data frames contained in the preset database; if the preset model update conditions are met , then the reference tooth model is determined based on all point cloud data frames, and the current tooth model is updated based on the reference tooth model.
  • Embodiments of the present disclosure also provide a device for acquiring a tooth model.
  • the device includes: a display module configured to respond to the current point cloud data frame of the collected teeth and perform a splicing process according to a preset tracking splicing algorithm and the current point cloud.
  • the data frame generates and displays the current tooth model;
  • the optimization module is used to store the current point cloud data frame into a preset database, and determine whether the preset model update is satisfied based on all point cloud data frames contained in the preset database.
  • update module configured to determine a reference tooth model based on all point cloud data frames when the preset model update condition is met, and update the current tooth based on the reference tooth model Model.
  • An embodiment of the present disclosure also provides an electronic device.
  • the electronic device includes: a processor; a memory used to store instructions executable by the processor; and the processor is used to read the instruction from the memory.
  • the instructions can be executed and executed to implement the method for obtaining a dental model as provided by embodiments of the present disclosure.
  • An embodiment of the present disclosure also provides a computer-readable storage medium, the storage medium stores a computer program, and the computer program is used to execute the method for obtaining a dental model as provided by the embodiment of the present disclosure.
  • a fourth aspect also provides a computer storage medium, wherein the computer storage medium can store a program, and when executed, the program can implement some or all of the steps in each implementation manner of the communication method provided in the first aspect of the present disclosure.
  • the tooth model acquisition scheme responds to the current point cloud data frame of the collected teeth, generates and displays the current tooth model according to the preset tracking splicing algorithm and the current point cloud data frame, and then, the current point cloud
  • the data frames are stored in the preset database, and all point cloud data frames contained in the preset database are used to determine whether the preset model update conditions are met. Therefore, if the preset model update conditions are met, the reference teeth are determined based on all point cloud data frames. model, and updates the current tooth model based on the reference tooth model.
  • the generation and display of the tooth model are processed in parallel with the global optimization of the tooth model, and the tooth model is updated at the appropriate time based on the results of the global optimization, which avoids the problem of large errors in the tooth model and the inability to continue to collect point cloud data of the teeth. frames, thus affecting the completeness of the acquisition of the tooth model, and on the basis of ensuring that the tooth model can be displayed in real time based on the point cloud data frame, the completeness and accuracy of the acquired tooth model are achieved.
  • Figure 1 is a schematic flow chart of a method for obtaining a dental model provided by an embodiment of the present disclosure
  • Figure 2 is a schematic diagram of a scene of acquiring a dental model provided by an embodiment of the present disclosure
  • Figure 3 is a schematic flow chart of another method for obtaining a tooth model provided by an embodiment of the present disclosure
  • Figure 4 is a schematic flow chart of another method for obtaining a tooth model provided by an embodiment of the present disclosure
  • Figure 5 is a schematic structural diagram of a dental model acquisition device provided by an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • embodiments of the present disclosure provide a method for obtaining a tooth model. This method will be introduced below with reference to specific embodiments.
  • Figure 1 is a schematic flowchart of a method for obtaining a dental model provided by an embodiment of the present disclosure.
  • the method can be executed by a dental model obtaining device, where the device can be implemented using software and/or hardware, and can generally be integrated into an electronic device.
  • the method includes:
  • Step 101 In response to the collected current point cloud data frame of the teeth, generate and display the current tooth model according to the preset tracking splicing algorithm and the current point cloud data frame.
  • a scanning device such as an intraoral scanner can be used to move in the user's oral cavity to obtain the current point cloud data frame of the corresponding teeth in the oral cavity in the current acquisition cycle, where the current point cloud data A frame can be understood as including simultaneously scanning to A combination of three-dimensional data points from multiple scanned points on the tooth.
  • the intraoral scanner needs to be moved to collect point cloud data frames for multiple consecutive acquisition cycles, in which all points in the oral cavity are collected in each acquisition cycle.
  • the point cloud data frame of the local tooth in the tooth Therefore, the complete model of the tooth can be obtained by splicing multiple point cloud data frames.
  • the current tooth model in the current acquisition cycle is determined based on the point cloud data frame.
  • the point cloud data frame in the point cloud data frame can be preprocessed, segmented, triangulated meshed, and meshed rendered.
  • the corresponding current tooth model is obtained.
  • the process of constructing and obtaining the current tooth model based on the point cloud data frame can be obtained by existing technologies (such as the fusion method based on the octree voxel field, etc.) and will not be described again here.
  • the current point cloud data frame is not the first point cloud data frame, that is, the tooth model has been constructed previously based on the point cloud data frames collected in the historical collection cycle. Therefore, in this embodiment, The current tooth model is obtained based on tracking splicing technology.
  • the target tooth model of the teeth in the previous collection cycle is obtained, and the current point cloud data frame is spliced on the target tooth model to obtain the updated model as the current tooth model.
  • the point cloud data frame in the current point cloud data frame can be matched with the point cloud data frame on the target tooth model of the previous collection cycle, or with the point cloud data frame of the previous collection cycle, Determine the overlapping area between the current point cloud data frame and the point cloud data frame on the target tooth model of the previous collection cycle, locate the splicing position of the current point cloud data frame based on the overlapping area, and locate the target tooth based on the splicing position in the previous collection cycle.
  • the current point cloud data frame is spliced on the model to obtain the current tooth model of the current period.
  • the iterative closest point (ICP) algorithm can be used, etc., which will not be listed one by one here.
  • the preset display interface can be understood as an interactive interface that displays the model obtained after tooth scanning in real time.
  • Step 102 Store the current point cloud data frame in the preset database, and All point cloud data frames contained in the library are judged whether they meet the preset model update conditions.
  • the current point cloud data frame is stored in a preset database, and all point clouds stored in the preset database are judged in the form of background processing without affecting the real-time display of the current tooth model. Whether the data frame meets the preset model update conditions.
  • two parallel threads can be built in advance. The first thread is used to determine the current tooth model in the current acquisition cycle based on the point cloud data frame and display the current tooth model on the preset display interface. The second thread is used to The current point cloud data frame is stored in the preset database, and it is determined whether all point cloud data frames of the teeth in the preset database meet the preset model update conditions.
  • the current frame number of all point cloud data frames contained in the preset database is counted, that is, the collected point cloud data frames are counted starting from the first collection. If the current frame number is greater than the preset quantity threshold, it is determined that the preset model update conditions are met, where the preset quantity threshold can be calibrated based on experimental data.
  • All point cloud data frames are judged whether they meet the preset model update conditions, including:
  • Step 301 Determine the first model position of each point cloud data frame based on all current point cloud data frames contained in the preset database.
  • the first model position of each point cloud data frame is determined based on all current point cloud data frames included in the preset database, where the first model position is determined based on all current point cloud data frames included in the preset database.
  • the first model position is obtained by global error optimization based on all current point cloud data frames. Therefore, the splicing position of the point cloud data frame in the tooth model obtained based on tracking technology is more accurate.
  • the above-mentioned global error optimization based on all current point cloud data frames can be implemented according to any global optimization algorithm in the existing technology.
  • the first error of each point cloud data frame is determined based on the beam method.
  • Model position among which, the beam method is an algorithm that combines the calculation of external orientation elements (outer points) and model point coordinates (inner points) into a whole.
  • the beam method adjustment uses collinear equations as a mathematical model, and uses the splicing position of each point cloud data frame in the three-dimensional space as a nonlinear function of unknown variables. After linearization, it is calculated according to the principle of least squares. This calculation is also based on providing an approximate solution, and iterates successively to reach the splicing position value of each point cloud data frame that is close to the optimal value, and uses the splicing position value as the first model position.
  • Step 302 Determine the second model position of each point cloud data frame in the current displayed tooth model.
  • the second model position of each point cloud data frame in the displayed current tooth model is determined, where the second model position is the coordinate position of the corresponding point cloud data frame in the current tooth model.
  • Step 303 Calculate the position error of each point cloud data frame based on the first model position and the second model position.
  • the second reference tooth model is a globally optimized model obtained based on all current point cloud data frames, and the current tooth model is a refined and coarse model obtained based on tracking splicing technology, therefore, according to the first model position and the second The model position calculates the position error of each point cloud data frame. Based on the calculation of the position error, it can be judged whether the error degree of the current tooth model is large, and whether the cumulative error may be large and the tooth model cannot be closed.
  • the position error of each point cloud data frame can be based on the mean of the coordinate differences between the key feature points in the first model position and the second model position.
  • the first model position and the second model position can be aligned according to a related alignment algorithm, the optical flow information between the first model position and the second model position can be calculated, and the optical flow information is determined based on the optical flow information. position error.
  • Step 304 Determine whether the preset model update conditions are met based on the position error.
  • the error mean of all position errors is calculated to determine whether the error mean is greater than the preset average error threshold. , where, if it is greater than the preset average error threshold, it is determined that the preset model update condition is met.
  • the maximum position error among all position errors is determined, and it is determined whether the maximum position error is greater than a preset maximum error threshold. If it is greater than the maximum error threshold, it is determined that the preset model update condition is met.
  • Step 103 If the preset model update conditions are met, the reference tooth model is determined based on all point cloud data frames, and the current tooth model is updated based on the reference tooth model.
  • the reference tooth model is determined based on all point cloud data frames, and the current tooth model is updated based on the reference tooth model. If this is not the first time that the reference tooth model is generated in the background, The current reference tooth model can be determined based on all point cloud data frames based on the last reference tooth model.
  • the tooth model displayed on the front desk may be For problems that cannot be closed, the current tooth model displayed is updated with a higher-precision reference tooth model obtained from all point cloud data frames in the preset database stored in the background to improve the precision of the current tooth model displayed and facilitate dental care.
  • the point cloud data frame can continue to be scanned, ensuring the fineness of the current tooth model visually displayed.
  • the reference tooth model can be generated in the background.
  • the background integrates the current point cloud data frame obtained each time into the point cloud data frame obtained historically to build a fusion field, so as to obtain a reference tooth model with higher accuracy.
  • the front desk quickly obtains and displays the current tooth model based on tracking and splicing technology.
  • the higher-resolution reference tooth model obtained in the background is switched to the front desk display to ensure that Based on the real-time display of the tooth model based on the point cloud data frame, the completeness and accuracy of the acquired tooth model are achieved.
  • the point cloud data frame collection of teeth ends, it is determined that the current tooth model displayed is the target tooth model, that is, the last displayed target tooth model is regarded as the complete tooth model. If the point cloud data frame collection of teeth does not end, repeat The above steps gradually obtain a complete tooth model. During the above process of obtaining the tooth model, if it is judged that all point cloud data frames contained in the preset database do not meet the preset model update conditions, the preset tracking splicing algorithm and the current The current tooth model generated and displayed from the point cloud data frame is used as the final tooth model obtained in the current cycle.
  • the reference tooth model is determined based on all point cloud data frames in different ways.
  • the reference tooth model is determined based on all point cloud data frames and their spatial splicing positions.
  • the method can be obtained by existing technologies (such as the fusion method based on the octree voxel field, etc.), and will not be described again here.
  • the reference tooth model is determined based on all point cloud data frames, including:
  • Step 401 if the previous reference tooth model determined in the last optimization is obtained, generate a Initial reference tooth model.
  • all point cloud data frames included in the preset database can be directly fused to obtain the initial reference tooth model.
  • Step 402 Determine whether the number of remaining point cloud data frames in the preset database is less than a preset quantity threshold.
  • the preset quantity threshold can be calibrated based on experimental data.
  • Step 403 If it is not less than the preset quantity threshold, update the initial reference tooth model according to the remaining point cloud data frames until the number of remaining point cloud data frames in the preset database is less than the preset quantity threshold.
  • Step 404 if the number of remaining point cloud data frames in the preset database is less than the preset number threshold, interrupt the point cloud data frame collection of teeth, and update the initial reference tooth model based on the remaining point cloud data frames to obtain a reference tooth model. .
  • the splicing position on the initial reference tooth model can be determined based on local overlap to quickly obtain the reference tooth model.
  • the foreground scanning point cloud data frames are continuous, in order to ensure that the generated initial reference tooth model contains as many collected point cloud data frames as possible, in the above embodiment
  • an initial reference tooth model is generated based on the global optimization algorithm (the method of generating the initial reference tooth model refers to the above embodiment (not repeated here), wherein, if the previous reference tooth model determined in the last optimization is obtained, then according to all point cloud data frames contained in the preset database and each point cloud in the previous reference tooth model The first model position of the data frame to generate the initial reference tooth model.
  • the point cloud data frame scanned by the foreground will still be added to the background database. Therefore, after the initial reference tooth model is generated, the current background database is determined.
  • the remaining number of point cloud data frames that did not participate in generating the initial reference tooth model is judged whether the remaining number is greater than the preset data threshold. If it is not greater than the preset data threshold, the scanning process is interrupted, and the remaining point cloud data frames are compared with the initial
  • the reference tooth model is globally optimized and fused to obtain an updated reference tooth model.
  • the updated reference tooth model is used to replace the current tooth model in the front desk. At this time, it is judged whether to scan all the teeth. If not, continue to the next cycle. Scan acquisition process.
  • the remaining point cloud data frames will be globally optimized and fused with the current initial reference tooth model to obtain the updated initial reference tooth model.
  • the foreground scanning process is interrupted, and the remaining point cloud data frames are globally optimized and fused with the initial reference tooth model to obtain an updated reference tooth model.
  • the preset model update conditions are met, the final The resulting reference tooth model replaces the current tooth model in the frontend. At this time, it is judged whether to scan all the teeth. If not, continue to enter the scanning acquisition process of the next cycle.
  • the tooth model acquisition method responds to the current point cloud data frame of the collected teeth, generates and displays the current tooth model according to the preset tracking splicing algorithm and the current point cloud data frame, and then,
  • the current point cloud data frame is stored in the preset database, and all point cloud data frames contained in the preset database are used to determine whether the preset model update conditions are met. Therefore, if the preset model update conditions are met, all point cloud data frames are used to determine whether the preset model update conditions are met. Determine the reference tooth model and update the current tooth model based on the reference tooth model.
  • the generation and display of the tooth model are processed in parallel with the global optimization of the tooth model, and the tooth model is updated at the appropriate time based on the results of the global optimization, which avoids the problem of large errors in the tooth model and the inability to continue to collect point cloud data of the teeth. frames, thus affecting the completeness of the acquisition of the tooth model, and on the basis of ensuring that the tooth model can be displayed in real time based on the point cloud data frame, the completeness and accuracy of the acquired tooth model are achieved.
  • the present disclosure also proposes a device for obtaining a dental model.
  • FIG. 5 is a schematic structural diagram of a device for acquiring a dental model provided by an embodiment of the present disclosure.
  • the device can be implemented by software and/or hardware, and can generally be integrated into an electronic device to acquire a dental model.
  • the device includes: a display module 510, an optimization module 520, and an update module 530, where,
  • the display module 510 is configured to generate and display the current tooth model according to the preset tracking splicing algorithm and the current point cloud data frame in response to the collected current point cloud data frame of the teeth;
  • the optimization module 520 is used to store the current point cloud data frame into a preset database, and determine whether the preset model update conditions are met based on all point cloud data frames contained in the preset database;
  • the update module 530 is used to update the model based on all point cloud data when the preset model update conditions are met.
  • the reference tooth model is determined based on the frame, and the current tooth model is updated based on the reference tooth model.
  • the dental model acquisition device provided by the embodiment of the present disclosure can execute the dental model acquisition method provided by any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the method.
  • it also includes: a model determination module, used for:
  • the current tooth model displayed is determined to be the target tooth model.
  • the display module 510 is specifically used for:
  • the current point cloud data frame is the first point cloud data frame collected, construct and display the current tooth model based on the current point cloud data frame;
  • the current point cloud data frame is spliced on the historical tooth model to obtain and display the current tooth model.
  • the optimization module 520 is specifically used to:
  • the current frame number of all point cloud data frames contained in the preset database is counted. If the current frame number is greater than the preset quantity threshold, it is determined that the preset model update condition is met.
  • the optimization module 520 is specifically used to:
  • the optimization module 520 is specifically used to:
  • the optimization module 520 is specifically used to:
  • the update module 530 is specifically used to:
  • the initial reference tooth model is updated according to the remaining point cloud data frames until the number of remaining point cloud data frames in the preset database is less than the preset number. threshold;
  • the point cloud data frame collection of the teeth is interrupted, and the point cloud data frame is updated according to the remaining point cloud data frames.
  • Initial reference tooth model to obtain said reference tooth model.
  • the update module 530 is specifically used to:
  • the present disclosure also proposes a computer program product, which includes a computer program/instructions.
  • a computer program product which includes a computer program/instructions.
  • Embodiments of the present disclosure also provide a computer storage medium, wherein the computer storage medium may store a program, and when executed, the program may implement some or all of the steps in each implementation manner of the above method for obtaining a dental model.
  • FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • the electronic device 600 in the embodiment of the present disclosure may include, but is not limited to, mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals ( Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in Figure 6 is only an example and should not be used in this disclosure. There are no limitations on the functions and scope of use of the embodiments.
  • electronic device 600 may include a processor (eg, central processing unit, graphics processor, etc.) 601 that may be loaded into random access memory according to a program stored in read-only memory (ROM) 602 or from memory 608 (RAM) 603 to perform various appropriate actions and processes.
  • ROM read-only memory
  • RAM memory 608
  • various programs and data required for the operation of the electronic device 600 are also stored.
  • the processor 601, ROM 602 and RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to bus 604.
  • I/O interface 605 input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration
  • An output device 607 such as a computer
  • a memory 608 including a magnetic tape, a hard disk, etc.
  • Communication device 609 may allow electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data.
  • FIG. 6 illustrates electronic device 600 with various means, it should be understood that implementation or availability of all illustrated means is not required. More or fewer means may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via communication device 609, or from memory 608, or from ROM 602.
  • the computer program is executed by the processor 601, the above-mentioned functions defined in the dental model acquisition method of the embodiment of the present disclosure are performed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), removable Programming read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the above.
  • the client and server can communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
  • Communications e.g., communications network
  • communications networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or developed in the future network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; it may also exist independently without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the electronic device responds to the current point cloud data frame of the collected teeth, and performs tracking and splicing according to the preset
  • the algorithm and the current point cloud data frame generate and display the current tooth model, and then store the current point cloud data frame into the preset database, and determine whether the preset model update conditions are met based on all point cloud data frames contained in the preset database. Therefore, if the preset model update conditions are met, the reference tooth model is determined based on all point cloud data frames, and the current tooth model is updated based on the reference tooth model.
  • the generation and display of the tooth model are processed in parallel with the global optimization of the tooth model, and the tooth model is updated at the appropriate time based on the results of the global optimization, which avoids the problem of large errors in the tooth model and the inability to continue to collect point cloud data of the teeth. frames, thereby affecting the acquisition of complete tooth models degree problem, and on the basis of ensuring that the tooth model can be displayed in real time based on the point cloud data frame, the completeness and accuracy of the acquired tooth model are achieved.
  • the electronic device may have computer program code for performing operations of the present disclosure written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, or a combination thereof. , also includes conventional procedural programming languages—such as "C" or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as an Internet service provider through Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as an Internet service provider through Internet connection
  • each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure can be implemented in software or hardware. Among them, the name of a unit does not constitute a limitation on the unit itself under certain circumstances.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM portable compact disk read-only memory
  • magnetic storage device or any suitable combination of the above.
  • the tooth model acquisition method processes the generation and display of the tooth model in parallel with the global optimization of the tooth model, and updates the tooth model at the appropriate time based on the results of the global optimization, thus avoiding the possibility of large errors in the tooth model.
  • the point cloud data frame can display the tooth model in real time, achieving the completeness and accuracy of the acquired tooth model, and has strong industrial practicability.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Epidemiology (AREA)
  • Dentistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)

Abstract

一种牙齿模型的获取方法，包括：响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和当前点云数据帧生成并显示当前牙齿模型；将当前点云数据帧存储到预设数据库，并根据预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件；若是满足预设模型更新条件，则根据所有点云数据帧确定参考牙齿模型，并根据参考牙齿模型更新当前牙齿模型。

Description

牙齿模型的获取方法、装置、设备及介质
本公开要求于2022年6月17日提交中国专利局、申请号为202210722394.6、发明名称为“牙齿模型的获取方法、装置、设备及介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及三维建模技术领域，尤其涉及一种牙齿模型的获取方法、装置、设备及介质。
背景技术
随着口腔数字化和椅旁修复技术的不断成熟和实际应用，口内扫描仪的使用不断增多，更多的诊所采用口内扫描仪扫描获取病人口腔的牙齿的三维数据模型。由于口内扫描需将口内扫描仪伸入病人口内进行扫描采集，其扫描头一般都比较小，它的取像窗口一般在15mm左右，因此不能直接获取整个口腔范围的牙齿的三维数据，需要通过移动和改变口内扫描仪的位置及朝向，来获取口腔内不同区域牙齿的三维数据，再通过扫描时的跟踪拼接和后续的优化处理过程，最终得到一致完整的牙齿的三维数据模型。
相关技术中，口内扫描仪在扫描移动过程中，为了确保新扫描获得的局部区域的牙齿的点云数据帧能够与已扫描区域的牙齿的点云数据帧进行有效地拼接，口内扫描仪移动扫描口内牙齿的点云数据帧，并采用跟踪拼接技术来确定新扫描的牙齿的点云数据帧的拼接位置。根据该拼接位置将当前扫描的牙齿的点云数据帧进行拼接处理以获取牙齿模型。这种连续拼接的方法，随着口内扫描仪移动距离(或扫描区域范围)的增大，跟踪拼接的误差会不断累积，会在扫描回路(口内扫描仪从某个位置开始扫描，不断移动口内扫描仪获取新区域的三维数据，最后又移动扫描到起始的位置，形成首尾相连的移动轨迹路 径)上扫描以将得到的点云数据帧进行连续拼接得到牙齿的完整模型。
然而，由于拼接误差的存在，上述基于局部区域的跟踪拼接的方法，随着口内扫描仪移动距离(或扫描区域范围)的增大，跟踪拼接的误差会不断累积，并在扫描回路闭合处导致三维数据发生错层错位而无法闭合，即产生回环误差。当产生回环误差后，由于数据的不一致性，会导致在回环闭合附近的后续扫描拼接错误或失败，从而无法有效继续扫描，导致口内牙齿的模型无法完整的获取。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题，本公开提供了一种牙齿模型的获取方法、装置、设备及介质，由此，将牙齿模型的生成显示与牙齿模型的全局优化并行处理，并在合适的时机根据全局优化后的结果对牙齿模型更新，避免了牙齿模型的误差较大无法继续采集牙齿的点云数据帧，从而影响牙齿模型的获取完整度的问题，并且在保证根据点云数据帧可以实时显示牙齿模型的基础上，实现了获取的牙齿模型的完整度和精准度。
本公开实施例提供了一种牙齿模型的获取方法，所述方法包括：响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和所述当前点云数据帧生成并显示当前牙齿模型；将所述当前点云数据帧存储到预设数据库，并根据所述预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件；若是满足所述预设模型更新条件，则根据所述所有点云数据帧确定参考牙齿模型，并根据所述参考牙齿模型更新所述当前牙齿模型。
本公开实施例还提供了一种牙齿模型的获取装置，所述装置包括：显示模块，用于响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和所述当前点云数据帧生成并显示当前牙齿模型；优化模块，用于将所述当前点云数据帧存储到预设数据库，并根据所述预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件；更新模块，用于在满足所述预设模型更新条件时，根据所述所有点云数据帧确定参考牙齿模型，并根据所述参考牙齿模型更新所述当前牙齿 模型。
本公开实施例还提供了一种电子设备，所述电子设备包括：处理器；用于存储所述处理器可执行指令的存储器；所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现如本公开实施例提供的牙齿模型的获取方法。
本公开实施例还提供了一种计算机可读存储介质，所述存储介质存储有计算机程序，计算机程序用于执行如本公开实施例提供的牙齿模型的获取方法。
第四方面，还提供一种计算机存储介质，其中，该计算机存储介质可存储有程序，该程序执行时可实现本公开第一方面提供一种通信方法的各实现方式中的部分或全部步骤。
本公开实施例提供的上述技术方案与现有技术相比具有如下优点：
本公开实施例提供的牙齿模型的获取方案，响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和当前点云数据帧生成并显示当前牙齿模型，进而，将当前点云数据帧存储到预设数据库，并根据预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件，从而，若是满足预设模型更新条件，则根据所有点云数据帧确定参考牙齿模型，并根据参考牙齿模型更新当前牙齿模型。由此，将牙齿模型的生成显示与牙齿模型的全局优化并行处理，并在合适的时机根据全局优化后的结果对牙齿模型更新，避免了牙齿模型的误差较大无法继续采集牙齿的点云数据帧，从而影响牙齿模型的获取完整度的问题，并且在保证根据点云数据帧可以实时显示牙齿模型的基础上，实现了获取的牙齿模型的完整度和精准度。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
为了更清楚地说明本公开实施例或现有技术中的技术方案，下面 将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的一种牙齿模型的获取方法的流程示意图；
图2为本公开实施例提供的一种牙齿模型的获取的场景示意图；
图3为本公开实施例提供的另一种牙齿模型的获取方法的流程示意图；
图4为本公开实施例提供的另一种牙齿模型的获取方法的流程示意图；
图5为本公开实施例提供的一种牙齿模型的获取装置的结构示意图；
图6为本公开实施例提供的一种电子设备的结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开的一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
为了解决上述问题，本公开实施例提供了一种牙齿模型的获取方法，下面结合具体的实施例对该方法进行介绍。
图1为本公开实施例提供的一种牙齿模型的获取方法的流程示意图，该方法可以由牙齿模型的获取装置执行，其中该装置可以采用软件和/或硬件实现，一般可集成在电子设备中。如图1所示，该方法包括：
步骤101，响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和当前点云数据帧生成并显示当前牙齿模型。
可以理解，在本公开的实施例中，可以通过口内扫描仪等扫描设备，在用户的口腔内移动以获取口腔内对应的牙齿在当前采集周期的当前点云数据帧，其中，当前点云数据帧可以理解为包括同时扫描到 的牙齿上的多个扫描点的三维数据点的组合。
如图2所示，由于口内扫描仪的扫描窗通常较小，因此，需要移动口内扫描仪以连续多个采集周期采集点云数据帧，其中，每个采集周期内采集的均为口腔内所有牙齿中的局部牙齿的点云数据帧，因此，多个点云数据帧拼接才能获取牙齿的完整模型。
在本实施例中，在获取牙齿在当前点云数据帧后，根据点云数据帧确定在当前采集周期的当前牙齿模型。
在本公开的一个实施例中，在基于点云数据帧构建获取当前牙齿模型时，可将点云数据帧中的点云数据帧进行预处理、分割、三角网格化以及网格渲染等过程得到对应的当前牙齿模型，其中，基于点云数据帧构建获取当前牙齿模型的过程可由现有技术(如基于八叉树体素场的融合方法等)得到，在此不再赘述。
在本公开的一个实施例中，若是当前点云数据帧不为首个点云数据帧，即之前已经根据历史采集周期采集过的点云数据帧构建了牙齿模型，因此，在本实施例中，根据跟踪拼接技术来获取当前牙齿模型。
在本实施例中，获取牙齿在上一个采集周期的目标牙齿模型，在目标牙齿模型上拼接当前点云数据帧以获取更新后的模型作为当前牙齿模型。在本实施例中，可以将当前点云数据帧中的点云数据帧与上一个采集周期的目标牙齿模型上的点云数据帧匹配，或者是与上一个采集周期的点云数据帧匹配，确定当前点云数据帧与上一个采集周期的目标牙齿模型上的点云数据帧的重叠区域，基于重叠区域定位当前点云数据帧的拼接位置，基于该拼接位置在上一个采集周期的目标牙齿模型上拼接当前点云数据帧以得到当前周期的当前牙齿模型。。其中，在将当前点云数据帧拼接在上一个采集周期的目标牙齿模型上时，可以采用迭代最近点(Iterative Closest Point，ICP)算法等，在此不一一进行列举。
进一步地，在得到当前牙齿模型后，为了实现实时显示扫描得到的牙齿模型，在预设显示界面上显示当前牙齿模型。其中，预设显示界面可以理解为实时显示牙齿扫描后得到的模型的交互界面。
步骤102，将当前点云数据帧存储到预设数据库，并根据预设数据 库中包含的所有点云数据帧判断是否满足预设模型更新条件。
容易理解的是，上述当前采集周期的当前牙齿模型，是基于拼接技术得到的，因此，可能会存在拼接误差，若是拼接误差逐渐累计，则可能导致得到的牙齿模型的误差较大，甚至在扫描一圈回到起点的位置时，牙齿模型无法闭合，因此，为了消除这种累计误差，需要对相关模型进行误差优化。而实时基于全局优化算法的耗时较大，若是等到基于全局优化算法完毕后，才对优化后的牙齿模型进行显示，显然会导致显示延迟，影响用户的视觉体验及扫描效率等。
在本公开的一个实施例中，将当前点云数据帧存储到预设数据库，在不会影响当前牙齿模型显示实时性的前提下，以后台处理的形式判断预设数据库中存储的所有点云数据帧是否满足预设模型更新条件。比如，可以预先构建2个并列的线程，第一线程用于根据点云数据帧确定在当前采集周期的当前牙齿模型，并在预设显示界面上显示当前牙齿模型，第二个线程用于将当前点云数据帧存储到预设数据库，并判断预设数据库中牙齿的所有点云数据帧是否满足预设模型更新条件。
在本实施例中，为了减少算力消耗，并非是每获取到一个点云数据帧，就进行全局的误差优化，而是根据预设数据库中牙齿的所有点云数据帧判断是否满足预设模型更新条件，只有在满足预设模型更新条件后，才认为前台显示的当前牙齿模型的误差可能较大，有可能因为误差导致无法当前牙齿模型偏离真实的牙齿较大，影响显示效果，甚至影响扫描流畅性及牙齿模型的闭合等。
需要说明的是，在不同的应用场景中，根据预设数据库中牙齿的所有点云数据帧判断是否满足预设模型更新条件的方式不同，示例如下：
在本公开的一个实施例中，统计预设数据库中包含的所有点云数据帧的当前帧数，即从首次采集开始对采集得到的点云数据帧进行计数处理，若是当前帧数大于预设数量阈值，则确定满足预设模型更新条件，其中，预设数量阈值可以根据实验数据标定。
在本公开的一个实施例中，如图3所示，根据预设数据库中包含 的所有点云数据帧判断是否满足预设模型更新条件，包括：
步骤301，根据预设数据库中包含的当前所有点云数据帧，确定每一个点云数据帧的第一模型位置。
在本实施例中，基于预设数据库中包含的当前所有点云数据帧，基于预设数据库中包含的当前所有点云数据帧确定每一个点云数据帧的第一模型位置，其中，该第一模型位置是根据当前所有点云数据帧进行全局误差优化得到的，因此，相对于基于跟踪技术得到的牙齿模型中的点云数据帧的拼接位置的精度更高。
其中，上述根据当前所有点云数据帧进行全局误差优化可以根据现有技术中任意一个全局优化算法来实现，在一些可能的实施例中，基于光束法构确定每一个点云数据帧的第一模型位置，其中，光束法是将外方位元素(局外点)和模型点坐标(局内点)的计算放在一个整体内进行的算法。光束法平差是以共线方程式作为数学模型，以每一个点云数据帧在三维空间中的拼接位置为未知数的非线性函数，经过线性化后按照最小二乘法原理进行计算。该计算也是在提供一个近似解的基础上，逐次迭代来达到趋近于最佳值的每个点云数据帧的拼接位置值，将该拼接位置值作为第一模型位置。
步骤302，确定显示的当前牙齿模型中每一个点云数据帧的第二模型位置。
在本实施例中，确定显示的当前牙齿模型中每一个点云数据帧的第二模型位置，其中，第二模型位置为对应的点云数据帧在当前牙齿模型的坐标位置。
步骤303，根据第一模型位置和第二模型位置计算每一个点云数据帧的位置误差。
由于第二参考牙齿模型是基于当前所有点云数据帧得到的全局优化处理后的模型，当前牙齿模型是基于跟踪拼接技术得到的精细化较粗的模型，因此，根据第一模型位置和第二模型位置计算每一个点云数据帧的位置误差，基于位置误差的计算可以判断当前牙齿模型的误差程度是否较大，是否有可能会导致累计误差较大导致牙齿模型无法闭合。
在一些可能的实施例中，可以根据第一模型位置和第二模位置中关键特征点之间的坐标差值的均值，基于坐标差值的均值作为每一个点云数据帧的位置误差。
在另一些可能的实施例中，可以根据相关的对齐算法将第一模型位置和第二模型位置对齐处理，计算第一模型位置到第二模型位置之间的光流信息，基于光流信息确定位置误差。
步骤304，根据位置误差判断是否满足预设模型更新条件。
在本实施例中，在获取位置误差后，根据位置误差判断是否满足预设模型更新条件，在一些可能的实施例中，计算所有位置误差的误差均值，判断误差均值是否大于预设平均误差阈值，其中，若是大于预设平均误差阈值，则确定满足预设模型更新条件。
在另一些可能的实施例中，确定所有位置误差中的最大位置误差，判断最大位置误差是否大于预设最大误差阈值，若是大于最大误差阈值，则确定满足预设模型更新条件。
步骤103，若是满足预设模型更新条件，则根据所有点云数据帧确定参考牙齿模型，并根据参考牙齿模型更新当前牙齿模型。
在本实施例中，若是满足预设模型更新条件，则根据所有点云数据帧确定参考牙齿模型，并根据参考牙齿模型更新当前牙齿模型，其中，若是当前并非是首次后台生成参考牙齿模型，在可以在上一次的参考牙齿模型的基础上根据所有点云数据帧确定当前的参考牙齿模型。
可以理解，在本公开的实施例中，若是满足预设模型更新条件，即可能显示的当前牙齿模型的误差较大时，为了保证显示效果，以及避免累计误差较大导致前台显示的牙齿模型可能无法闭合的问题，针对在后台存储的预设数据库中的所有点云数据帧得到的精度更高的参考牙齿模型来更新显示的当前牙齿模型，以提升显示的当前牙齿模型的精细度，便于牙齿的点云数据帧可以继续进行扫描，保证了视觉显示的当前牙齿模型的精细度。
其中，正如前面所提出的，由于参考牙齿模型的生成，和根据预设跟踪拼接算法和当前点云数据帧生成并显示当前牙齿模型是并行 的，比如，参考牙齿模型的生成可以是在后台生成，后台对每次获取到的当前点云数据帧融入历史获取的点云数据帧构建融合场，以便于获取精度更高的参考牙齿模型，前台基于跟踪拼接技术快速获取到当前牙齿模型并显示，在视觉上不会延迟显示牙齿模型的前提下，在必要的时候将后台得到的精细度更高的参考牙齿模型切换到前台显示，以保证根据点云数据帧可以实时显示牙齿模型的基础上，实现了获取的牙齿模型的完整度和精准度。
其中，若是牙齿的点云数据帧采集结束，则确定显示的当前牙齿模型为目标牙齿模型，即最后显示的目标牙齿模型作为完整的牙齿模型，若是牙齿的点云数据帧采集没有结束，则重复上述步骤逐步获取完整的牙齿模型，其中，在上述获取牙齿模型的过程中，若是判断预设数据库中包含的所有点云数据帧不满足预设模型更新条件，则将预设跟踪拼接算法和当前点云数据帧生成并显的当前牙齿模型作为当前周期最后得到的牙齿模型。
另外，需要说明的是，在不同的应用场景中，根据所有点云数据帧确定参考牙齿模型的方式不同，在本公开实施例中，根据所有点云数据帧及其空间拼接位置确定参考牙齿模型的方式可以由现有技术(如基于八叉树体素场的融合方法等)得到，在此不再赘述。
在一些可能的实施例中，如图4所示，根据所有点云数据帧确定参考牙齿模型，包括：
步骤401，若是获取到上一次优化确定的上一个参考牙齿模型，则根据预设数据库中包含的所有点云数据帧和上一个参考牙齿模型中每一个点云数据帧的第一模型位置，生成初始参考牙齿模型。
可以理解，若是当前并非是后台首次构建参考牙齿模型，即获取到上一次优化确定的上一个参考牙齿模型，则根据预设数据库中包含的所有点云数据帧和上一个参考牙齿模型中每一个点云数据帧的第一模型位置，生成初始参考牙齿模型。
在本公开的一个实施例中，若是当前是后台首次构建参考牙齿模型，则可直接根据预设数据库中包含的所有点云数据帧进行融合以得到初始参考牙齿模型。
步骤402，判断预设数据库中的剩余点云数据帧的数量是否小于预设数量阈值。
其中，预设数量阈值可根据实验数据标定。
步骤403，若是不小于预设数量阈值，则根据剩余点云数据帧更新初始参考牙齿模型，直到预设数据库中的剩余点云数据帧的数量小于预设数量阈值。
步骤404，若是预设数据库中的剩余点云数据帧的数量小于预设数量阈值，则中断对牙齿的点云数据帧采集，并根据剩余点云数据帧更新初始参考牙齿模型以得到参考牙齿模型。其中，根据剩余点云数据帧更新初始参考牙齿模型以得到参考牙齿模型时，可以基于局部重叠确定在初始参考牙齿模型上的拼接位置进行拼接以快速得到参考牙齿模型。
即在本公开的一个实施例中，由于前台扫描点云数据帧是持续的，因此，为了保证生成的初始参考牙齿模型尽可能包含更多的采集到的点云数据帧，在上述实施例中提到的根据所有点云数据帧确定参考牙齿模型的过程中，首先根据当前数据库中的当前所有点云数据帧，基于全局优化算法融合生成初始参考牙齿模型(初始参考牙齿模型的生成方式参照上述实施例，在此不再赘述)，其中，若是获取到上一次优化确定的上一个参考牙齿模型，则根据预设数据库中包含的所有点云数据帧和上一个参考牙齿模型中每一个点云数据帧的第一模型位置，生成初始参考牙齿模型。
由于初始参考牙齿模型的生成需要时间，因此，在生成初始参考牙齿模型的过程中仍然会有前台扫描的点云数据帧加入后台的数据库，因此，在生成初始参考牙齿模型后，判断当前后台数据库中没有参与生成初始参考牙齿模型的剩余点云数据帧的剩余数量，判断该剩余数量是否大于预设数据阈值，若是不大于预设数据阈值，则中断扫描过程，将剩余点云数据帧与初始参考牙齿模型进行全局优化融合以得到更新后的参考牙齿模型，使用更新后的参考牙齿模型替换掉前台的当前牙齿模型，此时判断是否扫描全部的牙齿，如若是没有则继续进入下一个周期的扫描采集过程。
反之，若是大于预设数据阈值，则将剩余点云数据帧与当前的初始参考牙齿模型进行全局优化融合以得到更新后的初始参考牙齿模型，此时继续重复上述判断，若是剩余点云数据帧不大于预设数据阈值，则中断前台的扫描过程，将剩余点云数据帧与初始参考牙齿模型进行全局优化融合以得到更新后的参考牙齿模型，同时在满足预设模型更新条件时，使用最终得到的参考牙齿模型替换掉前台的当前牙齿模型。此时判断是否扫描全部的牙齿，如若是没有则继续进入下一个周期的扫描采集过程。
综上，本公开实施例提供的牙齿模型的获取方法，响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和当前点云数据帧生成并显示当前牙齿模型，进而，将当前点云数据帧存储到预设数据库，并根据预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件，从而，若是满足预设模型更新条件，则根据所有点云数据帧确定参考牙齿模型，并根据参考牙齿模型更新当前牙齿模型。由此，将牙齿模型的生成显示与牙齿模型的全局优化并行处理，并在合适的时机根据全局优化后的结果对牙齿模型更新，避免了牙齿模型的误差较大无法继续采集牙齿的点云数据帧，从而影响牙齿模型的获取完整度的问题，并且在保证根据点云数据帧可以实时显示牙齿模型的基础上，实现了获取的牙齿模型的完整度和精准度。
为了实现上述实施例，本公开还提出了一种牙齿模型的获取装置。
图5为本公开实施例提供的一种牙齿模型的获取装置的结构示意图，该装置可由软件和/或硬件实现，一般可集成在电子设备中进行牙齿模型的获取。如图5所示，该装置包括：显示模块510、优化模块520、更新模块530，其中，
显示模块510，用于响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和当前点云数据帧生成并显示当前牙齿模型；
优化模块520，用于将当前点云数据帧存储到预设数据库，并根据预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件；
更新模块530，用于在满足预设模型更新条件时，根据所有点云数 据帧确定参考牙齿模型，并根据参考牙齿模型更新当前牙齿模型。
本公开实施例所提供的牙齿模型的获取装置可执行本公开任意实施例所提供的牙齿模型的获取方法，具备执行方法相应的功能模块和有益效果。
在一些可能的实施例中，还包括：模型确定模块，用于：
在牙齿的点云数据帧采集结束时，确定显示的当前牙齿模型为目标牙齿模型。
在一些可能的实施例中，显示模块510，具体用于：
在所述当前点云数据帧为采集的首个点云数据帧时，根据所述当前点云数据帧构建并显示当前牙齿模型；
在所述当前点云数据帧不为采集的首个点云数据帧时，获取最近显示的历史牙齿模型；
在所述历史牙齿模型上拼接所述当前点云数据帧以获取并显示当前牙齿模型。
在一些可能的实施例中，优化模块520，具体用于：
统计所述预设数据库中包含的所有点云数据帧的当前帧数，其中，若是所述当前帧数大于预设数量阈值，则确定满足预设模型更新条件。
在一些可能的实施例中，优化模块520，具体用于：
根据所述预设数据库中包含的当前所有点云数据帧，确定每一个点云数据帧的第一模型位置；
确定显示的当前牙齿模型中每一个点云数据帧的第二模型位置；
根据所述第一模型位置和所述第二模型位置计算每一个点云数据帧的位置误差；
根据所述位置误差判断是否满足预设模型更新条件。
在一些可能的实施例中，优化模块520，具体用于：
计算所有所述位置误差的误差均值；
判断所述误差均值是否大于预设平均误差阈值，其中，若是大于所述预设平均误差阈值，则确定满足所述预设模型更新条件。
在一些可能的实施例中，优化模块520，具体用于：
确定所有所述位置误差中的最大位置误差；
判断所述最大位置误差是否大于预设最大误差阈值，若是大于所述最大误差阈值，则确定满足所述预设模型更新条件。
在一些可能的实施例中，更新模块530，具体用于：
若是获取到上一次优化确定的上一个参考牙齿模型，则根据所述预设数据库中包含的所有点云数据帧和所述上一个参考牙齿模型中每一个点云数据帧的第一模型位置，生成初始参考牙齿模型；
判断所述预设数据库中的剩余点云数据帧的数量是否小于预设数量阈值；
在不小于所述预设数量阈值的情况下，根据所述剩余点云数据帧更新所述初始参考牙齿模型，直到所述预设数据库中的剩余点云数据帧的数量小于所述预设数量阈值；
在所述预设数据库中的剩余点云数据帧的数量小于所述预设数量阈值的情况下，中断对所述牙齿的点云数据帧采集，并根据所述剩余点云数据帧更新所述初始参考牙齿模型以得到所述参考牙齿模型。
在一些可能的实施例中，更新模块530，具体用于：
判断所述牙齿的点云数据帧是否采集完毕，在没有采集完毕时继续采集所述牙齿的当前点云数据帧。
为了实现上述实施例，本公开还提出一种计算机程序产品，包括计算机程序/指令，该计算机程序/指令被处理器执行时实现上述实施例中的牙齿模型的获取方法。
本公开实施例还提供一种计算机存储介质，其中，该计算机存储介质可存储有程序，该程序执行时可实现上述牙齿模型的获取方法的各实现方式中的部分或全部步骤。
图6为本公开实施例提供的一种电子设备的结构示意图。
下面具体参考图6，其示出了适于用来实现本公开实施例中的电子设备600的结构示意图。本公开实施例中的电子设备600可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图6示出的电子设备仅仅是一个示例，不应对本公 开实施例的功能和使用范围带来任何限制。
如图6所示，电子设备600可以包括处理器(例如中央处理器、图形处理器等)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储器608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有电子设备600操作所需的各种程序和数据。处理器601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
通常，以下装置可以连接至I/O接口605：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置606；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置607；包括例如磁带、硬盘等的存储器608；以及通信装置609。通信装置609可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有各种装置的电子设备600，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置609从网络上被下载和安装，或者从存储器608被安装，或者从ROM 602被安装。在该计算机程序被处理器601执行时，执行本公开实施例的牙齿模型的获取方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光 纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和当前点云数据帧生成并显示当前牙齿模型，进而，将当前点云数据帧存储到预设数据库，并根据预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件，从而，若是满足预设模型更新条件，则根据所有点云数据帧确定参考牙齿模型，并根据参考牙齿模型更新当前牙齿模型。由此，将牙齿模型的生成显示与牙齿模型的全局优化并行处理，并在合适的时机根据全局优化后的结果对牙齿模型更新，避免了牙齿模型的误差较大无法继续采集牙齿的点云数据帧，从而影响牙齿模型的获取完整 度的问题，并且在保证根据点云数据帧可以实时显示牙齿模型的基础上，实现了获取的牙齿模型的完整度和精准度。
电子设备可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等 等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅是本公开的具体实施方式，使本领域技术人员能够理解或实现本公开。对这些实施例的多种修改对本领域的技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本公开的精神或范围的情况下，在其它实施例中实现。因此，本公开将不会被限制于本文所示的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。
本公开提供的牙齿模型的获取方法，将牙齿模型的生成显示与牙齿模型的全局优化并行处理，并在合适的时机根据全局优化后的结果对牙齿模型更新，避免了牙齿模型的误差较大无法继续采集牙齿的点云数据帧，从而影响牙齿模型的获取完整度的问题，并且在保证根据 点云数据帧可以实时显示牙齿模型的基础上，实现了获取的牙齿模型的完整度和精准度，具有很强的工业实用性。

Claims (12)

  1. 一种牙齿模型的获取方法，其特征在于，包括以下步骤：
    响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和所述当前点云数据帧生成并显示当前牙齿模型；
    将所述当前点云数据帧存储到预设数据库，并根据所述预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件；
    若是满足所述预设模型更新条件，则根据所述所有点云数据帧确定参考牙齿模型，并根据所述参考牙齿模型更新所述当前牙齿模型。
  2. 如权利要求1所述的方法，其特征在于，还包括：
    若是牙齿的点云数据帧采集结束，则确定显示的当前牙齿模型为目标牙齿模型。
  3. 如权利要求1或2所述的方法，其特征在于，所述根据预设跟踪拼接算法和所述当前点云数据帧生成并显示当前牙齿模型，包括：
    若是所述当前点云数据帧为采集的首个点云数据帧，则根据所述当前点云数据帧构建并显示当前牙齿模型；
    若是所述当前点云数据帧不为采集的首个点云数据帧，则获取最近显示的历史牙齿模型；
    在所述历史牙齿模型上拼接所述当前点云数据帧以获取并显示当前牙齿模型。
  4. 如权利要求1-3任一所述的方法，其特征在于，所述根据所述预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件，包括：
    统计所述预设数据库中包含的所有点云数据帧的当前帧数，其中，若是所述当前帧数大于预设数量阈值，则确定满足预设模型更新条件。
  5. 如权利要求1-4任一所述的方法，其特征在于，所述根据所述预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件，包括：
    根据所述预设数据库中包含的当前所有点云数据帧，确定每一个点云数据帧的第一模型位置；
    确定显示的当前牙齿模型中每一个点云数据帧的第二模型位置；
    根据所述第一模型位置和所述第二模型位置计算每一个点云数据帧的位置误差；
    根据所述位置误差判断是否满足预设模型更新条件。
  6. 如权利要求1-5任一所述的方法，其特征在于，所述根据所述位置误差判断是否满足预设模型更新条件，包括：
    计算所有所述位置误差的误差均值；
    判断所述误差均值是否大于预设平均误差阈值，其中，若是大于所述预设平均误差阈值，则确定满足所述预设模型更新条件。
  7. 如权利要求1-6任一所述的方法，其特征在于，所述根据所述位置误差判断是否满足预设模型更新条件，包括：
    确定所有所述位置误差中的最大位置误差；
    判断所述最大位置误差是否大于预设最大误差阈值，若是大于所述最大误差阈值，则确定满足所述预设模型更新条件。
  8. 如权利要求1-7任一所述的方法，其特征在于，所述根据所述所有点云数据帧确定参考牙齿模型，包括：
    若是获取到上一次优化确定的上一个参考牙齿模型，则根据所述预设数据库中包含的所有点云数据帧和所述上一个参考牙齿模型中每一个点云数据帧的第一模型位置，生成初始参考牙齿模型；
    判断所述预设数据库中的剩余点云数据帧的数量是否小于预设数量阈值；
    若是不小于所述预设数量阈值，则根据所述剩余点云数据帧更新所述初始参考牙齿模型，直到所述预设数据库中的剩余点云数据帧的数量小于所述预设数量阈值；
    若是所述预设数据库中的剩余点云数据帧的数量小于所述预设数量阈值，则中断对所述牙齿的点云数据帧采集，并根据所述剩余点云数据帧更新所述初始参考牙齿模型以得到所述参考牙齿模型。
  9. 如权利要求1-8任一所述的方法，其特征在于，还包括：
    判断所述牙齿的点云数据帧是否采集完毕，若是没有采集完毕则继续采集所述牙齿的当前点云数据帧。
  10. 一种牙齿模型的获取装置，其特征在于，包括：
    显示模块，用于响应于采集到的牙齿的当前点云数据帧，根据预设跟踪拼接算法和所述当前点云数据帧生成并显示当前牙齿模型；
    优化模块，用于将所述当前点云数据帧存储到预设数据库，并根据所述预设数据库中包含的所有点云数据帧判断是否满足预设模型更新条件；
    更新模块，用于在满足所述预设模型更新条件时，根据所述所有点云数据帧确定参考牙齿模型，并根据所述参考牙齿模型更新所述当前牙齿模型。
  11. 一种电子设备，其特征在于，所述电子设备包括：
    处理器；
    用于存储所述处理器可执行指令的存储器；
    所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述可执行指令以实现上述权利要求1-9中任一所述的牙齿模型的获取方法。
  12. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序用于执行上述权利要求1-9中任一所述的牙齿模型的获取方法。
PCT/CN2023/100826 2022-06-17 2023-06-16 牙齿模型的获取方法、装置、设备及介质 WO2023241704A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210722394.6 2022-06-17
CN202210722394.6A CN115068140A (zh) 2022-06-17 2022-06-17 牙齿模型的获取方法、装置、设备及介质

Publications (1)

Publication Number Publication Date
WO2023241704A1 true WO2023241704A1 (zh) 2023-12-21

Family

ID=83255836

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/100826 WO2023241704A1 (zh) 2022-06-17 2023-06-16 牙齿模型的获取方法、装置、设备及介质

Country Status (2)

Country Link
CN (1) CN115068140A (zh)
WO (1) WO2023241704A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115068140A (zh) * 2022-06-17 2022-09-20 先临三维科技股份有限公司 牙齿模型的获取方法、装置、设备及介质
CN116492082B (zh) * 2023-06-21 2023-09-26 先临三维科技股份有限公司 基于三维模型的数据处理方法、装置、设备及介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109616197A (zh) * 2018-12-12 2019-04-12 泰康保险集团股份有限公司 牙齿数据处理方法、装置、电子设备及计算机可读介质
CN111784754A (zh) * 2020-07-06 2020-10-16 浙江得图网络有限公司 基于计算机视觉的牙齿正畸方法、装置、设备及存储介质
US20210186659A1 (en) * 2019-12-23 2021-06-24 Align Technology, Inc. 2d-to-3d tooth reconstruction, optimization, and positioning frameworks using a differentiable renderer
CN113516781A (zh) * 2021-07-12 2021-10-19 先临三维科技股份有限公司 一种三维动态跟踪方法、装置、电子设备和存储介质
CN114219897A (zh) * 2021-12-20 2022-03-22 山东大学 一种基于特征点识别的牙齿正畸结果预测方法及系统
US20220104920A1 (en) * 2020-10-02 2022-04-07 Align Technology, Inc. Methods and systems for designing dental apppliances
CN114612532A (zh) * 2022-02-24 2022-06-10 西安电子科技大学 一种三维牙齿配准方法、系统、计算机设备及存储介质
CN115068140A (zh) * 2022-06-17 2022-09-20 先临三维科技股份有限公司 牙齿模型的获取方法、装置、设备及介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR3027504B1 (fr) * 2014-10-27 2022-04-01 H 43 Procede de controle du positionnement de dents
WO2017144934A1 (en) * 2016-02-26 2017-08-31 Trophy Guided surgery apparatus and method
US11030746B2 (en) * 2018-01-18 2021-06-08 Chengdu Besmile Medical Technology Co., Ltd. Assisted dental beautification method and apparatus for implementing the same
EP3572029B1 (fr) * 2018-05-22 2022-09-21 Dental Monitoring Dispositif d'analyse d'une situation dentaire
WO2020037582A1 (en) * 2018-08-23 2020-02-27 Carestream Dental Technology Shanghai Co., Ltd. Graph-based key frame selection for 3-d scanning
CN109801357B (zh) * 2018-12-04 2023-10-31 先临三维科技股份有限公司 显示三维数字模型的方法及装置、存储介质、处理器
EP4185993A1 (en) * 2020-07-21 2023-05-31 Get-Grin Inc. Systems and methods for modeling dental structures
CN113483695B (zh) * 2021-07-01 2024-01-26 先临三维科技股份有限公司 三维扫描系统、辅助件、处理方法、装置、设备及介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109616197A (zh) * 2018-12-12 2019-04-12 泰康保险集团股份有限公司 牙齿数据处理方法、装置、电子设备及计算机可读介质
US20210186659A1 (en) * 2019-12-23 2021-06-24 Align Technology, Inc. 2d-to-3d tooth reconstruction, optimization, and positioning frameworks using a differentiable renderer
CN111784754A (zh) * 2020-07-06 2020-10-16 浙江得图网络有限公司 基于计算机视觉的牙齿正畸方法、装置、设备及存储介质
US20220104920A1 (en) * 2020-10-02 2022-04-07 Align Technology, Inc. Methods and systems for designing dental apppliances
CN113516781A (zh) * 2021-07-12 2021-10-19 先临三维科技股份有限公司 一种三维动态跟踪方法、装置、电子设备和存储介质
CN114219897A (zh) * 2021-12-20 2022-03-22 山东大学 一种基于特征点识别的牙齿正畸结果预测方法及系统
CN114612532A (zh) * 2022-02-24 2022-06-10 西安电子科技大学 一种三维牙齿配准方法、系统、计算机设备及存储介质
CN115068140A (zh) * 2022-06-17 2022-09-20 先临三维科技股份有限公司 牙齿模型的获取方法、装置、设备及介质

Also Published As

Publication number Publication date
CN115068140A (zh) 2022-09-20

Similar Documents

Publication Publication Date Title
WO2023241704A1 (zh) 牙齿模型的获取方法、装置、设备及介质
US20210056751A1 (en) Photography-based 3d modeling system and method, and automatic 3d modeling apparatus and method
CN112150490B (zh) 图像检测方法、装置、电子设备和计算机可读介质
CN111292420B (zh) 用于构建地图的方法和装置
WO2023213253A1 (zh) 一种扫描数据处理方法、装置、电子设备及介质
WO2023213254A1 (zh) 一种口内扫描处理方法、系统、电子设备及介质
US8587586B2 (en) Electronic device and method for meshing curved surface
WO2024001959A1 (zh) 一种扫描处理方法、装置、电子设备及存储介质
WO2023103999A1 (zh) 3d目标点渲染方法、装置、设备及存储介质
US11494961B2 (en) Sticker generating method and apparatus, and medium and electronic device
WO2022033444A1 (zh) 动态流体效果处理方法、装置、电子设备和可读介质
CN112150491B (zh) 图像检测方法、装置、电子设备和计算机可读介质
WO2023213252A1 (zh) 扫描数据处理方法、装置、设备及介质
WO2024087910A1 (zh) 正畸治疗监测方法、装置、设备及存储介质
WO2024001961A1 (zh) 一种扫描图像渲染方法、装置、电子设备及存储介质
WO2023198101A1 (zh) 基于人工智能的口腔检测方法、装置、电子设备及介质
WO2023213255A1 (zh) 扫描装置及其连接方法、装置、电子设备及介质
WO2023138467A1 (zh) 虚拟物体的生成方法、装置、设备及存储介质
CN116740382A (zh) 障碍物信息生成方法、装置、电子设备和计算机可读介质
CN113506356B (zh) 面积图的绘制方法、装置、可读介质和电子设备
CN113034603A (zh) 用于确定标定参数的方法和装置
WO2024109268A1 (zh) 一种数字模型比对方法、装置、设备及介质
WO2024109622A1 (zh) 一种牙颌模型剖面线生成方法、装置、设备及介质
WO2024051783A1 (zh) 一种三维重建方法、装置、设备和存储介质
CN112883757B (zh) 生成跟踪姿态结果的方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23823270

Country of ref document: EP

Kind code of ref document: A1