Dental arch three-dimensional model guided acquisition system

Abstract

The application relates to the technical field of oral orthodontic digitization and remote medical treatment, and discloses a tooth array three-dimensional model guided acquisition system. A photographing guide and image quality control module controls an oral image acquisition module to perform multi-view image photographing and image acquisition on an oral cavity, and performs real-time analysis on the view angle distribution, view angle coverage and image quality of the images in the image acquisition process, so as to judge whether the collected images meet the multi-view geometry constraint condition required by three-dimensional reconstruction. A three-dimensional reconstruction module is used for performing three-dimensional reconstruction processing on the multi-view images meeting the multi-view geometry constraint condition, and generating a tooth array three-dimensional model. An orthodontic analysis and evaluation module analyzes tooth array arrangement, occlusion relationship and tooth movement trend based on the tooth array three-dimensional model. According to the application, through the photographing structure constraint, photographing guide and image quality control mechanism, the tooth array three-dimensional model used for orthodontic preliminary screening, review and maintenance stage analysis can be constructed.

Description

Technical Field

[0001] This invention relates to the field of digital orthodontics and telemedicine, specifically to a three-dimensional dental model-guided acquisition system. Background Technology

[0002] In orthodontic treatment, a three-dimensional model of the dentition is crucial for diagnostic analysis, treatment evaluation, and retainer fabrication. Currently, clinical practice primarily relies on intraoral scanning equipment to obtain these models. However, such equipment is expensive and bulky, making it difficult to deploy in patients' home environments. Consequently, obtaining three-dimensional data remains highly dependent on in-person visits.

[0003] With the development of telemedicine and mobile imaging technologies, some orthodontic assistive systems have begun to attempt to allow patients to take oral images at home and upload them to a backend system for doctors to view. However, existing technologies mostly only support two-dimensional image display, or assume that users can independently complete the required image acquisition process, and generally suffer from the following problems: First, the lack of structural constraints on the shooting angle, shooting trajectory, and exposure of key tooth surfaces makes it difficult for the images to meet the geometric relationships required for three-dimensional reconstruction. Secondly, the image quality mainly relies on the user's subjective judgment and lacks an image quality screening mechanism as a prerequisite for 3D reconstruction. Finally, the information collected was mostly concentrated on the labial and buccal sides, with insufficient information obtained on the lingual and occlusal surfaces, making it difficult to construct a complete three-dimensional model of the dentition that meets orthodontic requirements.

[0004] Therefore, current technology lacks a systematic technical solution that can reliably acquire three-dimensional dental arch models for orthodontic analysis and maintenance management through home imaging without intraoral scanning equipment. Summary of the Invention

[0005] This invention provides a three-dimensional dental arch model guided acquisition system. Through structural constraints, imaging guidance and image quality control mechanisms, it enables non-professional users to acquire oral images in a home environment that meet the requirements for three-dimensional reconstruction, thereby constructing a three-dimensional dental arch model that can be used for analysis during orthodontic screening, follow-up examination and retention stages.

[0006] Therefore, the present invention provides the following technical solution: A 3D dental arch model-guided acquisition system includes an oral image acquisition module, an image capture guidance and quality control module, a 3D reconstruction module, and an orthodontic analysis and evaluation module connected in sequence. The image capture guidance and quality control module controls the oral image acquisition module to capture and acquire images of the oral cavity from multiple perspectives, and performs real-time analysis on the perspective distribution, perspective coverage, and image quality of the images during the image acquisition process to determine whether the acquired images meet the multi-view geometric constraints required for 3D reconstruction. The 3D reconstruction module performs 3D reconstruction processing on the multi-view images that meet the multi-view geometric constraints to generate a 3D dental arch model. The orthodontic analysis and evaluation module analyzes the dental arch alignment, occlusal relationship, and tooth movement trend based on the 3D dental arch model.

[0007] Optionally, the system further includes a three-dimensional model application module, which is connected to the orthodontic analysis and evaluation module, and applies the constructed three-dimensional model of the dentition to the following orthodontic scenarios: evaluation of dentition morphology and occlusal relationship during the initial orthodontic screening stage; follow-up examination and tooth movement effect analysis during orthodontic treatment; reconstruction of dentition morphology and re-fabrication of retainers during the orthodontic retention stage.

[0008] Optionally, the oral cavity image acquisition module includes a multi-degree-of-freedom mechanical platform, a camera component, and an mouth opener. The mouth opener is used to stabilize the oral cavity opening and expose the dentition area. The multi-degree-of-freedom mechanical platform is mounted on the mouth opener, and the camera component is mounted on the multi-degree-of-freedom mechanical platform.

[0009] Optionally, the mouth opener includes a mouth opener body, an elastic support, buccal retraction wings, an outer frame, and a robotic arm base; the mouth opener body is used to insert into the oral cavity and provide a basic support structure; the elastic support is disposed on both sides of the mouth opener body; the buccal retraction wings are disposed on both sides of the mouth opener body; the outer frame and robotic arm base are disposed on the outside of the mouth opener body, serving as the mounting foundation and reference coordinate structure for the multi-degree-of-freedom mechanical platform; the multi-degree-of-freedom mechanical platform includes a robotic arm mounting interface and an active rotary joint, a robotic arm, a delta robotic arm platform, and a rotary ball joint; the multi-degree-of-freedom mechanical platform is mounted on the outer frame and robotic arm base via the robotic arm mounting interface and the active rotary joint. The robotic arm is mounted on a frame and a base. The robotic arm mounting interface and active rotating joint are connected to the base of the robotic arm and drive it to rotate around a predetermined axis. A delta robotic arm platform is located at the end of the robotic arm. The delta robotic arm platform includes multiple symmetrically distributed drive arms and a moving platform. The end of each drive arm is connected to the moving platform via a rotating ball joint. The rotating ball joint is located between the drive arm and the moving platform, providing multi-directional rotational freedom. The range of motion of the delta robotic arm platform and the robotic arm together define the safe working space of the camera assembly, which is located between the outer side of the oral cavity and the oral cavity entrance area.

[0010] Optionally, the shooting guidance and image quality control module controls the multi-degree-of-freedom mechanical platform to complete multi-view shooting according to a preset trajectory. During the shooting process, it provides the user with shooting area and posture guidance, and performs clarity, view coverage, and effective area detection on the acquired multi-view images of the oral cavity. The shooting guidance and image quality control module is configured to: identify the spatial location and visible range of the dentition region based on image feature extraction results, and determine the coverage of the target tooth surface region by the current viewpoint; evaluate the quality of the acquired images based on preset quantitative indicators; dynamically plan or update subsequent shooting paths and key shooting postures based on the spatial distribution of the acquired images; and output posture adjustment commands or control the oral cavity image acquisition module to perform supplementary acquisition when the image does not meet preset reconstruction conditions.

[0011] Optionally, the shooting guidance and image quality control module performs quality assessment on the acquired oral images. The quantitative indicators include: a sharpness indicator calculated based on image gradient or edge intensity; an exposure indicator calculated based on image brightness distribution; a dentition region view coverage indicator calculated based on tooth region segmentation results; and a multi-view image overlap indicator calculated based on feature matching results. When any of the quantitative indicators is lower than a preset threshold, the shooting guidance and image quality control module triggers posture adjustment or supplementary acquisition.

[0012] Optionally, the 3D reconstruction module uses a combination of structured light motion recovery and multi-view stereo reconstruction to complete the 3D modeling process. The structured light motion recovery stage is used to recover the camera pose and generate sparse 3D point clouds. The multi-view stereo reconstruction stage further generates high-density 3D point clouds based on the sparse 3D point clouds and constructs a 3D mesh model of the dental arch.

[0013] Optionally, after constructing the 3D mesh model of the dental arch, the 3D reconstruction module registers the 3D mesh model of the dental arch with the historical model. During registration, firstly, feature matching is used to utilize the common features between the historical model and the 3D mesh model of the dental arch as initial registration points for initial coarse alignment; then, feature extraction is further refined and registration is performed using the iterative nearest point (ICP) algorithm. By iteratively searching for the closest point pairs between the historical model and the 3D mesh model of the dental arch, the optimal rotation matrix and displacement vector are calculated; after registration, the 3D model of the dental arch that integrates the historical model and the 3D mesh model of the dental arch is generated.

[0014] A method for guiding the acquisition of a three-dimensional dental arch model, the method comprising: Step 1: Take and acquire multi-view images of the oral cavity, and analyze the view distribution, view coverage and image quality of the images in real time during the image acquisition process to determine whether the acquired images meet the multi-view geometric constraints required for three-dimensional reconstruction. Step 2: Perform 3D reconstruction processing on the multi-view images that meet the multi-view geometric constraints to generate a 3D model of the dental arch; Step 3: Analyze the tooth arrangement, occlusal relationship and tooth movement trend based on the three-dimensional model of the dental arch.

[0015] A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to perform the steps of the dental arch three-dimensional model guided acquisition method.

[0016] The 3D dental arch model guided acquisition system provided by this invention uses a camera device for guided acquisition. The imaging device provides structural constraints on the shooting posture and path, and combined with imaging guidance and image quality control mechanisms, it acquires a 3D dental arch model that meets orthodontic analysis requirements under non-professional operating conditions. This 3D dental arch model is then applied to a remote orthodontic assistance system during the initial screening, follow-up examination, and retention stages of orthodontics. Compared with existing technologies, this invention has the following technical advantages: 1. Achieve the acquisition of three-dimensional models of the dental arch without intraoral scanning equipment, thus lowering the threshold for orthodontic digital data acquisition; 2. By structurally constraining the shooting posture and trajectory through the shooting device, the usability of image acquisition for non-professional users is improved; 3. Ensure that the data entering the 3D reconstruction process meets the requirements of orthodontic analysis through image quality control mechanisms; 4. The constructed three-dimensional model of the dentition can cover the buccal side, occlusal surface, and at least part of the lingual side, making it suitable for orthodontic analysis and retention management; 5. The system is suitable for different types of orthodontic patients during the initial screening and retention stages, and can be used in conjunction with bracketless invisible orthodontic systems and remote orthodontic monitoring systems during the follow-up stage, demonstrating good versatility. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the structure of a three-dimensional dental arch model-guided acquisition system in a specific embodiment of the present invention; Figure 2 This is a schematic diagram of the mechanical structure of the oral cavity image acquisition module in a specific embodiment of the present invention; Figure 3 This is a schematic diagram of the overall structure of the oral cavity image acquisition module in a specific embodiment of the present invention; Figure 4 This is a schematic diagram illustrating the generation of a three-dimensional dental arch model in a specific embodiment of the present invention; Figure 5 This is a diagram of model alignment and registration and tooth movement path in a specific embodiment of the present invention; Figure 6 This is a flowchart of retainer reconstruction and remote 3D printing in a specific embodiment of the present invention. Detailed Implementation

[0019] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] like Figure 1The diagram shown is a structural block diagram of the dental arch three-dimensional model guided acquisition system in an embodiment of the present invention. The system includes an oral image acquisition module 101, an image acquisition guidance and image quality control module 102, a three-dimensional reconstruction module 103, an orthodontic analysis and evaluation module 104, and a three-dimensional model application module 105.

[0022] The oral cavity image acquisition module 101 is used to acquire multi-view image data of a patient's dentition. The oral cavity image acquisition module 101 includes a multi-degree-of-freedom mechanical platform, a camera component (which can be a single camera, dual camera, or multi-camera imaging device) mounted on the end of a robotic arm on the multi-degree-of-freedom mechanical platform, and an mouth opener for stabilizing oral cavity opening and exposing the dentition area.

[0023] like Figure 2 As shown, the oral cavity image acquisition module 101 uses the mouth opener as the basic support and positioning structure of the system.

[0024] The mouth opener includes a mouth opener body 1, an elastic support 2, a buccal retraction wing 3, and an external frame and robotic arm base 4. The mouth opener body 1 is inserted into the oral cavity and provides a basic support structure; the elastic support 2 is located on both sides of the mouth opener body 1 to provide elastic tension during use, adapting to different patients' oral opening degrees and improving wearing comfort; the buccal retraction wing 3 is connected to both sides of the mouth opener body 1 to retract the labial and buccal tissues, thereby fully exposing the dentition area; the external frame and robotic arm base 4 are fixedly located on the outside of the mouth opener body 1, serving as the mounting base for a multi-degree-of-freedom mechanical platform and providing a stable reference coordinate system for subsequent mechanical movements.

[0025] The multi-degree-of-freedom mechanical platform includes a robotic arm mounting interface and an active rotary joint 5, a robotic arm 6, a delta robotic arm platform 7, and a rotary ball joint 8. The multi-degree-of-freedom mechanical platform is mounted on the external frame and robotic arm base 4 via the robotic arm mounting interface and the active rotary joint 5. The robotic arm mounting interface is located on the upper surface or side of the external frame and robotic arm base 4, for connection to the base of the robotic arm 6. The active rotary joint is located at or inside the robotic arm mounting interface, for driving the robotic arm 6 to rotate around a predetermined axis, thereby adjusting the spatial posture of the camera assembly. Preferably, the active rotary joint can be implemented using a servo motor, stepper motor, or a drive mechanism with an encoder. The robotic arm 6 is connected to the robotic arm mounting interface and the active rotary joint 5 at the robotic arm mounting interface, and acts as an actuator to drive the end-effector camera assembly in spatial movement. The robotic arm 6 preferably adopts a lightweight structural design, and can be made of aluminum alloy, engineering plastics, or carbon fiber composite materials to reduce overall weight while ensuring structural strength. The delta robotic arm platform 7 is located at the end of the robotic arm 6 and provides a multi-degree-of-freedom parallel motion structure. The delta robotic arm platform 7 includes multiple symmetrically distributed drive arms and a moving platform. The end of each drive arm is connected to the moving platform via a rotating ball joint 8. The rotating ball joints 8 are respectively located between each drive arm and the moving platform to provide multi-directional rotational degrees of freedom, thereby enabling spatial attitude adjustment of the mechanical structure. The rotating ball joints 8 can be implemented using metal ball joints or polymer material ball joint structures to balance motion flexibility and wear resistance.

[0026] The camera assembly includes a telescopic support rod 9 and a replaceable depth camera assembly 10. The telescopic support rod 9 is connected between the drive arms of the delta robotic arm platform 7 or between the drive arms and the moving platform, and is used to adjust its length, thereby changing the position and orientation of the camera assembly. The telescopic support rod 9 can be implemented using an electrically telescopic structure or a mechanical telescopic structure with a locking mechanism. The replaceable depth camera assembly 10 is installed on the moving platform end of the delta robotic arm platform 7 and is used to collect multi-view image data of the oral cavity region. The camera assembly can be a monocular camera, a binocular camera, or a structured light / ToF depth camera, and can be replaced through a detachable connection structure to adapt to different application scenarios. The camera safety working space 11 is jointly defined by the robotic arm mounting interface, the active rotating joint 5, and the range of motion of the robotic arm 6. The camera safety working space 11 is located between the outer side of the oral cavity and the oral cavity entrance area, and is used to limit the range of motion of the camera assembly, preventing it from entering the deep oral cavity region and coming into contact with soft tissue, thereby improving safety.

[0027] like Figure 3 The image shown is a schematic diagram of the overall structure of the oral cavity image acquisition module. Figure 3a is a side view schematic diagram of the multi-link adjustment mechanism of the oral cavity image acquisition module. Figure 3 b is a front view schematic diagram of the multi-link adjustment mechanism of the oral scanning auxiliary device.

[0028] The oral image acquisition module 101 uses a delta robotic arm platform 7, which includes a base, three symmetrically distributed drive arms, and a moving platform. Combined with a rotating ball joint 8 and a telescopic strut 9, it can achieve six degrees of freedom of movement of the platform, allowing the replaceable depth camera assembly 10 to cover areas such as the buccal side, lingual side, and occlusal surface. Preferably, the movement of the robotic arm 6 is restricted within a preset safety space to avoid contact with oral tissues.

[0029] The multi-degree-of-freedom mechanical platform is mounted on the outer frame of the mouth opener and the robotic arm base 4, forming a preset camera safety working space 11 with the outer frame and robotic arm base 4 as the reference coordinate system. The camera safety working space 11 is jointly limited by the structural stroke limit and the electronic control angle limit of each rotating joint of the multi-degree-of-freedom mechanical platform, so that the replaceable depth camera assembly 10 can only move within the safe shooting space from the outside of the oral cavity to the entrance area of ​​the oral cavity.

[0030] At the software level, the motion trajectory of the robotic arm 6 is planned and its posture is controlled by the shooting guidance and image quality control module 102, which guides the replaceable depth camera component 10 to complete multi-view image acquisition according to the preset shooting trajectory, thereby ensuring that the geometric relationship required for three-dimensional reconstruction is met between images from different perspectives.

[0031] The shooting guidance and image quality control module 102 is used to guide the posture and assess the quality of the shooting process, control the robotic arm to complete multi-view shooting according to a preset trajectory, and detect the sharpness, view coverage, and effective area of ​​the acquired images. Specifically, the shooting guidance and image quality control module 102 provides the user with shooting area and posture guidance during the shooting process, and analyzes the acquired oral cavity images to determine whether the images meet the quality requirements for entering the 3D reconstruction process; images that do not meet the quality requirements are not included in the subsequent 3D model construction process.

[0032] The 3D reconstruction module 103 is used to generate a 3D model of the dental arch based on the acquired multi-view image data through a multi-view geometric reconstruction algorithm or a deep learning 3D reconstruction algorithm.

[0033] The orthodontic analysis and assessment module 104 is used to extract tooth position, morphology and spatial relationship features based on the three-dimensional model of the dental arch, and to analyze the dental arch arrangement, occlusal relationship and tooth movement trend, thereby providing auxiliary assessment for orthodontic treatment.

[0034] The 3D model application module 105 is used to apply the constructed 3D dental arch model to at least one of the following orthodontic scenarios: assessment of dental arch morphology and occlusal relationship during the initial orthodontic screening stage; follow-up examination and analysis of tooth movement effects during orthodontic treatment; reconstruction of dental arch morphology and remanufacturing of retainers during the orthodontic retention stage.

[0035] In a preferred embodiment, the acquisition of the three-dimensional model of the dental arch is performed in the patient's mouth without wearing orthodontic appliances, so as to avoid the device having an adverse effect on the accuracy of tooth surface image acquisition and three-dimensional reconstruction.

[0036] In one embodiment, the process of generating a three-dimensional dental arch model using the dental arch three-dimensional model-guided acquisition system of the present invention is as follows: Figure 4 As shown.

[0037] Step 401: The imaging guidance and image quality control module controls the oral cavity image acquisition module to perform multi-view image acquisition. During the acquisition process, it performs real-time analysis and dynamic guidance on the shooting angle, shooting path, and image quality to obtain multi-view image data that meets the requirements of 3D reconstruction. Specifically, this includes: Step 1a: Perform feature extraction. Extract features from the acquired oral cavity images to identify the location, spatial orientation, and visible range of the dentition area, and determine whether the current viewpoint covers the target tooth surface area.

[0038] The extracted features include at least one of the following: tooth contour edge features, tooth surface texture features, interdental features, occlusal surface morphology features, and gingival-dental junction contour features.

[0039] Through the above feature extraction, the position, orientation, and visible range of the dental arch area in the current image can be identified, thereby determining whether the current shooting angle covers the target tooth surface area, and providing shooting posture adjustment prompts to the operator or robotic arm platform accordingly.

[0040] Step 1b involves image quality assessment, including real-time evaluation of the acquired images and quantification of the process to provide multi-view image data for subsequent 3D model reconstruction. This is achieved through real-time analysis of the captured images and a quantitative evaluation of the capturing process. The quantitative indicators include: (1) Image quality indicators, including image sharpness and exposure, are used to determine whether the image meets the requirements for feature extraction and matching; Among them, image sharpness evaluation refers to assessing whether an image is blurry by evaluating the image gradient or edge intensity; exposure evaluation refers to judging whether an image is overexposed or underexposed by the image brightness distribution.

[0041] (2) Spatial coverage indicators, including tooth area coverage and the completeness of collection of key tooth surface areas (including occlusal surface, labial surface, lingual surface, etc.); Among them, the evaluation of tooth region coverage refers to calculating the proportion of key tooth regions (such as teeth, gums, and shadow-occluded areas) in the image based on the tooth region segmentation results.

[0042] Tooth area coverage can be calculated in the following ways: α=S k / S, Where α represents the proportion of the tooth region, Sk represents the area of ​​the key tooth region, and S represents the total area of ​​the effective image. When this proportion is below a threshold, the user is prompted to adjust the angle or move closer. The quality of a single image, i.e., its coverage, is evaluated by calculating the tooth region coverage rate.

[0043] (3) Multi-view geometric metrics, including image overlap, are used to evaluate the geometric matching conditions between images from different viewpoints. Image overlap rate evaluation refers to calculating the proportion of overlapping areas between images from different viewpoints through feature point matching.

[0044] When any indicator falls below the preset threshold, the operator will be prompted to retake the photo or adjust the shooting angle to ensure that the acquired image meets the requirements for subsequent 3D model reconstruction.

[0045] Step 1c involves planning and dynamically adjusting the shooting path. Based on the prior dental arch geometry model and the perspective information of the currently acquired images, the camera movement shooting path and key points of the path are planned.

[0046] The system first generates an initial shooting path around the dental arch region based on the dental arch morphology; then, based on the real-time image analysis results, it dynamically adjusts the shooting path and determines several key shooting points.

[0047] Each key point corresponds to a preset shooting posture, including: camera position, camera orientation, and distance between the camera and the dental arch. The camera is moved sequentially to each key point to acquire images, ensuring that each area of ​​the dental arch can obtain image data from at least two different perspectives, thereby meeting the multi-view geometric conditions required for 3D reconstruction.

[0048] Step 1d involves determining the conditions for 3D reconstruction and supplementing data acquisition. When the camera reaches the key shooting point, the system uses image feature matching and recognition algorithms to perform quality checks on the currently acquired images, verifying whether the images meet the requirements and ensuring the data integrity of key areas such as the tooth surface and lingual side. Specifically, this includes: First, extract the tooth edge features, texture features, and interdental features from the current image; The features are then matched with corresponding features in the acquired images to calculate the feature correspondence between images from different viewpoints; When the number or distribution range of matched feature points reaches a preset threshold, the current viewpoint image is determined to meet the requirements for three-dimensional reconstruction. If the matching features are insufficient or key areas are not covered, the system guides the camera to move to a new shooting position to collect additional data, thereby ensuring the integrity of data for key areas such as the tooth surface, lingual surface, and occlusal surface.

[0049] Step 1e involves performing posture assessment and feedback guidance. Posture assessment is used to calculate the spatial posture deviation of the camera device relative to the dental arch area in real time during image acquisition, and to provide posture adjustment prompts when the deviation exceeds a set threshold.

[0050] Specifically, the system first extracts feature points in the oral cavity area using image recognition algorithms. These feature points include dental arch contour points, tooth edge points, and gingival boundary points. Then, based on the spatial distribution of these feature points in the image and combined with a preset dental arch geometric model, the system calculates the spatial posture parameters of the current camera device relative to the dental arch area, including the shooting angle, shooting distance, and viewing direction. The posture parameters are compared with a preset standard shooting posture to obtain a posture deviation value. When the deviation value exceeds a set threshold, the system guides the operator to adjust the position or shooting angle of the camera device through voice prompts or graphic prompts.

[0051] Step 402: The 3D reconstruction module reconstructs the 3D model of the dental arch based on multi-view images. Preferably, a combination of Structure from Motion (SfM) and Multi-View Stereo (MVS) methods is used to complete the 3D modeling process. The SfM stage primarily recovers the camera pose and generates a sparse 3D point cloud, while the MVS stage further generates a high-density 3D point cloud based on the sparse point cloud, ultimately constructing a 3D mesh model of the dental arch. During SfM, the system extracts local feature points from each image using feature extraction algorithms (such as SIFT or ORB) and performs feature matching. The relative position and pose of the camera are calculated using these matched feature points, thereby deducing the coordinates of the 3D points. The triangulation formula used in the process is: X=triangulate(P1,P2,x1,x2) Where P 1、 P2 is the camera projection matrix, x1 and x2 are the positions of the feature points on the corresponding image, and X is the calculated three-dimensional spatial coordinates.

[0052] In the MVS stage, the system uses the camera pose parameters and sparse 3D point cloud obtained in the SfM stage to perform depth estimation of the dental arch region through a multi-view dense matching algorithm, thereby generating a high-density 3D point cloud and further constructing a 3D mesh model of the dental arch.

[0053] In practical implementation, the depth information of corresponding pixels can be calculated through the disparity relationship between multi-view images. For example, under binocular or multi-view geometry, the depth D of a target point can be estimated through the disparity relationship, and its basic calculation relationship can be expressed as: D=f·B / d in: D is the depth of the target point; f is the camera focal length; B is the camera baseline distance; d represents the disparity between corresponding pixels.

[0054] This depth estimation relation can be used as an implementation method in multi-view dense matching.

[0055] In the MVS (Dense Reconstruction) stage, the system utilizes feature points from multiple images and employs depth estimation and image reconstruction techniques to generate a dense point cloud. Through depth map calculation and multi-view image registration, the system can meticulously reconstruct the three-dimensional morphology of the teeth.

[0056] Step 403: The 3D reconstruction module generates a precise 3D mesh from these densely reconstructed point clouds, presenting a complete 3D model of the teeth. After the 3D reconstruction is completed, registration is performed between the reconstructed 3D model of the oral cavity and the historical model. First, feature matching is used, utilizing common features between the historical model and the reconstructed model (such as tooth apex, gingival line, etc.) as initial registration points for initial coarse alignment. Next, the system further refines feature extraction and performs registration using the Iterative Closest Point (ICP) algorithm. By iteratively searching for the closest point pairs between the historical model and the reconstructed model, the optimal rotation matrix and translation vector are calculated. The goal of the ICP algorithm is to minimize the following objective function: E=Σ i ||p i ′-T(p i )‖² Where pi' is a point in the historical model, pi is the corresponding point in the reconstructed model, T is the rigid body transformation matrix, and n is the number of points.

[0057] During the registration process, the system uses the Iterative Closest Point (ICP) algorithm to register the reconstructed model with the historical model. It iteratively searches for the closest point pair between the two models and establishes an error function between the point clouds.

[0058] During the error minimization process, gradient descent, the Levenberg-Marquardt algorithm, or other nonlinear optimization methods can be used to solve for the optimal rigid body transformation parameters in order to obtain the optimal alignment result between the reconstructed model and the historical model for internal optimization of ICP.

[0059] Step 404: The orthodontic analysis and assessment module analyzes the tooth alignment, occlusal relationship and tooth movement trend based on the three-dimensional model of the dentition, thereby providing auxiliary assessment for orthodontic treatment.

[0060] like Figure 5 The diagram shown illustrates model alignment and registration, as well as tooth movement paths, in a specific embodiment of the present invention. By registering the current 3D dental arch model with historical models, the positional relationship of the dental arch in a unified coordinate system is obtained. Based on the changes in tooth position at different time points, the tooth movement path is determined for orthodontic treatment effectiveness evaluation.

[0061] like Figure 6 The diagram shown is a flowchart of retainer reconstruction and remote 3D printing in a specific embodiment of the present invention. First, the dental arch 3D model guides the acquisition system of the present invention for scanning and reconstruction to obtain an oral cavity model, i.e., a dental arch 3D model. Then, the oral cavity model is remotely transmitted to a remote printing device, and after 3D printing by the remote printing device, a new retainer is obtained.

[0062] This invention discloses a 3D dental arch model-guided image acquisition system. The system uses a camera device to structurally constrain the shooting posture and path of the camera components, guiding non-professional users to acquire multi-angle oral images. The system then assesses the quality of the acquired images, using only those meeting the requirements for 3D reconstruction for subsequent processing. Based on multi-view image reconstruction technology, the system constructs a 3D dental arch model including the buccal, occlusal, and at least part of the lingual regions. This 3D dental arch model can be applied to the analysis and management of orthodontic initial screening, orthodontic follow-up, and orthodontic retention stages. Ideally, the model is acquired while the patient is not wearing orthodontic appliances, providing a reliable data foundation for remote orthodontic assessment and retainer fabrication.

[0063] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0064] The present invention also provides a storage medium, which is a computer-readable storage medium storing a computer program thereon, the computer program being executable when it runs. Figure 4The method shown may include some or all of the steps. The storage medium may include read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc. The storage medium may also include non-volatile memory or non-transitory memory, etc.

[0065] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data provider to another website, computer, server, or data provider via wired or wireless means.

[0066] The embodiments of the present invention have been described in detail above. Specific implementation methods have been used to illustrate the present invention. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and systems of the present invention, and are merely some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention, and the content of this specification should not be construed as a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A dentition three-dimensional model guided acquisition system, characterized in that, The system includes a dental image acquisition module, an image capture guidance and quality control module, a 3D reconstruction module, and an orthodontic analysis and evaluation module connected in sequence. The image capture guidance and quality control module controls the dental image acquisition module to capture and acquire images of the oral cavity from multiple perspectives. During the image acquisition process, it performs real-time analysis on the perspective distribution, perspective coverage, and image quality of the images to determine whether the acquired images meet the multi-view geometric constraints required for 3D reconstruction. The 3D reconstruction module performs 3D reconstruction processing on the multi-view images that meet the multi-view geometric constraints to generate a 3D model of the dental arch. The orthodontic analysis and evaluation module analyzes the dental arch alignment, occlusal relationship, and tooth movement trend based on the 3D model of the dental arch.

2. The dentition three-dimensional model guided acquisition system according to claim 1, wherein, The system also includes a 3D model application module, which is connected to the orthodontic analysis and evaluation module. The constructed 3D model of the dentition is applied to the following orthodontic scenarios: evaluation of dentition morphology and occlusal relationship during the initial orthodontic screening stage; follow-up examination and analysis of tooth movement effects during orthodontic treatment; reconstruction of dentition morphology and re-fabrication of retainers during the orthodontic retention stage.

3. The dentition three-dimensional model guided acquisition system according to claim 1, wherein, The oral cavity image acquisition module includes a multi-degree-of-freedom mechanical platform, a camera component, and an mouth opener. The mouth opener is used to stabilize the oral cavity opening and expose the dentition area. The multi-degree-of-freedom mechanical platform is mounted on the mouth opener, and the camera component is mounted on the multi-degree-of-freedom mechanical platform.

4. The dentition three-dimensional model guided acquisition system according to claim 3, wherein, The mouth opener includes a mouth opener body, an elastic support, buccal retraction wings, an outer frame, and a robotic arm base. The mouth opener body is inserted into the oral cavity and provides basic support. The elastic support is located on both sides of the mouth opener body. The buccal retraction wings are located on both sides of the mouth opener body. The outer frame and robotic arm base are located on the outside of the mouth opener body, serving as the mounting base and reference coordinate structure for the multi-degree-of-freedom mechanical platform. The multi-degree-of-freedom mechanical platform includes a robotic arm mounting interface and an active rotary joint, a robotic arm, a delta robotic arm platform, and a rotary ball joint. The multi-degree-of-freedom mechanical platform is mounted on the outer frame via the robotic arm mounting interface and the active rotary joint. The frame and robotic arm base are mounted on the robotic arm. The robotic arm mounting interface and active rotating joint are connected to the base of the robotic arm and drive the robotic arm to rotate around a predetermined axis. The delta robotic arm platform is located at the end of the robotic arm. The delta robotic arm platform includes multiple symmetrically distributed drive arms and a moving platform. The end of each drive arm is connected to the moving platform through a rotating ball joint. The rotating ball joint is located between the drive arm and the moving platform, providing multi-directional rotational freedom. The range of motion of the delta robotic arm platform and the robotic arm together define the safe working space of the camera assembly. The safe working space is located between the outer side of the oral cavity and the oral cavity entrance area.

5. The dental arch three-dimensional model guided acquisition system according to claim 3, characterized in that, The shooting guidance and image quality control module controls the multi-degree-of-freedom mechanical platform to complete multi-view shooting according to a preset trajectory. During the shooting process, it provides the user with shooting area and posture guidance, and performs clarity, view coverage, and effective area detection on the acquired multi-view images of the oral cavity. Specifically, the shooting guidance and image quality control module is configured to: identify the spatial location and visible range of the dentition region based on image feature extraction results, and determine the coverage of the target tooth surface region by the current viewpoint; evaluate the quality of the acquired images based on preset quantitative indicators; dynamically plan or update subsequent shooting paths and key shooting postures based on the spatial distribution of the acquired images; and output posture adjustment commands or control the oral cavity image acquisition module to perform supplementary acquisition when the image does not meet preset reconstruction conditions.

6. The dental arch three-dimensional model guided acquisition system according to claim 5, characterized in that, The shooting guidance and image quality control module performs quality assessment on the acquired oral images. The quantitative indicators include: a sharpness indicator calculated based on image gradient or edge intensity; an exposure indicator calculated based on image brightness distribution; a dentition region view coverage indicator calculated based on tooth region segmentation results; and a multi-view image overlap indicator calculated based on feature matching results. When any of the quantitative indicators is lower than a preset threshold, the shooting guidance and image quality control module triggers posture adjustment or supplementary acquisition.

7. The dental arch three-dimensional model guided acquisition system according to claim 1, characterized in that, The 3D reconstruction module uses a combination of structured light motion recovery and multi-view stereo reconstruction to complete the 3D modeling process. The structured light motion recovery stage is used to recover the camera pose and generate sparse 3D point clouds. The multi-view stereo reconstruction stage further generates high-density 3D point clouds based on the sparse 3D point clouds and constructs a 3D mesh model of the dental arch.

8. The dental arch three-dimensional model guided acquisition system according to claim 7, characterized in that, After constructing the 3D mesh model of the dental arch, the 3D reconstruction module registers the 3D mesh model of the dental arch with the historical model. During the registration, feature matching is first used to utilize the common features between the historical model and the 3D mesh model of the dental arch as the initial registration points for initial coarse alignment. Then, the feature extraction is further refined and the registration is performed using the iterative nearest point ICP algorithm. By iteratively searching for the closest point pair between the historical model and the three-dimensional mesh model of the dental arch, the optimal rotation matrix and displacement vector are calculated. After registration is completed, a 3D model of the dental arch is generated that integrates the historical model and the 3D mesh model of the dental arch.

9. A method for guiding the acquisition of a three-dimensional dental arch model, characterized in that, The method includes: Step 1: Take and acquire multi-view images of the oral cavity, and analyze the view distribution, view coverage and image quality of the images in real time during the image acquisition process to determine whether the acquired images meet the multi-view geometric constraints required for three-dimensional reconstruction. Step 2: Perform 3D reconstruction processing on the multi-view images that meet the multi-view geometric constraints to generate a 3D model of the dental arch; Step 3: Analyze the tooth arrangement, occlusal relationship and tooth movement trend based on the three-dimensional model of the dental arch.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when run by the processor, executes the steps of the dental arch three-dimensional model guided acquisition method as described in claim 9.

Images