341 results about "Single tooth" patented technology

The invention relates to a CBCT image tooth segmentation method. The method comprises the following steps: generating a two-dimensional oral cavity panoramic film from a CBCT image; carrying out tooth two-dimensional segmentation and tooth ID classification on the two-dimensional oral cavity panoramic film by adopting a deep learning algorithm; calculating a key point coordinate of a two-dimensional single tooth and mapping the key point coordinate to a three-dimensional CBCT image coordinate; respectively cutting the CBCT image to obtain an area of each tooth; segmenting each three-dimensional tooth region by adopting a deep learning algorithm; and assigning ID to all the tooth segmentation results, and splicing to obtain a three-dimensional tooth segmentation result. According to the method, accurate segmentation of the tooth area in the CBCT image can be realized, complex conditions such as tight tooth arrangement, similar shapes and artifact interference can be effectively handled, the problems of tooth segmentation result fusion, ID confusion and metal artifact interference can be effectively solved, and resource consumption is remarkably reduced by determining the tooth key points on the panoramic film, so that the tooth segmentation efficiency is improved. The overall segmentation efficiency is improved, and the segmentation time is shortened, so that the accuracy of the segmentation result and the processing speed are improved.

The invention relates to a helical gear detection method based on waviness information and a gear detection system. The helical gear detection method based on waviness information comprises the following steps: extracting full-tooth waviness information of a helical gear; processing the full-tooth waviness information to obtain a spectrogram; calculating an angle alpha of waviness on any single tooth of the helical gear; and according to the angle alpha of the waviness on the single tooth and the spectrogram, judging whether the gear has noise requirements or not. According to the method, through full-tooth order analysis and single-tooth topology three-dimensional angle analysis of the involute helical gear, important factors influencing gear meshing noise are calculated and extracted, tooth surface waviness information can be effectively detected, ghost frequency can be effectively identified and found, and a ripple line angle can be effectively analyzed; the method greatly improves the fitting quality of data, thereby improving the detection precision of the gear, enabling the gear to meet the noise detection requirements, and providing a brand new detection method for high-speed and low-noise gear production.

The invention belongs to the technical field of machining, and particularly relates to a turbine disc mortise accurate positioning method for a five-axis numerical control broaching machine, which comprises the following steps of: S1, constructing a broaching force model, carrying out a broaching force test, and respectively obtaining turbine disc mortise broaching force coefficients in x, y and z directions so as to establish a single-tooth broaching force model; secondly, a multi-tooth broaching force model is built on the basis of a single-tooth cutting force model, S2, mechanical deformation analysis is conducted, and the workpiece deformation amount is calculated according to cutting force; measuring the displacement variation of a mortise cutting point by adopting laser; linear equation fitting is carried out based on the numerical values of the multiple sets of workpiece deformation and displacement variation, and a corresponding linear equation is obtained; and S3, when the broaching machine is adopted for machining, the cutting force is calculated based on the broaching force model, then corresponding cutting force loads are applied to the mortise broaching machine finite element model, deformation in the x direction, the y direction and the z direction is obtained, the actual deformation amount is calculated according to the linear equation in the S2, and accurate positioning coordinates are obtained.

The invention relates to the field of bevel gear pair friction-flash temperature characteristic calculation, and particularly discloses a bevel gear pair friction-flash temperature characteristic calculation method under real machining surface conditions. Comprising the following steps: calculating oil film shear stress, shear modulus and tooth surface micro-bulge contact shear stress in a helical gear meshing process by adopting a non-Newtonian fluid model and a micro-bulge contact model; summing the shearing stress of the oil film and the shearing stress of the micro-bulge, and performing integration to solve the friction force of the contact domain in the meshing process of the bevel gear and the friction coefficient in the single-tooth meshing period of the bevel gear; coupling oil film shear stress, micro-convex body contact shear stress and relative slippage of two interfaces, and solving heat generated by a tooth surface contact domain in the meshing process through a heat distribution model; substituting the obtained heat into a second kind of Volterra integral equation based on a fast moving heat source model, and calculating the interface flash temperature by adopting an iteration method; and the obtained interface flash temperature is reversely brought back to the non-Newtonian fluid model, and repeated iteration is carried out until convergence.

According to one embodiment of the present invention, the present invention can provide a dental model for dental practice, the dental model comprising an upper jaw part and a lower jaw part to which dental models are detachably coupled, the dental models comprising: a single tooth forming a tooth head and a tooth root, a coupling guide protrusion for preventing detachment and guiding the coupling direction when coupled to the tooth fixing block side is formed on the outer surface of the tooth root, and a dental nerve is formed in the interior of the tooth root; a tooth fixing block forming an internal space detachably coupled to the root of the single tooth, the internal space being filled with a conductive adhesive for measuring the length of the root canal; a gingival part in which a plurality of the tooth fixing blocks are assembled in accordance with a tooth arrangement; and a chin strap to which the gingival part and the tooth fixing block are fixed, the chin strap being coupled to the temporomandibular joint on either side of the maxillary part or the mandibular part.

The present invention relates to the technical field of dental medical treatment, and specifically discloses a method for using a CBCT (Cone Beam Computer Tomography) for automatically positioning a tooth, which comprises the following steps: S01, archiving CT data; S02, calculating AI and generating AI results; S03, entering CT reading by a client; S04, downloading and loading the CT data; S05, opening a function of a tooth lens; S06, selecting a corresponding tooth position in a tooth position list; and S07, selecting a 3D tooth rendering mode. The function of the ‘tooth lens’ is added into traditional CT reading, which is suitable for clinical disease diagnoses such as ‘tooth extraction, root canal therapy, tooth repair’ and the like in oral treatment, and doctors can precisely and quickly position the single tooth through selection for the tooth position, which facilitates more comprehensive analysis.

The invention provides a random rotation speed-oriented gear meshing stiffness calculation method, which belongs to the technical field of gear performance evaluation, and comprises the following steps: describing the actual operation state of a gear system by using a random rotation speed; determining the total potential energy of the gear according to the acting force of the meshing points; solving the total potential energy of the gear to obtain a potential energy calculation function about a meshing rotation angle; determining a meshing stiffness calculation function about the meshing rotation angle by using the potential energy calculation function; solving an average value of a single-tooth meshing area and a double-tooth meshing area of the meshing stiffness calculation function; and the meshing rigidity is simplified into a square wave function through the average value, and the meshing rigidity is changed into a time function from a corner function through the generated random rotating speed. According to the method, the running state of the gear system is described by using the random rotating speed, the influence caused by random fluctuation of the rotating speed is considered, the meshing rigidity of a wind power gear box and the like in the actual working environment can be reflected more truly, and the accuracy and applicability of meshing rigidity calculation are remarkably improved.

The invention relates to an image processing method which comprises the following steps: acquiring a visible light image, a near-infrared image and a fluorescence image of the same tooth area to obtain a multi-modal image; inputting the multi-modal image into a segmentation network, embedding a space attention module into a jump connection between an encoder and a decoder of the segmentation network, and outputting a binary mask of a tooth area by the segmentation network; extracting contours of a single tooth from the binary mask, and determining a minimum enclosing rectangle and a geometric center of gravity of each contour; distributing FDI tooth position codes for each contour according to the horizontal coordinates of the geometric center of gravity; according to the minimum enclosing rectangle, cutting out a corresponding single tooth image block from the multi-modal image; inputting the single tooth image block into a multi-branch convolutional neural network to obtain a unified feature vector; and inputting the unified feature vector into a full-connection classification network, and outputting probability values corresponding to different categories by the full-connection classification network. The invention also relates to an image processing device, a medium and a computer program product, and a tooth recognition system.

The present invention relates to a helical gear detection method and gear detection system based on waviness information. The helical gear detection method based on waviness information comprises the following steps: extracting the full tooth waviness information of the helical gear; processing the full tooth waviness information to obtain a frequency spectrum; calculating the angle α of the waviness on any single tooth of the helical gear; judging whether the gear meets the noise requirement based on the angle α of the waviness on the single tooth and the frequency spectrum. The present invention calculates and extracts the important factors affecting the gear meshing noise by analyzing the full tooth order of the involute helical gear and the three-dimensional angle of the single tooth topology. It can effectively detect the tooth surface waviness information, identify and discover ghost frequencies, and analyze the angle of the corrugation line. Compared with the existing detection method, it greatly improves the fitting quality of the data, thereby improving the detection accuracy of the gear, so that it meets the noise detection requirements, and provides a new detection method for the production of high-speed and low-noise gears.

Computer implemented method of generating a dental design, comprising: (a) capturing a facial image comprising a head of a patient and a smile; (b) displaying it as a first image; (c) capturing a 3D intraoral scan; (d) aligning the 3D scan to the head; (e) determining bounding boxes in the 3D scan, each comprising a single tooth; (f) showing a view of the 3D scan and the bounding boxes as a second image; (g) showing the bounding boxes as overlay on the first image; (i) allowing the bounding boxes to be resized / repositioned; (ii) defining a limited set of parameters to characterize the tooth inside the bounding box, and searching a number of candidate matching teeth from a 3D digital library of teeth, and proposing a candidate matching tooth; (iii) overlaying the first image with a digital representation of the proposed candidate matching tooth from the digital library.

The invention discloses a single-tooth meshing stiffness calculation method based on spline tooth surface fretting friction. The single-tooth meshing stiffness calculation method comprises the steps that a calculation model of the fretting friction of the tooth surface of a spline is established; establishing rigidity characterization models of the internal spline single tooth and the external spline single tooth; establishing a contact stiffness model of the spline; and establishing a spline single-tooth meshing stiffness model of the spline according to a coupling relationship among the calculation model of the fretting friction, the stiffness representation model and the contact stiffness model. The invention establishes a single-tooth meshing stiffness calculation method considering spline tooth surface fretting friction. The spline meshing rigidity can be described more accurately, and the method has important significance on shafting dynamic performance evaluation and prediction.

The invention relates to a precision detection device for gear processing, which is suitable for detecting the dynamic performance and single tooth precision of a gear, and comprises a base, a rotating bracket, a fixed block, a motor, a reduction gearbox, a test gear, a to-be-tested gear, a main measuring rod, a plurality of measuring rods and the like. High-precision detection of gear dynamic balance, vibration parameters and the tooth outer end and the contour line of a single gear is achieved, the reduction gearbox reduces the rotating speed of the gear and strengthens torque control, and the gear thickness difference design is matched, so that the multiple measuring rods can slide along the tooth outer end of the gear, tooth surface deformation and the contact state are accurately detected, and the device is made of high-carbon low-alloy tool steel. The gear detection device has high strength and wear resistance, adapts to various gear specifications, can output detection data and analysis results in real time, is simple to operate, high in detection precision and high in applicability, and can be widely applied to the fields of gear manufacturing, quality detection and maintenance.

An orthodontic appliance may include an archwire and multiple orthodontic brackets. The archwire may fit within a human mouth and contain multiple male connectors. Each orthodontic bracket may have a configuration that facilitates attaching the orthodontic bracket to a single tooth. Each orthodontic bracket may allow one of the male connectors to be locked into the orthodontic bracket with a snapping action. The male connector may be unable to slide with respect to the orthodontic bracket after being locked in the orthodontic bracket. A manual unlocking action may allow the male connector to disengage from the orthodontic bracket.

The invention discloses an intraoral scanning data correction method based on dynamic feature weight adjustment. The method comprises the following steps: S1, acquiring initial intraoral scanning data acquired by intraoral scanning equipment; s2, acquiring full oral cavity three-dimensional model data generated by cone beam computed tomography equipment; s3, extracting three-dimensional model information of a single tooth; s4, performing three-dimensional registration on the three-dimensional model information of the single tooth and a corresponding tooth model in the CBCT data based on a dynamic feature weight adjustment algorithm; s5, generating a full oral cavity correction model; s6, using a physical model generated by warehouse scanning as a verification standard; and S7, outputting the corrected full oral cavity three-dimensional model. According to the method, the problems of precision and consistency in oral three-dimensional scanning data are solved, the precision of the corrected whole oral model is remarkably improved, and the method has high practicability and clinical application value.

The invention discloses a tooth instance segmentation method and device based on anatomic form priori, and belongs to the field of computer vision and artificial intelligence. According to the method, model training is carried out on a CBCT image, a real segmentation mask is processed into a three-classification segmentation mask with enamel as a boundary, the three-classification segmentation mask serves as a supervision signal, a network can directly output a prediction segmentation mask containing tooth boundary information in a reasoning stage, and a detection frame is generated accordingly. And after the detection frame is scaled according to the same proportionality coefficient and projected back to the original image, cutting each tooth to obtain a CBCT image of the single tooth. A loss function based on anatomical morphological prior is introduced into segmentation training of a single tooth CBCT image, and a network is constrained through a self-adaptively extracted morphological skeleton, so that a prediction segmentation mask is kept continuous at a root tip part, and the problem of tooth root segmentation fracture is effectively relieved. According to the method, accurate positioning and high-quality segmentation of the tooth instances are realized, so that the segmentation of the tooth instances in the full-mouth CBCT image is quicker and more accurate.

The invention relates to a mechanical evaluation system based on rotation and inclination of a bracket-free appliance, and belongs to the technical field of orthodontic equipment. The system comprises four core units: an integral dental arch constraint unit simulates oral temperature through a constant-temperature water bath assembly, adjusts model postures through a camera holder type adjustable dental arch base, and constructs a precise constraint environment; the clinical displacement driving unit is based on an anchorage center bearing lever structure, and positioning-driving-data synchronization is achieved through adjustable anchorage positioning, multi-direction servo driving and displacement closed-loop calibration. The single-tooth mechanical sensing unit collects dynamic mechanical data, and interference is removed through Kalman filtering; and the data processing unit corrects attenuation deviation by using multiple linear regression in combination with environmental parameters, generates a mechanical attenuation curve, calculates a time attenuation percentage, and outputs a mechanical evaluation report by comparing with a clinical suitable force application interval. The evaluation accuracy and clinical suitability of the method provide a scientific basis for the optimization of an orthodontic scheme.

The invention relates to a motor stator, a manufacturing method thereof and a motor. The motor stator comprises a stator core, a plurality of coil holders, a plurality of first profiled coils and a plurality of second profiled coils. The stator core comprises a plurality of single teeth which are sequentially spliced along the circumference to form a whole circle. Each single tooth is coated with a wire frame, and a wire winding groove is formed in each wire frame. A first profiled coil is wound in the winding groove in one of any two adjacent single teeth, and a second profiled coil is wound in the winding groove in the other single tooth; in the radial direction of the stator core, the first profiled coil is provided with a first convex part and a first concave part which are arranged in sequence, the second profiled coil is provided with a second concave part and a second convex part which are arranged in sequence, and the first convex part of the first profiled coil is arranged in the second concave part of the adjacent second profiled coil. And the second convex part of the second profiled coil is arranged in the first concave part of the adjacent first profiled coil. According to the motor stator, the slot fullness rate can be improved, and the miniaturization requirement of a joint motor is met.

The utility model relates to the technical field of daily hardware fittings, in particular to a single-tooth hinge. The single-tooth hinge comprises a first auxiliary rod, a second auxiliary rod, a supporting rod and a base. The supporting rod is rotationally connected with the first auxiliary rod and the second auxiliary rod. The second auxiliary rod is provided with a second rotating shaft, and the first auxiliary rod is provided with a first rotating shaft; a single-tooth structure is further arranged between the end of the first auxiliary rod and the base and comprises a single-tooth part arranged on the first auxiliary rod and a protruding part arranged on the base and clamped into the single-tooth part. Due to the fact that only one single-tooth part and one protruding part are arranged, compared with a structure with multiple tooth parts, the damage probability is greatly reduced, the use frequency is improved, long-term stable push-pull operation is ensured, and due to the fact that the single-tooth structure is relatively simple, maintenance and repair are relatively easy.

The invention relates to the technical field of gears, in particular to a five-section type spiral gear for hydraulic equipment, which comprises a gear, the single tooth profile of the gear sequentially comprises an arc AB, a transition curve BC, an involute CC ', a transition curve B' C 'and an arc A' B 'from the tooth top to the tooth root, and the slope of the transition curve BC is monotonically decreased; each of the transition curve BC and the transition curve B 'C' comprises one of a Bayes curve, a high-order spline interpolation curve and an elliptic curve. Through the arrangement of the arcs AB and the arcs A 'B', the oil trapping problem can be effectively solved, and no extra influence is caused on gear meshing; through the arrangement of a transition curve BC and a transition curve B 'C', the tooth shape design of the gear can be flexibly adjusted according to actual use requirements; the performance of low vibration and low noise is achieved; and meanwhile, the situation that hydraulic equipment collides with one another can be avoided, and the use efficiency of the gear is effectively improved.

The utility model discloses an assembling and welding mechanism for a concentrated winding iron core. The device comprises a base, a hollow rotating platform, a first base table and a second base table, the hollow rotating platform is fixed to the base, the first base table and the second base table are fixed to the hollow rotating platform, and the hollow rotating platform rotates by 180 degrees to drive the first base table and the second base table to be interchanged in position. The first base station and the second base station are each provided with a positioning rotating tool, a pneumatic clamping jaw disc and a jacking mechanism in a rotating mode, the positioning rotating tools are used for assembling the single-tooth iron core into the stator, the pneumatic clamping jaw discs are arranged in the positioning rotating tools, the pneumatic clamping jaw discs are used for internally supporting the positioning rotating tools, and the jacking mechanisms are used for jacking the stator out of the positioning rotating tools. According to the utility model, the first base station and the second base station realize stator assembling and welding double stations, the first base station and the second base station rotate to exchange positions, the requirements of avoiding a framework and a coil are met, the welding operation and the assembling operation are continuously circulated, and the production efficiency is improved.

Computer implemented method of generating a dental design, comprising: (a) capturing a facial image comprising a head of a patient and a smile; (b) displaying it as a first image; (c) capturing a 3D intraoral 5 scan; (d) aligning the 3D scan to the head; (e) determining bounding boxes in the 3D scan, each comprising a single tooth; (f) showing a view of the 3D scan and the bounding boxes as a second image; (g) showing the bounding boxes as overlay on the first image; (i) allowing the bounding boxes to be resized / repositioned; (ii) defining a limited set of parameters to characterize the tooth inside the bounding box, and searching a number of candidate matching teeth from a 3D digital library of teeth, 10 and proposing a candidate matching tooth; (iii) overlaying the first image with a digital representation of the proposed candidate matching tooth from the digital library.

The utility model relates to an elbow cable tie which comprises a locking head, a bending part and a tie body which are connected in sequence, an extending-in opening and a pulling-out opening are formed in the two ends of an inner cavity of the locking head respectively, tie teeth are arranged on the two opposite sides of the tie body, and locking teeth matched with the tie teeth are arranged in the inner cavity of the locking head. And the extending direction of the bent part is inclined to the extending direction of the belt body. When the elbow binding belt is used for binding articles, the belt teeth on the two sides of the belt body are meshed with the locking teeth, the purpose of retaining the belt body is achieved, stress on the two sides reduces stress on a single tooth, tooth breakage is avoided, tooth loosening caused by pulling of the belt body is avoided through meshing of the two sides, and binding is more stable. Besides, the bending part is arranged between the locking head and the band body, and the extending direction of the bending part is inclined to the extending direction of the band body, so that the bending part can be close to the outer surface of an object to reduce a gap between the elbow binding band and the object during binding, the object can be prevented from sliding from the fixing cavity to be separated, and binding is more stable.

The invention relates to a model refined description method and system based on image measurement, and the method comprises the steps: carrying out the classification of image data in response to the obtained image data; respectively establishing identification baselines by using the top surface image, the inner side surface image and the outer side surface image; sudden change areas on the top face recognition base line, the inner side face recognition base line and the outer side face recognition base line are determined and matched, and an abnormal position is determined; determining a segmentation line, and performing segmentation processing on the three-dimensional point cloud data by using the segmentation line to obtain a single tooth model; and calculating a vacant area of the single tooth model and filling the vacant area of the single tooth model by using the regenerated three-dimensional point cloud data. According to the model refined description method and system based on image measurement disclosed by the invention, the three-dimensional point cloud data is segmented by means of the image, and repeated data is fused by using a position comparison mode, so that an accurate tooth model is obtained.

Embodiments of the present invention provide a method, system, devices and software which provide customized, clinically relevant designs, e.g. treatment plans / solutions for at least single tooth replacement therapy in real-time as needed to enable immediate confirmation of the validity and execution of patient-specific treatment solutions.A Machine Learning algorithm is used in a method or system for computer implementation of automatic restoration design. The restoration design includes the design of restorative elements such as crowns and abutments. Software is provided for carrying out the methods when executed on a digital processor. Manufacturing of the restorative elements is also included.

The invention discloses an IOS image and CBCT image registration method based on particle swarm and single-tooth optimization, and belongs to the field of image data processing, and the method comprises the following steps: respectively obtaining tooth semantic segmentation results and point cloud data of an IOS image and a CBCT image through preprocessing and segmentation steps; introducing a particle swarm optimization algorithm, and performing iterative search and optimization on six-degree-of-freedom rigid transformation parameters between the IOS image data and the CBCT image data so as to complete global initial registration of the dental arch scale; and on the basis of a result after global registration, a registration object is divided into a plurality of local units based on a single tooth, and local iteration alignment is performed on each unit, so that tiny dislocation on the single tooth is eliminated, and the overall registration effect is optimized. According to the method, on the basis of processing cross-modal difference and realizing global registration, the registration precision of a single tooth level is further ensured through a local optimization mechanism, and reliable automatic registration support is provided for clinical scenes such as orthodontics and implantation.

The invention discloses a rotary speed reducer gear tooth root strength test device which comprises a test bed, a mounting mechanism, a rotating mechanism, a limiting mechanism, a strength test mechanism and an observation mechanism. A mounting mechanism is arranged in the center of the test bench to fix a to-be-tested gear and can adapt to replacement of gears of different specifications; the mounting mechanism is connected with a rotating mechanism under the test bench, and a rotating motor is provided with an encoder to realize accurate rotation angle switching of a gear; limiting mechanisms are arranged on the left and right sides of the mounting mechanism and can move in the radial direction to be engaged with the gears for limiting or separated for avoiding. Strength test mechanisms are arranged in front and back, can be adjusted in the radial direction, can be meshed with a single tooth to apply force, and can be fed back by a force sensor to switch postures by rotating an oil cylinder and an air cylinder; an observation mechanism on the strength test mechanism is used for detecting tooth root cracks by using an endoscope and marking the tooth root cracks through a spray head. The device does not need repeated positioning, can continuously detect each tooth root, improves the efficiency and precision, is adaptive to gears of various specifications, and meets the industrial detection requirements.

The invention relates to a wear-resistant and heat-resistant single-tooth roller grate plate as well as a preparation method and application thereof, and relates to the technical field of steel smelting. The wear-resistant and heat-resistant single-tooth roller grate plate comprises a grate plate main body, wherein the grate plate main body comprises a grate plate framework and an alloy protective layer poured on the grate plate framework; and the alloy protection layer comprises the following components in percentage by mass: 1.7%-1.9% of C, 0.8%-1.5% of Si, 1.5%-3.0% of Mn, 0.02%-0.35% of P, 0.02%-0.035% of S, 27%-29% of Cr, 1.5%-2.5% of Mo, 1.6%-2.5% of Ni, 0.3%-1.0% of W, 0.1%-0.2% of V, 0.2%-0.5% of Ti, 0.01%-0.02% of Re and the balance of Fe and inevitable impurities. The single-tooth roller grate plate provided by the invention has good wear resistance and heat resistance.

The invention provides a PTv3-based intelligent automatic tooth arrangement method and device, and the method comprises the steps: collecting three-dimensional tooth point cloud data after orthodontic treatment, carrying out the noise filtering, outlier removal and triangular meshing processing of the point cloud data, and separating a single tooth model through a deep learning segmentation network; carrying out principal component analysis and principal axis alignment on the segmented tooth model, calculating curvature characteristics in combination with normal covariance, and dynamically allocating voxel retention density by adopting a curvature-driven gradient voxel downsampling strategy; generating data pairs before and after simulation orthodontics, and constructing an orthodontics database in combination with displacement direction probability constraint and an adjacent tooth collision punishment mechanism; a PTv3-based double-branch network architecture is constructed as an intelligent automatic tooth arrangement network model, a multi-objective loss function fusing geometric errors, collision constraints and clinical prior is set, and the model is trained through weighted optimization; and inputting the preprocessed tooth point cloud into the trained model, outputting spatial transformation parameters and generating a final arrangement result.

The invention belongs to the technical field of tooth image segmentation, and particularly relates to a two-stage CBCT tooth segmentation method based on a multi-direction multi-scale feature fusion network, and the method comprises the following steps: obtaining an oral cavity CBCT data set, and carrying out the preprocessing; a multi-direction and multi-scale feature fusion module M2FF-Block is constructed; based on the M2FF-Block, respectively constructing a multi-direction multi-scale feature fusion network M2FF-UNet of the two stages; tooth recognition is carried out in a global perspective to obtain the position of the center of mass of each tooth; cutting the original CBCT image according to the centroid position to obtain tooth block data corresponding to each tooth, and performing refined segmentation on a single tooth block by combining a center focusing mechanism; and constructing a post-processing algorithm suitable for a tooth segmentation problem, and correcting a segmentation result to obtain a final segmentation result. According to the method, the inherent multi-direction and multi-scale characteristics of the teeth can be effectively utilized, and the balance between the context information capture and the calculation efficiency is also realized, so that the positioning and segmentation of the teeth are more accurate.