An oral surgery positioning navigation method, system and storage medium

Abstract

The application provides an oral surgery positioning navigation method, system and storage medium, which comprises the following steps: obtaining a unit vector of a rotating shaft of a drill bit and a three-dimensional coordinate value of a drill tip in an optical three-dimensional coordinate system through calibration of an implant handset; scanning a patient CT three-dimensional model and segmenting a tooth CT model and an alveolar bone CT model; generating a tooth three-dimensional point cloud according to a real-time pattern of speckle structured light on the tooth of the patient and obtaining a matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system; and performing real-time navigation on the implant handset according to real-time point position deviation and real-time angle deviation of the drill bit. The matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system is calculated through tooth CT feature points and tooth point cloud feature points, and auxiliary navigation is performed through comparison of a target position of the implant and a real-time pose of the drill tip, a directional vector of an implant path and a unit vector of the rotating shaft of the drill bit, so that the method has the advantages of convenient operation, high positioning accuracy and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical equipment control, and relates to an oral surgery positioning and navigation method, system and storage medium. BACKGROUND

[0002] In the process of implementing oral surgery, drilling, grinding and other operations are performed on the patient's oral cavity by oral treatment equipment, which needs to be based on the relative positional relationship between the oral treatment equipment and the patient's oral cavity. In the process of implementing dental implant surgery, the optical positioning instrument needs to capture the patient reference plate fixed in the patient's oral cavity and the mobile phone reference plate fixed on the implant mobile phone in real time, and distinguish the movement of the patient and the movement of the implant mobile phone for real-time positioning.

[0003] In the process of configuring the surgical environment, first, the patient reference plate needs to be fixed in the patient's oral cavity by the clamping mechanism, and the patient must keep his mouth open for a long time to cooperate with the treatment, which will cause great discomfort to the patient; second, the clamping mechanism is fixed by clamping the patient's teeth, and when the position of the clamping mechanism cannot be fixed, the patient reference plate cannot be kept in a relative fixed state with the patient's oral cavity, so the patient's oral cavity cannot be accurately positioned by the patient reference plate. Third, the operator needs to observe the intraoral situation closely during the operation, which will inevitably block the light propagation between the optical positioning instrument and the patient reference plate, resulting in discontinuous operation during the operation. In general, the technical solution of positioning by the patient reference plate in oral surgery has the problems of complicated operation, poor patient experience, insufficient operation continuity, and easy displacement of the reference plate. Therefore, it is of great clinical value to develop a scheme for surgical positioning and navigation without a reference plate and directly through the patient's natural teeth. SUMMARY

[0004] The technical problem to be solved by the present application is to provide an oral surgery positioning and navigation method, system and storage medium, which can represent the real-time pose of the patient's oral cavity through the feature points on the patient's natural teeth, has the advantages of convenient operation, high positioning accuracy, and can reduce the discomfort of the patient's oral cavity.

[0005] Ensure navigation accuracy and treatment effect.

[0006] The technical solution adopted by the present application to solve the technical problem is as follows:

[0007] An oral surgery positioning and navigation method, comprising:

[0008] S1. Control the implant mobile phone to install the drill bit mounting sleeve on the calibration rod on the calibration plate, control the binocular positioning and navigation instrument to collect real-time images of the calibration feature points on the calibration plate, and calculate the pose of the calibration plate in the optical three-dimensional coordinate system according to the three-dimensional data model of the calibration plate and the optical three-dimensional coordinate system of the binocular positioning and navigation instrument ;

[0009] S2. Obtaining the three-dimensional coordinates of the root point of the calibration rod in the optical three-dimensional coordinate system according to the pose of the calibration plate in the optical three-dimensional coordinate system and the three-dimensional coordinates of the top point of the calibration rod in the optical three-dimensional coordinate system , according to and , the unit vector of the rotation axis of the drill bit in the optical three-dimensional coordinate system is calculated , wherein ;

[0010] S3. Obtaining the three-dimensional coordinate values of the end of the rotation axis of the drill bit in the optical three-dimensional coordinate system and the length of the drill bit , based on the three-dimensional coordinate values of the end of the rotation axis in the optical three-dimensional coordinate system and the length of the drill bit , combined with the unit vector of the rotation axis of the drill bit in the optical three-dimensional coordinate system , the three-dimensional coordinate values of the tip of the drill bit in the optical three-dimensional coordinate system are calculated , wherein , ;

[0011] S4. Controlling the CT scanning device to scan the patient's oral cavity to obtain a CT three-dimensional model of the patient's oral cavity

[0012] S5. Segmenting the CT three-dimensional model of the patient's oral cavity to obtain a tooth CT model and a tooth socket bone CT model

[0013] S6. Controlling the first camera and the second camera in the binocular positioning navigator to cooperate with the respective speckle emitters to emit speckle structured light, capturing real-time patterns formed by the speckle structured light on the patient's teeth, and generating a tooth three-dimensional point cloud according to the real-time patterns of the speckle structured light on the patient's teeth

[0014] S7. Extracting tooth CT feature points of the tooth CT model and tooth point cloud feature points of the tooth three-dimensional point cloud, registering the tooth CT model and the tooth three-dimensional point cloud according to the tooth CT feature points and the tooth point cloud feature points, and obtaining the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system ;

[0015] S8. Implanting an implant target pose in the CT three-dimensional model to obtain a target position of the implant in the CT three-dimensional coordinate system and a direction vector of the implant path ;

[0016] ​S9. The three-dimensional coordinate value of the drill bit tip in the optical three-dimensional coordinate system according to the three-dimensional coordinate value of the drill bit tip in the optical three-dimensional coordinate system , the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system is performed to obtain the three-dimensional coordinate value of the drill bit tip in the CT three-dimensional coordinate system , wherein ;

[0017] S10. The unit vector of the rotation axis of the drill bit in the optical three-dimensional coordinate system according to the unit vector of the rotation axis of the drill bit in the optical three-dimensional coordinate system is calculated to obtain the unit vector of the rotation axis of the drill bit in the CT three-dimensional coordinate system ;

[0018] S11. Comparative analysis of the target position of the implant in the CT three-dimensional coordinate system and the three-dimensional coordinate value of the drill bit tip in the CT three-dimensional coordinate system , comparative analysis of the direction vector of the implant path in the CT three-dimensional coordinate system and the unit vector of the drill bit rotation axis in the CT three-dimensional coordinate system , according to the comparative analysis result, the real-time point deviation and the real-time angle deviation of the drill bit are calculated

[0019] S12. Output the real-time point deviation and the real-time angle deviation of the drill bit, and real-time navigation of the implant handpiece according to the real-time point deviation and the real-time angle deviation of the drill bit.

[0020] Compared with the prior art, the beneficial effects of the technical scheme are: the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system is calculated through the tooth CT feature points and the tooth point cloud feature points, and the auxiliary navigation is performed by comparing the target position of the implant and the real-time pose of the drill bit tip, the direction vector of the implant path and the unit vector of the drill bit rotation axis, which has the advantages of convenient operation, high positioning accuracy, etc.

[0021] Further, the step S6 specifically comprises:

[0022] S601. Calibrate the binocular positioning navigator based on the camera parameters of the first camera and the second camera to obtain the equivalent focal length f and the baseline length B of the binocular positioning navigator, and obtain the rotation matrix and the translation vector of the second camera relative to the first camera

[0023] S602. Calibrate the speckle emitter to obtain the rotation matrix and the translation vector of the speckle emitter relative to the first camera

[0024] S603. Control the first camera to capture a first original image I1, control the second camera to capture a second original image I2, and based on the rotation matrix and translation vector of the second camera relative to the first camera and translation vector , the rotation matrix and translation vector of the speckle emitter relative to the first camera and translation vector , the polar correction processing is performed on I1 and I2 to obtain a first corrected image and a second corrected image after polar correction;

[0025] S604. Select a first matching point center and a first matching range centered on the first matching point center in the first corrected image, map the first matching point center and the first matching range in the first corrected image to obtain a second matching point center and a second matching range in the second corrected image, and define a search range in the second corrected image according to the second matching point center and the second matching range;

[0026] S605. Perform zero-mean normalized cross-correlation operation on the second matching range in the second corrected image according to the first matching range in the first corrected image to determine the best matching point P and the corresponding parallax d of the best matching point P of each pixel point on the first corrected image; the zero-mean normalized cross-correlation operation process is , when the value is maximum, the pixel point on the second corrected image is the best matching point P; wherein, is the pixel value of the pixel point on the first corrected image, is the average value of the pixel value of the pixel point in the first matching range of the first corrected image, is the pixel value of the pixel point on the second corrected image, is the average value of the pixel value of the pixel point in the search range of the second corrected image; represents the coordinates of the pixel point in the first corrected image or the second corrected image;

[0027] S606. Perform three-dimensional reconstruction according to the best matching point and the corresponding parallax d of the best matching point of each pixel point on the first corrected image to calculate the three-dimensional data of the pixel point in the three-dimensional point cloud model, wherein the coordinate value of the pixel point in the Z-axis of the three-dimensional point cloud model is , the coordinate value of the pixel point in the X-axis of the three-dimensional point cloud model is , and the coordinate value of the pixel point in the Y-axis of the three-dimensional point cloud model is , f is the equivalent focal length of the first camera and the second camera, and B is the baseline length of the first camera and the second camera;

[0028] S607. Generate a three-dimensional point cloud of teeth according to the coordinate values of the pixel point in the X-axis, Y-axis and Z-axis of the three-dimensional point cloud model.

[0029] The beneficial effects of the above scheme are: through the correction processing of the original image generated by the speckle structure light and then the zero-mean normalized cross-correlation operation, the three-dimensional data of the pixel points in the three-dimensional point cloud model are calculated and then the tooth three-dimensional point cloud is generated, which prepares for the subsequent registration between the tooth CT model and the tooth three-dimensional point cloud through the tooth three-dimensional point cloud.

[0030] Further, the step S7 specifically includes the following steps:

[0031] S701. Extract tooth CT feature points from the tooth CT model based on the FAST algorithm to obtain tooth CT feature points , extract tooth point cloud feature points from the tooth three-dimensional point cloud based on the FAST algorithm to obtain tooth point cloud feature points ; wherein, , is the tooth CT feature point, , is the tooth point cloud feature point;

[0032] S702. Obtain the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system and the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system;

[0033] S703. Perform Gaussian smoothing operation based on the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system or the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system to obtain a scale space function, and the operation process is:

[0034] , wherein, is the scale space function, G is a three-dimensional Gaussian kernel function, is the Gaussian kernel standard deviation, is the three-dimensional coordinate value of the tooth point cloud feature point in the optical three-dimensional coordinate system or the three-dimensional coordinate value of the tooth CT feature point in the CT three-dimensional coordinate system, is the scale multiplication coefficient;

[0035] S704. Calculate the gradient , the module length , the direction angle and the Z-axis angle of the tooth CT feature points or the tooth point cloud feature points in the neighborhood; wherein,

[0036] , , , , in the formula, T is the matrix transpose;

[0037] S705. characterizing the feature descriptor of the tooth CT feature point by gradient of points in the neighborhood of the tooth CT feature point , module length , direction angle and Z-axis angle , module length , direction angle and Z-axis angle ;

[0038] S706. confirming the pairing by judging whether the nearest neighbor distance ratio between the feature descriptor of the tooth CT feature point and the feature descriptor of the tooth point cloud feature point is less than the nearest neighbor distance threshold value; when the nearest neighbor distance ratio is less than the nearest neighbor distance threshold value, confirming the pairing, and when the nearest neighbor distance ratio is greater than or equal to the nearest neighbor distance threshold value, deleting the pairing, to obtain an initial pairing group ;

[0039] S707. optimizing the initial pairing group by the iterative closest point algorithm to obtain an accurate pairing group ;

[0040] S708. according to the accurate pairing group , combining the three-dimensional coordinate value of the corresponding tooth point cloud feature point in the optical three-dimensional coordinate system and the three-dimensional coordinate value of the corresponding tooth CT feature point in the CT three-dimensional coordinate system, calculating to obtain the matrix conversion relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system .

[0041] The beneficial effects of the above scheme are: according to the tooth CT feature point and the tooth point cloud feature point, the tooth CT model and the tooth three-dimensional point cloud are registered, the coarse registration is performed through the Gaussian smoothing operation, and then the coarse registration is performed through the iterative closest point algorithm, so as to obtain the accurate pairing group, and then the matrix conversion relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system is obtained based on the accurate pairing group.

[0042] Further, in the step S10, the unit vector of the rotating shaft in the CT three-dimensional coordinate system is calculated according to the unit vector of the rotating shaft in the optical three-dimensional coordinate system in the dental implant handheld device . Specifically, .

[0043] The beneficial effects of the above scheme are: the real-time pose of the rotating shaft in the CT three-dimensional coordinate system is obtained.

[0044] ​​​​​Furthermore, step S11 specifically includes the following steps:

[0045] S1101. Comparative analysis of the target position of the implant in the CT three-dimensional coordinate system The three-dimensional coordinates of the drill tip in the CT three-dimensional coordinate system The real-time positional deviation between the drill tip and the target position in the CT three-dimensional coordinate system is obtained. ;

[0046] The beneficial effects of adopting the above scheme are: to parameterize the real-time spatial difference between the drill bit tip and the target position in the CT three-dimensional coordinate system, and to provide data reference for real-time navigation.

[0047] The technical solution adopted by this invention to solve the technical problem is as follows:

[0048] An oral surgery positioning and navigation system, comprising:

[0049] The image acquisition module controls the planting mobile phone to attach its drill bit mounting sleeve to the calibration rod on the calibration plate, and controls the binocular positioning and navigation device to acquire real-time images of the calibration feature points on the calibration plate. Based on the three-dimensional data model of the calibration plate and the optical three-dimensional coordinate system of the binocular positioning and navigation device, the module calculates the pose of the calibration plate in the optical three-dimensional coordinate system. ;

[0050] The rotation axis calibration module is used to determine the pose of the calibration plate in the optical three-dimensional coordinate system. Obtain the three-dimensional coordinates of the root point of the calibration rod in the optical three-dimensional coordinate system. The three-dimensional coordinates of the top point of the calibration rod in the optical three-dimensional coordinate system ,according to and The unit vector of the drill bit's rotation axis in the optical three-dimensional coordinate system was calculated. ,in, ;

[0051] The unit vector calibration module is used to obtain the three-dimensional coordinates of the end of the drill bit's rotation axis in the optical three-dimensional coordinate system during implantation. and drill bit length Based on the three-dimensional coordinates of the end of the rotation axis in the optical three-dimensional coordinate system and drill bit length Combined with the unit vector of the drill bit's rotation axis in the optical three-dimensional coordinate system The three-dimensional coordinates of the drill tip in the optical three-dimensional coordinate system were calculated. ,in, , ;

[0052] a CT scanning module configured to control a CT scanning device to scan a patient's oral cavity to obtain a CT three-dimensional model of the patient's oral cavity;

[0053] a model segmentation module configured to segment the CT three-dimensional model of the patient's oral cavity to obtain a tooth CT model and an alveolar bone CT model;

[0054] a three-dimensional point cloud generation module configured to control a first camera and a second camera in a binocular positioning navigator to cooperate with respective speckle emitters to emit speckle structured light, capture a real-time pattern formed by the speckle structured light on a patient's tooth, and generate a tooth three-dimensional point cloud according to the real-time pattern of the speckle structured light on the patient's tooth;

[0055] a transformation relationship calculation module configured to extract tooth CT feature points of the tooth CT model and tooth point cloud feature points of the tooth three-dimensional point cloud, register the tooth CT model and the tooth three-dimensional point cloud according to the tooth CT feature points and the tooth point cloud feature points, and obtain a matrix transformation relationship between a CT three-dimensional coordinate system and an optical three-dimensional coordinate system ;

[0056] a target pose acquisition module configured to implant an implant target pose in the CT three-dimensional model to obtain a target position of the implant and a direction vector of an implant path in the CT three-dimensional coordinate system ; ;

[0057] a tip pose acquisition module configured to perform coordinate conversion according to three-dimensional coordinate values of a drill bit tip in the optical three-dimensional coordinate system , in combination with the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system to obtain three-dimensional coordinate values of the drill bit tip in the CT three-dimensional coordinate system , wherein ;

[0058] a rotation axis pose acquisition module configured to calculate a unit vector of a rotation axis of a drill bit in the CT three-dimensional coordinate system according to a unit vector of the rotation axis of the drill bit in the optical three-dimensional coordinate system ;

[0059] a comparative analysis module configured to compare and analyze the target position of the implant in the CT three-dimensional coordinate system and the three-dimensional coordinate values of the drill bit tip in the CT three-dimensional coordinate system , compare and analyze the direction vector of the implant path in the CT three-dimensional coordinate system and the unit vector of the rotation axis of the drill bit in the CT three-dimensional coordinate system , and calculate real-time point deviation and real-time angle deviation of the drill bit according to a result of the comparative analysis;

[0060] The real-time navigation module outputs the real-time positional and angular deviations of the drill bit, and provides real-time navigation for the planting mobile phone based on these deviations.

[0061] Furthermore, the 3D point cloud generation module specifically includes:

[0062] The camera calibration unit is used to calibrate the binocular positioning and navigation device based on the camera parameters of the first and second cameras, to obtain the equivalent focal length f and baseline length B of the binocular positioning and navigation device, and to obtain the rotation matrix of the second camera relative to the first camera. Translation vector ;

[0063] The emitter calibration unit is used to calibrate the speckle emitter and obtain the rotation matrix of the speckle emitter relative to the first camera. Translation vector ;

[0064] The epipolar correction unit is used to control the first camera to acquire a first raw image I1 and to control the second camera to acquire a second raw image I2, based on the rotation matrix of the second camera relative to the first camera. Translation vector The rotation matrix of the speckle emitter relative to the first camera Translation vector Epipolar correction is performed on I1 and I2 to obtain the first and second corrected images after epipolar correction.

[0065] The matching mapping unit is used to select the center of the first matching point and the first matching range with the center of the first matching point as the center point in the first corrected image, map the center of the first matching point and the first matching range in the first corrected image to the second corrected image to obtain the center of the second matching point and the second matching range in the second corrected image, and define the search range in the second corrected image according to the center of the second matching point and the second matching range.

[0066] The zero-mean normalized cross-correlation unit is used to perform zero-mean normalized cross-correlation on a second matching range in a second corrected image based on a first matching range in the first corrected image, to determine the optimal matching point p and the disparity d corresponding to the optimal matching point for each pixel in the first corrected image in the second corrected image; the zero-mean normalized cross-correlation process is as follows: ,when When the value is at its maximum, the corresponding pixel in the second corrected image is the optimal matching point P; where... The pixel value of the pixel in the first corrected image. an average value of pixel values of the pixel points on the first matching range in the first corrected image, a pixel value of the pixel point on the second corrected image, an average value of pixel values of the pixel points on the search range in the second corrected image; coordinates of the representative pixel point in the first corrected image or the second corrected image;

[0067] a pixel point analysis unit configured to perform three-dimensional reconstruction according to the best matching point corresponding to each pixel point on the first corrected image and the disparity d corresponding to the best matching point, and calculate three-dimensional data of the pixel point in a three-dimensional point cloud model, wherein a coordinate value of the pixel point on a Z axis in the three-dimensional point cloud model is , a coordinate value of the pixel point on an X axis in the three-dimensional point cloud model is , and a coordinate value of the pixel point on a Y axis in the three-dimensional point cloud model is , f is an equivalent focal length of the first camera and the second camera, and B is a baseline length of the first camera and the second camera;

[0068] a point cloud model generation unit configured to generate a tooth three-dimensional point cloud according to the coordinate values of the pixel point on the X axis, the Y axis and the Z axis in the three-dimensional point cloud model.

[0069] Further, the transformation relationship calculation module specifically includes:

[0070] a feature point extraction unit configured to extract tooth CT feature points from a tooth CT model based on a FAST algorithm to obtain tooth CT feature points , and extract tooth point cloud feature points from a tooth three-dimensional point cloud based on the FAST algorithm to obtain tooth point cloud feature points ; wherein, , the tooth CT feature points are , the tooth point cloud feature points are

[0071] a three-dimensional coordinate acquisition unit configured to acquire three-dimensional coordinate values of the tooth point cloud feature points in an optical three-dimensional coordinate system and three-dimensional coordinate values of the tooth CT feature points in a CT three-dimensional coordinate system;

[0072] a Gaussian smoothing operation unit configured to perform Gaussian smoothing operation based on the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system or the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system to obtain a scale space function, and the operation process is:

[0073] wherein, the scale space function is G is a three-dimensional Gaussian kernel function, a three-dimensional coordinate value of the tooth point cloud feature point in an optical three-dimensional coordinate system or a three-dimensional coordinate value of the tooth CT feature point in a CT three-dimensional coordinate system, a scale multiplication coefficient;

[0074] a feature point neighborhood parameter calculation unit configured to calculate a gradient , a module length , a direction angle and a Z-axis included angle of a point in a neighborhood of the tooth CT feature point or the tooth point cloud feature point; wherein,

[0075] , , , , in the formula, T is a matrix transpose;

[0076] a feature descriptor calculation unit configured to represent a feature descriptor of the tooth CT feature point by the gradient , the module length , the direction angle and the Z-axis included angle of the point in the neighborhood of the tooth CT feature point, and represent a feature descriptor of the tooth point cloud feature point by the gradient , the module length , the direction angle and the Z-axis included angle of the point in the neighborhood of the tooth point cloud feature point; and ;

[0077] a pair confirmation unit configured to perform pair confirmation by judging whether a nearest neighbor distance ratio between the feature descriptor of the tooth CT feature point and the feature descriptor of the tooth point cloud feature point is less than a nearest neighbor distance threshold value; when the nearest neighbor distance ratio is less than the nearest neighbor distance threshold value, the pair is confirmed, and when the nearest neighbor distance ratio is greater than or equal to the nearest neighbor distance threshold value, the pair is deleted, to obtain an initial pair group ;

[0078] an iterative optimization unit configured to optimize the initial pair group by an iterative nearest point algorithm to obtain an accurate pair group ;

[0079] a conversion relationship calculation unit configured to calculate a matrix conversion relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system according to the accurate pair group , in combination with the three-dimensional coordinate value of the corresponding tooth point cloud feature point in the optical three-dimensional coordinate system and the three-dimensional coordinate value of the corresponding tooth CT feature point in the CT three-dimensional coordinate system . ​​​

[0080] Further, in the rotating shaft posture acquisition module, according to a unit vector of the rotating shaft of the drill bit in the optical three-dimensional coordinate system in the planting mobile phone The unit vector of the rotating shaft in the CT three-dimensional coordinate system is calculated Specifically, ;

[0081] The contrast analysis module specifically includes:

[0082] A point deviation calculation unit is configured to contrast and analyze the three-dimensional coordinate values of the target position of the implant and the tip of the drill bit in the CT three-dimensional coordinate system , to obtain the real-time point deviation of the tip of the drill bit and the target position in the CT three-dimensional coordinate system ;

[0083] An angle deviation calculation unit is configured to contrast and analyze the direction vector of the implant path and the unit vector of the rotating shaft of the drill bit in the CT three-dimensional coordinate system , to obtain the real-time angle deviation of the tip of the drill bit and the target position in the CT three-dimensional coordinate system , wherein, is the vector dot product.

[0084] Correspondingly, a storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the oral surgery positioning and navigation method as described above. BRIEF DESCRIPTION OF DRAWINGS

[0085] Figure 1 is a flowchart of the oral surgery positioning and navigation method of the present application.

[0086] Figure 2 is a schematic diagram of the oral surgery positioning and navigation system of the present application.

[0087] In the figure, the components represented by each number are listed as follows:

[0088] Image acquisition module 1, rotating shaft calibration module 2, unit vector calibration module 3, CT scanning module 4, model segmentation module 5, three-dimensional point cloud generation module 6, transformation relationship calculation module 7, target posture acquisition module 8, tip posture acquisition module 9, rotating shaft posture acquisition module 10, contrast analysis module 11, real-time navigation module 12. DETAILED DESCRIPTION

[0089] ​​In order to make the objects, technical solutions and advantages of the present application clearer, more explicit, the following further describes the present application in detail with reference to the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and should not be used to limit the present application.

[0090] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or component referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first" and "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0091] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connected" should be understood broadly, for example, it can be fixedly connected, or detachably connected, or integrally connected; it can be mechanically connected, or electrically connected; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the communication between two components. When a component is referred to as "fixed to" or "disposed on" another element, it can be directly on another component or there can be a middle component. When a component is considered "connected" to another element, it can be directly connected to another element or there can be a middle element. For those skilled in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0092] In the process of performing oral surgery, the patient's oral cavity is drilled, ground and other operations by the oral treatment equipment, which needs to be performed according to the relative positional relationship between the oral treatment equipment and the patient's oral cavity. In the process of implanting tooth surgery, the optical positioning instrument needs to capture the patient reference plate fixed in the patient's oral cavity and the mobile phone reference plate fixed on the implant mobile phone in real time, and distinguish the movement of the patient and the movement of the implant mobile phone in real time.

[0093] In the process of configuring the surgical environment, first, the patient reference plate needs to be fixed in the patient's oral cavity through the clamping mechanism, and the patient must keep his mouth open for a long time to cooperate with the treatment, which will bring great discomfort to the patient; second, the clamping mechanism is fixed by clamping the patient's teeth, and when the position of the clamping mechanism cannot be kept fixed, the patient reference plate and the patient's oral cavity cannot be kept in a relative fixed state, so the patient's oral cavity cannot be accurately positioned through the patient reference plate. Third, the operator needs to observe the intraoral situation closely during the operation, which will inevitably block the light propagation between the optical positioning instrument and the patient reference plate, resulting in intermittent operation during the operation. In general, the technical scheme of positioning by means of the patient reference plate in oral surgery has the problems of complicated operation, poor patient experience, insufficient operation continuity, and easy displacement of the reference plate.

[0094] The industry urgently needs to propose a new scheme, and a scheme of directly positioning and navigating the operation through the patient's natural teeth without a reference plate has important clinical value.

[0095] In order to solve the above problems, the present application provides an oral surgery positioning and navigation method, system and storage medium, which are based on an oral surgery positioning and navigation device.

[0096] The oral surgery positioning and navigation device comprises a binocular positioning and navigation instrument, a CT scanning device, an implant mobile phone and a calibration plate. The binocular positioning and navigation instrument comprises a first camera and a second camera, the first camera and the second camera are fixedly arranged on the implant mobile phone, each of the first camera and the second camera is provided with a speckle emitter, and the calibration plate is provided with a calibration rod and a calibration feature point.

[0097] When positioning and navigating based on the oral surgery positioning and navigation device, the binocular positioning and navigation instrument is used to acquire the real-time pose of the implant mobile phone and the calibration plate, and the CT scanning device is used to scan to obtain a CT three-dimensional model of the patient's oral cavity. The real-time pose of the implant mobile phone in the optical three-dimensional coordinate system of the binocular positioning and navigation instrument is obtained through calibration, a matrix conversion relationship is established between the CT three-dimensional coordinate system in the CT three-dimensional model and the optical three-dimensional coordinate system of the binocular positioning and navigation instrument, the implant target attitude is implanted in the CT three-dimensional model, the comparison result is obtained by comparing the real-time pose of the drill bit of the implant mobile phone with the implant target attitude, and the real-time navigation is realized through the comparison result.

[0098] As shown in Figure 1 In order to solve the above problems, the present application provides an oral surgery positioning and navigation method, which specifically comprises the following steps:

[0099] S1. The control planting mobile phone installs the drill mounting sleeve on the calibration rod on the calibration plate, controls the binocular positioning navigator to collect the real-time image of the calibration feature point on the calibration plate, and calculates the pose of the calibration plate in the optical three-dimensional coordinate system according to the three-dimensional data model of the calibration plate and the optical three-dimensional coordinate system of the binocular positioning navigator In step S1, the relative position relationship of different structures on the calibration plate can be known according to the three-dimensional data model of the calibration plate. After the control planting mobile phone installs the drill mounting sleeve on the calibration rod on the calibration plate, the drill mounting sleeve sleeve and the calibration rod are considered to coincide in space. At this time, the control binocular positioning navigator collects the real-time image of the calibration feature point on the calibration plate, and the pose of the calibration feature point on the calibration plate in the optical three-dimensional coordinate system can be known. Since the three-dimensional data model of the calibration plate, the pose of the calibration plate in the optical three-dimensional coordinate system can be calculated by taking the three-dimensional data model of the calibration plate as a medium.

[0100] S2. According to the pose of the calibration plate in the optical three-dimensional coordinate system , the three-dimensional coordinates of the root point of the calibration rod in the optical three-dimensional coordinate system are obtained , and the three-dimensional coordinates of the top point of the calibration rod in the optical three-dimensional coordinate system are obtained , the unit vector of the rotation axis of the drill in the optical three-dimensional coordinate system is calculated according to and , wherein . According to step S1, the pose of the calibration plate in the optical three-dimensional coordinate system is known . Since the three-dimensional data model of the calibration plate is known, the three-dimensional coordinates of the root point and the top point of the calibration rod in the three-dimensional data model can be obtained according to the three-dimensional data model of the calibration plate. Combined with the pose of the calibration plate in the optical three-dimensional coordinate system , the three-dimensional coordinates of the root point of the calibration rod in the optical three-dimensional coordinate system are obtained , and the three-dimensional coordinates of the top point of the calibration rod in the optical three-dimensional coordinate system are obtained ; since the drill mounting sleeve is sleeved on the calibration rod on the calibration plate, the drill mounting sleeve sleeve and the calibration rod are considered to coincide in space. According to and , the unit vector of the rotation axis of the drill in the optical three-dimensional coordinate system is calculated .

[0101] S3. The three-dimensional coordinate values of the end of the rotation axis of the drill in the optical three-dimensional coordinate system are obtained , and the length of the drill is obtained , based on the three-dimensional coordinate values of the end of the rotation axis in the optical three-dimensional coordinate system and the length of the drill ​, and a unit vector of the rotation axis of the drill bit in the optical three-dimensional coordinate system , and a three-dimensional coordinate value of the drill bit tip in the optical three-dimensional coordinate system is calculated , wherein , . Based on the premise that the drill bit mounting sleeve is considered to be coincident with the calibration rod in space after the drill bit mounting sleeve is sleeved on the calibration rod on the calibration plate, the three-dimensional coordinate of the root point of the calibration rod in the optical three-dimensional coordinate system can be directly obtained in step S3. , a three-dimensional coordinate value of the end of the rotation axis in the optical three-dimensional coordinate system is obtained , and a three-dimensional coordinate value of the drill bit tip in the optical three-dimensional coordinate system is further obtained by converting the three-dimensional coordinate value of the end of the rotation axis in the optical three-dimensional coordinate system in combination with the length of the drill bit . .

[0102] S4. Control the CT scanning device to scan the oral cavity of the patient to obtain a CT three-dimensional model of the oral cavity of the patient. In step S4, the CT three-dimensional model of the oral cavity of the patient can be directly obtained by scanning the oral cavity of the patient by using the density difference between the teeth, the alveolar bone and other tissues in the oral cavity.

[0103] S5. Segment the CT three-dimensional model of the oral cavity of the patient to obtain a tooth CT model and an alveolar bone CT model. In step S5, segmentation refers to distinguishing the teeth and the alveolar bone in the CT three-dimensional model by setting a density threshold by using the density difference between the teeth and the alveolar bone, but only distinguishes the teeth and the alveolar bone, and does not change the relative positional relationship between the tooth CT model and the alveolar bone CT model.

[0104] S6. Control the first camera and the second camera in the binocular positioning navigator to cooperate with the respective speckle emitters to emit speckle structured light, capture a real-time pattern formed by the speckle structured light on the teeth of the patient, and generate a tooth three-dimensional point cloud according to the real-time pattern of the speckle structured light on the teeth of the patient. In step S6, the first camera and the second camera emit a pure and coherent infrared laser beam by using a laser diode, adopt a diffractive optical element as a speckle emitter, and vertically irradiate the infrared laser to the speckle emitter. When the speckle emitter passes through the speckle emitter, diffraction occurs, the infrared laser on the speckle emitter becomes countless diffraction light waves, and the diffraction light waves interfere with each other in the propagation process. At a specific projection distance, some points in the light field become bright (constructive interference) because of the superposition of wave crests, and some points become dark (destructive interference) because of the superposition of wave crests and troughs. Ultimately, thousands of tiny light spots with high randomness are randomly distributed and have light and dark interlaced on the surface of the object. This pattern is the "speckle structured light". Based on the speckle structured light, the three-dimensional depth information of the surface of the object can be accurately calculated by analyzing the offset of each small light spot relative to its position in the reference pattern, so as to construct a complete D point cloud.

[0105] S7. Extract tooth CT feature points of the tooth CT model and tooth point cloud feature points of the tooth three-dimensional point cloud, register the tooth CT model and the tooth three-dimensional point cloud according to the tooth CT feature points and the tooth point cloud feature points, and obtain the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system In step S7, the tooth CT feature points are points with high distinguishability on the tooth CT model, and the tooth point cloud feature points are points with high distinguishability on the tooth three-dimensional point cloud, which can be cusps, tooth roots, or points with special shapes between two teeth. For the same point with high distinguishability on the tooth, the three-dimensional coordinate value of the point in the CT three-dimensional coordinate system can be obtained according to the tooth CT feature point, and the three-dimensional coordinate value of the point in the optical three-dimensional coordinate system can be obtained according to the tooth point cloud feature point. After registering the tooth CT feature points and the tooth point cloud feature points, the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system can be obtained .

[0106] S8. Implant the implant target posture in the CT three-dimensional model to obtain the target position of the implant in the CT three-dimensional coordinate system and the direction vector of the implant path In step S8, the implant conditions are analyzed according to the CT three-dimensional model, and the best implantation scheme is designed in advance, so that the target posture of the implant can be known, and the target position of the implant in the CT three-dimensional coordinate system and the direction vector of the implant path .

[0107] S9. According to the three-dimensional coordinate value of the drill bit tip in the optical three-dimensional coordinate system , combined with the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system , the three-dimensional coordinate value of the drill bit tip in the CT three-dimensional coordinate system is obtained , wherein, .

[0108] S10. According to the unit vector of the rotation axis of the drill bit in the optical three-dimensional coordinate system , the unit vector of the rotation axis of the drill bit in the CT three-dimensional coordinate system is calculated After completing steps S3 and S4, the calibration of the implant mobile phone is completed, and the real-time three-dimensional coordinate values of the drill bit tip and the rotation axis of the implant mobile phone in the optical three-dimensional coordinate system are obtained. Combined with the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system , the real-time three-dimensional coordinate values of the drill tip and the rotation axis in the CT three-dimensional coordinate system can be obtained through conversion, thereby completing steps S9 and S10.

[0109] S11. Comparatively analyze the target position of the implant and the three-dimensional coordinate values of the drill tip in the CT three-dimensional coordinate system and the three-dimensional coordinate values of the drill tip in the CT three-dimensional coordinate system , comparatively analyze the direction vector of the implant path and the unit vector of the drill rotation axis in the CT three-dimensional coordinate system , and the unit vector of the drill rotation axis in the CT three-dimensional coordinate system According to the comparative analysis results, the real-time point deviation and the real-time angle deviation of the drill are calculated. When navigating the implant mobile phone, the most critical thing is to control the point and angle of the drill in the implant mobile phone. In step S11, the real-time point deviation and the real-time angle deviation of the drill can be obtained through comparison.

[0110] S12. Output the real-time point deviation and the real-time angle deviation of the drill, and navigate the implant mobile phone in real time according to the real-time point deviation and the real-time angle deviation of the drill.

[0111] The core of the technical solution is to generate a tooth three-dimensional point cloud according to the real-time pattern of the speckle structured light on the patient's teeth, determine the tooth feature points, and then register the tooth CT model and the tooth three-dimensional point cloud according to the tooth CT feature points and the tooth point cloud feature points, to obtain the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system , and then express the real-time point deviation and the real-time angle deviation in the CT three-dimensional coordinate system.

[0112] Based on the dynamic registration of the matrix transformation relationship between the speckle structured light in the optical three-dimensional coordinate system and the CT three-dimensional coordinate system, the real-time attitude of the drill tip and the drill rotation axis is obtained by calibrating the drill of the implant mobile phone. Then, the target position of the implant and the real-time attitude of the drill tip, the direction vector of the implant path and the unit vector of the drill rotation axis are compared to assist in navigation, which has the advantages of convenient operation, high positioning accuracy, etc. and can effectively improve the operation efficiency and accuracy.

[0113] Preferably, the step S6 specifically comprises:

[0114] S601. Calibrate the binocular positioning navigator based on the camera parameters of the first camera and the second camera to obtain the equivalent focal length f and the baseline length B of the binocular positioning navigator, and obtain the rotation matrix and the translation vector The equivalent focal length of the binocular positioning navigator is the equivalent focal length of the first camera and the second camera, and after correction, the equivalent focal lengths of the first camera and the second camera are the same, and f is taken; the baseline length of the binocular positioning navigator, that is, the horizontal distance between the optical centers of the first camera and the second camera after correction.

[0115] S602. Calibrate the speckle emitter to obtain the rotation matrix and the translation vector of the speckle emitter relative to the first camera. In step S601, the rotation matrix and the translation vector of the second camera relative to the first camera can be obtained through the camera parameters of the first camera and the second camera; in step S602, the rotation matrix and the translation vector of the speckle emitter relative to the first camera can be obtained in combination with the parameters of the speckle emitter. Thus, it can be understood that the first camera is the main camera of the binocular positioning navigator, and whether it is the second camera or the speckle emitter, it is rotated and translated through the first camera, so as to further process the data.

[0116] S603. Control the first camera to collect the first original image I1, control the second camera to collect the second original image I2, based on the rotation matrix and the translation vector of the second camera relative to the first camera, the rotation matrix and the translation vector of the speckle emitter relative to the first camera, polar correction processing is performed on I1 and I2 to obtain the first corrected image and the second corrected image after polar correction. In step S603, the first original image and the second original image are images directly collected after the speckle structured light is projected on the patient's oral cavity, and through calibration processing, the first original image and the second original image of the first camera and the second camera can be projected onto a completely coplanar and line-aligned plane to obtain the first corrected image and the second corrected image. Thereafter, any point on the first corrected image must be located on the same pixel line on the corresponding point on the second corrected image, based on which, in the subsequent matching data processing process, the two-dimensional search problem can be reduced to a one-dimensional search problem, greatly reducing the calculation amount.

[0117] S604. Select a first matching point center and a first matching range centered on the first matching point center in the first corrected image, map the first matching point center and the first matching range in the first corrected image to a second matching point center and a second matching range in the second corrected image to define a search range in the second corrected image according to the second matching point center and the second matching range. Step S604 is for matching operation by a local matching algorithm. Since there are rich speckle textures on the first corrected image and the second corrected image, the matching accuracy is very high. The local matching algorithm based on the region can further improve the matching accuracy.

[0118] S605. Perform zero-mean normalized cross-correlation operation on the second matching range in the second corrected image according to the first matching range in the first corrected image to determine a best matching point p and a disparity d corresponding to the best matching point p corresponding to each pixel point on the first corrected image on the second corrected image. The disparity is the horizontal coordinate difference of the best matching point p on the first corrected image and the second corrected image. The zero-mean normalized cross-correlation operation process is , when the value is maximum, the pixel point on the second corrected image is the best matching point P; wherein, is the pixel value of the pixel point on the first corrected image, is the average value of the pixel value of the pixel point on the first matching range in the first corrected image, is the pixel value of the pixel point on the second corrected image, is the average value of the pixel value of the pixel point on the search range in the second corrected image; represents the coordinates of the pixel point in the first corrected image or the second corrected image.

[0119] S606. Perform three-dimensional reconstruction according to the best matching point corresponding to each pixel point on the first corrected image and the disparity d corresponding to the best matching point to calculate three-dimensional data of the pixel point in the three-dimensional point cloud model, wherein the coordinate value of the pixel point in the Z-axis in the three-dimensional point cloud model is , the coordinate value of the pixel point in the X-axis in the three-dimensional point cloud model is , and the coordinate value of the pixel point in the Y-axis in the three-dimensional point cloud model is , f is the equivalent focal length of the first camera and the second camera, and B is the baseline length of the first camera and the second camera. After correction, the equivalent focal lengths of the first camera and the second camera are the same, and are f; the horizontal distance between the optical centers of the first camera and the second camera is the baseline length, and is B.

[0120] S607. Generate the tooth three-dimensional point cloud based on the coordinate values of the pixel points in the X-axis, Y-axis and Z-axis of the three-dimensional point cloud model. Based on the coordinate values of the pixel points in the X-axis, Y-axis and Z-axis of the three-dimensional point cloud model in step S606, the tooth three-dimensional point cloud can be generated by integration.

[0121] Based on the above technical solution, the original image generated by the speckle structure light is corrected and processed, and then the zero-mean normalized cross-correlation operation is performed, the three-dimensional data of the pixel points in the three-dimensional point cloud model is calculated, and the tooth three-dimensional point cloud is generated, which prepares for subsequent registration between the tooth CT model and the tooth three-dimensional point cloud through the tooth three-dimensional point cloud.

[0122] Preferably, the step S7 specifically comprises the following steps:

[0123] S701. Extract tooth CT feature points from the tooth CT model based on the FAST algorithm to obtain tooth CT feature points , extract tooth point cloud feature points from the tooth three-dimensional point cloud based on the FAST algorithm to obtain tooth point cloud feature points ; wherein, , is the tooth CT feature point, , is the tooth point cloud feature point. Based on the actual situation of the patient's oral cavity, points with high discrimination are selected as tooth CT feature points, which are tooth CT feature points on the tooth CT model and tooth point cloud feature points on the tooth three-dimensional point cloud.

[0124] S702. Obtain the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system and the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system. Since the tooth CT feature points and the tooth point cloud feature points are clear in step S701, the three-dimensional coordinate values of the feature points in the corresponding coordinate system can be directly obtained.

[0125] S703. Perform Gaussian smoothing operation based on the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system or the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system to obtain a scale space function, and the operation process is:

[0126] , wherein, is the scale space function, G is a three-dimensional Gaussian kernel function, is the Gaussian kernel standard deviation, is the three-dimensional coordinate value of the tooth point cloud feature point in the optical three-dimensional coordinate system or the three-dimensional coordinate value of the tooth CT feature point in the CT three-dimensional coordinate system, is the scale multiplication coefficient. In step S703, the scale space is constructed by Gaussian smoothing operation.

[0127] S704. Calculate the gradient of tooth CT feature points or tooth point cloud feature points in their neighborhood. , mold length Direction angle Angle with Z-axis ;in,

[0128] , , , ,exist In the formula, T is the matrix transpose. After constructing the scale space in step S703, the neighborhood around the key point can be divided into multiple sub-regions by calculating the gradient, magnitude, orientation angle, and Z-axis angle. In each sub-region, gradient orientation histograms in multiple directions are calculated, ultimately forming the feature description vector.

[0129] S705. Gradient of neighborhood points of tooth CT feature points , mold length Direction angle Angle with Z-axis Feature descriptors representing CT feature points of teeth The gradient of the neighborhood points of the tooth point cloud feature points. , mold length Direction angle Angle with Z-axis Feature descriptor representing feature points of a tooth point cloud and ;

[0130] S706. By determining the nearest neighbor distance ratio between the feature descriptors of tooth CT feature points and the feature descriptors of tooth point cloud feature points. The pairing is confirmed if the nearest neighbor distance ratio is less than the nearest neighbor distance threshold; otherwise, the pairing is deleted, resulting in the initial pairing group. At this point, the coarse registration is complete.

[0131] S707. The initial pairing group is optimized by using an iterative nearest-point algorithm to improve the registration accuracy, resulting in an accurate pairing group. In step S707, coarse registration is performed based on coarse registration using the iterative nearest point algorithm.

[0132] S708. Based on precise matching groups By combining the three-dimensional coordinates of the corresponding tooth point cloud feature points in the optical three-dimensional coordinate system and the three-dimensional coordinates of the corresponding tooth CT feature points in the CT three-dimensional coordinate system, the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system is calculated. .

[0133] Based on the above technical solution, the tooth CT model and the tooth 3D point cloud are registered according to the tooth CT feature points and tooth point cloud feature points. Coarse registration is performed by Gaussian smoothing operation, and then coarse registration is performed by iterative nearest point algorithm to obtain a precise pairing group. Then, the matrix transformation relationship between the CT 3D coordinate system and the optical 3D coordinate system is obtained based on the precise pairing group.

[0134] Preferably, in step S10, the rotation axis of the drill bit in the implantation mobile phone is determined by the unit vector in the optical three-dimensional coordinate system. The unit vector of the rotation axis in the CT three-dimensional coordinate system is calculated. Specifically: The real-time pose of the rotation axis in the CT 3D coordinate system can be obtained through simple conversion.

[0135] Preferably, step S11 specifically includes the following steps:

[0136] S1101. Comparative analysis of the target position of the implant in the CT three-dimensional coordinate system The three-dimensional coordinates of the drill tip in the CT three-dimensional coordinate system The real-time positional deviation between the drill tip and the target position in the CT three-dimensional coordinate system is obtained. ;

[0137] S1102. Comparative Analysis of the Direction Vector of the Planting Path in the CT Three-Dimensional Coordinate System The unit vector of the drill bit rotation axis in the CT three-dimensional coordinate system The real-time angular deviation between the drill tip and the target position in the CT three-dimensional coordinate system is obtained. c, where This is the dot product of vectors.

[0138] Based on the above technical solution, the real-time spatial difference between the drill bit tip and the target position in the CT three-dimensional coordinate system is parameterized to provide data reference for real-time navigation.

[0139] like Figure 2 As shown, to solve the above problems, the present invention provides an oral surgery positioning and navigation system, which includes: an image acquisition module 1, a rotation axis calibration module 2, a unit vector calibration module 3, a CT scanning module 4, a model segmentation module 5, a 3D point cloud generation module 6, a transformation relationship calculation module 7, a target posture acquisition module 8, a tip posture acquisition module 9, a rotation axis posture acquisition module 10, a comparison analysis module 11, and a real-time navigation module 12. Wherein:

[0140] Image acquisition module 1 is used to control the planting mobile phone to attach its drill bit mounting sleeve to the calibration rod on the calibration plate, and to control the binocular positioning and navigation device to acquire real-time images of the calibration feature points on the calibration plate. Based on the three-dimensional data model of the calibration plate and the optical three-dimensional coordinate system of the binocular positioning and navigation device, the pose of the calibration plate in the optical three-dimensional coordinate system is calculated. ;

[0141] Rotation axis calibration module 2 is used to determine the pose of the calibration plate in the optical three-dimensional coordinate system. Obtain the three-dimensional coordinates of the root point of the calibration rod in the optical three-dimensional coordinate system. The three-dimensional coordinates of the top point of the calibration rod in the optical three-dimensional coordinate system ,according to and The unit vector of the drill bit's rotation axis in the optical three-dimensional coordinate system was calculated. ,in, ;

[0142] Unit vector calibration module 3 is used to obtain the three-dimensional coordinates of the end of the drill bit's rotation axis in the optical three-dimensional coordinate system during implantation. and drill bit length Based on the three-dimensional coordinates of the end of the rotation axis in the optical three-dimensional coordinate system and drill bit length Combined with the unit vector of the drill bit's rotation axis in the optical three-dimensional coordinate system The three-dimensional coordinates of the drill tip in the optical three-dimensional coordinate system were calculated. ,in, , ;

[0143] CT scanning module 4 is used to control the CT scanning equipment to scan the patient's oral cavity and obtain a CT three-dimensional model of the patient's oral cavity;

[0144] Model segmentation module 5 is used to segment the CT 3D model of the patient's oral cavity to obtain a tooth CT model and an alveolar bone CT model;

[0145] The 3D point cloud generation module 6 is used to control the first and second cameras in the binocular positioning and navigation device to emit speckle structured light in conjunction with their respective speckle emitters, capture the real-time pattern formed by the speckle structured light on the patient's teeth, and generate a 3D point cloud of the teeth based on the real-time pattern of the speckle structured light on the patient's teeth.

[0146] Transformation relationship calculation module 7 is used to extract tooth CT feature points from the tooth CT model and tooth point cloud feature points from the tooth 3D point cloud. Based on the tooth CT feature points and tooth point cloud feature points, the tooth CT model and the tooth 3D point cloud are registered to obtain the matrix transformation relationship between the CT 3D coordinate system and the optical 3D coordinate system. ;

[0147] Target pose acquisition module 8 is used to acquire the target pose of the implant within the CT 3D model and obtain the target position of the implant in the CT 3D coordinate system. and the direction vector of the planting path ;

[0148] Tip attitude acquisition module 9 is used to obtain the three-dimensional coordinates of the drill tip in the optical three-dimensional coordinate system. Combining the matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system Perform coordinate transformation to obtain the three-dimensional coordinates of the drill bit tip in the CT three-dimensional coordinate system. ,in, ;

[0149] Rotation axis attitude acquisition module 10 is used to obtain the unit vector of the rotation axis of the drill bit in the planting mobile phone in the optical three-dimensional coordinate system. The unit vector of the drill bit's rotation axis in the CT three-dimensional coordinate system was calculated. ;

[0150] Comparison and analysis module 11 is used to compare and analyze the target position of the implant in the CT three-dimensional coordinate system. The three-dimensional coordinates of the drill tip in the CT three-dimensional coordinate system Comparative analysis of the direction vectors of the planting path in the CT three-dimensional coordinate system The unit vector of the drill bit rotation axis in the CT three-dimensional coordinate system Based on the comparative analysis results, the real-time position deviation and real-time angle deviation of the drill bit are calculated.

[0151] The real-time navigation module 12 is used to output the real-time position deviation and real-time angle deviation of the drill bit, and to perform real-time navigation of the planting mobile phone based on the real-time position deviation and real-time angle deviation of the drill bit.

[0152] Preferably, the 3D point cloud generation module specifically includes:

[0153] The camera calibration unit is used to calibrate the binocular positioning and navigation device based on the camera parameters of the first and second cameras, to obtain the equivalent focal length f and baseline length B of the binocular positioning and navigation device, and to obtain the rotation matrix of the second camera relative to the first camera. Translation vector ;

[0154] a transmitter calibration unit configured to calibrate the speckle transmitter to obtain a rotation matrix and a translation vector of the speckle transmitter relative to the first camera ; ;

[0155] a polar correction unit configured to control the first camera to capture a first original image I1 and the second camera to capture a second original image I2, perform polar correction on I1 and I2 based on the rotation matrix and the translation vector of the speckle transmitter relative to the first camera to obtain a first corrected image and a second corrected image ; ; ; ;

[0156] a matching mapping unit configured to select a first matching center and a first matching range centered on the first matching center in the first corrected image, map the first matching center and the first matching range in the first corrected image to a second matching center and a second matching range in the second corrected image, and define a search range in the second corrected image according to the second matching center and the second matching range

[0157] a zero-mean normalized cross-correlation operation unit configured to perform zero-mean normalized cross-correlation operation on the second matching range in the second corrected image according to the first matching range in the first corrected image to determine a best matching point P and a disparity d corresponding to the best matching point P of each pixel point in the first corrected image on the second corrected image; the zero-mean normalized cross-correlation operation process is , when is maximum, the pixel point on the second corrected image is the best matching point P; wherein, is a pixel value of the pixel point in the first corrected image, is an average value of pixel values of the pixel points in the first matching range in the first corrected image, is a pixel value of the pixel point in the second corrected image, is an average value of pixel values of the pixel points in the search range in the second corrected image; represents a coordinate of the pixel point in the first corrected image or the second corrected image;

[0158] a pixel point analysis unit configured to perform three-dimensional reconstruction according to the best matching point and the disparity d corresponding to the best matching point of each pixel point in the first corrected image to calculate three-dimensional data of the pixel point in a three-dimensional point cloud model, wherein a coordinate value of the pixel point in the Z-axis in the three-dimensional point cloud model is , and a coordinate value of the pixel point in the X-axis in the three-dimensional point cloud model is the coordinate value of the pixel point in the Y-axis of the three-dimensional point cloud model is f is the equivalent focal length of the first camera and the second camera, and B is the baseline length of the first camera and the second camera;

[0159] The point cloud model generation unit is configured to generate a tooth three-dimensional point cloud according to the coordinate values of the pixel point in the X-axis, the Y-axis and the Z-axis of the three-dimensional point cloud model.

[0160] Preferably, the transformation relationship calculation module specifically comprises:

[0161] The feature point extraction unit is configured to extract tooth CT feature points from the tooth CT model based on the FAST algorithm to obtain tooth CT feature points extract tooth point cloud feature points from the tooth three-dimensional point cloud based on the FAST algorithm to obtain tooth point cloud feature points ; wherein , is the tooth CT feature point, , is the tooth point cloud feature point.

[0162] The three-dimensional coordinate acquisition unit is configured to acquire three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system and three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system.

[0163] The Gaussian smoothing operation unit is configured to perform Gaussian smoothing operation based on the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system or the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system to obtain a scale space function, and the operation process is:

[0164] wherein, is the scale space function, G is a three-dimensional Gaussian kernel function, is a Gaussian kernel standard deviation, is the three-dimensional coordinate value of the tooth point cloud feature point in the optical three-dimensional coordinate system or the three-dimensional coordinate value of the tooth CT feature point in the CT three-dimensional coordinate system, is a scale multiplication coefficient.

[0165] The feature point neighborhood parameter calculation unit is configured to calculate the gradient , the module length , the direction angle and the Z-axis angle of the tooth CT feature points or the tooth point cloud feature points in the neighborhood; wherein,

[0166] , , , , T is the matrix transpose in the formula;

[0167] The feature descriptor calculation unit is configured to represent the feature descriptor of the tooth CT feature point by gradients of points in a neighborhood of the tooth CT feature point , module length , direction angle , and Z-axis angle The feature descriptor calculation unit is configured to represent the feature descriptor of the tooth point cloud feature point by gradients of points in a neighborhood of the tooth point cloud feature point , module length , direction angle , and Z-axis angle , and ;

[0168] The pair confirmation unit is configured to perform pair confirmation by judging whether a nearest neighbor distance ratio between the feature descriptor of the tooth CT feature point and the feature descriptor of the tooth point cloud feature point is less than a nearest neighbor distance threshold value; when the nearest neighbor distance ratio is less than the nearest neighbor distance threshold value, the pair is confirmed, and when the nearest neighbor distance ratio is greater than or equal to the nearest neighbor distance threshold value, the pair is deleted, to obtain an initial pair group ;

[0169] The iterative optimization unit is configured to optimize the initial pair group by an iterative nearest point algorithm to obtain an accurate pair group ;

[0170] The conversion relationship calculation unit is configured to calculate a matrix conversion relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system according to the accurate pair group , in combination with a three-dimensional coordinate value of the corresponding tooth point cloud feature point in the optical three-dimensional coordinate system and a three-dimensional coordinate value of the corresponding tooth CT feature point in the CT three-dimensional coordinate system .

[0171] Preferably, in the rotation axis posture acquisition module, a unit vector of the rotation axis of the drill bit in the optical three-dimensional coordinate system is calculated to obtain a unit vector of the rotation axis in the CT three-dimensional coordinate system Specifically, the unit vector of the rotation axis in the CT three-dimensional coordinate system is calculated by .

[0172] Preferably, the comparison and analysis module specifically includes:

[0173] The point position deviation calculation unit is configured to compare and analyze a target position of the implant in the CT three-dimensional coordinate system and a three-dimensional coordinate value of the drill bit tip in the CT three-dimensional coordinate system to obtain a real-time point position deviation of the drill bit tip and the target position in the CT three-dimensional coordinate system​​​​ ;

[0174] An angle deviation calculation unit is configured to compare and analyze a direction vector of the implant path and a unit vector of the drill bit rotation axis in the CT three-dimensional coordinate system to obtain a real-time angle deviation of the drill bit tip and the target position in the CT three-dimensional coordinate system. wherein, is a vector dot product

[0175] In order to solve the above problems, the application provides a storage medium, which stores a computer program, and the computer program comprises program instructions. When the program instructions are executed by a processor, the processor executes the oral surgery positioning navigation method as described above.

[0176] It should be understood that the application is not limited to the above examples, and can be improved or changed by those skilled in the art according to the above description, and all these improvements and changes shall belong to the protection scope of the appended claims of the application.​​

Claims

1. An oral surgery positioning navigation method, characterized by, The oral surgery positioning navigation method is implemented based on an oral surgery positioning navigation device, and the oral surgery positioning navigation device comprises a binocular positioning navigation instrument, a CT scanning device, an implant handset and a calibration plate; the binocular positioning navigation instrument comprises a first camera and a second camera, the first camera and the second camera are fixedly arranged on the implant handset, each of the first camera and the second camera is provided with a speckle emitter, and the calibration plate is provided with a calibration rod and calibration feature points; The oral surgery positioning navigation method comprises the following steps: S1. Control the planting mobile phone to install the drill bit mounting sleeve on the calibration rod on the calibration plate, control the binocular positioning navigator to collect the real-time image of the calibration feature point on the calibration plate, and calculate the pose of the calibration plate in the optical three-dimensional coordinate system according to the three-dimensional data model of the calibration plate and the optical three-dimensional coordinate system of the binocular positioning navigator C H M ; S2. The pose of the calibration plate under the optical three-dimensional coordinate system C H M Obtain the three-dimensional coordinates P1 of the root point of the calibration rod under the optical three-dimensional coordinate system and the three-dimensional coordinates P2 of the top point of the calibration rod under the optical three-dimensional coordinate system, and calculate the unit vector V of the drill bit in the planting mobile phone under the optical three-dimensional coordinate system according to P1 and P2 n wherein, S3. Obtain the three-dimensional coordinate value P of the end of the rotating shaft of the drill bit in the optical three-dimensional coordinate system in the planting mobile phone end and the drill bit length L, based on the three-dimensional coordinate value P of the end of the rotating shaft in the optical three-dimensional coordinate system end and the drill bit length L, combined with the unit vector V of the rotating shaft of the drill bit in the optical three-dimensional coordinate system n , the three-dimensional coordinate value P of the drill bit tip in the optical three-dimensional coordinate system is calculated tip , wherein P tip =P end +L*V n , P end =P1; S4. Control the CT scanning device to scan the patient's oral cavity to obtain a CT three-dimensional model of the patient's oral cavity; S5. Segment the CT three-dimensional model of the patient's oral cavity to obtain a tooth CT model and an alveolar bone CT model; S6. Control the first camera and the second camera in the binocular positioning navigation instrument to cooperate with the respective speckle emitters to emit speckle structured light, capture a real-time pattern formed by the speckle structured light on the patient's teeth, and generate a tooth three-dimensional point cloud according to the real-time pattern of the speckle structured light on the patient's teeth; S7. Extract tooth CT feature points of the tooth CT model and tooth point cloud feature points of the tooth three-dimensional point cloud, register the tooth CT model and the tooth three-dimensional point cloud according to the tooth CT feature points and the tooth point cloud feature points, and obtain a matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system CT H C ; S8. Implanting the implant target posture in the CT three-dimensional model, obtaining the target position T of the implant under the CT three-dimensional coordinate system target and the direction vector θ of the implant path target ; S9. The three-dimensional coordinate value P of the drill bit tip in the optical three-dimensional coordinate system tip , combined with the matrix transformation relationship of the CT three-dimensional coordinate system and the optical three-dimensional coordinate system CT H C Perform coordinate conversion to obtain the three-dimensional coordinate value P' of the drill bit tip in the CT three-dimensional coordinate system tip , wherein P' tip = P tip * CT H C ; S10. The unit vector V of the rotation axis of the drill bit in the optical three-dimensional coordinate system according to the planting mobile phone n The unit vector V of the rotation axis of the drill bit in the CT three-dimensional coordinate system is calculated n ; S11. Comparative analysis of the target position T of the implant in the CT three-dimensional coordinate system target and the three-dimensional coordinate value P' of the drill bit tip in the CT three-dimensional coordinate system tip Comparative analysis of the direction vector θ of the implant path in the CT three-dimensional coordinate system target and the unit vector V' of the drill bit rotation axis in the CT three-dimensional coordinate system n According to the comparative analysis results, the real-time point position deviation and real-time angle deviation of the drill bit are calculated; S12. Output the real-time point position deviation and the real-time angle deviation of the drill bit, and perform real-time navigation on the implant handset according to the real-time point position deviation and the real-time angle deviation of the drill bit; The step S6 specifically comprises the following steps: S601. Calibrate the binocular positioning navigation instrument based on the camera parameters of the first camera and the second camera to obtain the equivalent focal length f and the baseline length B of the binocular positioning navigation instrument, and obtain the rotation matrix R1 and the translation vector T1 of the second camera relative to the first camera; S602. Calibrate the speckle emitter to obtain the rotation matrix R2 and the translation vector T2 of the speckle emitter relative to the first camera; S603. Control the first camera to capture a first original image I1, control the second camera to capture a second original image I2, perform epipolar correction processing on I1 and I2 based on the rotation matrix R1 and the translation vector T1 of the second camera relative to the first camera, the rotation matrix R2 and the translation vector T2 of the speckle emitter relative to the first camera, to obtain a first corrected image and a second corrected image after epipolar correction; S604. Select a first matching point center and a first matching range with the first matching point center as the center point in the first corrected image, map the first matching point center and the first matching range in the first corrected image to a second matching point center and a second matching range in the second corrected image to define a search range in the second corrected image according to the second matching point center and the second matching range; S605. According to the first matching range in the first corrected image, a zero-mean normalized cross-correlation operation is performed on the second matching range in the second corrected image to determine the best matching point P and the corresponding parallax d of the best matching point on the second corrected image for each pixel point on the first corrected image; the zero-mean normalized cross-correlation operation process is When the ZNCC value is maximum, the pixel point on the second corrected image is the best matching point P; wherein T(i,j) is the pixel value of the pixel point on the first corrected image, is the average value of the pixel value of the pixel point on the first matching range in the first corrected image, and C(i,j) is the pixel value of the pixel point on the second corrected image, is the average value of the pixel value of the pixel point on the search range in the second corrected image; (i,j) represents the coordinates of the pixel point on the first corrected image or the second corrected image; S606. According to the best matching point corresponding to each pixel point on the first corrected image and the disparity d corresponding to the best matching point, three-dimensional reconstruction is performed to calculate the three-dimensional data of the pixel point in the three-dimensional point cloud model, wherein the coordinate value of the pixel point in the Z-axis of the three-dimensional point cloud model is The coordinate value of the pixel point in the X-axis of the three-dimensional point cloud model is The coordinate value of the pixel point in the Y-axis of the three-dimensional point cloud model is f is the equivalent focal length of the first camera and the second camera, and B is the baseline length of the first camera and the second camera. S607. Generate the tooth three-dimensional point cloud according to the coordinate values of the pixel points in the X axis, the Y axis and the Z axis of the three-dimensional point cloud model.

2. The oral surgery positioning navigation method according to claim 1, wherein, The step S7 specifically comprises the following steps: S701. Extract tooth CT feature points from the tooth CT model based on the FAST algorithm to obtain tooth CT feature points F m =(f m1 ,f m2 ...) tooth point cloud feature points F c =(f c1 ,f c2 ...) are obtained by extracting tooth point cloud feature points from the tooth three-dimensional point cloud based on the FAST algorithm; wherein f m1 , f m2 are tooth CT feature points, and f c1 , f c2 are tooth point cloud feature points; S702. Obtain the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system and the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system; S703. Perform Gaussian smoothing operation based on the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system or the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system to obtain a scale space function, and the operation process is as follows: L(x, y, z, σ) = G(x, y, z, kσ) * I(x, y, z), wherein, L is a scale space function, G is a three-dimensional Gaussian kernel function, sigma is a Gaussian kernel standard deviation, I(x, y, z) is a three-dimensional coordinate value of a tooth point cloud feature point in an optical three-dimensional coordinate system or a three-dimensional coordinate value of a tooth CT feature point in a CT three-dimensional coordinate system, k is a scale multiplication coefficient; S704. Calculate the gradient of the tooth CT feature point or the tooth point cloud feature point in the neighborhood, the modulus m(x, y, z), the direction angle theta and the Z-axis angle phi; wherein, In T is the matrix transpose in the formula. S705. Gradient of points in the neighborhood of the tooth CT feature point Module length m(x, y, z), direction angle θ, and Z-axis angle φ represent the feature descriptor d of the tooth CT feature point m Gradient of points in the neighborhood of the tooth point cloud feature point Module length m(x, y, z), direction angle θ, and Z-axis angle φ represent the feature descriptor d of the tooth point cloud feature point c1 and d c2 ; S706. Confirm the matching by judging whether the nearest neighbor distance ratio between the feature descriptor of the tooth CT feature point and the feature descriptor of the tooth point cloud feature point is less than the nearest neighbor distance threshold value; when the nearest neighbor distance ratio is less than the nearest neighbor distance threshold value, the matching is confirmed, and when the nearest neighbor distance ratio is greater than or equal to the nearest neighbor distance threshold value, the matching is deleted, to obtain an initial matching group [(f ,f m1 ,f c1 ),(f m2 ,f c2 )...]. S707. Optimizing the initial pairing group by the iterative closest point algorithm to obtain the accurate pairing group [(f m1 ,f c1 ) m2 ,f c2 )...] S708. According to the accurate pairing group [(f m1 ,f c1 ) m2 ,f c2 )...], combined with the three-dimensional coordinate values of the corresponding tooth point cloud feature points in the optical three-dimensional coordinate system and the three-dimensional coordinate values of the corresponding tooth CT feature points in the CT three-dimensional coordinate system, the matrix conversion relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system is calculated CT H C .

3. The method of claim 1, wherein, In the step S10, a unit vector V of the rotating shaft of the drill bit in the optical three-dimensional coordinate system is calculated according to the angle of the rotating shaft of the drill bit in the planting mobile phone n The unit vector V of the rotating shaft in the CT three-dimensional coordinate system is calculated n Specifically: V' n = V n * CT H C .

4. The oral surgery positioning navigation method of claim 1, wherein, The step S11 specifically includes the following steps: S1101. Target position T of the implant in the CT three-dimensional coordinate system is analyzed target and three-dimensional coordinate values P' of the drill bit tip in the CT three-dimensional coordinate system tip , real-time point deviation Δd = |P' tip -T target | of the drill bit tip and the target position in the CT three-dimensional coordinate system is obtained S1102. Compare and analyze the direction vector θ of the implant path in the CT three-dimensional coordinate system target and the unit vector V' of the drill bit rotation axis in the CT three-dimensional coordinate system n , to obtain the real-time angle deviation Δθ = arccos(V' n · θ target ) between the drill bit tip and the target position in the CT three-dimensional coordinate system, wherein · is the vector dot product.

5. An oral surgery positioning navigation system, characterized by, The oral surgery positioning navigation system is implemented based on an oral surgery positioning navigation device, the oral surgery positioning navigation device includes a binocular positioning navigation instrument, a CT scanning device, an implant mobile phone and a calibration board; the binocular positioning navigation instrument includes a first camera and a second camera, the first camera and the second camera are fixedly arranged on the implant mobile phone, each of the first camera and the second camera is provided with a speckle emitter, and the calibration board is provided with a calibration rod and calibration feature points; The oral surgery positioning navigation system includes: The image acquisition module is used for controlling the planting mobile phone to sleeve the drill bit mounting sleeve on the calibration rod on the calibration plate, controlling the binocular positioning navigator to acquire real-time images of the calibration characteristic points on the calibration plate, and calculating the pose of the calibration plate under the optical three-dimensional coordinate system according to the three-dimensional data model of the calibration plate and the optical three-dimensional coordinate system of the binocular positioning navigator C H M ; The rotation axis calibration module is configured to calibrate the rotation axis of the drill bit in the optical three-dimensional coordinate system according to the position and posture of the calibration plate in the optical three-dimensional coordinate system C H M The three-dimensional coordinates P1 of the root point of the calibration rod in the optical three-dimensional coordinate system and the three-dimensional coordinates P2 of the top point of the calibration rod in the optical three-dimensional coordinate system are obtained, and a unit vector V of the rotation axis of the drill bit in the optical three-dimensional coordinate system is calculated according to P1 and P2 n , wherein, A unit vector calibration module is configured to acquire a three-dimensional coordinate value P of an end of a rotating shaft of a drill bit in the planting mobile phone in an optical three-dimensional coordinate system end and a drill bit length L, based on the three-dimensional coordinate value P of the end of the rotating shaft of the drill bit in the optical three-dimensional coordinate system end and the drill bit length L, in combination with a unit vector V of the rotating shaft of the drill bit in the optical three-dimensional coordinate system n to calculate a three-dimensional coordinate value P of a tip of the drill bit in the optical three-dimensional coordinate system tip wherein P tip = P end + L*V n , and P end = P1; The CT scanning module is configured to control the CT scanning device to scan the oral cavity of the patient to obtain a CT three-dimensional model of the oral cavity of the patient. The model segmentation module is configured to segment the CT three-dimensional model of the oral cavity of the patient to obtain a tooth CT model and an alveolar bone CT model. The three-dimensional point cloud generation module is configured to control the first camera and the second camera in the binocular positioning navigation instrument to cooperate with the respective speckle emitters to emit speckle structured light, capture real-time patterns formed by the speckle structured light on the teeth of the patient, and generate a tooth three-dimensional point cloud based on the real-time patterns of the speckle structured light on the teeth of the patient. The transformation relationship calculation module is configured to extract tooth CT feature points of the tooth CT model and tooth point cloud feature points of the tooth three-dimensional point cloud, register the tooth CT model and the tooth three-dimensional point cloud according to the tooth CT feature points and the tooth point cloud feature points, and obtain a matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system CT H C ; The target posture acquisition module is configured to implant an implant target posture in a CT three-dimensional model, and acquire a target position T of the implant in a CT three-dimensional coordinate system target and a direction vector θ of the implant path target ; The tip posture acquisition module is configured to acquire a three-dimensional coordinate value P of the drill bit tip in an optical three-dimensional coordinate system according to a three-dimensional coordinate value P of the drill bit tip in the optical three-dimensional coordinate system tip , in combination with a matrix transformation relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system CT H C , to perform coordinate conversion and acquire a three-dimensional coordinate value P' of the drill bit tip in the CT three-dimensional coordinate system tip , wherein P' tip = P tip * CT H C ; The rotation axis posture acquisition module is configured to acquire a unit vector V of the rotation axis of the drill bit in the optical three-dimensional coordinate system according to the rotation axis of the drill bit in the planting mobile phone n The unit vector V of the rotation axis of the drill bit in the CT three-dimensional coordinate system is calculated n ; The comparative analysis module is configured to comparatively analyze a target position T of the implant in a CT three-dimensional coordinate system target and a three-dimensional coordinate value P' of the drill bit tip in the CT three-dimensional coordinate system tip comparatively analyze a direction vector θ of the implant path in the CT three-dimensional coordinate system target and a unit vector V' of the drill bit rotation axis in the CT three-dimensional coordinate system n The real-time point deviation and the real-time angle deviation of the drill bit are calculated according to the comparative analysis result. The real-time navigation module is configured to output real-time positional deviations and real-time angular deviations of the drill bit, and perform real-time navigation on the implant mobile phone based on the real-time positional deviations and the real-time angular deviations of the drill bit. The three-dimensional point cloud generation module specifically includes: The camera calibration unit is configured to calibrate the binocular positioning navigation instrument based on camera parameters of the first camera and the second camera to obtain an equivalent focal length f and a baseline length B of the binocular positioning navigation instrument, and obtain a rotation matrix R1 and a translation vector T1 of the second camera relative to the first camera. The emitter calibration unit is configured to calibrate the speckle emitter to obtain a rotation matrix R2 and a translation vector T2 of the speckle emitter relative to the first camera. The epipolar correction unit is configured to control the first camera to capture a first original image I1, control the second camera to capture a second original image I2, perform epipolar correction processing on I1 and I2 based on the rotation matrix R1 and the translation vector T1 of the second camera relative to the first camera, the rotation matrix R2 and the translation vector T2 of the speckle emitter relative to the first camera, and obtain a first corrected image and a second corrected image after epipolar correction. The matching mapping unit is configured to select a first matching center and a first matching range centered on the first matching center in the first corrected image, map the first matching center and the first matching range in the first corrected image to a second matching center and a second matching range in a second corrected image, and define a search range in the second corrected image according to the second matching center and the second matching range. a zero-mean normalized cross-correlation operation unit configured to perform a zero-mean normalized cross-correlation operation on a second matching range in the second corrected image according to a first matching range in the first corrected image, to determine a best matching point P and a disparity d corresponding to the best matching point P of each pixel point in the first corrected image in the second corrected image; the zero-mean normalized cross-correlation operation process is When the ZNCC value is maximum, the pixel point in the second corrected image corresponding to the maximum value is the best matching point P; wherein T(i,j) is a pixel value of a pixel point in the first corrected image, is an average value of pixel values of pixel points in the first matching range in the first corrected image, and C(i,j) is a pixel value of a pixel point in the second corrected image, is an average value of pixel values of pixel points in the search range in the second corrected image; (i,j) represents a coordinate of a pixel point in the first corrected image or the second corrected image. The pixel point analysis unit is configured to perform three-dimensional reconstruction according to the best matching point corresponding to each pixel point on the first corrected image and the disparity d corresponding to the best matching point, and calculate three-dimensional data of the pixel point in the three-dimensional point cloud model, wherein the coordinate value of the pixel point in the Z-axis of the three-dimensional point cloud model is The coordinate value of the pixel point in the X-axis of the three-dimensional point cloud model is The coordinate value of the pixel point in the Y-axis of the three-dimensional point cloud model is f is the equivalent focal length of the first camera and the second camera, and B is the baseline length of the first camera and the second camera. The point cloud model generation unit is configured to generate a tooth three-dimensional point cloud according to coordinate values of the pixel points in the X axis, the Y axis and the Z axis of the three-dimensional point cloud model.

6. An oral surgery positioning navigation system according to claim 5, wherein, The transformation relationship calculation module specifically includes: The feature point extraction unit is configured to extract tooth CT feature points from the tooth CT model based on a FAST algorithm to obtain tooth CT feature points F m =(f m1 ,f m2 ...) and extract tooth point cloud feature points from the tooth three-dimensional point cloud based on the FAST algorithm to obtain tooth point cloud feature points F c =(f c1 ,f c2 ...); wherein f m1 , f m2 are tooth CT feature points, and f c1 , f c2 are tooth point cloud feature points. The three-dimensional coordinate acquisition unit is configured to acquire three-dimensional coordinate values of tooth point cloud feature points in an optical three-dimensional coordinate system and three-dimensional coordinate values of tooth CT feature points in a CT three-dimensional coordinate system. The Gaussian smoothing operation unit is configured to perform Gaussian smoothing operation based on the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system or the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system to obtain a scale space function, and the operation process is as follows: L(x, y, z, sigma) = G(x, y, z, k * sigma) * I(x, y, z), wherein L is the scale space function, G is a three-dimensional Gaussian kernel function, sigma is a Gaussian kernel standard deviation, I(x, y, z) is the three-dimensional coordinate values of the tooth point cloud feature points in the optical three-dimensional coordinate system or the three-dimensional coordinate values of the tooth CT feature points in the CT three-dimensional coordinate system, and k is a scale multiplication coefficient. The feature point neighborhood parameter calculation unit is configured to calculate the gradient of points in the neighborhood of the tooth CT feature point or the tooth point cloud feature point Modulus m(x, y, z), direction angle θ, and Z-axis angle φ; wherein, In T is the matrix transpose in the formula. The feature descriptor calculation unit is configured to represent the feature descriptor d of the tooth CT feature point by the gradient ∇L, the modulus m(x, y, z), the direction angle θ, and the Z-axis included angle φ of the point in the neighborhood of the tooth CT feature point. m The feature descriptor calculation unit is configured to represent the feature descriptor d of the tooth CT feature point by the gradient ∇L, the modulus m(x, y, z), the direction angle θ, and the Z-axis included angle φ of the point in the neighborhood of the tooth CT feature point. c1 And d c2 ; The pairing confirmation unit is configured to confirm the pairing by judging whether a nearest neighbor distance ratio between the feature descriptor of the tooth CT feature point and the feature descriptor of the tooth point cloud feature point is less than a nearest neighbor distance threshold value; when the nearest neighbor distance ratio is less than the nearest neighbor distance threshold value, the pairing is confirmed, and when the nearest neighbor distance ratio is greater than or equal to the nearest neighbor distance threshold value, the pairing is deleted, to obtain an initial pairing group [(f ,f m1 ,f c1 ),(f m2 ,f c2 )...]. an iterative optimization unit for optimizing the initial pairing set by an iterative closest point algorithm to obtain an accurate pairing set [(f m1 ,f c1 ) , (f m2 ,f c2 )...] The conversion relationship calculation unit is configured to calculate a matrix conversion relationship between the CT three-dimensional coordinate system and the optical three-dimensional coordinate system according to the accurate matching groups [(f m1 ,f c1 ),(f m2 ,f c2 )...] in combination with the three-dimensional coordinate values of the corresponding tooth point cloud feature points in the optical three-dimensional coordinate system and the three-dimensional coordinate values of the corresponding tooth CT feature points in the CT three-dimensional coordinate system. CT H C .

7. The oral surgery positioning navigation system of claim 5, wherein, In the rotation axis posture acquisition module, a unit vector V of the rotation axis of the drill bit in the optical three-dimensional coordinate system is calculated according to the rotation axis of the drill bit in the planting mobile phone n The unit vector V of the rotation axis in the CT three-dimensional coordinate system is calculated n Specifically, V n = V n * CT H C ; The comparison and analysis module specifically includes: The point deviation calculation unit is configured to compare and analyze the target position T of the implant in the CT three-dimensional coordinate system target and the three-dimensional coordinate value P' of the drill bit tip in the CT three-dimensional coordinate system tip , to obtain the real-time point deviation Δd = |P' tip -T target | of the drill bit tip and the target position in the CT three-dimensional coordinate system. An angle deviation calculation unit is configured to compare and analyze a direction vector θ of the implant path in a CT three-dimensional coordinate system target and a unit vector V' of the drill bit rotation axis in the CT three-dimensional coordinate system n to obtain a real-time angle deviation Δθ = arccos(V' n · θ target ) between the drill bit tip and the target position in the CT three-dimensional coordinate system, wherein · is a vector dot product.

8. A storage medium, characterized by The storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by the processor, the processor executes the oral surgery positioning navigation method in any one of claims 1-4.

Images