Panoramic track generation method and apparatus for dental image capture

Abstract

This invention provides a method and apparatus for generating panoramic tracks from dental images. The method includes the following steps: constructing a dental arch model, wherein the dental arch model includes multiple simulated tooth points; acquiring multiple sets of projection images of the dental arch model; determining the target position of each simulated tooth point in each set of projection images; determining the target coefficient of each set of projection images based on the target position; and determining the panoramic track for dental image capture based on the target coefficient. This invention features a simple calculation process, better adaptability, and a shorter panoramic track generation time, thereby improving the overall operational efficiency of the dental panoramic reconstruction system.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, specifically to a method and apparatus for generating panoramic tracks in dental image capture. Background Technology

[0002] With the improvement of people's living standards and the rise of various dental clinics, people are paying more and more attention to their oral health. Surveys show that dentists currently often use panoramic radiography as the primary method for examining patients for common oral diseases due to its smaller dosage and lower cost. Panoramic radiography mostly employs curved surface tomography (CPT) reconstruction technology.

[0003] In dental panoramic imaging systems, teeth are ideally positioned within the focal plane. If a tooth deviates from the focal plane, the spatial resolution and contrast of the resulting panoramic image will be low, and the tooth will appear blurry. In actual panoramic reconstruction, the stitching tracks for different teeth within the focal plane differ. An ideal reconstruction track ensures that each tooth is clearly reconstructed.

[0004] However, considering the diverse shapes and sizes of teeth among individuals, it is difficult to find an ideal track that perfectly meets the reconstruction requirements. Therefore, a near-ideal reconstruction track can determine the final quality of the panoramic dental imaging. Existing literature commonly employs track generation schemes based on geometric constraints. Specifically, this involves establishing geometric relationships based on the respective panoramic motion trajectories, calculating the stitching coefficients of different frames using complex mathematical derivations, and then generating the panoramic track using certain rules. However, this type of scheme requires the operator to be familiar with the motion trajectories of different dental panoramic imaging systems, and also requires constructing a geometric model corresponding to the motion trajectory, followed by a series of mathematical derivations to calculate the track coefficients, making the generation of the panoramic track quite challenging. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method for generating panoramic tracks from dental images. The calculation process is simple, has better adaptability, and the panoramic track generation process takes less time, thereby improving the overall operating efficiency of the dental panoramic reconstruction system.

[0006] The technical solution adopted in this invention is as follows:

[0007] A method for generating a panoramic track from dental images includes the following steps: constructing a dental arch model, wherein the dental arch model includes multiple simulated tooth points; acquiring multiple sets of projection images of the dental arch model; determining the target position of each simulated tooth point in each set of projection images; determining the target coefficient of each set of projection images based on the target position; and determining the panoramic track from the dental images based on the target coefficient.

[0008] According to one embodiment of the present invention, the dental arch model is a steel ball dental arch model, and a steel ball is set for each simulated tooth point of the steel ball dental arch model.

[0009] According to an embodiment of the present invention, determining the target position of each simulated tooth point in each group of projected images specifically includes the following steps: preprocessing each group of projected images; segmenting and extracting each group of preprocessed projected images; determining whether the steel ball exists in each group of segmented and extracted projected images; if it exists, calculating the target position of the steel ball.

[0010] According to an embodiment of the present invention, determining whether the steel ball exists in each group of projected images after segmentation and extraction specifically includes the following steps: determining whether there is a non-suspected target in each group of projected images after segmentation and extraction; if so, removing the non-suspected target; determining whether the steel ball exists in each group of projected images after removing the non-suspected target; if so, calculating the target position of the steel ball.

[0011] According to one embodiment of the present invention, the criteria for determining whether the non-suspected target exists are as follows:

[0012]

[0013] Among them, A(C i Ne(C) represents the area of ​​the segmented extraction result. ij ) represents the neighborhood target statistics of the j-th pixel in the segmentation extraction result, where n ci T1 and T2 represent the target sum of the segmentation and extraction results, and are experimental values.

[0014] According to one embodiment of the present invention, the criteria for determining whether the steel ball exists are as follows:

[0015]

[0016] Among them, W ci H represents the width of the segmentation and extraction result. ci T3, T4, and T5 represent the high values ​​of the segmentation and extraction results, respectively.

[0017] According to one embodiment of the present invention, the target position of the steel ball is calculated as follows:

[0018]

[0019] Where P represents the target position of the current projected image, and n ci Y represents the total number of targets in the segmentation and extraction results. cij This represents the vertical coordinate of the j-th point in the segmentation and extraction result.

[0020] According to one embodiment of the present invention, the target coefficients of each group of projected images are calculated as follows:

[0021] V i =|P i+1 -P i |,i=1,2,...,N

[0022] Among them, V i (i = 1, 2, ..., N) represents the target coefficient of the i-th group of projected images, |...| represents taking the absolute value, P i The i-th group of projected images represents the target position, and N represents the total number of projected images.

[0023] According to an embodiment of the present invention, determining the panoramic track for dental image capture based on the target coefficient specifically includes the following steps: determining the node positions of the dental image capture based on the target coefficient; and using a spline interpolation algorithm to interpolate between the node positions to determine the panoramic track for dental image capture.

[0024] A panoramic track generation device for dental image capture includes: a modeling module for constructing a dental arch model, wherein the dental arch model includes multiple simulated tooth points; an acquisition module for acquiring multiple sets of projected images of the dental arch model; a first calculation module for determining a target position for each simulated tooth point in each set of projected images; a second calculation module for determining a target coefficient for each set of projected images based on the target position; and a third calculation module for determining a panoramic track for dental image capture based on the target coefficient.

[0025] The beneficial effects of this invention are:

[0026] 1) This invention does not require prior knowledge of the corresponding dental panoramic track, nor does it require the establishment of a corresponding geometric model and a complex mathematical derivation process under that model. It can obtain the final panoramic track based on its projection image using only a pre-constructed dental arch model. The calculation process is simple and has better adaptability.

[0027] 2) This invention can achieve results comparable to commonly used geometrically constrained track generation schemes using a simpler principle process, thereby reducing the reliance on knowledge of the motion trajectory of the dental panoramic machine. Furthermore, the panoramic track generation process takes less time, which in turn improves the operating efficiency of the entire dental panoramic reconstruction system. Attached Figure Description

[0028] Figure 1A flowchart of a method for generating panoramic tracks from dental images according to an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of the structure of a dental arch model according to an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of the target coefficient results according to an embodiment of the present invention;

[0031] Figure 4 A block diagram illustrating a panoramic track generation device for dental image capture according to an embodiment of the present invention. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Figure 1 This is a flowchart of a method for generating panoramic tracks from dental images, as described in an embodiment of the present invention.

[0034] like Figure 1 As shown, the panoramic track generation method for dental image capture according to an embodiment of the present invention includes the following steps:

[0035] S1, Construct a dental arch model, which includes multiple simulated tooth points.

[0036] Specifically, one can first obtain the basic parameters of the human dental arch, such as the basic number of human teeth (the number of human teeth is 27), and then construct a corresponding dental arch model, for example, using 27 steel balls. Figure 2 The steel ball dental arch model shown is provided, and a steel ball is set for each simulated tooth point in the steel ball dental arch model.

[0037] S2, acquire multiple sets of projection images of the dental arch model.

[0038] Specifically, an initial panoramic track can be set first, and then multiple sets of projected images of the dental arch model, i.e., the steel ball dental arch model, can be captured based on this initial panoramic track. For example, N frames of projected images of the steel ball dental arch model can be captured. The initial panoramic track can be the oracle's dental arch shooting track.

[0039] S3, determine the target location of each simulated tooth point in each set of projected images.

[0040] Specifically, each group of projection images can be preprocessed and segmented and extracted. Then, it can be determined whether a steel ball exists in each segmented and extracted group of projection images. If it exists, the target position of the steel ball is calculated.

[0041] More specifically, brightness correction and defective pixel / line correction can be performed on each group of projected images. Then, a nonlocal mean filtering algorithm can be used to denoise each corrected group of projected images, thus achieving preprocessing of each group of projected images. The nonlocal mean filtering algorithm can be programmed using CUDA, thereby solving the speed problem of nonlocal mean filtering.

[0042] Furthermore, each preprocessed group of projected images can be segmented using a maximum inter-class variance threshold, and then connected component extraction can be performed on the segmented global results. The result of connected component extraction can be labeled as C. i , i = 1, 2, ..., n, where n is the number of connected component extraction results, i.e., the number of segmentation results.

[0043] Furthermore, it can be determined whether there are any non-suspected targets in each group of projected images after segmentation and extraction. If so, the non-suspected targets are removed. It should be noted that non-suspected targets are targets that are determined to be non-steel balls after connected component extraction. If the segmentation and extraction result, i.e., the connected component extraction result, is determined to be a non-suspected target, then that connected component extraction result can be eliminated.

[0044] The criteria for determining whether there is a non-suspected target are as follows:

[0045]

[0046] Among them, A(C i ) represents the segmentation and extraction result, i.e., the connected component extraction result C. i The area of ​​Ne(C) ij ) represents the segmentation and extraction result, i.e., the connected component extraction result C. i Statistical analysis of the neighborhood of the j-th pixel, n ci This represents the segmentation and extraction result, specifically the connected component extraction result C. i The target sum, T1 and T2 are experimental values.

[0047] Furthermore, it can be determined whether a steel ball exists in each group of projected images after removing non-suspected targets. If it exists, the target position of the steel ball is calculated; if it does not exist, the target position of the projected image is recorded as 0.

[0048] The conditions for determining whether a steel ball exists are as follows:

[0049]

[0050] Among them, Wci H represents the width of the segmentation and extraction result. ci T3, T4, and T5 represent the high values ​​of the segmentation and extraction results, respectively.

[0051] It should be noted that if any of the above conditions for determining whether a steel ball exists are not met, it is determined that no steel ball exists, the target position of the corresponding projected image is recorded as 0, and the process moves on to the next set of projected images; if any of the above conditions for determining whether a steel ball exists are met, the target position of the steel ball is calculated.

[0052] Furthermore, the target position of the steel ball is calculated as follows:

[0053]

[0054] Where P represents the target position of the current projected image, and n ci Y represents the total number of targets in the segmentation and extraction results. cij This represents the vertical coordinate of the j-th point in the segmentation and extraction result.

[0055] S4, determine the target coefficients for each group of projected images based on the target location.

[0056] Specifically, the target coefficients for each group of projected images can be calculated using the following formula:

[0057] V i =|P i+1 -P i |,i=1,2,...,N

[0058] Among them, V i (i = 1, 2, ..., N) represents the target coefficient of the i-th group of projected images, |...| represents taking the absolute value, P i Let N represent the target position of the i-th group of projected images, and N represent the total number of projected images.

[0059] It should be noted that the target coefficients of each set of projected images can reflect the motion trajectory of the projected images containing the steel ball. Therefore, these coefficients can serve as a benchmark for constructing the panoramic track. For example, corresponding to... Figure 2 The projection image of the dental arch model shown, if T1 is 3, T2 is 4, T3 is 20, T4 is 4, and T5 is 0.92, yields the following results: Figure 3 The target coefficient results are shown.

[0060] S5 determines the panoramic track for dental image capture based on the target coefficient.

[0061] Specifically, the node positions of dental image capture can be determined based on the target coefficients, and then a spline interpolation algorithm can be used to interpolate between the node positions to determine the panoramic track of dental image capture.

[0062] More specifically, the number of node positions corresponds to the number of steel balls, for example, 27, and the node positions are calculated as follows:

[0063]

[0064] Where k represents the index of the steel ball, 1≤k≤27, round(...) represents the nearest integer value, and n Bk This represents the number of projection groups covered by the k-th steel ball. This represents the index of the projected image covered by the k-th steel ball. N represents the target coefficient of the projected image covered by the k-th steel ball. xk N represents the index of the projected image corresponding to the k-th node position. yk This represents the coefficient corresponding to the k-th node.

[0065] Furthermore, after calculating the node positions, the target coefficients of the first and last sets of projected images can be initialized. Then, a cubic B-spline interpolation algorithm can be used to interpolate the node positions of all projected images, and the number of points inserted between node positions is:

[0066] In k =N x(k+1) -N xk -1.

[0067] Furthermore, the panoramic track for dental image capture can be determined based on the node positions of the dental images and the insertion points between the node positions.

[0068] The beneficial effects of this invention are as follows:

[0069] 1) This invention does not require prior knowledge of the corresponding dental panoramic track, nor does it require the establishment of a corresponding geometric model and a complex mathematical derivation process under that model. It can obtain the final panoramic track based on its projection image using only a pre-constructed dental arch model. The calculation process is simple and has better adaptability.

[0070] 2) This invention can achieve results comparable to commonly used geometrically constrained track generation schemes using a simpler principle process, thereby reducing the reliance on knowledge of the motion trajectory of the dental panoramic machine. Furthermore, the panoramic track generation process takes less time, which in turn improves the operating efficiency of the entire dental panoramic reconstruction system.

[0071] Corresponding to the panoramic track generation method for dental image acquisition proposed in the above embodiments, the present invention also proposes a panoramic track generation device for dental image acquisition.

[0072] like Figure 4As shown, the panoramic track generation device for dental image capture according to an embodiment of the present invention includes a modeling module 10, an acquisition module 20, a first calculation module 30, a second calculation module 40, and a third calculation module 50. The modeling module 10 is used to construct a dental arch model, which includes multiple simulated tooth points; the acquisition module 20 is used to acquire multiple sets of projection images of the dental arch model; the first calculation module 30 is used to determine the target position of each simulated tooth point in each set of projection images; the second calculation module 40 is used to determine the target coefficient of each set of projection images based on the target position; and the third calculation module 50 is used to determine the panoramic track for dental image capture based on the target coefficient.

[0073] In one embodiment of the present invention, the modeling module 10 can first obtain the basic parameters of the human dental arch, such as the basic number of human teeth (the number of human teeth is 27), and then construct a corresponding dental arch model, for example, using 27 steel balls. Figure 2 The steel ball dental arch model shown is provided, and a steel ball is set for each simulated tooth point in the steel ball dental arch model.

[0074] In one embodiment of the present invention, the acquisition module 20 can be used to set an initial panoramic track, and then capture multiple sets of projection images of the dental arch model, i.e., the steel ball dental arch model, according to the initial panoramic track. For example, N frames of projection images of the steel ball dental arch model can be captured. The initial panoramic track can be the dental arch imaging track of the prophet.

[0075] In one embodiment of the present invention, the first calculation module 30 can be used to preprocess each group of projected images and segment and extract each group of preprocessed projected images. Then, it can be determined whether there is a steel ball in each group of segmented and extracted projected images. If there is, the target position of the steel ball is calculated.

[0076] More specifically, brightness correction and defective pixel / line correction can be performed on each group of projected images. Then, a nonlocal mean filtering algorithm can be used to denoise each corrected group of projected images, thus achieving preprocessing of each group of projected images. The nonlocal mean filtering algorithm can be programmed using CUDA, thereby solving the speed problem of nonlocal mean filtering.

[0077] Furthermore, each preprocessed group of projected images can be segmented using a maximum inter-class variance threshold, and then connected component extraction can be performed on the segmented global results. The result of connected component extraction can be labeled as C. i , i = 1, 2, ..., n, where n is the number of connected component extraction results, i.e., the number of segmentation results.

[0078] Furthermore, it can be determined whether there are any non-suspected targets in each group of projected images after segmentation and extraction. If so, the non-suspected targets are removed. It should be noted that non-suspected targets are targets that are determined to be non-steel balls after connected component extraction. If the segmentation and extraction result, i.e., the connected component extraction result, is determined to be a non-suspected target, then that connected component extraction result can be eliminated.

[0079] The criteria for determining whether there is a non-suspected target are as follows:

[0080]

[0081] Among them, A(C i ) represents the segmentation and extraction result, i.e., the connected component extraction result C. i The area of ​​Ne(C) ij ) represents the segmentation and extraction result, i.e., the connected component extraction result C. i Statistical analysis of the neighborhood of the j-th pixel, n ci This represents the segmentation and extraction result, specifically the connected component extraction result C. i The target sum, T1 and T2 are experimental values.

[0082] Furthermore, it can be determined whether a steel ball exists in each group of projected images after removing non-suspected targets. If it exists, the target position of the steel ball is calculated; if it does not exist, the target position of the projected image is recorded as 0.

[0083] The conditions for determining whether a steel ball exists are as follows:

[0084]

[0085] Among them, W ci H represents the width of the segmentation and extraction result. ci T3, T4, and T5 represent the high values ​​of the segmentation and extraction results, respectively.

[0086] It should be noted that if any of the above conditions for determining whether a steel ball exists are not met, it is determined that no steel ball exists, the target position of the corresponding projected image is recorded as 0, and the process moves on to the next set of projected images; if any of the above conditions for determining whether a steel ball exists are met, the target position of the steel ball is calculated.

[0087] Furthermore, the target position of the steel ball is calculated as follows:

[0088]

[0089] Where P represents the target position of the current projected image, and n ci Y represents the total number of targets in the segmentation and extraction results. cij This represents the vertical coordinate of the j-th point in the segmentation and extraction result.

[0090] In one embodiment of the present invention, the second calculation module 40 can calculate the target coefficient of each group of projected images using the following formula:

[0091] V i =|P i+1 -P i |,i=1,2,...,N

[0092] Among them, V i (i = 1, 2, ..., N) represents the target coefficient of the i-th group of projected images, |...| represents taking the absolute value, P i Let N represent the target position of the i-th group of projected images, and N represent the total number of projected images.

[0093] It should be noted that the target coefficients of each set of projected images can reflect the motion trajectory of the projected images containing the steel ball. Therefore, these coefficients can serve as a benchmark for constructing the panoramic track. For example, corresponding to... Figure 2 The projection image of the dental arch model shown, if T1 is 3, T2 is 4, T3 is 20, T4 is 4, and T5 is 0.92, yields the following results: Figure 3 The target coefficient results are shown.

[0094] In one embodiment of the present invention, the third calculation module 50 can be used to determine the node positions of dental image capture based on the target coefficient, and then use a spline interpolation algorithm to interpolate between the node positions to determine the panoramic track of dental image capture.

[0095] More specifically, the number of node positions corresponds to the number of steel balls, for example, 27, and the node positions are calculated as follows:

[0096]

[0097] Where k represents the index of the steel ball, 1≤k≤27, round(...) represents the nearest integer value, and n Bk This represents the number of projection groups covered by the k-th steel ball. This represents the index of the projected image covered by the k-th steel ball. N represents the target coefficient of the projected image covered by the k-th steel ball. xk N represents the index of the projected image corresponding to the k-th node position. yk This represents the coefficient corresponding to the k-th node.

[0098] Furthermore, after calculating the node positions, the target coefficients of the first and last sets of projected images can be initialized. Then, a cubic B-spline interpolation algorithm can be used to interpolate the node positions of all projected images, and the number of points inserted between node positions is:

[0099] In k =N x(k+1) -N xk -1.

[0100] Furthermore, the panoramic track for dental image capture can be determined based on the node positions of the dental images and the insertion points between the node positions.

[0101] The beneficial effects of this invention are as follows:

[0102] 1) This invention does not require prior knowledge of the corresponding dental panoramic track, nor does it require the establishment of a corresponding geometric model and a complex mathematical derivation process under that model. It can obtain the final panoramic track based on its projection image using only a pre-constructed dental arch model. The calculation process is simple and has better adaptability.

[0103] 2) This invention can achieve results comparable to commonly used geometrically constrained track generation schemes using a simpler principle process, thereby reducing the reliance on knowledge of the motion trajectory of the dental panoramic machine. Furthermore, the panoramic track generation process takes less time, which in turn improves the operating efficiency of the entire dental panoramic reconstruction system.

[0104] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. "A plurality of" means two or more, unless otherwise explicitly specified.

[0105] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0106] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0107] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

Claims

1. A method for generating panoramic tracks from dental images, characterized in that, Includes the following steps: Construct a dental arch model, wherein the dental arch model includes multiple tooth simulation points; Obtain multiple sets of projection images of the dental arch model; Determine the target location of each simulated tooth point in each set of the projected images; Determine the target coefficient for each group of projected images based on the target location; The panoramic track for dental image capture is determined based on the target coefficients. The step of determining the panoramic track for dental image capture based on the target coefficient specifically includes: determining the node positions of the dental image capture based on the target coefficient; and using a spline interpolation algorithm to interpolate between the node positions to determine the panoramic track for dental image capture. The target coefficients for each group of projected images are calculated as follows: V i =|P i+1 -P i |,i=1,2,...,N Among them, V i (i = 1, 2, ..., N) represents the target coefficient of the i-th group of projected images, |...| represents taking the absolute value, P i The i-th group of projected images represents the target position, and N represents the total number of projected images.

2. The panoramic track generation method for dental image acquisition according to claim 1, characterized in that, The dental arch model is a steel ball dental arch model, and a steel ball is set for each simulated tooth point in the steel ball dental arch model.

3. The panoramic track generation method for dental image acquisition according to claim 2, characterized in that, Determining the target location of each simulated tooth point in each group of projected images specifically includes the following steps: Preprocess each group of projected images; Segment and extract each group of preprocessed projection images; Determine whether the steel ball exists in each group of projected images after segmentation and extraction; If it exists, then calculate the target position of the steel ball.

4. The panoramic track generation method for dental image acquisition according to claim 3, characterized in that, The step of determining whether the steel ball exists in each group of projected images after segmentation and extraction specifically includes the following steps: Determine whether there is a non-suspected target in each group of projected images after segmentation and extraction; If they exist, then remove the non-suspected targets; Determine whether the steel ball exists in each group of projected images after removing the suspected target; If it exists, then calculate the target position of the steel ball.

5. The panoramic track generation method for dental image acquisition according to claim 4, characterized in that, The criteria for determining whether the non-suspected target exists are as follows: (A(C i )<T1)∪(No(C ij )<T2), Among them, A(C i Ne(C) represents the area of ​​the segmented extraction result. ij ) represents the neighborhood target statistics of the j-th pixel in the segmentation extraction result, where n ci T1 and T2 represent the target sum of the segmentation and extraction results, and are experimental values.

6. The panoramic track generation method for dental image acquisition according to claim 5, characterized in that, The conditions for determining whether the steel ball exists are as follows: Among them, W ci H represents the width of the segmentation and extraction result. ci This indicates the high level of segmentation and extraction results; T3, T4, and T5 are experimental values. If any of the above conditions for determining the presence of a steel ball are met, then the target position of the steel ball is calculated.

7. The panoramic track generation method for dental image acquisition according to claim 6, characterized in that, The target position of the steel ball is calculated as follows: Where P represents the target position of the current projected image, and n ci Y represents the total number of targets in the segmentation and extraction results. cij This represents the vertical coordinate of the j-th point in the segmentation and extraction result.

8. A panoramic track generation device for dental image capture, characterized in that, include: A modeling module is used to construct a dental arch model, wherein the dental arch model includes multiple tooth simulation points; The acquisition module is used to acquire multiple sets of projection images of the dental arch model; A first calculation module is used to determine the target position of each simulated tooth point in each group of projected images; The second calculation module is used to determine the target coefficients of each group of projected images based on the target location. The third calculation module is used to determine the panoramic track for dental image capture based on the target coefficients. The third calculation module is specifically used for: determining the node positions of dental image capture based on the target coefficients; and using a spline interpolation algorithm to interpolate between the node positions to determine the panoramic track for dental image capture. The target coefficients for each group of projected images are calculated as follows: V i =|P i+1 -P i |,i=1,2,...,N Among them, V i (i = 1, 2, ..., N) represents the target coefficient of the i-th group of projected images, |...| represents taking the absolute value, P i The i-th group of projected images represents the target position, and N represents the total number of projected images.

Images