Point cloud registration method, device, electronic device and storage medium

Abstract

The embodiments of the present invention disclose a point cloud registration method, device, electronic device and storage medium. The method may include: obtaining a first anchor point manually selected in a first target point cloud image, and a second anchor point manually selected in a second target point cloud image corresponding to the first anchor point; determining a first registration point from the first target point cloud image according to the first anchor point, and determining a second registration point from the second target point cloud image according to the second anchor point, wherein the first registration point and the second registration point are corresponding registration points; using a preset iterative closest point algorithm, based on the first anchor point and the first registration point, and the second anchor point and the second registration point, register the first target point cloud image with the second target point cloud image. The technical solution of the embodiments of the present invention can realize fast point cloud registration.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of point cloud processing technology, and in particular to a point cloud registration method, device, electronic device and storage medium. Background Art

[0002] At present, cone beam computed tomography (CBCT) technology is widely used in oral surgery. It should be noted that in some applications, two CBCT data, specifically, point cloud images obtained based on the two CBCT data, need to be registered.

[0003] However, the currently used point cloud registration scheme has the problem of low efficiency, which needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present invention provide a point cloud registration method, device, electronic device and storage medium for rapid point cloud registration.

[0005] According to one aspect of the present invention, a point cloud registration method is provided, which may include:

[0006] Obtaining a first anchor point manually selected in the first target point cloud image, and a second anchor point manually selected in the second target point cloud image corresponding to the first anchor point;

[0007] Determine a first registration point from the first target point cloud image according to the first anchor point, and determine a second registration point from the second target point cloud image according to the second anchor point, wherein the first registration point and the second registration point are corresponding registration points;

[0008] The first target point cloud image and the second target point cloud image are registered based on the first anchor point and the first registration point, and the second anchor point and the second registration point by using a preset iterative closest point algorithm.

[0009] According to another aspect of the present invention, a point cloud registration device is provided, which may include:

[0010] An anchor point acquisition module, used to acquire a first anchor point manually selected in the first target point cloud image, and a second anchor point manually selected in the second target point cloud image corresponding to the first anchor point;

[0011] A registration point determination module, configured to determine a first registration point from a first target point cloud image according to a first anchor point, and to determine a second registration point from a second target point cloud image according to a second anchor point, wherein the first registration point and the second registration point are corresponding registration points;

[0012] The point cloud registration module is used to register the first target point cloud image with the second target point cloud image based on the first anchor point and the first registration point, and the second anchor point and the second registration point by using a preset iterative closest point algorithm.

[0013] According to another aspect of the present invention, there is provided an electronic device, which may include:

[0014] at least one processor; and

[0015] a memory communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor implements the point cloud registration method provided by any embodiment of the present invention when executing the computer program.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer instructions are stored, and the computer instructions are used to enable a processor to implement the point cloud registration method provided by any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains the first anchor point manually selected in the first target point cloud image and the second anchor point manually selected in the second target point cloud image corresponding to the first anchor point, so as to automatically determine the remaining registration points based on these anchor points; according to the first anchor point, the first registration point is determined from the first target point cloud image, and according to the second anchor point, the second registration point corresponding to the first registration point is determined from the second target point cloud image. The automatic determination of the registration points can make it unnecessary to manually select the remaining registration points except the anchor points, which helps to improve the efficiency of point cloud registration; the first target point cloud image and the second target point cloud image are registered based on the manually selected and automatically determined registration points using the preset ICP algorithm. The above technical solution reduces the number of manually selected points by automatically determining the remaining registration points on the basis of the manually selected anchor points, thereby reducing the time consumption of manually selecting points, thereby improving the efficiency of point cloud registration.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a point cloud registration method provided according to an embodiment of the present invention;

[0022] Figure 2 is a flow chart of another point cloud registration method provided according to an embodiment of the present invention;

[0023] Figure 3 is a flow chart of another point cloud registration method provided according to an embodiment of the present invention;

[0024] Figure 4 is a structural block diagram of a point cloud registration device provided according to an embodiment of the present invention;

[0025] Figure 5 It is a structural schematic diagram of an electronic device for implementing the point cloud registration method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. The situations of "target", "original", etc. are similar and will not be repeated here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Before introducing the embodiments of the present invention, an exemplary description of the currently used point cloud registration scheme is first given to better understand why the point cloud registration scheme is inefficient, and further to better understand why the point cloud registration process described in the embodiments of the present invention can solve this problem.

[0029] For example, the iterative closest point (ICP) algorithm can be used for point cloud registration. Specifically, the same position on the two point cloud images is manually clicked, and after manually clicking multiple pairs of registration points, the two point cloud images can be directly matched based on these registration points through the ICP algorithm. Obviously, this implementation solution that requires manually clicking multiple pairs of registration points is time-consuming and needs to be improved.

[0030] Figure 1 : is a flow chart of a point cloud registration method provided in an embodiment of the present invention. This embodiment is applicable to point cloud registration, and in particular to the case of registering point cloud images obtained based on CBCT data. The method can be executed by a point cloud registration device provided in an embodiment of the present invention, which can be implemented by software and / or hardware, and can be integrated in an electronic device, which can be various user terminals or servers.

[0031] See also Figure 1 The method of the embodiment of the present invention specifically includes the following steps:

[0032] S110, obtaining a first anchor point manually selected in the first target point cloud image, and a second anchor point manually selected in the second target point cloud image corresponding to the first anchor point.

[0033] The first target point cloud image and the second target point cloud image can be understood as two point cloud images to be registered, and all points in the point cloud images can be referred to as target points.

[0034] Here, taking the first target point cloud image as an example, the first anchor point can be understood as a target point manually selected in the first target point cloud image, which is used as a registration point in the subsequent registration process of the two point cloud images, and more importantly, is used to automatically determine (or generate) the remaining registration points from the first target point cloud image. The number of the first anchor point can be one or more, and in particular, can be one, so as to reduce the workload of manual selection as much as possible, thereby improving the efficiency of point cloud registration.

[0035] The second anchor point is similar to the first anchor point and will not be described in detail here.

[0036] It should be noted that the first anchor point and the second anchor point are corresponding registration points, that is, the two correspond to the same position on their respective target point cloud images.

[0037] Get the first anchor point and the second anchor point.

[0038] S120. Determine a first registration point from the first target point cloud image according to the first anchor point, and determine a second registration point from the second target point cloud image according to the second anchor point, wherein the first registration point and the second registration point are corresponding registration points.

[0039] Among them, the first registration point can be understood as a target point in the first target point cloud image, and the target point is used as a registration point in the subsequent registration process of the two point cloud images. The number of first registration points can be one or more, and in particular, it can be multiple, which helps to ensure the accuracy of point cloud registration. In practical applications, optionally, when there are multiple first registration points, the multiple first registration points can be distributed in a concentrated manner or in a dispersed manner. Compared with the former, the latter can better ensure the accuracy of point cloud registration; the multiple first registration points can be distributed unevenly or evenly. Compared with the former, the latter can better ensure the accuracy of point cloud registration. According to the first anchor point, the first registration point is automatically determined from the first target point cloud image.

[0040] The second registration point is similar to the first registration point and will not be described in detail here.

[0041] It should be noted that each first registration point corresponds one-to-one to each second registration point. In other words, for each first registration point in each first registration point, there is a second registration point in each second registration point that uniquely corresponds to the first registration point, and these two registration points correspond to the same position on their respective target point cloud images.

[0042] S130. Using a preset iterative closest point algorithm, based on the first anchor point and the first registration point, and the second anchor point and the second registration point, register the first target point cloud image with the second target point cloud image.

[0043] Among them, the first anchor point corresponds to the second anchor point, and the first registration point corresponds to the second registration point, that is, they are corresponding registration points on the two point cloud images. Therefore, the preset ICP algorithm can be used to realize the registration of the two point cloud images based on these registration points.

[0044] The technical solution of the embodiment of the present invention obtains the first anchor point manually selected in the first target point cloud image and the second anchor point manually selected in the second target point cloud image corresponding to the first anchor point, so as to automatically determine the remaining registration points based on these anchor points; according to the first anchor point, the first registration point is determined from the first target point cloud image, and according to the second anchor point, the second registration point corresponding to the first registration point is determined from the second target point cloud image. The automatic determination of the registration points can make it unnecessary to manually select the remaining registration points except the anchor points, which helps to improve the efficiency of point cloud registration; the first target point cloud image and the second target point cloud image are registered based on the manually selected and automatically determined registration points using the preset ICP algorithm. The above technical solution reduces the number of manually selected points by automatically determining the remaining registration points on the basis of the manually selected anchor points, thereby reducing the time consumption of manually selecting points, thereby improving the efficiency of point cloud registration.

[0045] In addition, considering that errors are inevitable in manual point selection, the above technical solution can avoid the failure of point cloud registration due to inaccurate registration points (i.e., the corresponding registration points are in different positions in the two point cloud images) by reducing the number of manual point selection, thereby improving the success rate of point cloud registration.

[0046] An optional technical solution, the above point cloud registration method further includes:

[0047] Obtaining a first initial point cloud image and a second initial point cloud image of a target oral cavity;

[0048] For a target jaw in a target oral cavity, based on the target jaw, a first initial point cloud image is segmented to obtain a first target point cloud image, and a second initial point cloud image is segmented to obtain a second target point cloud image, wherein the target jaw is an upper jaw or a lower jaw.

[0049] The target oral cavity can be understood as the oral cavity represented by the two target point cloud images. In combination with the application scenarios that may be involved in the embodiments of the present invention, it can be particularly understood as the oral cavity that needs surgery. The first initial point cloud image and the second initial point cloud image are point cloud images initially obtained for the target oral cavity. In combination with the application scenarios that may be involved in the embodiments of the present invention, it can be particularly understood as point cloud images that simultaneously include the upper jaw and the lower jaw in the target oral cavity. The first initial point cloud image and the second initial point cloud image are obtained.

[0050] The target jaw can be understood as the upper jaw or the lower jaw in the target oral cavity. The target jaw is segmented from the first initial point cloud image to obtain a first target point cloud image, that is, the first target point cloud image can be understood as the part of the first initial point cloud image that represents the target jaw. In practical applications, optionally, the above-mentioned image segmentation process can be implemented by means of threshold segmentation or artificial intelligence (AI) segmentation, which can be set according to actual needs and is not specifically limited here.

[0051] The second target point cloud image is similar to the first target point cloud image and will not be described in detail here.

[0052] The above technical solution can perform target jaw-related processing based on the target point cloud image by segmenting the target point cloud image where the target jaw is located from the initial point cloud image to meet actual processing requirements.

[0053] On this basis, optionally, a first initial point cloud image and a second initial point cloud image of the target oral cavity are obtained, including:

[0054] Acquire first cone-beam computerized tomography data and second cone-beam computerized tomography data of a target oral cavity;

[0055] converting the first cone-beam computerized tomography data into first point cloud data, and converting the second cone-beam computerized tomography data into second point cloud data;

[0056] The first point cloud data is reconstructed to obtain a first initial point cloud image of the target oral cavity, and the second point cloud data is reconstructed to obtain a second initial point cloud image of the target oral cavity.

[0057] Among them, the first CBCT data and the second CBCT data can be understood as the CBCT data obtained for the target oral cavity respectively. In combination with the application scenarios that may be involved in the embodiments of the present invention, for example, one of the two can be the implant planning CBCT data that the patient has completed and the other is the CBCT data scanned when the patient wears the splint on the day of surgery.

[0058] The first CBCT data is converted into first point cloud data, and then the first point cloud data is reconstructed, especially three-dimensionally, to obtain a first initial point cloud image. Similarly, the second CBCT data is converted into second point cloud data, and then the second point cloud data is reconstructed, especially three-dimensionally, to obtain a second initial point cloud image. In combination with the application scenarios that may be involved in the embodiments of the present invention, optionally, the reconstructed point cloud image is a point cloud model, which is a point cloud model composed of multiple points.

[0059] The above technical solution realizes the effective conversion from CBCT data to the initial point cloud image.

[0060] Figure 2 It is a flow chart of another point cloud registration method provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, according to the first anchor point, a first registration point is determined from the first target point cloud image, which may include: according to the first anchor point, a plurality of uniformly distributed first registration points are determined from the first target point cloud image, wherein each first registration point and each second registration point are one-to-one corresponding registration points. Among them, the explanations of the terms that are the same as or corresponding to the above-mentioned embodiments are not repeated here.

[0061] See also Figure 2 The method of this embodiment may specifically include the following steps:

[0062] S210, obtaining a first anchor point manually selected in the first target point cloud image, and a second anchor point manually selected in the second target point cloud image corresponding to the first anchor point.

[0063] S220. According to the first anchor point, determine a plurality of uniformly distributed first registration points from the first target point cloud image, and according to the second anchor point, determine a plurality of uniformly distributed second registration points from the second target point cloud image, wherein each first registration point and each second registration point are one-to-one corresponding registration points.

[0064] There are multiple first registration points, and each first registration point is evenly distributed in the space where the first target point cloud image is located. Correspondingly, there are multiple second registration points, and each second registration point is evenly distributed in the space where the second target point cloud image is located. Moreover, each first registration point corresponds to each second registration point one by one, that is, the first registration point and the second registration point appear in pairs, so as to perform point cloud registration based on this.

[0065] S230. Using a preset iterative closest point algorithm, based on the first anchor point and each first registration point, and the second anchor point and each second registration point, register the first target point cloud image with the second target point cloud image.

[0066] The technical solution of the embodiment of the present invention helps to improve the accuracy of point cloud registration by automatically determining multiple registration points, especially multiple uniformly distributed registration points, from the target point cloud image.

[0067] Figure 3It is a flow chart of another point cloud registration method provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, according to the first anchor point, a plurality of evenly distributed first registration points are determined from the first target point cloud image, which may include: determining the farthest point in the first target point cloud image that is farthest from the first anchor point; between the farthest point in the first target point cloud image and the first anchor point, a plurality of evenly distributed first registration points are determined. Among them, the explanations of the terms that are the same or corresponding to the above-mentioned embodiments are not repeated here.

[0068] See also Figure 3 The method of this embodiment may specifically include the following steps:

[0069] S310, obtaining a first anchor point manually selected in the first target point cloud image, and a second anchor point manually selected in the second target point cloud image corresponding to the first anchor point.

[0070] S320, determining the farthest point in the first target point cloud image that is farthest from the first anchor point, and determining a plurality of evenly distributed first registration points between the farthest point in the first target point cloud image and the first anchor point.

[0071] The farthest point may be understood as the target point in the first target point cloud image that is farthest from the first anchor point. The number of the farthest point may be one or more, which depends on the actual setting and is not specifically limited here.

[0072] In combination with application scenarios that may be involved in the embodiments of the present invention, optionally, the farthest point may be a target point that is farthest from the first anchor point among at least some of the target points in the first target point cloud image. On this basis, for the case of partial target points, exemplarily, the partial target point is, for example, a local target point in the first target point cloud image. For example, based on the first anchor point, the first target point cloud image is divided into at least two local point cloud images, and each local point cloud image may correspond to its own partial target point, and then each local point cloud image may correspond to its own farthest point, and the farthest point can be determined from each local point cloud image, and then combined with subsequent steps, the first registration point is determined for each farthest point; another exemplary case is that in the case where the first target point cloud image is a three-dimensional image, since the first anchor point is usually a target point on the surface of the first target point cloud image, the partial target point is, for example, also a target point on the surface, thereby ensuring that the farthest point obtained thereby has the same properties as the first anchor point, thereby ensuring the accuracy of the first registration point determined subsequently; of course, the partial target point may also be a target point in other cases, which is not specifically limited here.

[0073] Furthermore, a plurality of evenly distributed first registration points are determined between the farthest point in the first target point cloud image and the first anchor point. Compared with determining concentrated first registration points around the first anchor point, determining dispersed registration points between the first anchor point and the farthest point helps to improve the accuracy of point cloud registration.

[0074] S330. Determine a plurality of evenly distributed second registration points from the second target point cloud image according to the second anchor point, wherein each first registration point is in one-to-one correspondence with each second registration point.

[0075] The determination process of the second registration point and the first registration point may be the same or different, and in particular may be the same, which helps to obtain one-to-one correspondence between the first registration point and the second registration point.

[0076] S340. Using a preset iterative closest point algorithm, based on the first anchor point and each first registration point, and the second anchor point and each second registration point, register the first target point cloud image with the second target point cloud image.

[0077] The technical solution of the embodiment of the present invention determines the farthest point in the first target point cloud image that is farthest from the first anchor point, and then determines a plurality of first registration points that are dispersedly distributed between the first anchor point and the farthest point. Compared with concentrated distribution, dispersed distribution helps to improve the point cloud registration accuracy.

[0078] An optional technical solution is to determine a plurality of uniformly distributed first registration points between the farthest point in the first target point cloud image and the first anchor point, including:

[0079] determining a first distance between the farthest point and the first anchor point;

[0080] Acquire a preset number of registration points, wherein the number of registration points represents the number of first registration points to be determined from the first target point cloud image;

[0081] Determine, according to the first distance, a second distance between two adjacent first registration points among the first registration points of the uniformly distributed number of registration points;

[0082] According to the second distance, a first registration point having a uniformly distributed number of registration points is determined between the farthest point in the first target point cloud image and the first anchor point.

[0083] The first distance can be understood as the distance between the farthest point and the first anchor point, and the distance can be represented by Euclidean distance, Mahalanobis distance, or cosine distance, etc., which can be set according to actual needs and is not specifically limited here. Determine the first distance.

[0084] The number of registration points is a preset number, which represents the number of first registration points to be determined from the first target point cloud image. The number of registration points is obtained.

[0085] On this basis, in order to determine a uniformly distributed number of first registration points between the farthest point and the first anchor point, the second distance between any two adjacent first registration points among these first registration points can be determined based on the first distance. For example, the second distance can be set to = first distance / number of registration points, and then these first registration points can be determined based on the second distance.

[0086] The above technical solution realizes the effective determination of the first registration point of the uniformly distributed registration points described above through distance calculation.

[0087] On this basis, optionally, according to the second distance, a first registration point having a uniformly distributed number of registration points is determined between the farthest point in the first target point cloud image and the first anchor point, including:

[0088] Determine a third distance between two adjacent target points in the first target point cloud image;

[0089] Determine, according to the third distance, the number of target points of the target points spanned by the second distance in the first target point cloud image;

[0090] Taking the number of target points as the step length, a first registration point having a uniformly distributed number of registration points is determined between the farthest point in the first target point cloud image and the first anchor point.

[0091] The third distance can be understood as the distance between any two adjacent target points in the first target point cloud image, and the representation of this distance can be the same as or different from the first distance, and in particular can be the same, so as to ensure the accuracy of the first registration point determination. Determine the third distance.

[0092] According to the third distance, the number of target points of the target points spanned by the second distance in the first target point cloud image is determined, for example, the number of target points can be set to be the second distance / the third distance. Furthermore, the number of target points can be used as the step length to determine the first registration point between the farthest point and the first anchor point, that is, the target point with the number of target points or the number of target points-1 between it and the last determined first registration point can be used as the currently determined first registration point, so as to achieve the sequential determination of each first registration point.

[0093] The above technical solution calculates the number of target points between two adjacent first registration points through the second distance between two adjacent first registration points and the third distance between two adjacent target points, and uses this as the step size to achieve the sequential determination of each first registration point.

[0094] In order to better understand the above-mentioned technical solutions as a whole, the following is an exemplary description of the above-mentioned technical solutions in combination with specific examples. For example, the specific implementation process of this example is as follows:

[0095] S1. The user imports CBCT data. In this example, the CBCT data includes the patient's completed implant planning CBCT data and the CBCT data scanned when the patient wore a splint on the day of surgery.

[0096] S2. Convert the two sets of CBCT data into point cloud data respectively, and perform three-dimensional reconstruction on the two sets of point cloud data respectively, so as to obtain corresponding initial point cloud images.

[0097] S3. Segment the target jaw from the two initial point cloud images respectively to obtain corresponding target point cloud images.

[0098] S4. Here, taking any one of the two target point cloud images as an example, the user can click any target point on the central axis of the target point cloud image as an anchor point. In this example, optionally, the central axis can be a central axis in the vertical direction.

[0099] S5. According to the preset number of registration points and in combination with the anchor points, the remaining uniformly distributed registration points are automatically determined from the target point cloud image.

[0100] S6. Based on the anchor points and registration points in the two target point cloud images, the two target point cloud images are registered using the ICP algorithm.

[0101] In the point cloud registration process based on oral CBCT data described in the above example, the user only needs to click an anchor point at the same position of each of the two target point cloud images, and then the remaining registration points can be automatically determined based on this, thereby improving the point cloud registration speed; moreover, the determined registration points are dispersed and evenly distributed in the three-dimensional space, thereby improving the point cloud registration accuracy.

[0102] Figure 4 This is a structural block diagram of a point cloud registration device provided in an embodiment of the present invention, and the device is used to execute the point cloud registration method provided in any of the above embodiments. The device and the point cloud registration method of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the point cloud registration device, please refer to the embodiment of the above point cloud registration method. Figure 4The device may specifically include: an anchor point acquisition module 410, a registration point determination module 420, and a point cloud registration module 430.

[0103] An anchor point acquisition module 410, used to acquire a first anchor point manually selected in the first target point cloud image, and a second anchor point manually selected in the second target point cloud image corresponding to the first anchor point;

[0104] A registration point determination module 420, configured to determine a first registration point from the first target point cloud image according to the first anchor point, and to determine a second registration point from the second target point cloud image according to the second anchor point, wherein the first registration point and the second registration point are corresponding registration points;

[0105] The point cloud registration module 430 is used to register the first target point cloud image with the second target point cloud image based on the first anchor point and the first registration point, and the second anchor point and the second registration point by using a preset iterative closest point algorithm.

[0106] Optionally, the registration point determination module 420 may include:

[0107] The first registration point determination submodule is used to determine a plurality of evenly distributed first registration points from the first target point cloud image according to the first anchor point, wherein each first registration point is a one-to-one corresponding registration point to each second registration point.

[0108] On this basis, optionally, the first registration point determination submodule may include:

[0109] A farthest point determination unit, used to determine the farthest point in the first target point cloud image that is farthest from the first anchor point;

[0110] The first registration point determination unit is used to determine a plurality of evenly distributed first registration points between the farthest point in the first target point cloud image and the first anchor point.

[0111] On this basis, optionally, the first registration point determination unit may include:

[0112] A first distance determination subunit, configured to determine a first distance between the farthest point and the first anchor point;

[0113] A registration point quantity acquisition subunit is used to acquire a preset registration point quantity, wherein the registration point quantity is the quantity of first registration points to be determined from the first target point cloud image;

[0114] A second distance determination subunit is used to determine, according to the first distance, a second distance between two adjacent first registration points among the first registration points of the uniformly distributed number of registration points;

[0115] The first registration point determination subunit is used to determine a uniformly distributed number of first registration points between the farthest point in the first target point cloud image and the first anchor point according to the second distance.

[0116] On this basis, optionally, the first registration point determination subunit is specifically used to:

[0117] Determine a third distance between two adjacent target points in the first target point cloud image;

[0118] Determine, according to the third distance, the number of target points of the target points spanned by the second distance in the first target point cloud image;

[0119] Taking the number of target points as the step length, a first registration point having a uniformly distributed number of registration points is determined between the farthest point in the first target point cloud image and the first anchor point.

[0120] Optionally, the point cloud registration device further includes:

[0121] An initial point cloud image obtaining module, used to obtain a first initial point cloud image and a second initial point cloud image of a target oral cavity;

[0122] The target point cloud image acquisition module is used to segment the first initial point cloud image based on the target jaw in the target mouth to obtain the first target point cloud image, and segment the second initial point cloud image to obtain the second target point cloud image, wherein the target jaw is the upper jaw or the lower jaw.

[0123] On this basis, optionally, an initial point cloud image acquisition module is specifically used for:

[0124] Acquire first cone-beam computerized tomography data and second cone-beam computerized tomography data of a target oral cavity;

[0125] converting the first cone-beam computerized tomography data into first point cloud data, and converting the second cone-beam computerized tomography data into second point cloud data;

[0126] The first point cloud data is reconstructed to obtain a first initial point cloud image of the target oral cavity, and the second point cloud data is reconstructed to obtain a second initial point cloud image of the target oral cavity.

[0127] The point cloud registration device provided by the embodiment of the present invention obtains the first anchor point manually selected in the first target point cloud image and the second anchor point manually selected in the second target point cloud image corresponding to the first anchor point through the anchor point acquisition module, so as to automatically determine the remaining registration points based on each anchor point; through the registration point determination module, the first registration point can be determined from the first target point cloud image according to the first anchor point, and the second registration point corresponding to the first registration point can be determined from the second target point cloud image according to the second anchor point. The automatic determination of the registration point can make it unnecessary to manually select the remaining registration points except the anchor point, which helps to improve the efficiency of point cloud registration; through the point cloud registration module, the preset ICP algorithm is used to register the first target point cloud image with the second target point cloud image based on the manually selected and automatically determined registration points. The above device reduces the number of manually selected points by automatically determining the remaining registration points on the basis of the manually selected anchor points, thereby reducing the time consumption of manually selecting points, thereby improving the efficiency of point cloud registration.

[0128] The point cloud registration device provided in the embodiment of the present invention can execute the point cloud registration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0129] It is worth noting that in the embodiment of the above-mentioned point cloud registration device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0130] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0131] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0132] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0133] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a point cloud registration method.

[0134] In some embodiments, the point cloud registration method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the point cloud registration method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the point cloud registration method in any other appropriate manner (e.g., by means of firmware).

[0135] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0136] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0137] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0138] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0139] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0140] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0141] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0142] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A point cloud registration method, characterized in that: include: Acquire a first anchor point manually selected in a first target point cloud image, and a second anchor point manually selected in a second target point cloud image corresponding to the first anchor point; Determine a first registration point from the first target point cloud image according to the first anchor point, and determine a second registration point from the second target point cloud image according to the second anchor point; Using a preset iterative closest point algorithm, based on the first anchor point and the first registration point, and the second anchor point and the second registration point, register the first target point cloud image with the second target point cloud image; Wherein, determining a first registration point from the first target point cloud image according to the first anchor point includes: Determine the farthest point in the first target point cloud image that is farthest from the first anchor point; Determine a plurality of first registration points that are evenly distributed between the farthest point in the first target point cloud image and the first anchor point; Wherein, each of the first registration points and each of the second registration points are one-to-one corresponding registration points.

2. The method according to claim 1, characterized in that: Determining a plurality of uniformly distributed first registration points between the farthest point in the first target point cloud image and the first anchor point includes: Determining a first distance between the farthest point and the first anchor point; Acquire a preset number of registration points, wherein the number of registration points is the number of first registration points to be determined from the first target point cloud image; Determine, according to the first distance, a second distance between two adjacent first registration points among the number of first registration points evenly distributed; According to the second distance, a first number of registration points having a uniform distribution is determined between the farthest point in the first target point cloud image and the first anchor point.

3. The method according to claim 2, characterized in that The step of determining, according to the second distance, a first registration point having a uniformly distributed number of registration points between the farthest point in the first target point cloud image and the first anchor point, comprises: Determine a third distance between two adjacent target points in the first target point cloud image; Determine, according to the third distance, the number of target points of the target points spanned by the second distance in the first target point cloud image; The number of target points is used as a step size, and first registration points having the number of registration points evenly distributed are determined between the farthest point in the first target point cloud image and the first anchor point.

4. The method according to claim 1, characterized in that Also includes: Obtaining a first initial point cloud image and a second initial point cloud image of a target oral cavity; For the target jaw in the target oral cavity, based on the target jaw, the first initial point cloud image is segmented to obtain the first target point cloud image, and the second initial point cloud image is segmented to obtain the second target point cloud image, wherein the target jaw is the upper jaw or the lower jaw.

5. The method according to claim 4, characterized in that The step of obtaining a first initial point cloud image and a second initial point cloud image of the target oral cavity includes: Acquire first cone-beam computerized tomography data and second cone-beam computerized tomography data of a target oral cavity; converting the first cone-beam computerized tomography data into first point cloud data, and converting the second cone-beam computerized tomography data into second point cloud data; The first point cloud data is reconstructed to obtain a first initial point cloud image of the target oral cavity, and the second point cloud data is reconstructed to obtain a second initial point cloud image of the target oral cavity.

6. A point cloud registration device, characterized in that: include: An anchor point acquisition module, used to acquire a first anchor point manually selected in a first target point cloud image, and a second anchor point manually selected in a second target point cloud image corresponding to the first anchor point; A registration point determination module, configured to determine a first registration point from the first target point cloud image according to the first anchor point, and to determine a second registration point from the second target point cloud image according to the second anchor point; a point cloud registration module, configured to register the first target point cloud image with the second target point cloud image based on the first anchor point and the first registration point, and the second anchor point and the second registration point, using a preset iterative closest point algorithm; Wherein, the registration point determination module includes: a farthest point determination unit, configured to determine a farthest point in the first target point cloud image that is farthest from the first anchor point; A first registration point determination unit, configured to determine a plurality of first registration points that are evenly distributed between the farthest point and the first anchor point in the first target point cloud image; Wherein, each of the first registration points and each of the second registration points are one-to-one corresponding registration points.

7. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor performs the point cloud registration method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the point cloud registration method as described in any one of claims 1 to 5 when executed.

Images