A denture point cloud ICP registration method, system, device and storage medium based on maximum overlap rate

Abstract

The present invention relates to a method, system, device, and storage medium for ICP registration of denture point clouds based on maximum overlap. The method constructs a source point cloud and a target point cloud and calculates the overlap ratio using a KD-tree to search for the nearest neighbor between them. If the overlap ratio falls below a threshold, the algorithm iterates and calculates a new registration source point cloud until a stopping condition is met. The algorithm then constructs a heat map to display areas of inconsistency between the denture design model and the processed model. Finally, the denture is modified based on these inconsistencies.

Description

Technical Field

[0001] The present invention relates to a denture point cloud ICP registration method, system, device and storage medium based on maximum overlap rate, belonging to the fields of computer vision, image processing and digital stomatology, and particularly to industrial denture detection. Background Art

[0002] Denture inspection is an essential step in denture fabrication. Due to machining errors and manual measurement errors, inconsistencies may occur between the denture fabrication model and the designed model. These discrepancies directly impact the clinical suitability of the denture. Accurately detecting inconsistencies between the denture fabrication model and the designed model is crucial for providing precise guidance to the denture fabricator during denture fabrication.

[0003] The commonly used method at present is to use the ICP algorithm for denture point cloud registration. However, it takes minimizing the mean square error of all point pairs in the point cloud as the constraint condition, only considers the distance relationship between points and global registration, ignores the distribution of points and local characteristics, cannot reflect the quality of the registration results of the denture processing model and the design model, has no direct constraint effect, does not meet the requirement of maximizing the overlapping area of ​​denture registration, and cannot accurately locate inconsistent areas. Summary of the Invention

[0004] In order to solve the above problems in the prior art, the present invention proposes a denture point cloud ICP registration method and system based on maximum overlap rate.

[0005] The technical solutions of the present invention are as follows:

[0006] In one aspect, the present invention provides a denture point cloud ICP registration method based on maximum overlap ratio, characterized in that it comprises the following steps:

[0007] Scan the denture design model and the denture processing model to obtain the target point cloud and source point cloud respectively. Search for the nearest neighbor of each point in the source point cloud in the target point cloud, and construct a first point set with a set of corresponding points as elements. Similarly, search for the nearest neighbor of each point in the target point cloud in the source point cloud to construct a second point set. The intersection of the first and second point sets is taken as the third point set.

[0008] Set a tolerance range, and consider the elements whose distance between corresponding points in the third point set is less than the tolerance range as coincident points. Calculate the overlap rate based on the number of coincident points and the total number of point clouds.

[0009] Set the overlap rate threshold. Before each iterative transformation, determine whether the current overlap rate is less than the threshold. If it is greater than the threshold, output the current registration source point cloud. If it is less than the threshold, perform iterative transformation on the source point cloud. After each iterative transformation, calculate and determine whether the overlap rate of the new source point cloud is less than the overlap rate of the previous generation and whether the number of iterations is less than the maximum number of iterations. If the conditions are met, continue the iteration. If only one or both conditions are met, stop the iteration and output the current registration source point cloud.

[0010] Corresponding points are searched based on the output registered source point cloud and target point cloud, and a heat map showing the inconsistent areas between the denture design model and the denture processing model is generated based on the distance relationship of the corresponding points.

[0011] As a preferred embodiment of the present invention, an improved ICP algorithm based on overlap ratio is adopted and a bidirectional KD-tree is used to search for the nearest neighbor point.

[0012] As a preferred embodiment of the present invention, the distance between corresponding points in the third point set is the Euclidean distance, which is calculated as follows:

[0013]

[0014] Where: dis is the Euclidean distance between the two points; x2 and x1 are the positions of the two points on the x-axis; y2 and y1 are the positions of the two points on the y-axis; z2 and z1 are the positions of the two points on the z-axis.

[0015] As a preferred embodiment of the present invention, the overlap ratio calculation formula is:

[0016]

[0017] Where: C i is the overlap ratio; N pc is the number of coincident points; N p is the total number of point clouds;

[0018] As a preferred embodiment of the present invention, the source point cloud iteration step is:

[0019] First, calculate the centroid of the source point cloud and the target point cloud respectively. The calculation formula is as follows:

[0020]

[0021]

[0022] in: represents the centroid of the source point cloud; p i represents the i-th source point; represents the centroid of the target point cloud; q i represents the i-th target point;

[0023] Then perform centroid removal on the source point cloud and the target point cloud. The calculation formula is as follows:

[0024]

[0025]

[0026] in: Indicates the coordinate point of the source point cloud after removing the centroid; Indicates the coordinate point of the target point cloud after removing the centroid;

[0027] The matrix H is constructed by removing the centroid coordinates of the source point cloud and the target point cloud, and then SVD decomposition is performed. The specific expression is as follows:

[0028]

[0029] When H is full rank,

[0030]

[0031] Corresponding to the unique U, V combination, the corresponding rotation matrix R and translation matrix t are calculated as follows:

[0032]

[0033] Apply the above relationship to the source point cloud to obtain the new source point cloud after iteration.

[0034] As a preferred embodiment of the present invention, the heat map generation step is:

[0035] Search for corresponding points based on the output registered source point cloud and target point cloud, build an index for each set of corresponding points, and extract points inside and outside the index respectively;

[0036] For the points in the index, calculate the Euclidean distance of the corresponding points and find the maximum value d max and the minimum value d min , and calculate the median d mid , the calculation formula is as follows:

[0037]

[0038] Set the points within the tolerance range to the first color. For points outside the tolerance range, use the minimum, median, and maximum values ​​in the above steps to determine the calculated distances, and map the distances from small to large to gradient color values ​​from the first color to the second color.

[0039] The points outside the index are set to the second color, and finally the two parts of the point cloud are merged to obtain the final heat map.

[0040] On the other hand, the present invention also provides a denture point cloud ICP registration system based on maximum overlap ratio, comprising the following modules:

[0041] The point set construction module scans the denture design model and the denture processing model to obtain the target point cloud and the source point cloud respectively. The module searches for the nearest neighbor of each point in the source point cloud in the target point cloud, and constructs the first point set with a set of corresponding points as elements. Similarly, the module searches for the nearest neighbor of each point in the target point cloud in the source point cloud to construct the second point set. The intersection of the first and second point sets is taken as the third point set.

[0042] The overlap rate calculation module sets a tolerance range and considers the elements with a distance between corresponding points in the third point set less than the tolerance range as coincident points. The overlap rate is calculated based on the number of coincident points and the total number of point clouds.

[0043] The source point cloud registration module sets the overlap rate threshold. Before each iterative transformation, it determines whether the current overlap rate is less than the threshold. If it is greater than the threshold, the current registered source point cloud is output. If it is less than the threshold, the source point cloud is iteratively transformed. After each iterative transformation, it is calculated and determined whether the overlap rate of the new source point cloud is less than the overlap rate of the previous generation and whether the number of iterations is less than the maximum number of iterations. If the conditions are met, the iteration continues. If only one or both conditions are met, the iteration stops and the current registered source point cloud is output.

[0044] The heat map drawing module searches for corresponding points based on the output registration source point cloud and target point cloud, and generates a heat map showing the inconsistent areas between the denture design model and the denture processing model based on the distance relationship of the corresponding points.

[0045] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for evaluating the error state of an electric energy meter as described in any embodiment of the present invention is implemented.

[0046] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for evaluating the error state of an electric energy meter as described in any embodiment of the present invention.

[0047] The present invention has the following beneficial effects:

[0048] 1. The present invention proposes an ICP registration algorithm based on overlap rate, which uses maximizing overlap rate instead of minimizing mean square error, and performs local registration with overlapping area as the optimization target. It is more in line with the requirements of denture registration, improves the registration accuracy and efficiency, and is applicable to different types of dentures.

[0049] 2. The present invention proposes an ICP registration algorithm based on overlap ratio, which uses a bidirectional KD-tree to search for nearest neighbor points, thus reducing the error caused by mismatching.

[0050] 3. The present invention uses a heat map algorithm based on correspondence to accurately mark the difference and overlap of the denture registration results, achieving an intuitive presentation of registration accuracy and distance information, which can effectively guide processing personnel to modify the denture. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is the overall flow chart of the present invention;

[0052] Figure 2 Definition of tolerance range and coincidence point of the present invention;

[0053] Figure 3 Schematic diagram of point cloud registration according to the present invention. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0055] It should be understood that the step numbers used herein are only for convenience of description and are not intended to limit the order in which the steps are to be executed.

[0056] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0057] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0058] The term "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items.

[0059] Example 1:

[0060] See also Figure 1 , a denture point cloud ICP registration method based on maximum overlap rate, comprising the following steps:

[0061] Scan the denture design model and the denture processing model to obtain the target point cloud and source point cloud respectively. Search for the nearest neighbor of each point in the source point cloud in the target point cloud, and construct a first point set with a set of corresponding points as elements. Similarly, search for the nearest neighbor of each point in the target point cloud in the source point cloud to construct a second point set. The intersection of the first and second point sets is taken as the third point set.

[0062] Set a tolerance range, and consider the elements whose distance between corresponding points in the third point set is less than the tolerance range as coincident points. Calculate the overlap rate based on the number of coincident points and the total number of point clouds.

[0063] Set the overlap rate threshold. Before each iterative transformation, determine whether the current overlap rate is less than the threshold. If it is greater than the threshold, output the current registration source point cloud. If it is less than the threshold, perform iterative transformation on the source point cloud. After each iterative transformation, calculate and determine whether the overlap rate of the new source point cloud is less than the overlap rate of the previous generation and whether the number of iterations is less than the maximum number of iterations. If the conditions are met, continue the iteration. If only one or both conditions are met, stop the iteration and output the current registration source point cloud.

[0064] Corresponding points are searched based on the output registered source point cloud and target point cloud, and a heat map showing the inconsistent areas between the denture design model and the denture processing model is generated based on the distance relationship of the corresponding points.

[0065] As a preferred implementation of this embodiment, an improved ICP algorithm based on overlap ratio is adopted and a bidirectional KD-tree is used to search for the nearest neighbor point.

[0066] As a preferred implementation of this embodiment, the distance between corresponding points in the third point set is the Euclidean distance, which is calculated as follows:

[0067]

[0068] Where: dis is the Euclidean distance between the two points; x2 and x1 are the positions of the two points on the x-axis; y2 and y1 are the positions of the two points on the y-axis; z2 and z1 are the positions of the two points on the z-axis.

[0069] As a preferred implementation of this embodiment, the overlap ratio calculation formula is:

[0070]

[0071] Where: C i is the overlap ratio; N pc is the number of coincident points; N p is the total number of point clouds;

[0072] As a preferred implementation of this embodiment, the source point cloud iteration step is:

[0073] First, calculate the centroid of the source point cloud and the target point cloud respectively. The calculation formula is as follows:

[0074]

[0075]

[0076] in: represents the centroid of the source point cloud; p i represents the i-th source point; represents the centroid of the target point cloud; q i represents the i-th target point;

[0077] Then perform centroid removal on the source point cloud and the target point cloud. The calculation formula is as follows:

[0078]

[0079]

[0080] in: Indicates the coordinate point of the source point cloud after removing the centroid; Indicates the coordinate point of the target point cloud after removing the centroid;

[0081] The matrix H is constructed by removing the centroid coordinates of the source point cloud and the target point cloud, and then SVD decomposition is performed. The specific expression is as follows:

[0082]

[0083] When H is full rank,

[0084]

[0085] For the unique combination of U and V, the corresponding rotation matrix R and translation matrix t are calculated as follows:

[0086]

[0087] Apply the above relationship to the source point cloud to obtain the new source point cloud after iteration.

[0088] As a preferred implementation of this embodiment, the heat map generation steps are:

[0089] Search for corresponding points based on the output registered source point cloud and target point cloud, build an index for each set of corresponding points, and extract points inside and outside the index respectively;

[0090] For the points in the index, calculate the Euclidean distance of the corresponding points and find the maximum value d max and the minimum value d min , and calculate the median dmid , the calculation formula is as follows:

[0091]

[0092] Set the points within the tolerance range to the first color. For points outside the tolerance range, use the minimum, median, and maximum values ​​in the above steps to determine the calculated distances, and map the distances from small to large to gradient color values ​​from the first color to the second color.

[0093] The points outside the index are set to the second color, and finally the two parts of the point cloud are merged to obtain the final heat map.

[0094] Specifically, in this embodiment:

[0095] First, we use the improved ICP algorithm based on overlap rate, introduce a tolerance range to define coincidence points, and use the maximum overlap rate of point clouds as the iterative convergence condition for registration. The specific steps are as follows:

[0096] Step S01: Input two sets of point clouds, the source point cloud is recorded as P, and the number of point clouds is recorded as N p , the target point cloud is recorded as Q, and the number of point clouds is recorded as N q .

[0097] Step S02: Use a bidirectional KD-tree to search for neighboring points. Build a KD-tree for the source point cloud P and search for the nearest neighbor of each point in the target point cloud Q to obtain the corresponding point set (p, q), where p represents a point in the source point cloud P and q represents a point in the target point cloud Q.

[0098] Step S03: Construct a KD-tree for the target point cloud Q, search for the nearest neighbor of each point in the source point cloud P, and obtain the corresponding point set (p',q'), where p' represents a point in the source point cloud P and q' represents a point in the target point cloud Q;

[0099] Step S04: Take the intersection of the point sets (p, q) and (p', q') to obtain a new point set (m, n), which is used as the final corresponding point set;

[0100] Step S05: Calculate the Euclidean distance dis for the corresponding points. The Euclidean distance calculation formula (1) in three-dimensional space is as follows:

[0101]

[0102] Step S06: Set the radius ε of the tolerance range based on experimental data and industrial requirements. Figure 2 , the corresponding points that fall into the tolerance range are regarded as the coincidence points of the point, and the number of coincidence points is recorded as N pc , the total number of point clouds is recorded as N p , use formula (2) to calculate the overlap rate C i, the initial overlap rate is set to 0;

[0103]

[0104] Step S07: according to industrial production requirements, the overlap rate threshold M_coin is set to 0.9, and it is determined whether the overlap rate calculated in the previous step is less than M_coin. If so, the next step is performed; if not, the loop is terminated and the operation ends.

[0105] Step S08: Calculate the centroids of the source point cloud and the target point cloud, denoted as The calculation formulas (3) and (4) are as follows:

[0106]

[0107]

[0108] Step S09: Remove the centroid of the source point cloud and the target point cloud to obtain The calculation formulas (5) and (6) are as follows:

[0109]

[0110]

[0111] Step S10: construct the matrix H and perform SVD decomposition on it;

[0112]

[0113] Step S11: When H is full rank,

[0114]

[0115] And corresponding to the unique combination of U and V, the corresponding rotation matrix R and translation matrix t are calculated, and the calculation formula is as follows (8);

[0116]

[0117] Step S12: Apply the transformation matrix to the source point cloud P to obtain a new source point cloud P', and determine the calculated overlap ratio C i Is it less than the previous overlap rate C? i-1 (The overlap rate calculated for the first time is compared with the initial overlap rate 0), and the number of iterations iter is less than the maximum number of iterations max_iters. If both conditions are met at the same time, the new point cloud P' replaces the source point cloud P for the next iteration; if only one condition is met, or both conditions are not met, the loop is terminated and the result is output.

[0118] Then draw a heat map. The heat map uses a color gradient from blue to red to reflect the distance between corresponding points. Blue represents points within the tolerance range, and the remaining points appear in different colors according to the distance. The closer the color is to red, the farther the distance is and the greater the difference.

[0119] The specific steps are as follows:

[0120] Step S01: Input the OR-ICP registration result and the target point cloud, search for corresponding points, build an index for each pair of corresponding points, extract points inside and outside the index and save them;

[0121] Step S02: For the points in the index, calculate the Euclidean distance of the corresponding points and find the maximum value d max and the minimum value d min , solve the median d according to formula (9) mid ;

[0122]

[0123] Step S03: Set the red, green, and blue colors. Points within the tolerance range are set to blue. Points outside the tolerance range are judged by the maximum value (max), the median value (mid), and the minimum value (min) based on the calculated distance. The distances are mapped from small to large to gradient color values ​​from blue to red for rendering.

[0124] Step S04: Points outside the index cannot be matched due to a large distance, and are rendered in red;

[0125] Step S05: Merge the two point clouds and visualize them, and the heat map is drawn.

[0126] Finally, the denture was modified by mapping the inconsistent areas in the completed thermogram.

[0127] Example 2:

[0128] This embodiment provides a denture point cloud ICP registration system based on maximum overlap ratio, including the following modules:

[0129] The point set construction module scans the denture design model and the denture processing model to obtain the target point cloud and the source point cloud respectively. The module searches for the nearest neighbor of each point in the source point cloud in the target point cloud, and constructs the first point set with a set of corresponding points as elements. Similarly, the module searches for the nearest neighbor of each point in the target point cloud in the source point cloud to construct the second point set. The intersection of the first and second point sets is taken as the third point set.

[0130] The overlap rate calculation module sets a tolerance range and considers the elements whose distance between corresponding points in the third point set is less than the tolerance range as coincident points. The overlap rate is calculated based on the number of coincident points and the total number of point clouds.

[0131] The source point cloud registration module sets the overlap rate threshold. Before each iterative transformation, it determines whether the current overlap rate is less than the threshold. If it is greater than the threshold, the current registered source point cloud is output. If it is less than the threshold, the source point cloud is iteratively transformed. After each iterative transformation, it is calculated and determined whether the overlap rate of the new source point cloud is less than the overlap rate of the previous generation and whether the number of iterations is less than the maximum number of iterations. If the conditions are met, the iteration continues. If only one or both conditions are met, the iteration stops and the current registered source point cloud is output.

[0132] The heat map drawing module searches for corresponding points based on the output registration source point cloud and target point cloud, and generates a heat map showing the inconsistent areas between the denture design model and the denture processing model based on the distance relationship of the corresponding points.

[0133] Example 3:

[0134] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method described in any embodiment of the present invention is implemented.

[0135] Example 4:

[0136] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0137] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.

[0138] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0139] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0140] In the several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), magnetic disk or optical disk, and other media that can store program code.

[0141] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention's description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A denture point cloud ICP registration method based on maximum overlap ratio, characterized in that: The following steps are involved: Scan the denture design model and the denture processing model to obtain the target point cloud and source point cloud respectively. Search for the nearest neighbor of each point in the source point cloud in the target point cloud, and construct a first point set with a set of corresponding points as elements. Similarly, search for the nearest neighbor of each point in the target point cloud in the source point cloud to construct a second point set. The intersection of the first and second point sets is taken as the third point set. Set a tolerance range, and consider the elements whose distance between corresponding points in the third point set is less than the tolerance range as coincident points. Calculate the overlap rate based on the number of coincident points and the total number of point clouds. Set the overlap rate threshold. Before each iterative transformation, determine whether the current overlap rate is less than the threshold. If it is greater than the threshold, output the current registration source point cloud. If it is less than the threshold, perform iterative transformation on the source point cloud. After each iterative transformation, calculate and determine whether the overlap rate of the new source point cloud is less than the overlap rate of the previous generation and whether the number of iterations is less than the maximum number of iterations. If the conditions are met, continue the iteration. If only one or both conditions are met, stop the iteration and output the current registration source point cloud. The source point cloud iteration steps are: First, calculate the centroid of the source point cloud and the target point cloud respectively. The calculation formula is as follows: in: represents the centroid of the source point cloud; p i represents the i-th source point; represents the centroid of the target point cloud; q i represents the i-th target point; Then perform centroid removal on the source point cloud and the target point cloud. The calculation formula is as follows: in: Indicates the coordinate point of the source point cloud after removing the centroid; Indicates the coordinate point of the target point cloud after removing the centroid; The matrix H is constructed by removing the centroid coordinates of the source point cloud and the target point cloud, and then SVD decomposition is performed. The specific expression is as follows: When H is full rank, Corresponding to the unique U, V combination, the corresponding rotation matrix R and translation matrix t are calculated as follows: Apply the above relationship to the source point cloud to obtain the iterated new source point cloud; Corresponding points are searched based on the output registered source point cloud and target point cloud, and a heat map showing the inconsistent areas between the denture design model and the denture processing model is generated based on the distance relationship of the corresponding points.

2. The method for ICP registration of denture point clouds based on maximum overlap ratio according to claim 1, characterized in that: An improved ICP algorithm based on overlap ratio is adopted and bidirectional KD-tree is used to search for the nearest neighbor points.

3. The method for ICP registration of denture point clouds based on maximum overlap ratio according to claim 1, characterized in that: The distance between corresponding points in the third point set is the Euclidean distance, which is calculated as follows: Where: dis is the Euclidean distance between the two points; x2 and x1 are the positions of the two points on the x-axis; y2 and y1 are the positions of the two points on the y-axis; z2 and z1 are the positions of the two points on the z-axis.

4. The method for ICP registration of denture point clouds based on maximum overlap ratio according to claim 1, characterized in that: The overlap rate calculation formula is: Where: C i is the overlap ratio; N pc is the number of coincident points; N p is the total number of point clouds.

5. The method for ICP registration of denture point clouds based on maximum overlap ratio according to claim 1, characterized in that: The heat map generation steps are: Search for corresponding points based on the output registered source point cloud and target point cloud, build an index for each set of corresponding points, and extract points inside and outside the index respectively; For the points in the index, calculate the Euclidean distance of the corresponding points and find the maximum value d max and the minimum value d min , and calculate the median d mid , the calculation formula is as follows: Set the points within the tolerance range to the first color. For points outside the tolerance range, use the minimum, median, and maximum values ​​in the above steps to determine the calculated distances, and map the distances from small to large to gradient color values ​​from the first color to the second color. The points outside the index are set to the second color, and finally the two parts of the point cloud are merged to obtain the final heat map.

6. A denture point cloud ICP registration system based on maximum overlap ratio, characterized by: The method according to any one of claims 1 to 5, comprising the following modules: The point set construction module scans the denture design model and the denture processing model to obtain the target point cloud and the source point cloud respectively. The module searches for the nearest neighbor of each point in the source point cloud in the target point cloud, and constructs the first point set with a set of corresponding points as elements. Similarly, the module searches for the nearest neighbor of each point in the target point cloud in the source point cloud to construct the second point set. The intersection of the first and second point sets is taken as the third point set. The overlap rate calculation module sets a tolerance range and considers the elements with a distance between corresponding points in the third point set less than the tolerance range as coincident points. The overlap rate is calculated based on the number of coincident points and the total number of point clouds. The source point cloud registration module sets the overlap rate threshold. Before each iterative transformation, it determines whether the current overlap rate is less than the threshold. If it is greater than the threshold, the current registered source point cloud is output. If it is less than the threshold, the source point cloud is iteratively transformed. After each iterative transformation, it is calculated and determined whether the overlap rate of the new source point cloud is less than the overlap rate of the previous generation and whether the number of iterations is less than the maximum number of iterations. If the conditions are met, the iteration continues. If only one or both conditions are met, the iteration stops and the current registered source point cloud is output. The heat map drawing module searches for corresponding points based on the output registration source point cloud and target point cloud, and generates a heat map showing the inconsistent areas between the denture design model and the denture processing model based on the distance relationship of the corresponding points.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images