Method and device for detecting sternum deformation based on three-dimensional point cloud data

Abstract

The present invention discloses a sternum deformation detection method and device based on three-dimensional point cloud data, wherein the method comprises: obtaining three-dimensional point cloud data of the body surface of a person with sternum deformity to be detected; shearing the three-dimensional point cloud data of the body surface of the person with sternum deformity to be detected to obtain effective three-dimensional point cloud data of the sheared thorax; extracting several cross sections of the effective three-dimensional point cloud data of the sheared thorax at equal height; performing single-section processing on each of the cross sections to obtain the offset angle value corresponding to each of the cross sections; obtaining the offset angle value corresponding to the overlap of multiple cross sections according to the offset angle value corresponding to each of the cross sections; judging whether the sternum to be detected is deformed according to the offset angle value corresponding to the overlap of multiple cross sections and the preset reasonable range of the offset angle. The present invention can safely detect sternum deformation based on three-dimensional point cloud data.

Description

Technical Field

[0001] The present invention relates to the technical field of point cloud data analysis, and in particular to a sternum deformation detection method and device based on three-dimensional point cloud data. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] Sternum deformation can easily lead to diseases such as funnel chest and pectus carinatum. Both funnel chest and pectus carinatum are congenital diseases that often occur in children. They may already exist at birth and the deformation will become more and more obvious with age. The existing methods for detecting sternum deformation, that is, checking and analyzing funnel chest and pectus carinatum, are mostly CT. CT scans can evaluate the degree of depression and symmetry of funnel chest, the degree of compression and displacement of the heart, the degree of compression of the lungs and other combined problems.

[0004] However, the traditional CT method of detecting sternal deformation has the problem of excessive radiation. Most people with sternal deformity are children, and multiple examinations are required during the diagnosis, treatment, and recovery process. Radiation has a greater impact on children. Summary of the invention

[0005] An embodiment of the present invention provides a sternum deformation detection method based on three-dimensional point cloud data, which is used to safely detect sternum deformation based on three-dimensional point cloud data. The method includes:

[0006] Acquire the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected;

[0007] Cutting the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected to obtain effective three-dimensional point cloud data of the cut thorax part;

[0008] Extract several cross sections at equal heights from the effective three-dimensional point cloud data of the cut thorax portion;

[0009] Process each cross section as a single cross section to obtain a deviation angle value corresponding to each cross section; and obtain a deviation angle value corresponding to the overlap of multiple cross sections according to the deviation angle value corresponding to each cross section;

[0010] Whether the sternum to be tested is deformed is determined based on the offset angle values ​​corresponding to the overlap of multiple sections and the pre-set reasonable range of the offset angles.

[0011] The embodiment of the present invention further provides a sternum deformation detection device based on three-dimensional point cloud data, which is used to safely detect sternum deformation based on three-dimensional point cloud data. The device includes:

[0012] An acquisition unit, used for acquiring three-dimensional point cloud data of the body surface of a person with sternal deformity to be detected;

[0013] A shearing unit, used for shearing the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected, to obtain effective three-dimensional point cloud data of the sheared thorax part;

[0014] An extraction unit is used to extract several cross sections at equal heights from the effective three-dimensional point cloud data of the cut thorax part;

[0015] The offset angle value determination unit is used to process each cross section as a single cross section to obtain the offset angle value corresponding to each cross section; and obtain the offset angle value corresponding to the overlap of multiple cross sections according to the offset angle value corresponding to each cross section;

[0016] The detection unit is used to determine whether the sternum to be detected is deformed according to the offset angle value corresponding to the overlap of multiple sections and the preset reasonable range value of the offset angle.

[0017] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned sternum deformation detection method based on three-dimensional point cloud data when executing the computer program.

[0018] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned sternum deformation detection method based on three-dimensional point cloud data is implemented.

[0019] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned sternum deformation detection method based on three-dimensional point cloud data is implemented.

[0020] In an embodiment of the present invention, a sternum deformation detection scheme based on three-dimensional point cloud data is compared with the unsafe technical scheme of detecting sternum deformation by CT scanning in the prior art, by: obtaining three-dimensional point cloud data of the body surface of a person with sternum deformity to be detected; shearing the three-dimensional point cloud data of the body surface of the person with sternum deformity to be detected to obtain effective three-dimensional point cloud data of the sheared thorax part; extracting a number of cross sections at equal heights from the effective three-dimensional point cloud data of the sheared thorax part; performing single-section processing on each of the cross sections to obtain a deviation angle value corresponding to each of the cross sections; obtaining a deviation angle value corresponding to the overlap of multiple cross sections according to the deviation angle value corresponding to each of the cross sections; judging whether the sternum to be detected is deformed according to the deviation angle values ​​corresponding to the overlap of multiple cross sections and a pre-set reasonable range of the deviation angle, thereby realizing safe detection of sternum deformation based on three-dimensional point cloud data. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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. In the drawings:

[0022] Figure 1 It is a schematic diagram of the principle of detecting sternum deformation using body surface three-dimensional point cloud data in an embodiment of the present invention;

[0023] Figure 2a It is an original data image collected by a three-dimensional laser scanner in an embodiment of the present invention; Figure 2b This is a data diagram after cutting in an embodiment of the present invention;

[0024] Figure 3 In the process of removing abnormal discrete points in a cross section in an embodiment of the present invention, the cross section is based on an irregular triangulated network diagram of a minimum enclosing rectangle, and a cross section is taken as an example here;

[0025] Figure 4a It is an original cross-sectional view in the embodiment of the present invention; Figure 4b This is a cross-sectional view after removing abnormal discrete points in an embodiment of the present invention;

[0026] Figure 5 This is a result diagram of the offset angle value calculated by overlapping multiple sections in an embodiment of the present invention;

[0027] Figure 6 A schematic diagram of setting a reasonable range value in an embodiment of the present invention;

[0028] Figure 7 Schematic diagram of the process of sternum deformation detection based on three-dimensional point cloud data in an embodiment of the present invention;

[0029] Figure 8 Schematic diagram of the structure of a device for detecting sternum deformation based on three-dimensional point cloud data in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0031] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0032] In view of the defects and shortcomings of the traditional CT method for detecting sternal deformation, the embodiment of the present invention provides a sternal deformation detection solution based on three-dimensional point cloud data. The solution is a solution for detecting sternal deformation using three-dimensional point cloud data of the body surface collected by a three-dimensional laser scanner, so as to solve the problem that the detection of sternal deformation is unsafe due to excessive radiation of traditional CT. The sternal deformation detection solution based on three-dimensional point cloud data is introduced in detail below.

[0033] Figure 7 FIG. 1 is a flow chart of sternum deformation detection based on three-dimensional point cloud data in an embodiment of the present invention. Figure 7 As shown, the method comprises the following steps:

[0034] Step 101: Acquire body surface three-dimensional point cloud data of a person with sternal deformity to be detected;

[0035] Step 102: cutting the body surface three-dimensional point cloud data of the subject with sternal deformity to be detected to obtain effective three-dimensional point cloud data of the cut thorax part;

[0036] Step 103: extracting a number of cross sections at equal heights from the effective three-dimensional point cloud data of the cut thorax portion;

[0037] Step 104: Performing single-section processing on each cross section to obtain a deviation angle value corresponding to each cross section; and obtaining a deviation angle value corresponding to the overlap of multiple cross sections according to the deviation angle value corresponding to each cross section;

[0038] Step 105: Determine whether the sternum to be inspected is deformed according to the offset angle value corresponding to the overlap of multiple sections and the preset reasonable range of the offset angle.

[0039] The sternum deformation detection method based on three-dimensional point cloud data provided by the embodiment of the present invention, when working: obtain the three-dimensional point cloud data of the body surface of the person with sternum deformity to be detected; cut the three-dimensional point cloud data of the body surface of the person with sternum deformity to be detected to obtain the effective three-dimensional point cloud data of the cut thorax part; extract a plurality of cross sections with equal height from the effective three-dimensional point cloud data of the cut thorax part; perform single-section processing on each of the cross sections to obtain the offset angle value corresponding to each of the cross sections; obtain the offset angle value corresponding to the overlap of multiple cross sections according to the offset angle value corresponding to each of the cross sections; determine whether the sternum to be detected is deformed according to the offset angle value corresponding to the overlap of multiple cross sections and the preset reasonable range value of the offset angle.

[0040] Compared with the unsafe technical solution of using CT scanning to detect sternum deformation in the prior art, the sternum deformation detection method based on three-dimensional point cloud data provided by the embodiment of the present invention can safely detect sternum deformation based on three-dimensional point cloud data. The sternum deformation detection method based on three-dimensional point cloud data is introduced in detail below.

[0041] The sternum deformation detection method based on three-dimensional point cloud data provided in the embodiment of the present invention is a method for detecting sternum deformation by using the offset angle of each cross section in the three-dimensional point cloud data. The embodiment of the present invention adopts the following scheme:

[0042] S1. Obtaining three-dimensional point cloud data of the body surface of a person suspected of having (to be detected) sternal deformity, i.e., the above step 101.

[0043] S2. Cutting the acquired three-dimensional point cloud data of the body surface of the person suspected of having sternal deformity, i.e., the above-mentioned step 102.

[0044] In one embodiment, the above step S2 cuts the acquired body surface three-dimensional point cloud data, and point cloud processing software may be used to cut out valid data of the thorax.

[0045] S3, extracting a number of cross sections at equal heights from the thorax point cloud data, i.e., the above step 103.

[0046] In one embodiment, the method of taking out a plurality of cross sections at equal height in step S3 is as follows:

[0047] The height of the entire point cloud (valid three-dimensional point cloud data) is calculated, denoted as H, and a height (preset height) that is smaller than H (the smaller meaning may be smaller than a preset value, which can be determined based on a large number of experiments) is specified, denoted as h, and the point cloud is cycled in order of height from the lowest point (the lowest point may be the part close to the direction of the person being tested) to the highest point (for example, the part close to the direction of the head of the person being tested), and a cross section is taken out every h units to obtain a number of cross sections taken out at the same height.

[0048] As can be seen from the above, in one embodiment, extracting a number of cross sections from the effective three-dimensional point cloud data of the cut thorax portion at equal heights may include:

[0049] Determining the point cloud height of the valid three-dimensional point cloud data, and setting a preset height for dividing the point cloud height into a plurality of equal parts;

[0050] The point cloud is looped from the lowest point according to the height, and a cross section is taken out at every preset height until the preset height is equal to the height of the remaining point cloud to obtain a number of cross sections taken out at the same height.

[0051] S4, processing all cross sections into single cross sections, i.e. the above step 104.

[0052] In one embodiment, the single section processing in the above step S4, taking one section as an example, specifically includes:

[0053] Eliminate outliers (because the 3D laser scanner may be penetrating when collecting data, some discrete outliers will appear inside the cross section). The cross section can be fitted using the smallest bounding rectangle triangulated irregular network (TIN, Triangulated Irregular Network) and outliers in the cross section can be eliminated.

[0054] Find the two points farthest from each other in the cross section and connect them, record them as the horizontal axis of the cross section, take out the midpoint of the horizontal axis, record it as the center point O of the cross section, draw a perpendicular line through point O to the horizontal axis, record it as the vertical axis of the cross section;

[0055] Find the two points closest to the center point O in the point cloud on both sides of the horizontal axis and connect them to point O. The line connecting the nearest point on the chest and point O is recorded as the section offset line. The acute angle formed by the offset line and the longitudinal axis of the section is recorded as the section offset angle. Calculate the angle value of the section offset angle.

[0056] As can be seen from the above, in one embodiment, performing single-section processing on each cross section to obtain the offset angle value corresponding to each cross section may include:

[0057] The irregular triangulated network with the smallest bounding rectangle is used to fit the cross section, and the abnormal points in the fitted cross section are removed to obtain the cross section after the abnormal points are removed;

[0058] For the cross section after removing the abnormal points, the horizontal axis, the center point and the vertical axis of the cross section are made; according to the horizontal axis, the center point and the vertical axis of the cross section, the deviation angle value corresponding to each cross section is obtained.

[0059] As can be seen from the above, in one embodiment, fitting a cross section using an irregular triangulated network of a minimum bounding rectangle, removing abnormal points in the fitted cross section, and obtaining a cross section after removing the abnormal points may include:

[0060] Find the maximum value in the horizontal direction, the minimum value in the horizontal direction, the maximum value in the vertical direction and the minimum value in the vertical direction of the cross-section point cloud, draw the minimum outer bounding rectangle, and draw the irregular triangulated network based on the minimum outer bounding rectangle according to the rules of the irregular triangulated network;

[0061] Traverse all triangles in the triangulated network, determine the triangle containing the smallest outer rectangle vertex, retain the other two points and line segments outside the rectangular vertices in the determined triangle, remove duplicates from all retained points, and obtain the cross section after removing abnormal points.

[0062] From the above, it can be seen that in one embodiment, for the cross section after removing the abnormal points, the cross section horizontal axis, the center point and the cross section vertical axis are obtained; according to the cross section horizontal axis, the center point and the cross section vertical axis, the offset angle value corresponding to each cross section is obtained, which may include:

[0063] After removing the abnormal points, the cross-sectional point cloud is traversed, and the points are paired in pairs. The distance between all two points is calculated by the distance formula between two points. The two points with the farthest distance are connected and recorded as the horizontal axis of the cross section. The midpoint of the horizontal axis is taken as the center point of the cross section.

[0064] Rotate the horizontal axis 90 degrees around the center point to obtain a straight line passing through the center point and perpendicular to the horizontal axis as the longitudinal axis of the cross section;

[0065] Find the two points closest to the center point in the front and rear parts of the point cloud divided by the horizontal axis, connect the two points with the center point respectively, get the front radius and the rear radius of the cross section, take the acute angle formed by the front radius and the longitudinal axis of the cross section as the cross section offset angle, and calculate the angle value of the offset angle.

[0066] S5. Setting a reasonable range value, i.e., the above step 105.

[0067] After the above step S4, each section obtains a corresponding offset angle value, and a reasonable range value is set. If the offset angle exceeds the reasonable value, it means that the sternum is deformed.

[0068] As can be seen from the above, in one embodiment, judging whether the sternum to be detected is deformed according to the offset angle values ​​corresponding to the overlap of multiple sections and the preset reasonable range of the offset angles may include:

[0069] When the offset angle value corresponding to the overlap of multiple sections exceeds a preset reasonable range of the offset angle, it is determined that the sternum to be detected is deformed.

[0070] In order to facilitate understanding of how to implement the present invention, an example is given below for detailed description.

[0071] At present, the method of detecting sternal deformation and checking children's pectus carinatum and pectus excavatum based on traditional CT has the problem of excessive radiation, and multiple examinations are required during the diagnosis, treatment and recovery process, which has a great impact on children. In view of the technical problem that the existing traditional CT radiation is too large, resulting in unsafe sternal deformation detection, an embodiment of the present invention provides a sternal deformation detection method based on three-dimensional point cloud data. The method is based on the three-dimensional point cloud data of the body surface collected by a three-dimensional laser scanner. First, the data is cut using point cloud data processing software (the present invention takes CloudCompare as an example), and then several sections are taken from the effective point cloud data after cutting. Then each section is processed as a single section (including removing abnormal points, determining the horizontal axis, vertical axis and offset angle, and calculating the offset angle value). Finally, a reasonable range value is set and it is determined whether the sternum is deformed.

[0072] The embodiment of the present invention discloses a sternum deformation detection method based on three-dimensional point cloud data. The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0073] Figure 1 The specific flow chart of the method for detecting sternum deformation using body surface three-dimensional point cloud data provided by the present invention, the specific method of the present invention comprises the following steps:

[0074] Step S1: Acquire the three-dimensional point cloud data of the body surface of the person with sternal deformity collected by a three-dimensional laser scanner. The following example is set to be based on one point cloud data. That is, in one embodiment, acquiring the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected may include: acquiring the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected collected by a three-dimensional laser scanner.

[0075] Figure 2a It is an original data image collected by a three-dimensional laser scanner in an embodiment of the present invention; Figure 2b This is a data diagram after cutting in an embodiment of the present invention.

[0076] Step S2: Cut the acquired point cloud data by using the cutting function in the point cloud processing software (CloudCompare is used as an example here) to cut the data, leaving only the valid data of the thorax below the shoulders and above the abdomen.

[0077] Step S3: extracting several cross sections of the sheared thorax portion with equal height from the effective data.

[0078] Step S3.1: Find the highest and lowest points in the point cloud and record the elevations of the two points as H max With H min Calculate the height difference between the two points, that is, the height of the point cloud, recorded as H, that is, H = H max -H min , specify an h (here h=10) that divides H equally and is smaller than H as an example.

[0079] Step S3.2: From the lowest point elevation of the point cloud, i.e. H min Start by following

[0080] h i =H min +i*h(i=1,2…,H max / h)

[0081] Enter the loop and loop to h i When extracting the elevation ratio h in the point cloud i The first small section (because there are some discrete abnormal points in the point cloud data, it is necessary to set a number of points n to be taken out. Here, n = 10 is taken as an example. If the number of points taken out is less than n, it means that some discrete points are taken out, and then continue to take points down; if the number of points taken out is greater than n, it means that the cross-section point cloud is taken out), and it will continue to cycle until h i =H maxWhen , i sections are completely removed.

[0082] Step S4: Perform single-section processing on the multiple sections taken out in the above S3, and one section is taken as an example here.

[0083] Step S4.1: Remove the abnormal points inside the cross section (because the 3D laser scanner has penetrating properties when collecting data, some discrete abnormal points will appear inside the point cloud) and fit the cross section contour.

[0084] Figure 3 In order to remove abnormal discrete points in the cross section, the cross section is based on the irregular triangulated network diagram of the minimum enclosing rectangle. Here we take a cross section as an example.

[0085] Step S4.1.1: Find the four extreme values ​​of the cross-sectional point cloud (maximum value in the horizontal direction, minimum value in the horizontal direction, maximum value in the vertical direction, and minimum value in the vertical direction, i.e., X min , X max , Y min , Y max ), draw the minimum enclosing rectangle, and then draw the irregular triangulated network based on the minimum enclosing rectangle according to the rules of irregular triangulated network.

[0086] Step S4.1.2: Traverse all triangles in the triangulation network, first determine the triangle containing the smallest outer rectangle vertex, then retain the other two points and line segments outside the rectangular vertices in these triangles, and deduplicate all the retained points, which are the cross-sectional contour points after eliminating abnormal points (according to the triangulation network rules, the rectangular vertices will only form triangles with the outer contour points, and retaining the contour points indirectly eliminates abnormal discrete points).

[0087] Figure 4a It is an original cross-sectional view in the embodiment of the present invention; Figure 4b This is a cross-sectional view after removing abnormal discrete points in an embodiment of the present invention.

[0088] Step S4.2: Draw the cross-section axis, center point, and cross-section axis after removing abnormal points, and calculate the offset angle.

[0089] Step S4.2.1: Traverse the point cloud after removing the abnormal points in the above step S4.1, pair the points in pairs, and use the distance formula between the two points

[0090]

[0091] Calculate the distance between all two points (the traversed points need to be marked as single points to avoid multiple pairings of the same point), take out the two points with the farthest distance, connect them and record them as the horizontal axis of the section; take out the midpoint of the horizontal axis and record it as the center point O of the section.

[0092] Step S4.2.2: Rotate the horizontal axis 90° around point O to obtain a straight line passing through point O and perpendicular to the horizontal axis, which is recorded as the longitudinal axis of the section. Specifically, the two end points of the horizontal axis can be rotated around point O. The specific formula is:

[0093]

[0094] (where (x 1 ,y 1 ) is the initial point, (x 2 ,y 2 ) is the point after rotation, (x 0 ,y 0 ) is the reference point and θ is the rotation angle).

[0095] Step S4.2.3: Find the two points closest to the center point O in the front and rear parts of the point cloud divided by the horizontal axis and connect them to point O respectively, record them as the front and rear radii of the section, record the acute angle formed by the front radius and the longitudinal axis of the section as the section offset angle, and calculate the angle value of the offset angle.

[0096] Figure 5 This is the result diagram of the offset angle value calculated by overlapping multiple sections.

[0097] Step S5: Setting a reasonable range of the offset angle. When the cross-sectional offset angle exceeds the reasonable range, it is determined to be sternum deformation.

[0098] Figure 6 This is a schematic diagram for setting a reasonable range of values, and the dotted area is a reasonable offset value.

[0099] The present invention also provides a sternum deformation detection device based on three-dimensional point cloud data in an embodiment, as described in the following embodiment. Since the principle of solving the problem by the device is similar to that of the sternum deformation detection method based on three-dimensional point cloud data, the implementation of the device can refer to the implementation of the sternum deformation detection method based on three-dimensional point cloud data, and the repeated parts will not be repeated.

[0100] Figure 8 FIG. 1 is a schematic diagram of the structure of a device for detecting sternum deformation based on three-dimensional point cloud data in an embodiment of the present invention. Figure 8 As shown, the device comprises:

[0101] An acquisition unit 01 is used to acquire the body surface three-dimensional point cloud data of the person with sternal deformity to be detected;

[0102] The shearing unit 02 is used to shear the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected, and obtain the effective three-dimensional point cloud data of the sheared thorax part;

[0103] Extraction unit 03, used for extracting several cross sections at equal heights from the effective three-dimensional point cloud data of the cut thorax part;

[0104] The offset angle value determination unit 04 is used to process each cross section as a single cross section to obtain the offset angle value corresponding to each cross section; and obtain the offset angle value corresponding to the overlap of multiple cross sections according to the offset angle value corresponding to each cross section;

[0105] The detection unit 05 is used to determine whether the sternum to be detected is deformed according to the offset angle value corresponding to the overlap of multiple sections and the preset reasonable range of the offset angle.

[0106] In one embodiment, the taking-out unit is specifically used for:

[0107] Determining the point cloud height of the valid three-dimensional point cloud data, and setting a preset height for dividing the point cloud height into a plurality of equal parts;

[0108] The point cloud is looped from the lowest point according to the height, and a cross section is taken out at every preset height until the preset height is equal to the height of the remaining point cloud to obtain a number of cross sections taken out at the same height.

[0109] In one embodiment, the offset angle value determination unit is specifically used to:

[0110] The irregular triangulated network with the smallest bounding rectangle is used to fit the cross section, and the abnormal points in the fitted cross section are removed to obtain the cross section after the abnormal points are removed;

[0111] For the cross section after removing the abnormal points, the horizontal axis, the center point and the vertical axis of the cross section are made; according to the horizontal axis, the center point and the vertical axis of the cross section, the deviation angle value corresponding to each cross section is obtained.

[0112] In one embodiment, an irregular triangulated network with a minimum bounding rectangle is used to fit a cross section, and abnormal points in the fitted cross section are removed to obtain a cross section after the abnormal points are removed, including:

[0113] Find the maximum value in the horizontal direction, the minimum value in the horizontal direction, the maximum value in the vertical direction and the minimum value in the vertical direction of the cross-section point cloud, draw the minimum outer bounding rectangle, and draw an irregular triangulated network based on the minimum outer bounding rectangle according to the rules of the irregular triangulated network;

[0114] Traverse all triangles in the triangulated network, determine the triangle containing the smallest outer rectangle vertex, retain the other two points and line segments outside the rectangular vertices in the determined triangle, remove duplicates from all retained points, and obtain the cross section after removing abnormal points.

[0115] In one embodiment, for the cross section after removing the abnormal points, the horizontal axis, the center point and the vertical axis of the cross section are obtained; according to the horizontal axis, the center point and the vertical axis of the cross section, the deviation angle value corresponding to each cross section is obtained, including:

[0116] After removing the abnormal points, the cross-sectional point cloud is traversed, and the points are paired in pairs. The distance between all two points is calculated by the distance formula between two points. The two points with the farthest distance are connected and recorded as the horizontal axis of the cross section. The midpoint of the horizontal axis is taken as the center point of the cross section.

[0117] Rotate the horizontal axis 90 degrees around the center point to obtain a straight line passing through the center point and perpendicular to the horizontal axis as the longitudinal axis of the cross section;

[0118] Find the two points closest to the center point in the front and rear parts of the point cloud divided by the horizontal axis, connect the two points with the center point respectively, get the front radius and the rear radius of the cross section, take the acute angle formed by the front radius and the longitudinal axis of the cross section as the cross section offset angle, and calculate the angle value of the offset angle.

[0119] In one embodiment, the detection unit is specifically used to determine that the sternum to be detected is deformed when the offset angle value corresponding to the overlap of multiple sections exceeds a preset reasonable range of the offset angle.

[0120] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned sternum deformation detection method based on three-dimensional point cloud data when executing the computer program.

[0121] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned sternum deformation detection method based on three-dimensional point cloud data is implemented.

[0122] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned sternum deformation detection method based on three-dimensional point cloud data is implemented.

[0123] In an embodiment of the present invention, a sternum deformation detection scheme based on three-dimensional point cloud data is compared with the unsafe technical scheme of detecting sternum deformation by CT scanning in the prior art, by: obtaining the body surface three-dimensional point cloud data of a person with sternum deformity to be detected; shearing the body surface three-dimensional point cloud data of the person with sternum deformity to be detected to obtain effective three-dimensional point cloud data of the sheared thorax part; extracting several cross-sections of the effective three-dimensional point cloud data of the sheared thorax part at equal height; performing single-section processing on each of the cross-sections to obtain the offset angle value corresponding to each of the cross-sections; obtaining the offset angle value corresponding to the overlap of multiple cross-sections according to the offset angle value corresponding to each of the cross-sections; judging whether the sternum to be detected is deformed according to the offset angle value corresponding to the overlap of multiple cross-sections and the pre-set reasonable range of the offset angle, so that the sternum deformation can be safely detected based on the three-dimensional point cloud data.

[0124] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0128] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A sternum deformation detection method based on three-dimensional point cloud data, characterized in that: include: Acquire the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected; Cutting the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected to obtain effective three-dimensional point cloud data of the cut thorax part; Extract several cross sections at equal heights from the effective three-dimensional point cloud data of the cut thorax portion; Process each cross section as a single cross section to obtain a deviation angle value corresponding to each cross section; and obtain a deviation angle value corresponding to the overlap of multiple cross sections according to the deviation angle value corresponding to each cross section; According to the offset angle values ​​corresponding to the overlap of multiple sections and the pre-set reasonable range of the offset angle, it is determined whether the sternum to be tested is deformed; Each of the cross sections is processed as a single cross section to obtain a deviation angle value corresponding to each of the cross sections, including: fitting the cross section using an irregular triangulated network of a minimum bounding rectangle, removing abnormal points in the fitted cross section, and obtaining a cross section after removing the abnormal points; for the cross section after removing the abnormal points, making a cross section horizontal axis, a center point, and a cross section vertical axis; and obtaining a deviation angle value corresponding to each of the cross sections according to the cross section horizontal axis, the center point, and the cross section vertical axis; Fitting a cross section using an irregular triangulated network with a minimum enclosing rectangle, removing abnormal points in the fitted cross section, and obtaining a cross section after removing the abnormal points, including: finding the maximum value in the horizontal axis direction, the minimum value in the horizontal axis direction, the maximum value in the vertical axis direction, and the minimum value in the vertical axis direction of the cross section point cloud, drawing a minimum enclosing rectangle, and drawing an irregular triangulated network based on the minimum enclosing rectangle according to the rules of the irregular triangulated network; traversing all triangles in the triangulated network, determining a triangle containing a vertex of the minimum enclosing rectangle, retaining two other points and line segments outside the vertices of the rectangle in the determined triangle, deduplicating all the retained points, and obtaining a cross section after removing the abnormal points; For the cross section after removing the abnormal points, make the cross section horizontal axis, center point and cross section vertical axis; according to the cross section horizontal axis, center point and cross section vertical axis, obtain the offset angle value corresponding to each cross section, including: traversing the cross section point cloud after removing the abnormal points, pairing the points in pairs, calculating the distance between all two points by the distance formula between two points, taking out the two points with the farthest distance and connecting them, and recording them as the cross section horizontal axis; taking the midpoint of the horizontal axis as the center point of the cross section; rotating the horizontal axis 90 degrees around the center point, and obtaining a straight line passing through the center point and perpendicular to the horizontal axis as the cross section vertical axis; respectively finding the two points closest to the center point in the front and rear parts of the point cloud divided by the horizontal axis, connecting the two points with the center point respectively, obtaining the front radius and the rear radius of the cross section, taking the acute angle formed by the front radius and the longitudinal axis of the cross section as the cross section offset angle, and calculating the angle value of the offset angle.

2. The method according to claim 1, characterized in that Extract several cross sections from the effective 3D point cloud data of the cut thorax at equal heights, including: Determining the point cloud height of the valid three-dimensional point cloud data, and setting a preset height for dividing the point cloud height into a plurality of equal parts; The point cloud is looped from the lowest point according to the height, and a cross section is taken out at every preset height until the preset height is equal to the height of the remaining point cloud to obtain a number of cross sections taken out at the same height.

3. The method according to claim 1, characterized in that According to the offset angle values ​​corresponding to the overlap of multiple sections and the pre-set reasonable range of the offset angle, it is determined whether the sternum to be tested is deformed, including: When the offset angle value corresponding to the overlap of multiple sections exceeds a preset reasonable range of the offset angle, it is determined that the sternum to be detected is deformed.

4. A sternum deformation detection device based on three-dimensional point cloud data, characterized in that: include: An acquisition unit, used for acquiring three-dimensional point cloud data of the body surface of a person with sternal deformity to be detected; A shearing unit, used for shearing the three-dimensional point cloud data of the body surface of the person with sternal deformity to be detected, to obtain effective three-dimensional point cloud data of the sheared thorax part; An extraction unit is used to extract several cross sections at equal heights from the effective three-dimensional point cloud data of the cut thorax part; The offset angle value determination unit is used to process each cross section as a single cross section to obtain the offset angle value corresponding to each cross section; and obtain the offset angle value corresponding to the overlap of multiple cross sections according to the offset angle value corresponding to each cross section; The detection unit is used to determine whether the sternum to be detected is deformed according to the offset angle value corresponding to the overlap of multiple sections and the preset reasonable range of the offset angle; Each of the cross sections is processed as a single cross section to obtain a deviation angle value corresponding to each of the cross sections, including: fitting the cross section using an irregular triangulated network of a minimum bounding rectangle, removing abnormal points in the fitted cross section, and obtaining a cross section after removing the abnormal points; for the cross section after removing the abnormal points, making a cross section horizontal axis, a center point, and a cross section vertical axis; and obtaining a deviation angle value corresponding to each of the cross sections according to the cross section horizontal axis, the center point, and the cross section vertical axis; Fitting a cross section using an irregular triangulated network with a minimum enclosing rectangle, removing abnormal points in the fitted cross section, and obtaining a cross section after removing the abnormal points, including: finding the maximum value in the horizontal axis direction, the minimum value in the horizontal axis direction, the maximum value in the vertical axis direction, and the minimum value in the vertical axis direction of the cross section point cloud, drawing a minimum enclosing rectangle, and drawing an irregular triangulated network based on the minimum enclosing rectangle according to the rules of the irregular triangulated network; traversing all triangles in the triangulated network, determining a triangle containing a vertex of the minimum enclosing rectangle, retaining two other points and line segments outside the vertices of the rectangle in the determined triangle, deduplicating all the retained points, and obtaining a cross section after removing the abnormal points; For the cross section after removing the abnormal points, make the cross section horizontal axis, center point and cross section vertical axis; according to the cross section horizontal axis, center point and cross section vertical axis, obtain the offset angle value corresponding to each cross section, including: traversing the cross section point cloud after removing the abnormal points, pairing the points in pairs, calculating the distance between all two points by the distance formula between two points, taking out the two points with the farthest distance and connecting them, and recording them as the cross section horizontal axis; taking the midpoint of the horizontal axis as the center point of the cross section; rotating the horizontal axis 90 degrees around the center point, and obtaining a straight line passing through the center point and perpendicular to the horizontal axis as the cross section vertical axis; respectively finding the two points closest to the center point in the front and rear parts of the point cloud divided by the horizontal axis, connecting the two points with the center point respectively, obtaining the front radius and the rear radius of the cross section, taking the acute angle formed by the front radius and the longitudinal axis of the cross section as the cross section offset angle, and calculating the angle value of the offset angle.

5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

7. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images