Method, device, electronic device and storage medium for detecting penetration of biological model

Abstract

The embodiment of the present invention provides a method, device, electronic device and storage medium for detecting mold penetration of a biological model, the method comprising: obtaining a frame image to be detected; obtaining a grid set corresponding to the part where the mold penetration action is initiated as a first type of grid set; obtaining a grid set corresponding to the part to be detected as a second type of grid set; determining a reference point in the first type of grid set as a first reference point; and determining a reference point in the second type of grid set as a second reference point; determining the mold penetration probability of the frame image to be detected based on the spatial distance between the first reference point and the second reference point; determining whether the frame image to be detected has a mold penetration phenomenon according to the mold penetration probability of the frame image to be detected. The above method reduces the labor consumption when performing mold penetration detection on a biological model and improves the detection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a biological model penetration detection method, device, electronic equipment and storage medium. Background Art

[0002] At present, due to the increasingly widespread application of 3D virtual characters in animation production and movie special effects, the production of 3D virtual characters has become increasingly important. At present, the production of 3D virtual characters mainly includes: capturing various actions of the target character through motion capture technology, and then migrating the captured actions to a specified 3D human body model, and driving the 3D human body model to perform various actions. However, there are many problems in the process of migrating the captured actions to the specified 3D human body model. For example, due to the different body shapes of the target character and the 3D human body model to be driven, the 3D human body model may be driven to perform some actions that are not in line with the principles of physics, such as Figure 1 As shown, the driven 3D human body model 110 may cause the hand 101 to extend into the limb 102. This situation where the 3D human body model is driven to perform some actions that do not conform to the principles of physics is called "piercing the model".

[0003] Currently, the problem of mold penetration is mainly solved by staff manually checking whether there is mold penetration in the human body model. When the problem of mold penetration is detected, the mold penetration of the human body model is corrected through manual correction.

[0004] However, when manually detecting whether there is any penetration in the human body model, the staff needs to perform penetration detection on the human body model in each frame of the image. This method is not only labor-intensive and time-consuming, but also has low detection efficiency. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method, device, electronic device and storage medium for detecting mold penetration of a biological model, so as to reduce the labor consumption when performing mold penetration detection on a biological model and improve the detection efficiency of mold penetration detection on a biological model.

[0006] In order to achieve the above object, an embodiment of the present invention provides a biological model penetration detection method, comprising:

[0007] Acquire a frame image to be detected, wherein the frame image to be detected includes: a part to be detected of the three-dimensional biological model and a part where the penetration action is initiated;

[0008] Obtaining a mesh set corresponding to a part of the three-dimensional biological model where the penetration action is initiated as a first-category mesh set;

[0009] For a part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained as a second type of grid set;

[0010] Determine a reference point in the first type of grid set as a first reference point; and determine a reference point in the second type of grid set as a second reference point;

[0011] Determining a penetration probability of the frame image to be detected based on a spatial distance between the first reference point and the second reference point;

[0012] Whether the frame image to be detected has a mode penetration phenomenon is determined according to the mode penetration probability of the frame image to be detected.

[0013] Further, determining whether the frame image to be detected has a mode penetration phenomenon according to the mode penetration probability of the frame image to be detected includes:

[0014] Determine whether the probability of penetration between the first reference point and the second reference point is not greater than a preset probability threshold;

[0015] If yes, determine that the frame image to be detected does not have a mode penetration phenomenon;

[0016] If not, the frame image to be detected is marked.

[0017] Furthermore, the step of obtaining a grid set corresponding to a location where a penetration action of the three-dimensional biological model is initiated includes:

[0018] Determine the coordinates of the core point of the penetration action initiation site of the three-dimensional biological model; and determine the coordinates of the reference points of each grid in the preset area where the penetration action initiation site is located;

[0019] Based on the coordinates of the reference points of each grid in the preset area where the punching action initiation site is located and the coordinates of the core point of the punching action initiation site, a first distance between the reference points of each grid and the core point of the punching action initiation site is calculated;

[0020] A set consisting of grids whose first distance is less than the first preset distance is determined as a grid set corresponding to the location where the penetration action is initiated.

[0021] Furthermore, the step of determining the coordinates of the core point of the penetration action initiation site of the three-dimensional biological model; and determining the coordinates of the reference points of each grid in the preset area where the penetration action initiation site is located, includes:

[0022] Determine the coordinates of the designated joint point in the penetration action initiation part of the three-dimensional biological model as the coordinates of the core point; and determine the coordinates of the center of gravity of each grid in the preset area where the penetration action initiation part is located as the coordinates of the reference point.

[0023] Furthermore, for the part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained as a second type of grid set, including:

[0024] Determine the coordinates of the core point of the part to be detected of the three-dimensional biological model; and determine the coordinates of the reference points of each grid in the preset area where the part to be detected is located;

[0025] Based on the coordinates of the core point of the part to be detected and the coordinates of the reference points of each grid in the preset area where the part to be detected is located, calculate the second distance between the reference point of each grid and the core point of the part to be detected;

[0026] A set consisting of grids whose second distance is less than the second preset distance is determined as a grid set corresponding to the part to be detected.

[0027] Furthermore, the step of determining the coordinates of the core point of the part to be detected of the three-dimensional biological model; and determining the coordinates of the reference points of each grid in the preset area where the part to be detected is located, includes:

[0028] The coordinates of the joint points to be detected in the part to be detected are determined as the coordinates of the core point; and the coordinates of the center of gravity of each grid in the preset area where the part to be detected is located are determined as the coordinates of the reference point.

[0029] Further, the step of determining a reference point in the first type of grid set as a first reference point; and determining a reference point in the second type of grid set as a second reference point includes:

[0030] A central point in a first type of grid set is determined as a first reference point; and a central point in a second type of grid set is determined as a second reference point.

[0031] Furthermore, the determining the penetration probability of the frame image to be detected based on the spatial distance between the first reference point and the second reference point includes:

[0032] Based on the spatial distance between the first reference point and the second reference point, and the preset weights for the first reference point and the second reference point, the probability of the frame image to be detected having a mode penetration phenomenon is determined.

[0033] Furthermore, the frame image to be detected includes a plurality of parts to be detected of the three-dimensional biological model;

[0034] The step of obtaining a grid set corresponding to the part to be detected of the three-dimensional biological model as the second type of grid set includes: obtaining a grid set corresponding to each part to be detected of the three-dimensional biological model; and taking the grid sets corresponding to each part to be detected as the second type of grid set;

[0035] The step of determining the reference point in the second type grid set as the second reference point includes: determining the reference point in the second type grid set for each second type grid set; using the reference points in each second type grid set as the second reference point;

[0036] The determining, based on the spatial distance between the first reference point and the second reference point, the penetration probability of the frame image to be detected includes:

[0037] Determine the probability of penetration between the first reference point and each second reference point according to the spatial distance between the first reference point and each second reference point;

[0038] The maximum mode penetration probability is determined as the mode penetration probability of the frame image to be detected.

[0039] In order to achieve the above-mentioned object, an embodiment of the present invention provides a biological model penetration detection device, comprising:

[0040] An image acquisition module is used to acquire a frame image to be detected, wherein the frame image to be detected includes: a part to be detected of the three-dimensional biological model and a part where the penetration action is initiated;

[0041] A first mesh acquisition module is used to acquire a mesh set corresponding to a part of the three-dimensional biological model where the penetration action is initiated, as a first type of mesh set;

[0042] A second grid acquisition module is used to acquire a grid set corresponding to a part to be detected of a three-dimensional biological model as a second type of grid set;

[0043] A reference point determination module, used to determine a reference point in a first type of grid set as a first reference point; and determine a reference point in a second type of grid set as a second reference point;

[0044] A mode penetration probability determination module, used to determine the mode penetration probability of the frame image to be detected based on the spatial distance between the first reference point and the second reference point;

[0045] The mode penetration phenomenon determination module is used to determine whether the mode penetration phenomenon occurs in the frame image to be detected according to the mode penetration probability of the frame image to be detected.

[0046] In order to achieve the above object, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus;

[0047] Memory, used to store computer programs;

[0048] The processor is used to implement any of the above-mentioned steps of the biological model penetration detection method when executing the program stored in the memory.

[0049] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any of the above-mentioned steps of the biological model penetration detection method is implemented.

[0050] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above-mentioned steps of the biological model penetration detection method.

[0051] According to the method provided by the embodiment of the present invention, a frame image to be detected is obtained, and a grid set corresponding to the part of the three-dimensional biological model where the penetration action is initiated is obtained as a first type of grid set; for the part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained as a second type of grid set; a reference point in the first type of grid set is determined as a first reference point; and a reference point in the second type of grid set is determined as a second reference point; based on the spatial distance between the first reference point and the second reference point, the penetration probability of the frame image to be detected is determined; and whether the frame image to be detected has a penetration phenomenon is determined according to the penetration probability of the frame image to be detected. Whether the frame image to be detected has a penetration phenomenon can be determined by the penetration probability of the frame image to be detected, that is, an automated screening is performed before the frame image to be detected is manually penetrated, and the frame image to be detected that is determined to have no penetration phenomenon after the automated screening can no longer be manually penetrated, thereby reducing the labor consumption when performing penetration detection on the biological model, and also improving the detection efficiency of the penetration detection on the biological model. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0053] Figure 1 A schematic diagram of a human body model with a penetration phenomenon;

[0054] Figure 2A flow chart of a biological model penetration detection method provided by an embodiment of the present invention;

[0055] Figure 3a A schematic diagram of a three-dimensional organism model;

[0056] Figure 3b A schematic diagram of a part to be inspected of a three-dimensional biological model;

[0057] Figure 4 Another schematic diagram of a three-dimensional organism model;

[0058] Figure 5 A flow chart for obtaining a first type of grid set;

[0059] Figure 6 is a schematic diagram of the human body model skeleton;

[0060] Figure 7 A flow chart for obtaining a second type of grid set;

[0061] Figure 8 Another flow chart of the biological model penetration detection method provided by the embodiment of the present invention;

[0062] Fig. 9 Another flow chart of the biological model penetration detection method provided by the embodiment of the present invention;

[0063] Fig.10 A structural diagram of a biological model penetration detection device provided by an embodiment of the present invention;

[0064] Fig.11 Another structural diagram of the biological model penetration detection device provided by an embodiment of the present invention;

[0065] Fig.12 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0067] Since the existing method of manually detecting whether there is mold penetration in a human body model not only consumes huge manpower and is time-consuming, but also has low detection efficiency, in order to reduce the manpower consumption when performing mold penetration detection on a biological model and improve the detection efficiency of mold penetration detection on a biological model, an embodiment of the present invention provides a biological model mold penetration detection method, device, electronic device and storage medium.

[0068] See also Figure 2 , Figure 2 A process for a biological model penetration detection method, comprising:

[0069] Step 201 , obtaining a frame image to be detected, wherein the frame image to be detected includes: a part to be detected of a three-dimensional biological model and a part where a penetration action is initiated.

[0070] In the embodiment of the present invention, the three-dimensional organism model can be a model of any organism including a head and limbs, such as a human body model or an animal model (cat model), etc.; the three-dimensional organism model can also be an anthropomorphic or real posture 3D model.

[0071] In the embodiment of the present invention, the part where the penetration action of the three-dimensional organism model is initiated may be the limbs of the three-dimensional organism model, such as the arms and / or legs of the three-dimensional organism model, etc. The part to be detected of the three-dimensional organism model may be: the head, spine, chest or lower limbs of the three-dimensional organism model, etc.

[0072] If the penetration action of the 3D biological model is initiated at the arm of the 3D biological model, and the part to be detected of the 3D biological model is the chest of the 3D biological model, then the frame image to be detected in this step includes the arm and chest of the 3D biological model.

[0073] Step 202: obtaining a mesh set corresponding to a part of the three-dimensional biological model where the penetration action is initiated, as a first type of mesh set.

[0074] Step 203 , for the part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained as a second type of grid set.

[0075] Step 204: determine a reference point in the first type of grid set as a first reference point; and determine a reference point in the second type of grid set as a second reference point.

[0076] Step 205: determining the penetration probability of the frame image to be detected based on the spatial distance between the first reference point and the second reference point.

[0077] Step 206: Determine whether the frame image to be detected has a mode penetration phenomenon according to the mode penetration probability of the frame image to be detected.

[0078] According to the method provided by the embodiment of the present invention, a frame image to be detected is obtained, and a grid set corresponding to the part of the three-dimensional biological model where the penetration action is initiated is obtained as a first type of grid set; for the part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained as a second type of grid set; a reference point in the first type of grid set is determined as a first reference point; and a reference point in the second type of grid set is determined as a second reference point; based on the spatial distance between the first reference point and the second reference point, the penetration probability of the frame image to be detected is determined; and whether the frame image to be detected has a penetration phenomenon is determined according to the penetration probability of the frame image to be detected. Whether the frame image to be detected has a penetration phenomenon can be determined by the penetration probability of the frame image to be detected, that is, an automated screening is performed before the frame image to be detected is manually penetrated, and the frame image to be detected that is determined to have no penetration phenomenon after the automated screening can no longer be manually penetrated, thereby reducing the labor consumption when performing penetration detection on the biological model, and also improving the detection efficiency of the penetration detection on the biological model.

[0079] In the embodiment of the present invention, the three-dimensional organism model may be composed of a plurality of mesh sets, and the shape of the mesh may be a triangle. Figure 3a A schematic diagram of a three-dimensional organism model, such as Figure 3a As shown, the three-dimensional biological model 310 is composed of a collection of multiple grids; if the part to be detected of the three-dimensional biological model 310 is its chest, Figure 3b The figure shows a schematic diagram of the part to be tested of the three-dimensional biological model.

[0080] The shape of the mesh can be triangular. Figure 4 Another schematic diagram of a three-dimensional organism model is shown in FIG. Figure 4 As shown, the three-dimensional organism model 410 is composed of a collection of multiple triangular meshes;

[0081] In the embodiment of the present invention, Figure 5 To obtain a flowchart of the first type of grid set, see Figure 5 The step of obtaining the mesh set corresponding to the part of the three-dimensional biological model where the penetration action is initiated in step 202 may specifically include:

[0082] Step 501, determining the coordinates of the core point of the penetration action initiation site of the three-dimensional biological model; and determining the coordinates of the reference points of each grid in a preset area where the penetration action initiation site is located.

[0083] In the embodiment of the present invention, the part to be detected and the part initiating the penetration action of the three-dimensional organism model may include the joint points of the three-dimensional organism. Figure 6 As shown, Figure 6Schematic diagram of the human body model skeleton, which shows multiple human body joints: 0-hips (hip joint), 1-spine_virtual (spine virtual joint), 1-leftupleg_virtual (left upper limb virtual joint), 1-rightupleg_virtual (right upper limb virtual joint), 2-spine (spine joint), 2-leftupleg (left upper limb joint), 2-rightupleg (right upper limb joint), 3-spine1 (spine joint 1), 3-leftleg (left limb joint), 3-rightleg (right limb joint), 4-spine_split (spina bifida joint), 4-leftfoot (left foot joint), 4-rightfoot (right foot joint), 5-spine2 (spine joint 2), 5-lefttoebase (left sole joint), 5-righttoebase (right sole joint), 6-neck_virtual (neck virtual joint), 6 -lefttoe_end (left toe joint point), 6-righttoe_end (right toe joint point), 6-leftshoulder_virtual (left shoulder virtual joint point), 6-rightshoulder_virtual (right shoulder virtual joint point), 7-neck (neck joint point), 7-leftshoulder (left shoulder joint point), 7-rightshoulder (right shoulder joint point), 8-head (head joint point), 8-leftshoulder_split (left shoulder split joint point), 8-rightshoulder_split (right shoulder split joint point), 9-headtop_end (head end joint point), 9-leftarm (left arm joint point), 9-rightarm (right arm joint point), 10-leftforearm (left forearm joint point), 10-rightforearm (right forearm joint point), 11-lefthand (left hand joint point), 11-righthand (right hand joint point).

[0084] In this step, the coordinates of the core point can be determined by the coordinates of the designated joint point in the starting position of the penetration action of the three-dimensional biological model. Figure 6, if the initiating part of the penetration action of the 3D organism model is the left arm, the specified joint point of the initiating part of the penetration action can be: 8-leftshoulder_split (left shoulder split joint point), 9-leftarm (left arm joint point), 10-leftforearm (left forearm joint point) or 11-lefthand (left hand joint point), etc., that is, the coordinates of 8-leftshoulder_split (left shoulder split joint point), 9-leftarm (left arm joint point), 10-leftforearm (left forearm joint point) or 11-lefthand (left hand joint point) can be determined as the coordinates of the core point. See Figure 6 If the initiating part of the penetration action of the three-dimensional biological model is the right leg, the designated joint point of the initiating part of the penetration action can be: 3-rightleg (right limb joint point), 4-rightfoot (right foot joint point), 5-righttoebase (right sole joint point) or 6-righttoe_end (right toe joint point), etc.

[0085] In this step, the coordinates of the core point can also be determined by the coordinates of any point in the starting part of the penetration action of the three-dimensional biological model. For example, if the starting part of the penetration action of the three-dimensional biological model is the left arm, the coordinates of the core point can be determined by the coordinates of any point in the left arm.

[0086] In this step, the coordinates of the center of gravity of each mesh in the preset area where the penetration action is initiated can be determined as the coordinates of the reference point. The preset area includes multiple meshes that constitute the penetration action initiation area. For example, if the shape of each mesh in the preset area is a triangle, the coordinates of the center of gravity of each mesh can be determined according to the triangle center of gravity calculation formula as the coordinates of the reference point.

[0087] In this step, the coordinates of any vertex of each mesh in the preset area where the penetration action initiation site is located can also be determined as the coordinates of the reference point.

[0088] The preset area where the punching action is initiated can be: an area with a preset distance as the center and a specified joint point of the punching action initiated area. The preset distance can be set to 2 cm or 3 cm, etc. The preset area where the punching action is initiated can also be: an area of ​​other shapes including the specified joint point of the punching action initiated area, such as a rectangular area and a square area, etc. For example, Figure 6As shown, if the initiating part of the penetration action of the three-dimensional biological model is the right leg, and the designated joint point of the initiating part of the penetration action is 6-righttoe_end (right toe joint point), then the preset area where the initiating part of the penetration action is located can be a circular area with 6-righttoe_end (right toe joint point) as the center and a radius of 2 cm.

[0089] Step 502, based on the coordinates of the reference points of each grid in the preset area where the punching action is initiated and the coordinates of the core point of the punching action initiation site, calculate the first distance between the reference points of each grid and the core point of the punching action initiation site.

[0090] Specifically, the following formula may be used to calculate the first distance between the reference point of each grid and the core point of the part where the penetration action is initiated:

[0091]

[0092] Among them, d BD Indicates the distance between the reference point B of the mesh and the core point D where the punch action is initiated, x B ,y B and z B Respectively represent the horizontal coordinate, vertical coordinate and vertical coordinate of the reference point B of the grid, x D ,y D and z D They respectively represent the horizontal, vertical and vertical coordinates of the core point where the penetration action is initiated.

[0093] Step 503: determine a set consisting of grids whose first distance is less than the first preset distance as a grid set corresponding to the location where the penetration action is initiated, as a first type of grid set.

[0094] Among them, the larger the first preset distance is, the higher the complexity of the biological model penetration detection in the embodiment of the present invention is and the better the detection accuracy is. The first preset distance can be specifically set according to the requirements of complexity and detection accuracy in actual applications. For example, the first preset distance can be set to the maximum length from the wrist to the fingertips of the biological model.

[0095] In the embodiment of the present invention, Figure 7 To obtain a flowchart for the second type of grid set, see Figure 7 , step 203 may specifically include:

[0096] Step 701, determining the coordinates of the core point of the part to be detected of the three-dimensional biological model; and determining the coordinates of the reference points of each grid in a preset area where the part to be detected is located.

[0097] In this step, the coordinates of the joint points to be detected in the part to be detected can be determined as the coordinates of the core point. For example, if the part to be detected of the three-dimensional biological model is the chest, see Figure 6 , the joint point to be detected in the part to be detected can be: 4-spine_split (spina bifida joint point) or 5-spine2 (spinal joint point 2), etc. That is, the coordinates of 4-spine_split (spina bifida joint point) or 5-spine2 (spinal joint point 2) can be determined as the coordinates of the core point of the part to be detected.

[0098] In this step, the coordinates of any point in the part to be detected can also be determined as the coordinates of the core point of the part to be detected. For example, if the part to be detected of the three-dimensional biological model is the abdomen, the coordinates of any point in the abdomen can be determined as the coordinates of the core point of the part to be detected.

[0099] In this step, the coordinates of the centroid of each grid in the preset area where the part to be detected is located can be determined as the coordinates of the reference point. The preset area where the part to be detected is located includes multiple grids constituting the part to be detected. For example, if the shape of each grid in the preset area where the part to be detected is a triangle, the coordinates of the centroid of each grid can be determined according to the triangle centroid calculation formula as the coordinates of the reference point.

[0100] In this step, the coordinates of any vertex of each grid in the preset area where the part to be detected is located can also be determined as the coordinates of the reference point of the grid.

[0101] The preset area where the part to be detected is located can be: an area with a preset distance as the center and a joint point to be detected of the part to be detected as the radius. The preset distance can be set to 4 cm or 5 cm, etc. The preset area where the part to be detected is located can also be: an area of ​​other shapes including the joint point to be detected of the part to be detected, such as a rectangular area and a square area, etc. For example, Figure 6 As shown, if the part to be detected of the three-dimensional biological model is the chest, and the joint point to be detected of the part to be detected is 4-spine_split (spina bifida joint point), then the preset area where the part to be detected is located can be a circular area with 4-spine_split (spina bifida joint point) as the center and a radius of 5 cm.

[0102] Step 702 , based on the coordinates of the core point of the part to be detected and the coordinates of the reference points of each grid in the preset area where the part to be detected is located, calculate the second distance between the reference point of each grid and the core point of the part to be detected.

[0103] Specifically, the second distance between the reference point of each grid and the core point of the part to be detected can be calculated using the following formula:

[0104]

[0105] Among them, d EF Represents the distance between the reference point E of the grid and the core point F of the part to be detected, x E ,y E and z E They represent the horizontal, vertical and vertical coordinates of the reference point E of the grid, respectively. F ,y F and z F They respectively represent the horizontal, vertical and vertical coordinates of the core point of the part to be detected.

[0106] In this step, the second distance between the reference point of each grid and the core point of the part to be detected may also be: the height difference or level difference between the reference point of each grid and the core point of the part to be detected, etc.

[0107] Step 703: determine a set consisting of grids whose second distance is less than the second preset distance as a grid set corresponding to the part to be detected, as a second type of grid set.

[0108] Among them, the larger the second preset distance is, the higher the complexity of the biological model penetration detection in the embodiment of the present invention is and the better the detection accuracy is. The second preset distance can be specifically set according to the requirements of complexity and detection accuracy in actual applications. For example, the second preset distance can be set to 3 cm.

[0109] See also Figure 8 , Figure 8 Another process of the biological model penetration detection method includes:

[0110] Steps 801 to 803 correspond to steps 201 to 203 respectively and are the same, and are not repeated here.

[0111] Step 804: determine a reference point in the first type of grid set as a first reference point; and determine a reference point in the second type of grid set as a second reference point.

[0112] In this step, a center position point in the first type of grid set can be determined as the first reference point. The first type of grid set can include multiple center position points, and the multiple center positions can specifically be: the center of gravity of each grid in the first type of grid set, or any vertex of each grid in the first type of grid set. The multiple center position points of the first type of grid set can all be used as the first reference point.

[0113] In this step, the center position point in the second type of grid set can be determined as the second reference point. The second type of grid set can include multiple center position points, and the multiple center positions can specifically be: the center of gravity of each grid in the second type of grid set, or any vertex of each grid in the second type of grid set. The multiple center position points of the second type of grid set can all be used as the second reference point.

[0114] Step 805: determining the penetration probability of the frame image to be detected based on the spatial distance between the first reference point and the second reference point.

[0115] In this step, the following formula can be used to determine the penetration probability of the frame image to be detected based on the spatial distance between the first reference point and the second reference point:

[0116]

[0117] Where P is the penetration probability of the frame image to be detected, A represents the first type of grid set, and B represents the second type of grid set; a is an element in the first type of grid set A, that is, a represents a grid in set A; b is an element in set B, that is, b represents a grid in set B, where a∈A, b∈B; P a is the coordinate of the first reference point corresponding to the grid a in the set A, P b is the coordinate of the second reference point corresponding to the grid b in the set B; d(P a , P b ) is the distance between the first reference point corresponding to grid a and the second reference point corresponding to grid b; L A is the number of elements in set A, L B is the number of elements in set B.

[0118] In the embodiment of the present invention, the probability of the frame image to be detected having the pattern penetration phenomenon can also be determined based on the spatial distance between the first reference point and the second reference point, and the preset weights for the first reference point and the second reference point. Specifically, the probability of the frame image to be detected having the pattern penetration phenomenon can be determined using the following formula:

[0119]

[0120] Where P is the penetration probability of the frame image to be detected, A represents the first type of grid set, and B represents the second type of grid set; a is an element in the first type of grid set A, that is, a represents a grid in set A; b is an element in set B, that is, b represents a grid in set B, where a∈A, b∈B; P a is the coordinate of the first reference point corresponding to the grid a in the set A, P b is the coordinate of the second reference point corresponding to the grid b in the set B; d(P a, P b ) is the distance between the first reference point corresponding to grid a and the second reference point corresponding to grid b; ω a-b P a and P b The preset weight between .

[0121] In the embodiment of the present invention, a weight can be preset for each mesh in the biological model. For example, if the part to be detected is the chest and the part where the penetration action is initiated is the hand, and if the penetration phenomenon between the hand and the chest is of particular concern in actual applications, the weights of the meshes of the hand and the chest can be set to be greater than the weights of the meshes of other parts. Figure 3b The schematic diagram of the 3D biological model in which the part to be detected is the chest is shown in FIG. Figure 3b If the breast penetration phenomenon is of particular concern in practical applications, Figure 3b The meshes in the chest region 320 of the biological model are all set with higher weights than the meshes in other parts.

[0122] Step 806, determine whether the penetration probability of the frame image to be detected is not greater than a preset probability threshold. If the determination result is yes, execute step 807; if the determination result is no, execute step 808.

[0123] The preset probability threshold may be set to 0.8 or 0.9, etc. according to actual application conditions.

[0124] Step 807: Determine whether the frame image to be detected has no pattern penetration.

[0125] Step 808: Mark the frame image to be detected.

[0126] In this step, the penetration probability of the frame image to be detected is greater than the preset probability threshold, indicating that the possibility of the frame image to be detected having a penetration phenomenon is relatively high, and then the frame image to be detected is marked so that the staff can further detect the penetration situation of the frame image to be detected.

[0127] By adopting the method provided by the embodiment of the present invention, it is determined whether the penetration probability of the frame image to be detected is not greater than the preset probability threshold. If not, it can be directly determined that no penetration phenomenon has occurred in the frame image to be detected, that is, the frame images to be detected in which no penetration phenomenon has occurred can be automatically screened out through the penetration probability. For the frame images to be detected that are determined to have no penetration phenomenon after automatic screening, manual penetration detection may no longer be performed, thereby reducing the labor consumption in performing penetration detection on the biological model, and also improving the detection efficiency of penetration detection on the biological model.

[0128] See also Fig. 9 , Fig. 9Another process for the biological model penetration detection method includes:

[0129] Step 901 , obtaining a frame image to be detected, wherein the frame image to be detected includes: a penetration action initiating part of a three-dimensional biological model and a plurality of parts to be detected.

[0130] In the embodiment of the present invention, the part to be detected of the three-dimensional biological model may be: multiple parts or all of the head, spine, chest and lower limbs of the three-dimensional biological model.

[0131] Step 902: Obtain a mesh set corresponding to the location where the penetration action of the three-dimensional biological model is initiated, as a first type of mesh set.

[0132] Step 902 is the same as step 202 and will not be described again here.

[0133] Step 903 , for each part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained; and the grid sets corresponding to each part to be detected are all taken as the second type of grid sets.

[0134] In this step, the method of obtaining the grid set corresponding to each part to be detected can refer to the above Figure 7 The embodiments shown will not be described in detail here.

[0135] Step 904, determining a reference point in the first type grid set as a first reference point; and, for each second type grid set, determining a reference point in the second type grid set; and using the reference points in each second type grid set as second reference points.

[0136] In this step, the method of determining the first reference point and determining each second reference point for each second type grid set can refer to the above step 804, which will not be repeated here.

[0137] Step 905: Determine the penetration probability between the first reference point and each second reference point according to the spatial distance between the first reference point and each second reference point.

[0138] In this step, for each second reference point, the following formula can be used to determine the probability of mode penetration between the first reference point and the second reference point:

[0139]

[0140] Wherein, P' is the penetration probability between the first reference point and the second reference point, A represents the first type of grid set, B' represents the second type of grid set; a is an element in the first type of grid set A, that is, a represents a grid in set A; b' is an element in set B', that is, b' represents a grid in set B', where a∈A, b'∈B'; Pa is the coordinate of the first reference point corresponding to the grid a in the set A, P b " is the coordinate of the second reference point corresponding to the grid b' in the set B'; d(P a , P b' ) is the distance between the first reference point corresponding to the grid a and the second reference point corresponding to the grid b'; L A is the number of elements in set A, L B’ is the number of elements in set B'.

[0141] In the embodiment of the present invention, for each second reference point, the probability of penetration between the first reference point and the second reference point can also be determined based on the spatial distance between the first reference point and the second reference point and the preset weights for the first reference point and the second reference point. Specifically, the following formula can be used to determine the probability of penetration between the first reference point and the second reference point:

[0142]

[0143] Wherein, P' is the penetration probability between the first reference point and the second reference point, A represents the first type of grid set, B' represents the second type of grid set; a is an element in the first type of grid set A, that is, a represents a grid in set A; b' is an element in set B', that is, b' represents a grid in set B', where a∈A, b'∈B'; P a is the coordinate of the first reference point corresponding to the grid a in the set A, P b " is the coordinate of the second reference point corresponding to the grid b' in the set B'; d(P a , P b' ) is the distance between the first reference point corresponding to the grid a and the second reference point corresponding to the grid b'; ω a-b' P a and P b' The preset weight between .

[0144] Step 906: determine the maximum model penetration probability as the model penetration probability of the frame image to be detected.

[0145] Step 907, determining whether the frame image to be detected has a mode penetration phenomenon according to the mode penetration probability of the frame image to be detected.

[0146] In this step, the method of determining whether the frame image to be detected has a penetration phenomenon can refer to steps 806 to 808, which will not be repeated here.

[0147] By using the method provided by the embodiment of the present invention, by judging whether the penetration probability of the frame image to be detected is not greater than the preset probability threshold, if it is not greater, it can be directly determined that the frame image to be detected has not undergone the penetration phenomenon. That is, the frame images to be detected that have not undergone the penetration phenomenon can be automatically screened out by the penetration probability, and the frame images to be detected that have not undergone the penetration phenomenon after the automatic screening can no longer be manually tested for the penetration phenomenon, thereby reducing the labor consumption when performing the penetration detection on the biological model, and also improving the detection efficiency of the penetration detection on the biological model.

[0148] In the embodiment of the present invention, the mold penetration detection may be performed one by one on the multiple frames of the frame images to be detected, or the mold penetration detection may be performed on the multiple frames of the frame images to be detected at the same time.

[0149] When the penetration detection is performed one by one on multiple frames of images to be detected, the penetration action initiation position of the three-dimensional biological model in each frame of the image to be detected can be the same. When the penetration detection is performed on the first frame of the image to be detected, the identifiers of each grid in the first type of grid set corresponding to the penetration action initiation position of the three-dimensional biological model in the first frame of the image to be detected can be saved.

[0150] For each subsequent frame image to be detected, the first type of grid set corresponding to the initiation site of the penetration action of the three-dimensional biological model can be directly obtained by the identification of each grid in the first type of grid set corresponding to the initiation site of the penetration action. The identification of each grid can be a specific symbol or number, etc.

[0151] In an embodiment of the present invention, when performing mold penetration detection on multiple frames of frame images to be detected one by one, it is only necessary to obtain the first type of grid set corresponding to the part where the mold penetration action is initiated once, which further simplifies the steps of calculating the mold penetration probability of the frame images to be detected, and further improves the detection efficiency of the mold penetration detection on the frame images to be detected.

[0152] Based on the same inventive concept, according to the biological model penetration detection method provided by the above embodiment of the present invention, correspondingly, another embodiment of the present invention also provides a biological model penetration detection device, whose structural schematic diagram is shown in FIG. Fig.10 As shown, specifically including:

[0153] The image acquisition module 1001 is used to acquire a frame image to be detected, wherein the frame image to be detected includes: a part to be detected of the three-dimensional biological model and a part where the penetration action is initiated;

[0154] A first mesh acquisition module 1002 is used to acquire a mesh set corresponding to a location where a penetration action of a three-dimensional biological model is initiated, as a first type of mesh set;

[0155] The second grid acquisition module 1003 is used to acquire a grid set corresponding to the part to be detected of the three-dimensional biological model as a second type of grid set;

[0156] The reference point determination module 1004 is used to determine a reference point in the first type of grid set as a first reference point; and determine a reference point in the second type of grid set as a second reference point;

[0157] A penetration probability determination module 1005, configured to determine the penetration probability of the frame image to be detected based on the spatial distance between the first reference point and the second reference point;

[0158] The mode penetration phenomenon determination module 1006 is used to determine whether the mode penetration phenomenon occurs in the frame image to be detected according to the mode penetration probability of the frame image to be detected.

[0159] It can be seen that, by using the device provided by the embodiment of the present invention, a frame image to be detected is obtained, and a grid set corresponding to the initiation position of the penetration action of the three-dimensional biological model is obtained as a first type of grid set; for the position to be detected of the three-dimensional biological model, a grid set corresponding to the position to be detected is obtained as a second type of grid set; a reference point in the first type of grid set is determined as a first reference point; and a reference point in the second type of grid set is determined as a second reference point; based on the spatial distance between the first reference point and the second reference point, the penetration probability of the frame image to be detected is determined; and whether the frame image to be detected has a penetration phenomenon is determined according to the penetration probability of the frame image to be detected. Whether the frame image to be detected has a penetration phenomenon can be determined by the penetration probability of the frame image to be detected, that is, an automated screening is performed before the frame image to be detected is manually penetrated, and the frame image to be detected that is determined to have no penetration phenomenon after the automated screening can no longer be manually penetrated. This reduces the labor consumption when performing penetration detection on the biological model, and also improves the detection efficiency of the penetration detection on the biological model.

[0160] Furthermore, the penetration phenomenon determination module 1006 is specifically used to determine whether the penetration probability between the first reference point and the second reference point is not greater than a preset probability threshold; if so, determine that the frame image to be detected does not have a penetration phenomenon; if not, mark the frame image to be detected.

[0161] For further information, see Fig.11 The first grid acquisition module 1002 includes:

[0162] The first coordinate determination submodule 1101 is used to determine the coordinates of the core point of the penetration action initiation site of the three-dimensional biological model; and determine the coordinates of the reference points of each grid in the preset area where the penetration action initiation site is located;

[0163] The first distance determination submodule 1102 is used to calculate the first distance between the reference point of each grid and the core point of the penetration action initiation part based on the coordinates of the reference point of each grid in the preset area where the penetration action initiation part is located and the coordinates of the core point of the penetration action initiation part;

[0164] The first grid determination submodule 1103 is used to determine a set consisting of grids whose first distance is less than a first preset distance as a grid set corresponding to a penetration action initiation location, as a first type of grid set.

[0165] Furthermore, the first coordinate determination submodule 1101 is specifically used to determine the coordinates of a specified joint point in the initiation part of the penetration action of the three-dimensional biological model as the coordinates of the core point; and to determine the coordinates of the center of gravity of each grid in the preset area where the penetration action is initiated as the coordinates of the reference point.

[0166] For further information, see Fig.11 The second grid acquisition module 1003 includes:

[0167] The second coordinate determination submodule 1104 is used to determine the coordinates of the core point of the part to be detected of the three-dimensional biological model; and determine the coordinates of the reference points of each grid in the preset area where the part to be detected is located;

[0168] The second distance determination submodule 1105 is used to calculate the second distance between the reference point of each grid and the core point of the part to be detected based on the coordinates of the core point of the part to be detected and the coordinates of the reference point of each grid in the preset area where the part to be detected is located;

[0169] The second grid determination submodule 1106 is used to determine a set consisting of grids whose second distance is less than the second preset distance as a grid set corresponding to the part to be detected.

[0170] Furthermore, the second coordinate determination submodule 1104 is specifically used to determine the coordinates of the joint points to be detected in the part to be detected as the coordinates of the core point; and to determine the coordinates of the center of gravity of each grid in the preset area where the part to be detected is located as the coordinates of the reference point.

[0171] Furthermore, the reference point determination module 1004 is specifically configured to determine a central position point in a first type of grid set as a first reference point; and determine a central position point in a second type of grid set as a second reference point.

[0172] Furthermore, the penetration probability determination module 1005 is specifically used to determine the probability of the penetration phenomenon occurring in the frame image to be detected based on the spatial distance between the first reference point and the second reference point, and the preset weights for the first reference point and the second reference point.

[0173] Furthermore, the frame image to be detected includes a plurality of parts to be detected of the three-dimensional biological model;

[0174] The second grid acquisition module 1003 is specifically used to acquire a grid set corresponding to each part to be detected of the three-dimensional biological model; and the grid sets corresponding to each part to be detected are all used as the second type of grid sets;

[0175] The reference point determination module 1004 is used to determine, for each second type grid set, a reference point in the second type grid set; and use the reference points in each second type grid set as second reference points;

[0176] The penetration probability determination module 1005 is specifically used to determine the penetration probability between the first reference point and each second reference point according to the spatial distance between the first reference point and each second reference point; and determine the maximum penetration probability as the penetration probability of the frame image to be detected.

[0177] It can be seen that, by using the device provided by the embodiment of the present invention, by judging whether the penetration probability of the frame image to be detected is not greater than the preset probability threshold, if it is not greater, it can be directly determined that the frame image to be detected has not undergone the penetration phenomenon. That is, the frame images to be detected that have not undergone the penetration phenomenon can be automatically screened out by the penetration probability, and the frame images to be detected that have not undergone the penetration phenomenon after the automatic screening can no longer be manually tested for the penetration phenomenon, which reduces the labor consumption when performing the penetration detection on the biological model, and also improves the detection efficiency of the penetration detection on the biological model.

[0178] The embodiment of the present invention further provides an electronic device, such as Fig.12 As shown, it includes a processor 1201, a communication interface 1202, a memory 1203 and a communication bus 1204, wherein the processor 1201, the communication interface 1202, and the memory 1203 communicate with each other through the communication bus 1204.

[0179] Memory 1203, used for storing computer programs;

[0180] The processor 1201 is used to implement the following steps when executing the program stored in the memory 1203:

[0181] Acquire a frame image to be detected, wherein the frame image to be detected includes: a part to be detected of the three-dimensional biological model and a part where the penetration action is initiated;

[0182] Obtaining a mesh set corresponding to a part of the three-dimensional biological model where the penetration action is initiated as a first-category mesh set;

[0183] For a part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained as a second type of grid set;

[0184] Determine a reference point in the first type of grid set as a first reference point; and determine a reference point in the second type of grid set as a second reference point;

[0185] Determining a penetration probability of the frame image to be detected based on a spatial distance between the first reference point and the second reference point;

[0186] Whether the frame image to be detected has a mode penetration phenomenon is determined according to the mode penetration probability of the frame image to be detected.

[0187] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0188] The communication interface is used for communication between the above terminal and other devices.

[0189] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0190] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0191] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, in which a computer program is stored. When the computer program is executed by a processor, the biological model penetration detection method described in any of the above embodiments is implemented.

[0192] In another embodiment of the present invention, a computer program product including instructions is provided, which, when executed on a computer, enables the computer to execute the biological model penetration detection method described in any one of the above embodiments.

[0193] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0194] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0195] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, electronic device and storage medium, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0196] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A biological model penetration detection method, characterized in that: include: Acquire a frame image to be detected, wherein the frame image to be detected includes: a part to be detected of the three-dimensional biological model and a part where the penetration action is initiated; Obtaining a mesh set corresponding to a part of the three-dimensional biological model where the penetration action is initiated as a first-category mesh set; For a part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained as a second type of grid set; Determine a reference point in the first type of grid set as a first reference point; and determine a reference point in the second type of grid set as a second reference point; Determining a penetration probability of the frame image to be detected based on a spatial distance between the first reference point and the second reference point; Determining whether the frame image to be detected has a mode penetration phenomenon according to the mode penetration probability of the frame image to be detected; Determining a reference point in the first type of grid set as a first reference point; And, determining a reference point in the second type of grid set as a second reference point, comprising: Determine a center point in the first type of grid set as a first reference point; And, determine the center point in the second type of grid set as the second reference point.

2. The method according to claim 1, characterized in that The determining whether the frame image to be detected has a mode penetration phenomenon according to the mode penetration probability of the frame image to be detected includes: Determine whether the probability of penetration between the first reference point and the second reference point is not greater than a preset probability threshold; If yes, determine that the frame image to be detected does not have a mode penetration phenomenon; If not, the frame image to be detected is marked.

3. The method according to claim 1, characterized in that: The step of obtaining a grid set corresponding to a location where a penetration action of the three-dimensional biological model is initiated includes: Determine the coordinates of the core point of the penetration action initiation site of the three-dimensional biological model; and determine the coordinates of the reference points of each grid in the preset area where the penetration action initiation site is located; Based on the coordinates of the reference points of each grid in the preset area where the punching action initiation site is located and the coordinates of the core point of the punching action initiation site, a first distance between the reference points of each grid and the core point of the punching action initiation site is calculated; A set consisting of grids whose first distance is less than the first preset distance is determined as a grid set corresponding to the location where the penetration action is initiated.

4. The method according to claim 3, characterized in that: Determining the coordinates of the core point of the location where the penetration action of the three-dimensional biological model is initiated; And, determining the coordinates of the reference points of each grid in the preset area where the penetration action initiation site is located, including: Determine the coordinates of a designated joint point in the initiation position of the penetration action of the three-dimensional biological model as the coordinates of the core point; And, determine the coordinates of the center of gravity of each grid in the preset area where the penetration action is initiated, as the coordinates of the reference point.

5. The method according to claim 1, characterized in that For the part to be detected of the three-dimensional biological model, a grid set corresponding to the part to be detected is obtained as the second type of grid set, including: Determine the coordinates of the core point of the part to be detected of the three-dimensional biological model; and determine the coordinates of the reference points of each grid in the preset area where the part to be detected is located; Based on the coordinates of the core point of the part to be detected and the coordinates of the reference points of each grid in the preset area where the part to be detected is located, calculate the second distance between the reference point of each grid and the core point of the part to be detected; A set consisting of grids whose second distance is less than the second preset distance is determined as a grid set corresponding to the part to be detected.

6. The method according to claim 5, characterized in that The step of determining the coordinates of the core point of the part to be detected of the three-dimensional biological model; and determining the coordinates of the reference points of each grid in the preset area where the part to be detected is located, comprises: The coordinates of the joint points to be detected in the part to be detected are determined as the coordinates of the core point; and the coordinates of the center of gravity of each grid in the preset area where the part to be detected is located are determined as the coordinates of the reference point.

7. The method according to claim 1, characterized in that The determining, based on the spatial distance between the first reference point and the second reference point, the penetration probability of the frame image to be detected includes: Based on the spatial distance between the first reference point and the second reference point, and the preset weights for the first reference point and the second reference point, the probability of the frame image to be detected having a mode penetration phenomenon is determined.

8. The method according to claim 1, characterized in that: The frame image to be detected includes a plurality of parts to be detected of the three-dimensional biological model; The step of obtaining a grid set corresponding to the part to be detected of the three-dimensional biological model as the second type of grid set includes: obtaining a grid set corresponding to each part to be detected of the three-dimensional biological model; and taking the grid sets corresponding to each part to be detected as the second type of grid set; The step of determining the reference point in the second type grid set as the second reference point includes: determining the reference point in the second type grid set for each second type grid set; using the reference points in each second type grid set as the second reference point; The determining, based on the spatial distance between the first reference point and the second reference point, the penetration probability of the frame image to be detected includes: Determine the probability of penetration between the first reference point and each second reference point according to the spatial distance between the first reference point and each second reference point; The maximum mode penetration probability is determined as the mode penetration probability of the frame image to be detected.

9. A biological model penetration detection device, characterized in that: include: An image acquisition module is used to acquire a frame image to be detected, wherein the frame image to be detected includes: a part to be detected of the three-dimensional biological model and a part where the penetration action is initiated; A first mesh acquisition module is used to acquire a mesh set corresponding to a part of the three-dimensional biological model where the penetration action is initiated, as a first type of mesh set; A second grid acquisition module is used to acquire a grid set corresponding to a part to be detected of a three-dimensional biological model as a second type of grid set; A reference point determination module, used to determine a reference point in a first type of grid set as a first reference point; and determine a reference point in a second type of grid set as a second reference point; A mode penetration probability determination module, used to determine the mode penetration probability of the frame image to be detected based on the spatial distance between the first reference point and the second reference point; A mode penetration phenomenon determination module, used to determine whether the mode penetration phenomenon occurs in the frame image to be detected according to the mode penetration probability of the frame image to be detected; The reference point determination module is specifically used to determine a central position point in a first type of grid set as a first reference point; and to determine a central position point in a second type of grid set as a second reference point.

10. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 8 when executing a program stored in a memory.

11. 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 steps described in any one of claims 1 to 8 are implemented.

Images