Ice surface damage monitoring method, device and equipment and storage medium

Through video data analysis and network model identification technology, the positioning of the ice surface damage is automatically solved, and the difficulty of positioning in the existing ice surface ice replenishment technology is improved, and the efficiency and comprehensiveness of ice replenishment are improved.

CN119086551APending Publication Date: 2024-12-06ZHEJIANG UNIVIEW TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310664085.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-06-06
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the existing ice-based ice replenishment technology, it is difficult to quickly and accurately locate the ice-based damage location with the naked eye observation, resulting in insufficient ice-based ice replenishment efficiency and comprehensiveness.

Method used

By obtaining ice rink video data, determine the motion parameters, physical parameters and sports equipment parameters of the target ice surface position, calculate the depth of the damage and automatically locate the damage position, and use video data and network models to identify action categories to optimize the ice replenishment process.

Benefits of technology

It realizes automatic monitoring of the degree of ice damage and rapid positioning of the ice surface that needs to be repaired, improves the efficiency and comprehensiveness of ice replenishment, and reduces the time and artificial error of artificial ice replenishment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119086551A_ABST
    Figure CN119086551A_ABST
Patent Text Reader

Abstract

The invention provides an ice surface damage monitoring method and device, equipment and a storage medium. The method comprises the following steps: acquiring first video data of an ice rink; under the condition that the first video data comprises at least one target ice surface position, determining a first target parameter, a second target parameter and a third target parameter corresponding to each target ice surface position based on the first video data; and determining the damage depth of each target ice surface position based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and determining the target damaged ice surface position based on the damage depth of each target ice surface position. Therefore, the ice surface damage degree can be automatically monitored, the position of the ice surface needing to be repaired can be quickly positioned, and the ice supplementing efficiency and the ice supplementing comprehensiveness are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of ice surface re-icing, and in particular to an ice surface damage monitoring method, device, equipment and storage medium. Background Art

[0002] The skates that skaters wear when skating are equipped with ice skates. When skaters perform a series of graceful movements on the ice, the ice skates will cause certain damage to the ice surface. If these ice surface damages are not repaired in time, it will affect the performance of the next skater on the field, causing the pace to be interrupted and thus affecting the grading. In serious cases, it will cause the skater to fall during high-speed movement and affect personal safety. Therefore, in skating competitions, the ice rink needs to be repaired in time to make the ice surface smooth again.

[0003] In the relevant ice repair technology, the ice repair work is mainly carried out by ice repair vehicles and ice repair workers. The ice repair vehicle first cleans the reference objects on the ice surface, then sprays water and spreads the sprayed water evenly to freeze it into ice, so as to repair the minor damage to the ice surface. The ice repair worker carries ice repair tools, searches for the damaged parts of the ice surface in different areas, and performs manual repairs.

[0004] However, when using the above method to repair ice, the judgment of the location of ice damage mainly depends on the naked eye observation of the ice repairer. However, usually the bottom layer of the ice rink is covered with plastic sheeting, the ice surface is white and transparent, and the venue lights are bright, so some ice damage is difficult to detect with the naked eye. The time for ice repairers to repair ice is also very short, and it is difficult for them to quickly locate the ice damage with the naked eye, which may result in the inability to repair the ice surface comprehensively. Summary of the invention

[0005] The present invention aims to solve one of the technical problems in the related art to at least a certain extent. To this end, the present invention provides an ice surface damage monitoring method, device, equipment and storage medium to automatically monitor the degree of ice surface damage and quickly locate the position of the ice surface that needs to be repaired, thereby improving the efficiency and comprehensiveness of ice repair.

[0006] The present invention provides an ice surface damage monitoring method, comprising:

[0007] Acquire first video data of an ice rink, wherein the first video data includes a target human body in the ice rink and an ice surface contacted by the target human body;

[0008] In the case where the first video data includes at least one target ice surface position, a first target parameter, a second target parameter and a third target parameter corresponding to each target ice surface position are determined based on the first video data; wherein the target ice surface position is an ice surface position where a target human body is injured in the first video data, the first target parameter is a motion parameter of a reference object within a preset range of each target ice surface position, the second target parameter is a physical parameter of each target ice surface position, and the third target parameter is a parameter of sports equipment worn by the target human body;

[0009] The damage depth of each target ice surface position is determined based on the first target parameter, the second target parameter, and the third target parameter corresponding to each target ice surface position, and the target damaged ice surface position is determined based on the damage depth of each target ice surface position.

[0010] In some possible implementations, the determining the damage depth at each target ice surface position based on the first target parameter, the second target parameter, and the third target parameter corresponding to each target ice surface position includes: for any target ice surface position, determining the initial kinetic energy of a reference object within a preset range of the target ice surface position based on the first target parameter; determining the icebreaking resistance based on the second target parameter and the third target parameter; and determining the damage depth at the target ice surface position based on the initial kinetic energy of the reference object and the icebreaking resistance.

[0011] In some possible implementations, the first target parameters include the throwing angle, maximum height value, and mass of the reference object within a preset range of the target ice surface position, and determining the initial kinetic energy of the reference object within the preset range of the target ice surface position based on the first target parameters includes: determining the initial velocity of the reference object based on the throwing angle and the maximum height value of the reference object; determining the initial kinetic energy of the reference object based on the initial velocity and the mass of the reference object.

[0012] In some possible implementations, the ice-breaking resistance includes crushing resistance and bending resistance, the second target parameter includes the ice surface thickness, ice density and Poisson's ratio of each target ice surface position, and the third target parameter includes the bending strength, friction coefficient, first angle, second angle, component width, elastic modulus and third angle of the component of the sports equipment; wherein the first angle is the angle between the front of the end position of the component and the ice surface, the second angle is the angle between the side of the end position of the component and the ice surface, and the third angle is the angle between the main body of the component and the end position of the component; determining the ice-breaking resistance based on the second target parameter and the third target parameter includes: determining the crushing resistance based on the bending strength, the ice surface thickness, the friction coefficient, the first angle and the second angle; determining the bending resistance based on the ice density, the component width, the ice surface thickness, the Poisson's ratio of the target ice surface position, the friction coefficient, the first angle, the second angle, the elastic modulus and the third angle; determining the ice-breaking resistance based on the crushing resistance and the bending resistance.

[0013] In some possible implementations, determining a target damaged ice surface position based on the damage depth at each target ice surface position includes: taking a target ice surface position where the damage depth exceeds a preset threshold as the target damaged ice surface position.

[0014] In some possible implementations, before acquiring first video data of the ice rink, the method further includes: acquiring second video data of the ice rink, the second video data including the target human body; determining an action category of the target human body based on the second video data; and acquiring the first video data of the ice rink includes: when the action category is a preset action category, acquiring the first video data of the ice rink.

[0015] In some possible implementations, determining the action category of the target human body based on the second video data includes: dividing the second video data into at least two frames of video images, and inputting each of the video images into a first network model to obtain joint feature data of the target human body in each of the video images; wherein the first network model is used to extract joint features of each of the video images; inputting the joint feature data corresponding to each of the video images into a second network model to obtain the action category of the target human body; wherein the second network model is used to classify the actions of the target human body.

[0016] The present invention also provides an ice surface injury monitoring device, comprising: an acquisition module, used to acquire first video data of an ice rink, the first video data including a target human body in the ice rink and the ice surface with which the target human body contacts; a determination module, used to determine, based on the first video data, first target parameters, second target parameters and third target parameters corresponding to each target ice surface position when at least one target ice surface position is included in the first video data; wherein the target ice surface position is an ice surface position where the target human body is injured in the first video data, the first target parameter is a motion parameter of a reference object within a preset range of each target ice surface position, the second target parameter is a physical parameter of each target ice surface position, and the third target parameter is a parameter of sports equipment worn by the target human body; a monitoring module, used to determine the injury depth of each target ice surface position based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and determine the target injured ice surface position based on the injury depth of each target ice surface position.

[0017] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an ice surface damage monitoring method as described above is implemented.

[0018] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the ice surface damage monitoring method as described in any one of the above is implemented.

[0019] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the ice surface damage monitoring method as described above is implemented.

[0020] The ice surface damage monitoring method, device, equipment and storage medium provided by the present invention obtain first video data of the ice rink. When the first video data includes at least one target ice surface position, the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position are determined based on the first video data; the damage depth of each target ice surface position is then determined based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and the target damaged ice surface position is determined based on the damage depth of each target ice surface position, so that the position requiring manual ice repair can be located according to the damage depth of the target ice surface position, thereby realizing automatic monitoring of the degree of ice surface damage, and quickly locating the ice surface position requiring repair, thereby improving the efficiency and comprehensiveness of ice repair. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 is a schematic diagram of a scenario of the ice surface damage monitoring method provided by the present invention;

[0023] Figure 2 is one of the flow charts of the ice surface damage monitoring method according to an embodiment of the present invention;

[0024] Figure 3 This is the second flow chart of the ice surface damage monitoring method according to an embodiment of the present invention;

[0025] Figure 4 This is the third flow chart of the ice surface damage monitoring method according to an embodiment of the present invention;

[0026] Figure 5a is a schematic diagram of a coordinate system for the maximum displacement of a reference object according to an embodiment of the present invention;

[0027] Figure 5b is a schematic diagram of a coordinate system of a maximum height of a reference object according to an embodiment of the present invention;

[0028] Figure 6a is a schematic diagram of the relationship between the front side of the ice skate and the ice surface according to an embodiment of the present invention;

[0029] Figure 6b is a schematic diagram of the relationship between the side surface of the ice skate and the ice surface according to an embodiment of the present invention;

[0030] Figure 7 This is the fourth flow chart of the ice surface damage monitoring method according to an embodiment of the present invention;

[0031] Figure 8 This is the fifth flow chart of the ice surface damage monitoring method according to an embodiment of the present invention;

[0032] Fig. 9 It is an ice surface damage monitoring device according to an embodiment of the present invention;

[0033] Fig.10 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] For ease of understanding, this specification provides an example scenario of an ice surface damage monitoring method. The example scenario is applied in the following example: Figure 1 In the application environment shown, there are a camera device 110, a server 120 and an alarm device 130, and both the camera device 110 and the alarm device 130 can establish a communication connection with the server 120 via the Internet.

[0036] Among them, the camera device 110 can be a high-speed camera available on the market, and the camera device 110 is used to capture video images of the ice rink. In this scenario example, it should be noted that the ice rink can be an ice skating rink, and the ice rink is divided into multiple areas. A camera device 110 is installed in each area, and each camera device 110 is used to capture the target human body and the ice surface of the ice rink in the corresponding area. It should be noted here that the target human body can be a skater. After each camera device 110 captures the video image of the corresponding ice rink area, each camera device 110 will send the video image and its monitoring location information to the server 120, and the server 120 will process the video image.

[0037] In this scenario example, the camera device 110 can be directly controlled to shoot the ice surface that the target human body contacts on the ice rink to obtain the first video data. The first video data mainly includes the ice surface and the reference object within the preset range of the ice surface. The server 120 then determines the damage depth of the ice surface based on the first video data. In an embodiment of the present invention, the reference object can be specifically ice debris, and the first video data includes the ice surface and the ice debris raised around the ice surface.

[0038] In some scenario examples, the camera device 110 may be controlled to shoot the target human body to obtain the second video data. After receiving the second video data, the server 120 performs motion recognition on the target human body in the second video data to determine whether the skater has performed a preset action category. It should be noted that the preset action category may be a figure skating action or other action that may cause damage to the ice surface. It is understandable that during skating, skaters usually impact the ice surface when performing figure movements, thereby causing damage to the ice surface.

[0039] If the server 120 determines that the target human body has performed a preset action category, it can be inferred that the target human body may cause damage to the ice surface. At this time, the camera device 110 can be controlled to shoot the ice surface that the target human body touches to obtain the first video data, and the server 120 determines the ice surface damage depth based on the first video data.

[0040] When the ice surface damage depth of the ice surface position where the target human body is injured (i.e., the target ice surface position) exceeds a preset threshold, where the preset threshold is the maximum depth that the ice repair vehicle can repair, the server 120 will use the target ice surface position as the target damaged ice surface position, and send the monitoring position information corresponding to the target damaged ice surface position to the alarm device 130, and through the alarm device 130, the ice repairer will be prompted with the target damaged ice surface position (i.e., the position where manual ice repair is required) so that the ice repairer can repair the ice surface in a timely and accurate manner.

[0041] In this scenario example, the alarm device 130 may be a display screen. As an example, when the server 120 sends the monitoring location information of the target damaged ice surface location to the display screen, the display screen will display the monitoring location information corresponding to the target damaged ice surface location, so that the ice repairer can view the ice surface location that needs to be repaired. In addition, the alarm device 130 may also include a speaker, and the speaker emits an alarm sound to remind the ice repairer that manual ice repair is required and the ice surface location that needs manual ice repair.

[0042] With reference to the scenario example of the ice surface damage monitoring method in the aforementioned embodiment, the ice surface damage monitoring method in an embodiment of the present invention is described in detail below.

[0043] Figure 2 FIG. 1 is one of the flow charts of the ice surface damage monitoring method according to an embodiment of the present invention. Figure 2 As shown, the method may include the following steps:

[0044] Step 210: Acquire first video data of the ice rink.

[0045] Step 220: When the first video data includes at least one target ice surface position, determine a first target parameter, a second target parameter, and a third target parameter corresponding to each target ice surface position based on the first video data.

[0046] Step 230: Determine the damage depth of each target ice surface position based on the first target parameter, the second target parameter, and the third target parameter corresponding to each target ice surface position, and determine the target damaged ice surface position based on the damage depth of each target ice surface position.

[0047] It should be noted that the first video data includes the target human body in the ice rink and the ice surface that the target human body contacts, the target ice surface position is the ice surface position where the target human body is injured in the first video data, the first target parameter is the motion parameter of the reference object within the preset range of each target ice surface position, the second target parameter is the physical parameter of each target ice surface position, and the third target parameter is the parameter of the sports equipment worn by the target human body. The target human body can be a skater in the ice rink. In addition, the reference object can be the ice debris raised around the ice surface that caused the injury; the preset range can be manually set by the staff according to actual needs, and is not specifically limited here; the sports equipment can be the skates worn by the target human body.

[0048] Specifically, the ice rink can be divided into multiple areas, each area is equipped with a camera device, and each camera device is used to monitor the corresponding area, that is, to shoot a video of the corresponding monitoring area. The camera device can first shoot the target human body and the ice surface contacted by the target human body in the corresponding monitoring area in real time to obtain video data, and the camera device then uploads the video data to the server, and the video data is the first video data.

[0049] After obtaining the first video data, the target ice surface position can be determined from the first video data. Specifically, the first video data can be converted into multiple frames of video images, and then target detection is performed on each frame of the video image. It is understandable that a large number of movements of skaters during competitions or training will cause friction between the ice skates and the ice surface, as well as impact of the ice skates on the ice surface, which will not only damage the ice surface, but also cause ice debris to be raised. Therefore, the detection object of the target detection here can be ice debris, that is, when ice debris is detected to be raised, the position where the ice debris is raised is used as the target ice surface position, or the position with a preset distance from the position where the ice debris is raised is used as the target ice surface position, where the preset distance can be set based on experience.

[0050] After determining the target ice surface position where damage exists in the first video data, the first target parameter, the second target parameter and the third target parameter corresponding to the target ice surface position can be determined from the first video data. The first target parameter is the relevant parameter of the reference object around the target ice surface position, for example, the initial angle of ice debris lifting, the displacement of ice debris, etc. The second target parameter is the physical parameter of the target ice surface position, for example, the thickness of the ice surface, the friction coefficient of the ice surface, etc. The third target parameter is the parameter of the sports equipment worn by the target human body in contact with the target ice surface position, for example, the sports equipment parameter can be the width of the ice skate blade, the bending strength of the ice skate blade, etc.

[0051] It should be noted that the second target parameter and the third target parameter can be pre-set by the staff according to the actual situation, and when calculating the damage depth, the pre-set second target parameter and the third target parameter can be directly called. In addition, for the same ice rink, the second target parameter can be a fixed value.

[0052] When the ice skates cause damage to the ice surface, multiple pieces of ice debris will be raised. Therefore, in the first video data obtained by shooting, multiple pieces of ice debris (i.e., reference objects) may be raised around a target ice surface position. It is understandable that the greater the impact of the skater's ice skates on the ice surface, the greater the height and displacement of the ice debris raised, and the greater the degree of damage to the ice surface. Therefore, in this embodiment, the first target parameters corresponding to each target ice surface position can be the relevant parameters of the ice debris with the largest height and displacement around the target ice surface position; or the relevant parameters of the ice debris with the largest volume around the target ice surface position.

[0053] After obtaining the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, the damage depth of each target ice surface position is calculated according to the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position. Then, the target ice surface position with more severe damage is determined according to the damage depth of each target ice surface position. The target ice surface position with more severe damage is the target damaged ice surface position. Since the target damaged ice surface position is more severely damaged, the ice repairer needs to manually repair ice at the target damaged ice surface position.

[0054] Therefore, by installing multiple cameras for monitoring ice surface damage on the ice rink, the first video data of the ice rink is obtained, and then the motion parameters of the reference object within the preset range of the target ice surface position, the physical parameters of the target ice surface position and the sports equipment parameters are determined based on the first video data, and the damage depth of the target ice surface position is determined based on the above parameters, and then the target damaged ice surface position is determined, so that the ice repairer can quickly locate the position that needs manual ice repair based on the position information of the target damaged ice surface. In this way, the degree of ice surface damage can be automatically monitored, and the position of the ice surface that needs to be repaired can be quickly located, which improves the efficiency and comprehensiveness of ice repair.

[0055] Figure 3 FIG. 2 is a flowchart of the ice surface damage monitoring method according to an embodiment of the present invention. Figure 3 As shown, in step 230, determining the damage depth of each target ice surface position based on the first target parameter, the second target parameter, and the third target parameter corresponding to each target ice surface position may include the following steps:

[0056] Step 310: For any target ice surface position, determine the initial kinetic energy of a reference object within a preset range of the target ice surface position based on the first target parameter.

[0057] Step 320: Determine ice breaking resistance based on the second target parameter and the third target parameter.

[0058] Step 330: Determine the damage depth of the target ice surface location based on the initial kinetic energy and ice breaking resistance of the reference object.

[0059] It is understandable that when the skate blade collides with the ice surface, part of the impact energy causes damage to the ice surface, and the other part of the impact energy causes the ice debris (i.e., the reference object) to be lifted up. Therefore, the impact energy can be expressed as:

[0060] E c =E z +E p (1)

[0061] Among them, E c is the impact energy of the skate blade on the ice surface, E z E is the energy corresponding to the ice debris lifting phenomenon. p The energy corresponding to the damage caused to the ice surface when the ice skate blade collides with the ice surface. In addition, the impact energy E can be calculated by conducting multiple experiments on the ice surface. c The energy E that causes the ice debris to be raised z The conversion ratio coefficient K ice , proportionality coefficient K ice ≤1, that is, E z =K ice E c .

[0062] When the ice skates and ice blades collide with the ice surface and cause damage to the ice surface, it can be regarded as the ice skates and ice blades performing an impact-type ice-breaking motion on the ice surface. In the ice-breaking motion, they are only affected by the ice-breaking resistance, so:

[0063] E p =R ice S=(1 / K ice -1)E z (2)

[0064] Among them, R ice is the ice breaking resistance, and S is the damage depth. Based on the above formula, if the initial kinetic energy of the reference object (i.e., the energy that causes the ice debris to be lifted) and the ice breaking resistance are determined, the ice surface damage depth can be determined. In this embodiment, the initial kinetic energy of the reference object can be determined by the first target parameter, and the ice breaking resistance can be determined by the second target parameter and the third target parameter.

[0065] In some embodiments, the first target parameter includes a throwing angle, a maximum height value, and a mass of the reference object within a preset range of the target ice surface position. Figure 4FIG. 3 is a flowchart of the ice surface damage monitoring method according to an embodiment of the present invention. Figure 4 As shown, in step 310, for any reference object within the preset range of the target ice surface position, determining the initial kinetic energy of the reference object within the preset range of the target ice surface position based on the first target parameter may include the following steps:

[0066] Step 410: Determine the initial velocity of the reference object based on the throwing angle and the maximum height value of the reference object.

[0067] Step 420: Determine the initial kinetic energy of the reference object based on the initial velocity and the mass of the reference object.

[0068] Specifically, kinetic energy is the energy of an object due to its motion, and the magnitude of kinetic energy can be calculated by half of the product of the mass of the object and the square of its velocity. Thus, the initial kinetic energy of the reference object can be determined by the initial velocity and mass of the reference object.

[0069] It is understandable that the greater the impact of the skater on the ice surface, the greater the height and displacement of the reference ice debris will be, and the deeper the damage to the ice surface will be. However, when using a high-speed camera to capture the ice debris, it is difficult to capture the entire movement trajectory of the ice debris, and it is also difficult to capture the location where the ice debris falls.

[0070] Therefore, this embodiment first uses the torque formula and the angular momentum formula to determine the trajectory equation of the ice debris when it is in projectile motion, so that only the parameters of the ice debris at the starting position and the parameters of the ice debris at any position in the projectile motion need to be obtained to obtain the position information of the ice debris falling. Furthermore, the maximum displacement formula and the maximum height formula of the ice debris can be obtained through the torque formula and the angular momentum formula, and then the initial velocity formula of the ice debris is obtained based on the maximum displacement formula and the maximum height formula; finally, the initial velocity of the ice debris is calculated based on the ice debris throwing angle and the maximum height value obtained from the first video data.

[0071] Figure 5a Schematic diagram of the coordinate system of the maximum displacement of ice debris in the embodiment of the present invention. Figure 5a As shown, when the skate blade collides with the ice surface, the ice debris is thrown out at an angle θ to the horizontal plane. If the resistance is ignored, the ice debris is only subjected to the downward gravity mg. Figure 5a In the figure, at time t, the ice slag reaches point A. At this time, the horizontal velocity of the ice slag is: v x =v 0x =v0cosθ, the vertical velocity of ice debris is: v y , where v x is the horizontal velocity of the ice debris at point A, v y is the vertical velocity of the ice slag at point A, v0 is the initial velocity of the ice slag at point O, v 0xis the initial horizontal velocity of the ice slag at point O. It should be noted that point A can refer to any point of the ice slag during the projectile motion.

[0072] As we all know, the formula for angular momentum is: in, is the angular momentum, is the distance from the particle to the center of rotation, m is the mass, is the linear velocity. The formula for torque is: in, is the torque, To do my best.

[0073] Based on the above angular momentum formula, the angular momentum of the ice debris around point O in this embodiment can be obtained as:

[0074] L g =-(mv y x-mv x y) (3)

[0075] Among them, L g is the angular momentum of the ice debris around point O, m is the mass of the ice debris, x is the horizontal displacement of the ice debris when it is at point A, and y is the vertical height of the ice debris when it is at point A.

[0076] Based on the above torque formula, if we assume that the counterclockwise rotation is the positive direction, we can get the torque of the ice slag as: M g =-mg·x, where mg is the weight of the ice slag. Based on the angular momentum formula (3) and the moment formula of the ice slag, the integral formula can be obtained as follows:

[0077]

[0078] Among them, t1 is the time when the ice residue is at point O, t x is the time taken by the ice slag to travel from point O to point A. Integrating the above integral formula (4) yields:

[0079]

[0080] Based on formula (5), the trajectory equation of the ice debris projectile can be further derived as:

[0081]

[0082] The coordinate information of the ice debris landing point B can be obtained through the trajectory equation of the ice debris. However, since the initial velocity v0 of the ice debris is unknown, the coordinates O(0, 0) of the ice debris thrown and the coordinates B(R, 0) of the ice debris landing are substituted into formula (4) for derivation, and the relationship between the maximum displacement R of the ice debris and the initial velocity v0 of the ice debris can be obtained.

[0083] Specifically, by substituting the coordinates O(0, 0) where the ice debris is thrown and the coordinates B(R, 0) where the ice debris lands into the above formula (4), we can obtain:

[0084]

[0085] Among them, L g (t2) is the angular momentum of the ice debris at point B, t2 is the time it takes for the ice debris to travel from point O to point B, L g (t1) is the angular momentum of the ice debris at point O. In addition, from the symmetry, the vertical velocity of the ice debris at point B is: v y =v 0y =v0sinθ. Therefore, by substituting the vertical velocity of the ice debris at the landing point B into formula (7), we can get the relationship between the maximum displacement formula R of the ice debris and the initial velocity of the ice debris:

[0086]

[0087] Figure 5b Schematic diagram of the coordinate system of the maximum height of ice debris in the embodiment of the present invention. Figure 5b As shown, the ice debris reaches the maximum height at point C. For path CB, x(t3)=x0; y(t3)=H; x(t2)=R, y(t2)=0 and M=mg(Rx), where t3 is the time when the ice debris is at point C. The angular momentum formula and torque formula of the ice debris around point B can be obtained:

[0088]

[0089]

[0090] Similarly, for path OC, the angular momentum and torque of the ice slag around point O can be calculated by x(t1)=0, y(t1)=0, x(t3)=x0, y(t3)=H, and M=-mg x.

[0091]

[0092] Thus, it can be concluded that Finally, according to v 0x =v0cosθ,v y =v 0y =v0 sinθ, the relationship between the maximum height H of the ice debris and the initial velocity of the ice debris can be obtained as follows:

[0093]

[0094] After obtaining the relationship between the maximum displacement of the ice debris and the initial velocity and the relationship between the maximum height of the ice debris and the initial velocity, the maximum height value of the ice debris measured from the first video data and the throwing angle θ of the ice debris can be substituted into the above-mentioned maximum displacement formula and maximum height formula to determine the maximum displacement value of the ice debris and the initial velocity of the ice debris, and then the initial kinetic energy of the ice debris can be determined.

[0095] In some embodiments, icebreaking resistance includes crushing resistance and bending resistance, the second target parameter includes ice surface thickness, ice density and Poisson's ratio at each target ice surface position, and the third target parameter includes bending strength, friction coefficient, first angle, second angle, component width, elastic modulus and third angle of components of the sports equipment; wherein the first angle is the angle between the front of the end position of the component and the ice surface, the second angle is the angle between the side of the end position of the component and the ice surface, and the third angle is the angle between the main body of the component and the end position of the component.

[0096] In this embodiment, the sports equipment may be ice skates worn by the target human body, and the component of the sports equipment may be the skates of the ice skates. Therefore, the width of the component may be the width of the skates, the end position of the component may be the tip of the skates, and the body of the component may be the blade of the skates. Furthermore, the first angle may be the angle between the front of the tip of the skates and the ice surface, the second angle may be the angle between the side of the tip of the skates and the ice surface, and the third angle may be the angle between the blade of the skates and the tip of the skates.

[0097] Figure 6a Schematic diagram of the relationship between the front side of the ice skate and the ice surface according to an embodiment of the present invention. Figure 6b Schematic diagram of the relationship between the side of the ice skate and the ice surface according to the embodiment of the present invention. Figure 6a and Figure 6b The first angular position, the second angular position and the third angular position shown in . Figure 7 FIG. 4 is a flowchart of the ice surface damage monitoring method according to an embodiment of the present invention. Figure 7 As shown, in some embodiments, determining the icebreaking resistance based on the second target parameter and the third target parameter in step 320 may include the following steps:

[0098] Step 710: Determine the crushing resistance based on the bending strength, the ice surface thickness, the friction coefficient, the first angle, and the second angle.

[0099] Step 720: Determine the bending resistance based on the ice density, the assembly width, the ice surface thickness, the Poisson's ratio of the target ice surface position, the friction coefficient, the first angle, the second angle, the elastic modulus, and the third angle.

[0100] Step 730: Determine ice breaking resistance based on the crushing resistance and the bending resistance.

[0101] Specifically, the ice breaking resistance can be divided into the breaking resistance R C and bending resistance R B Among them, the crushing resistance R C It can be calculated by the following formula:

[0102]

[0103] Among them, R c is the crushing resistance, σ f is the bending strength of the skate, h i is the ice surface thickness, is the first angle, μ is the friction coefficient, and ψ is the second angle. It should be noted that the ice surface thickness h i Generally, it is between 5.5cm and 6cm; the μ friction coefficient can be 0.02 to 0.09.

[0104] Bending resistance R B It can be calculated by the following formula:

[0105]

[0106] Among them, R B is the bending resistance, B is the width of the skate, E is the elastic modulus, v is the Poisson's ratio of the target ice surface, ρ W is the ice density, and α is the third angle. It should be noted that the ice blade width B is generally about 4 mm.

[0107] Get the crushing resistance R C and bending resistance R B The ice breaking resistance can then be determined by:

[0108]

[0109] Where V is the impact velocity of the skate blade when it hits the ground, which can be calculated by the formula E z =K ice E c And the conversion formula of speed and kinetic energy, we get the landing impact speed V of the skate blade. After getting the ice breaking resistance R ice and the initial kinetic energy E of the reference object z After that, the ice breaking resistance R ice and the initial kinetic energy E of the reference object z Substituting into formula (2), the damage depth at the target ice surface position can be obtained.

[0110] In some implementations, determining the target damaged ice surface position based on the damage depths of each target ice surface position in step 230 may include: taking the target ice surface position whose damage depth exceeds a preset threshold as the target damaged ice surface position.

[0111] It should be noted that the preset threshold value can be manually set by the staff according to the maximum ice filling depth of the ice repair vehicle, and is not specifically limited here.

[0112] Specifically, when the damage depth of the target ice surface position exceeds the maximum ice filling depth of the ice repair vehicle, the target ice surface position needs to be manually filled with ice, so that the target ice surface position is used as the target damaged ice surface position. At the same time, the position information of the target damaged ice surface position can be recorded and sent to the alarm device, and the alarm device issues an alarm prompt to prompt the ice repairer to manually fill the target damaged ice surface position.

[0113] The method of obtaining the target damaged ice surface position can be specifically: the ice rink area is divided into several grids with smaller unit areas, each grid has fixed position information, and a grid monitoring camera is installed around the ice rink to monitor each grid of the entire ice rink. The grid monitoring camera and the aforementioned camera device are turned on and monitored at the same time, and the grid monitoring camera will also output corresponding grid monitoring video data. After determining the target damaged ice surface position, the time when the camera device photographed the target damaged ice surface position can be obtained, and then the video image of the corresponding time can be found in the grid monitoring video data based on this time. Finally, the position information of the target damaged ice surface position can be determined based on the position information of the grid where the target human body is located in the video image, that is, the position information of the grid where the target human body is located can be used as the position information of the target damaged ice surface position.

[0114] In some embodiments, before obtaining the first video data of the ice rink in step 210, the method may further include the following steps: obtaining second video data of the ice rink, the second video data including the target human body; and determining the action category of the target human body based on the second video data. Obtaining the first video data of the ice rink includes: obtaining the first video data of the ice rink when the action category is a preset action category.

[0115] It should be noted that the preset action types can be manually set by the staff according to the figure skating actions and are not limited here.

[0116] When monitoring the damage to the ice surface, the camera device can be controlled to shoot the target human body in the ice rink to obtain the second video data. Then, the action type of the target human body in the second video data is identified to determine whether the target human body is performing a preset action type, wherein there can be multiple cameras, which jointly shoot the target human body and the ice surface that the target human body contacts. It is understandable that when a skater performs figure skating movements, the ice blades of the skates may impact the ice surface. Therefore, in this embodiment, if it is determined that the target human body is performing a preset action type, it can be inferred that the ice surface may be damaged, and at this time, the camera device can be controlled to shoot the ice surface that the target human body contacts.

[0117] Specifically, after obtaining the second video data, the second video data can be converted into multiple frames of video images, and then the human posture recognition model can be used to identify the action of the target human body in each frame of the video image, so as to determine the action category of the target human body. Specifically, the human posture recognition model mainly extracts the behavioral features of the target human body in the video image, and then classifies the actions of the target human body based on the behavioral features to determine the action category of the target human body.

[0118] After determining the target human body's action category, the target human body's action category can be compared with a preset action category to determine whether the target human body's action category is the preset action category. When it is determined that the target human body's action category is the preset action category, it indicates that the target human body has performed a figure skating action. At this time, the camera device can be controlled to continuously shoot the ice surface that the target human body contacts to obtain the first video data.

[0119] Figure 8 FIG. 5 is a flowchart of the ice surface damage monitoring method according to an embodiment of the present invention. Figure 8 As shown, in some implementations, determining the action category of the target human body based on the second video data may include the following steps:

[0120] Step 810: Divide the second video data into at least two frames of video images, and input each video image into the first network model to obtain joint feature data of the target human body in each video image; wherein the first network model is used to extract joint feature data of each video image.

[0121] Step 820: Input the joint feature data corresponding to each video image into the second network model to obtain the action category of the target human body; wherein the second network model is used to classify the action of the target human body.

[0122] In this embodiment, the Openpose model can be used as the first network model, and the ST-GCN model can be used as the second network model. Among them, the Openpose model is a posture estimation model of the key points of the human skeleton. The Openpose model is an open source library developed by a university based on convolutional neural network (CNN) and supervised learning (SL) and Caffe as the framework. It can realize the estimation of postures such as human body movements, facial expressions, and finger movements.

[0123] Specifically, after obtaining the second video data, the second video data can be converted into multiple frames of video images. Then, each frame of the video image is first input into the Openpose model, which will extract the skeletal joint features of the target human body in each frame of the video image, thereby obtaining the joint feature data corresponding to each frame of the video image. Next, the joint feature data corresponding to each frame of the video image is input into the ST-GCN model, and the ST-GCN model will establish a spatiotemporal feature map based on the feature data of each joint point.

[0124] The process of the ST-GCN model to establish a spatiotemporal feature graph based on the feature data of each joint point is as follows: First, define a node set, which includes the feature vectors and coordinate estimation confidence of the target human skeleton joint points in each frame of the video image. Secondly, define an edge set, which includes two parts: the first part is that the joint points in the same frame of the video image are connected according to the natural connection relationship of the human body to form a spatial edge; the second part is to connect the same joint points in two adjacent frames of the video image to form a temporal edge. Finally, the sum of the node set and the edge set is the spatiotemporal feature graph defined by the ST-GCN model. The coordinates and confidence of each joint point constitute the attributes of the joint point, which will be input into the graph convolutional neural network as data.

[0125] After obtaining the spatiotemporal feature map, the ST-GCN model will perform multi-layer convolution operations on the spatiotemporal feature map to obtain a high-level spatiotemporal feature map. Finally, a classification operation is performed based on the high-level spatiotemporal feature map to determine the action type of the target human body.

[0126] It should be noted that the specific working processes of the Openpose model and the ST-GCN model can refer to the existing Openpose model and the ST-GCN model working processes, which will not be repeated here.

[0127] Thus, by first controlling each camera device to shoot the target human body in the ice rink, the second video data is obtained, and based on the second video data, it is determined whether the target human body is performing figure skating movements; when it is determined that the target human body is performing figure skating movements, the camera device is controlled to shoot the ice surface that the target human body contacts in the ice rink, the first video data is obtained, and based on the first video data, the first target parameter, the second target parameter, and the third target parameter corresponding to each target ice surface position are determined; finally, based on the first target parameter, the second target parameter, and the third target parameter corresponding to each target ice surface position, the damage depth of each target ice surface position is determined, and when the damage depth of the target ice surface position exceeds the maximum ice filling depth of the ice repair vehicle, the alarm device is used to prompt the ice repairer to manually fill the ice at that position. Thus, the degree of ice surface damage is automatically monitored, and the ice surface position that needs to be repaired is quickly located, thereby improving the efficiency and comprehensiveness of ice filling.

[0128] Fig. 9 This is an ice surface damage monitoring device according to an embodiment of the present invention. Fig. 9 As shown, the ice surface damage monitoring device 900 includes:

[0129] The acquisition module 910 is used to acquire first video data of the ice rink, where the first video data includes a target human body in the ice rink and an ice surface that the target human body contacts.

[0130] Determination module 920 is used to determine the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position based on the first video data when the first video data includes at least one target ice surface position; wherein the target ice surface position is the ice surface position causing injury to the target human body in the first video data, the first target parameter is the motion parameter of a reference object within a preset range of each target ice surface position, the second target parameter is the physical parameter of each target ice surface position, and the third target parameter is the parameter of the sports equipment worn by the target human body.

[0131] The monitoring module 930 is used to determine the damage depth of each target ice surface position based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and determine the target damaged ice surface position based on the damage depth of each target ice surface position.

[0132] Thus, the first video data of the ice rink is acquired by the acquisition module 910. When the first video data includes at least one target ice surface position, the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position are determined based on the first video data by the determination module 920. The monitoring module 930 then determines the damage depth of each target ice surface position based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and determines the target damaged ice surface position based on the damage depth of each target ice surface position, so that the position requiring manual ice repair can be located according to the damage depth of the target ice surface position, thereby realizing automatic monitoring of the degree of ice surface damage, and quickly locating the ice surface position requiring repair, thereby improving the efficiency and comprehensiveness of ice repair.

[0133] It should be noted that for details not disclosed in the ice surface damage monitoring device of this embodiment, please refer to the details disclosed in the embodiment of the ice surface damage monitoring method in the embodiments of this specification, and they will not be repeated here.

[0134] Fig.10 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.10 As shown, the electronic device may include: a processor (processor) 1010, a communication interface (Communications Interface) 1020, a memory (memory) 1030 and a communication bus 1040, wherein the processor 1010, the communication interface 1020, and the memory 1030 communicate with each other through the communication bus 1040. Processor 1010 can call logic instructions in memory 1030 to execute an ice surface injury monitoring method, which includes: obtaining first video data of an ice rink; when the first video data includes at least one target ice surface position, determining first target parameters, second target parameters and third target parameters corresponding to each target ice surface position based on the first video data; wherein the target ice surface position is the ice surface position where the target human body is injured in the first video data, the first target parameter is the motion parameter of a reference object within a preset range of each target ice surface position, the second target parameter is the physical parameter of each target ice surface position, and the third target parameter is the parameter of sports equipment worn by the target human body; determining the injury depth of each target ice surface position based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and determining the target injured ice surface position based on the injury depth of each target ice surface position.

[0135] In addition, the logic instructions in the above-mentioned memory 1030 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0136] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the ice surface injury monitoring method provided by the above-mentioned methods, which includes: obtaining first video data of an ice rink; when the first video data includes at least one target ice surface position, determining first target parameters, second target parameters and third target parameters corresponding to each target ice surface position based on the first video data; wherein the target ice surface position is the ice surface position where the target human body is injured in the first video data, the first target parameter is the motion parameter of a reference object within a preset range of each target ice surface position, the second target parameter is the physical parameter of each target ice surface position, and the third target parameter is the parameter of the sports equipment worn by the target human body; determining the injury depth of each target ice surface position based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and determining the target injured ice surface position based on the injury depth of each target ice surface position.

[0137] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the ice surface injury monitoring method provided by the above-mentioned methods, the method comprising: obtaining first video data of an ice rink; in a case where the first video data includes at least one target ice surface position, determining first target parameters, second target parameters and third target parameters corresponding to each target ice surface position based on the first video data; wherein the target ice surface position is the ice surface position where the target human body is injured in the first video data, the first target parameter is the motion parameter of a reference object within a preset range of each target ice surface position, the second target parameter is the physical parameter of each target ice surface position, and the third target parameter is the parameter of sports equipment worn by the target human body; determining the injury depth of each target ice surface position based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and determining the target injured ice surface position based on the injury depth of each target ice surface position.

[0138] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0139] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring ice surface damage, characterized in that: include: Acquire first video data of an ice rink, wherein the first video data includes a target human body in the ice rink and an ice surface contacted by the target human body; In the case where the first video data includes at least one target ice surface position, a first target parameter, a second target parameter and a third target parameter corresponding to each target ice surface position are determined based on the first video data; wherein the target ice surface position is an ice surface position where a target human body is injured in the first video data, the first target parameter is a motion parameter of a reference object within a preset range of each target ice surface position, the second target parameter is a physical parameter of each target ice surface position, and the third target parameter is a parameter of sports equipment worn by the target human body; The damage depth of each target ice surface position is determined based on the first target parameter, the second target parameter, and the third target parameter corresponding to each target ice surface position, and the target damaged ice surface position is determined based on the damage depth of each target ice surface position.

2. The ice surface damage monitoring method according to claim 1, characterized in that: The determining the damage depth of each target ice surface position based on the first target parameter, the second target parameter, and the third target parameter corresponding to each target ice surface position includes: For any target ice surface position, determining the initial kinetic energy of a reference object within a preset range of the target ice surface position based on the first target parameter; determining icebreaking resistance based on the second target parameter and the third target parameter; The damage depth of the target ice surface position is determined based on the initial kinetic energy of the reference object and the ice breaking resistance.

3. The ice surface damage monitoring method according to claim 2, characterized in that: The first target parameter includes a throwing angle, a maximum height value, and a mass of the reference object within a preset range of the target ice surface position, and determining the initial kinetic energy of the reference object within the preset range of the target ice surface position based on the first target parameter includes: determining an initial velocity of the reference object based on the throwing angle and the maximum height value of the reference object; An initial kinetic energy of the reference object is determined based on the initial velocity of the reference object and the reference object mass.

4. The ice surface damage monitoring method according to claim 3, characterized in that: The ice-breaking resistance includes crushing resistance and bending resistance, the second target parameter includes ice surface thickness, ice density and Poisson's ratio at each target ice surface position, and the third target parameter includes bending strength, friction coefficient, first angle, second angle, component width, elastic modulus and third angle of the component of the sports equipment; wherein the first angle is the angle between the front of the end position of the component and the ice surface, the second angle is the angle between the side of the end position of the component and the ice surface, and the third angle is the angle between the main body of the component and the end position of the component; The determining of the icebreaking resistance based on the second target parameter and the third target parameter comprises: determining the crushing resistance based on the bending strength, the ice surface thickness, the friction coefficient, the first angle, and the second angle; determining the bending resistance based on the ice density, the assembly width, the ice surface thickness, the Poisson's ratio of the target ice surface position, the friction coefficient, the first angle, the second angle, the elastic modulus, and the third angle; The ice breaking resistance is determined based on the crushing resistance and the bending resistance.

5. The ice surface damage monitoring method according to any one of claims 1 to 4, characterized in that: The determining of the target damaged ice surface position based on the damage depth of each target ice surface position includes: The target ice surface position where the damage depth exceeds a preset threshold is used as the target damaged ice surface position.

6. The ice surface damage monitoring method according to any one of claims 1 to 4, characterized in that: Before acquiring the first video data of the ice rink, the method further includes: Acquire second video data of the ice rink, wherein the second video data includes the target human body; Determine the action category of the target human body based on the second video data; The obtaining of first video data of the ice rink includes: When the action category is a preset action category, the first video data of the ice rink is acquired.

7. The ice surface damage monitoring method according to claim 6, characterized in that: Determining the action category of the target human body based on the second video data includes: The second video data is divided into at least two frames of video images, and each of the video images is input into the first network model to obtain joint feature data of the target human body in each of the video images; wherein the first network model is used to extract joint feature data of each of the video images; The joint feature data corresponding to each of the video images is input into a second network model to obtain the action category of the target human body; wherein the second network model is used to classify the action of the target human body.

8. An ice surface damage monitoring device, characterized in that: include: An acquisition module, configured to acquire first video data of an ice rink, wherein the first video data includes a target human body in the ice rink and an ice surface contacted by the target human body; a determination module, for determining, in the case where at least one target ice surface position is included in the first video data, a first target parameter, a second target parameter and a third target parameter corresponding to each target ice surface position based on the first video data; wherein the target ice surface position is an ice surface position where the target human body is injured in the first video data, the first target parameter is a motion parameter of a reference object within a preset range of each target ice surface position, the second target parameter is a physical parameter of each target ice surface position, and the third target parameter is a parameter of a sports equipment worn by the target human body; A monitoring module is used to determine the damage depth of each target ice surface position based on the first target parameter, the second target parameter and the third target parameter corresponding to each target ice surface position, and determine the target damaged ice surface position based on the damage depth of each target ice surface position.

9. An electronic 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 program, the ice surface damage monitoring method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the ice surface damage monitoring method according to any one of claims 1 to 7 is implemented.