Sports timing method and apparatus, electronic device, and storage medium

Abstract

The application discloses a motion timing method and device, electronic equipment and storage medium, and relates to the technical field of detection. The method comprises the following steps: acquiring instantaneous state information of a target object at each moment in a motion process, wherein the motion process comprises a static state of the target object; for any moment, determining a state difference value of the moment according to the instantaneous state information of the moment and the instantaneous state information of the previous moment; determining a motion starting moment and a motion ending moment of the target object according to the state difference values of the moments and a critical value, wherein the critical value is determined according to the state difference value of the static state of the target object; and determining a motion time of the target object according to the motion starting moment and the motion ending moment. Therefore, the accuracy of detecting the motion time of the moving object is improved.

Description

Technical Field

[0001] This application relates to the field of detection technology, and in particular to a motion timing method, device, electronic device, and storage medium. Background Technology

[0002] In the aviation industry, the landing gear retraction and extension time is an important performance parameter of an aircraft. There are generally two methods to measure the landing gear retraction and extension time: the first is to use a stopwatch to time it directly; the second is to use sensors installed on the aircraft to time it.

[0003] However, the landing gear retraction and extension time obtained by using a stopwatch has a large error, and the data cannot meet the accuracy requirements for quality. When using a sensor for timing, the landing gear retraction and extension time is recorded in the flight control computer, which is inconvenient to read and is not conducive to daily quality control and maintenance. Summary of the Invention

[0004] The main objective of this application is to provide a motion timing method, device, electronic device, and storage medium to improve the accuracy of detecting the motion time of a moving object.

[0005] To achieve the above objectives, this application provides a sports timing method, comprising:

[0006] Acquire instantaneous state information of the target object at each moment during its motion, wherein the motion process includes the static state and the motion state of the target object;

[0007] For any given moment, the state difference at that moment is determined based on the instantaneous state information at that moment and the instantaneous state information at the previous moment;

[0008] The start and end times of the motion of the target object are determined based on the state difference and critical value at each time point, wherein the critical value is determined based on the state difference when the target object is at rest.

[0009] The motion time of the target object is determined based on the start time and end time of the motion.

[0010] Optionally, after acquiring the instantaneous state information of the target object at each moment during its motion, the method further includes: performing data conversion on the instantaneous state information at each moment to obtain state parameters at each moment; determining the state difference at any given moment based on the instantaneous state information at that moment and the instantaneous state information at the previous moment includes: performing a subtraction operation between the state parameters at that moment and the state parameters at the previous moment to obtain the state difference at that moment.

[0011] Optionally, determining the start and end times of the target object's motion based on the state differences and critical values ​​at each time step includes: determining the static time interval of the target object during the motion process based on the state differences at each time step; determining the critical value based on all the state differences corresponding to the static time interval; comparing the state differences at each time step with the critical value in chronological order, and taking the time corresponding to the state difference that first exceeds the critical value as the start time of the motion, and taking the time corresponding to the state difference that last exceeds the critical value as the end time of the motion.

[0012] Optionally, determining the critical value based on all the state differences corresponding to the static time interval includes: determining the state mean and state variance of all the state differences within the static time interval; and determining the critical value using a preset formula based on the state mean and the state variance.

[0013] Optionally, the preset formula is:

[0014] L = M + nS

[0015] Wherein, L is the critical value, M is the state mean, S is the state variance, and n is the coefficient of the state variance.

[0016] Optionally, after determining the state difference at any given time based on the instantaneous state information at that time and the instantaneous state information at the previous time, the method further includes: using a moving average algorithm to denoise the state difference at each time.

[0017] Optionally, obtaining the instantaneous state information of the target object at each moment during its motion includes: obtaining image data of the target object at each moment during its motion; determining the instantaneous state information at each moment based on the image data at each moment; for any instantaneous state information at any moment, the instantaneous state information includes the position information and color channel value of at least one pixel in the image data, and the position information in the instantaneous state information at each moment is the same.

[0018] Furthermore, to achieve the above objectives, this application also provides a motion timing device, comprising: an acquisition module for acquiring instantaneous state information of a target object at various moments during its motion, the motion process including a stationary state and a moving state of the target object; a first determination module for determining a state difference at any given moment based on the instantaneous state information of that moment and the instantaneous state information of the previous moment; a second determination module for determining the start time and end time of the motion of the target object based on the state differences at each moment and a critical value, the critical value being determined based on the state difference when the target object is in a stationary state; and a motion time determination module for determining the motion time of the target object based on the start time and the end time of the motion.

[0019] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the motion timing method as described above.

[0020] This application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the motion timing method as described above.

[0021] The motion timing method of this application acquires the instantaneous state information of the target object before, during, and after the motion process, then determines the state difference between the instantaneous state information at each moment and the instantaneous state information at the corresponding previous moment, and determines the change in the motion state of the target object by using the state difference at each moment, thereby determining the starting moment and ending moment of the motion of the target object, and finally determining the motion time of the target object by using the starting moment and ending moment of the motion, thereby improving the accuracy of detecting the motion time of the moving object. Attached Figure Description

[0022] Figure 1 This is a scenario example of the motion timing method provided in this application;

[0023] Figure 2 This is one of the flowcharts of the motion timing method in the embodiments of this application;

[0024] Figure 3 This is the second flowchart of the motion timing method according to an embodiment of this application;

[0025] Figure 4 This is a schematic diagram illustrating the state difference distribution as a specific example of this application;

[0026] Figure 5 This is the third flowchart of the motion timing method according to the embodiments of this application;

[0027] Figure 6 This is a schematic diagram illustrating the positional relationship between the landing gear and the camera, which is a specific example of this application.

[0028] Figure 7 This is a schematic diagram of the structure of the motion timing device according to an embodiment of this application;

[0029] Figure 8 A schematic diagram of the physical structure of an electronic device is provided;

[0030] In the diagram: 110, data acquisition unit; 120, sports timing system server; 700, sports timing device; 710, acquisition module; 720, first determination module; 730, second determination module; 740, sports time determination module; 810, processor; 820, communication interface; 830, memory; 840, communication bus.

[0031] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] During the critical phases of takeoff and landing, the operation of the landing gear directly impacts flight safety. Problems with landing gear retraction and extension can lead to serious consequences. For example, if the landing gear fails to retract in time during takeoff, it increases air resistance, reduces lift, affects the aircraft's climb performance, and may even cause takeoff failure. During landing, failure to lower the landing gear on time can result in a landing without it, which is extremely dangerous. Therefore, clearly defining and adhering to the timing of landing gear retraction and extension is crucial for ensuring safety.

[0034] Typically, testing an aircraft's landing gear retraction and extension time is used for safety verification, performance analysis and optimization, maintenance, and troubleshooting. Therefore, landing gear retraction and extension time is a very important performance parameter for an aircraft.

[0035] Currently, there are two main methods for detecting the landing gear retraction and extension time of aircraft: The first method is to use a stopwatch, but this method has a large error, and the obtained time data cannot meet the accuracy requirements for quality control. The second method is to install sensors on the aircraft for timing. However, the time results obtained by the sensors are recorded in the flight control computer, which is inconvenient to read and hinders routine quality control and maintenance of the aircraft.

[0036] Therefore, embodiments of this application provide a motion timing method, device, electronic device, and storage medium. By acquiring instantaneous state information of a moving object during its motion, analyzing the changes in the moving object's motion state, the starting point and ending point of the moving object's motion are found, and the motion time is determined, effectively improving the accuracy of detecting the motion time of a moving object and reducing errors.

[0037] For ease of understanding, this specification provides a scenario example of a motion timing method, which is applied in situations such as... Figure 1 In the application environment shown, there are data acquisition unit 110 and sports timing system server 120. Data acquisition unit 110 and sports timing system server 120 can establish a communication connection through the Internet or other means.

[0038] In this scenario example, the data acquisition device 110 can be a standalone device or component capable of acquiring state information of a moving object, such as a camera or sensor. Alternatively, it can be an integrated device such as a camera, recorder, or sensor capable of acquiring state information of a moving object. No specific limitations are imposed on the data acquisition device 110 here. The data acquisition device 110 can acquire the state information of the observed object at a preset acquisition frequency. This state information can be any information used to determine whether the object is in motion, such as color channel values ​​in image data, pitch and volume values ​​in audio data, and displacement data.

[0039] For example, if the status information is the color channel value in the image data, then the movement of an object can be determined by monitoring changes in the image pixels. If the object is moving, the pixel parameters at the same location in different images will be different, which can be used to determine whether the object is moving. If the status information is displacement data, then the movement of an object can be determined by whether the displacement data changes.

[0040] In this scenario example, the sports timing system may include individual components such as a clock, data storage, arithmetic unit, and controller. The sports timing system may also be integrated and run on a server (i.e., sports timing system server 120), which may include interconnected clocks, data storage units, arithmetic units, and control units. No specific limitations are imposed on the sports timing system server 120 here.

[0041] Specifically, taking the motion timing system server 120 as an example, the clock can be connected to the data acquisition unit 110, and the clock can continuously provide clock signals to the data acquisition unit 110 according to the preset acquisition frequency; the data storage unit can be used to store the status information collected by the data acquisition unit 110 in a time sequence, and can also store the data output by the calculation unit; the calculation unit can be used to identify the start and end times of the observed object's motion according to the status information at each moment, and calculate the motion time of the object; the control unit can be used to receive user instructions, set a fixed acquisition frequency, control the data acquisition unit 110 to start or stop working, and control the data storage unit to input or output data.

[0042] Referring to the scenario examples of the motion timing method in the foregoing embodiments, the motion timing method of this application will be described in detail below.

[0043] Figure 2 This is one of the flowcharts for a sports timing method according to an embodiment of this application. This sports timing method can be executed by the sports timing system server described in the foregoing embodiments. Figure 2 As shown, this sports timing method may include the following steps:

[0044] Step 210: Obtain the instantaneous state information of the target object at each moment during its motion.

[0045] Step 220: For any given moment, determine the state difference between that moment and the previous moment based on the instantaneous state information at that moment.

[0046] Step 230: Determine the start and end times of the target object's motion based on the state differences and critical values ​​at each moment. The critical values ​​are determined based on the state differences when the target object is at rest.

[0047] Step 240: Determine the motion time of the target object based on the start and end times of the motion.

[0048] First, it should be noted that the target object can be any moving object whose motion time needs to be detected, such as the landing gear of an aircraft, a vehicle, etc. Second, the motion process described in this embodiment needs to include both the static and dynamic processes of the target object, and the static process needs to collect sufficient instantaneous state information. For example, the motion process can include the static process before the target object moves and the dynamic process, or it can include the static process after the target object moves. Finally, instantaneous state information refers to information that can characterize the motion state of the target object, such as color channel values ​​in image data, pitch and volume values ​​in audio data, displacement data, etc.

[0049] In this embodiment, a data acquisition device can be set up to collect information about the target object. The data acquisition device can collect information about the target object in real time, or it can be controlled to start continuously collecting information about the target object before it is ready to move. For example, the landing gear of an aircraft only moves when the aircraft takes off or lands. Therefore, the data acquisition device can be controlled to start collecting information before the aircraft is ready to take off or land.

[0050] Furthermore, the data acquisition device can be any device or component capable of collecting state information of a moving object, such as a camera, recorder, or sensor. As an example, if the data acquisition device is a camera, it can continuously collect image data of the target object or directly record video of the target object to obtain video data, which is then processed to obtain image data. As another example, if the data acquisition device is a displacement sensor, it can continuously collect displacement data of the target object. When the displacement data does not change, it indicates that the target object is stationary; if the displacement data changes, it indicates that the target object is in motion.

[0051] In step 210, the control unit in the motion timing system server can control the data acquisition unit to continuously collect the instantaneous state information of the target object. After the data acquisition unit obtains the instantaneous state information at each moment, it can send all the instantaneous state information to the data storage unit in the motion timing system server. The data storage unit obtains the instantaneous state information of the target object at each moment and stores all the instantaneous state information; the computing unit in the motion timing system server can retrieve the required instantaneous state information from the data storage unit for calculation or processing.

[0052] As an example, the control unit in the sports timing system server has a pre-set fixed frequency f for information acquisition. The control unit can control the clock to send signals to the data acquisition unit at the fixed frequency f. When the control unit sends a "start" command to the data acquisition unit, the data acquisition unit will begin acquiring the instantaneous state information of the target object at the fixed frequency f. When the control unit sends a "stop" command to the data acquisition unit, the data acquisition unit will stop acquiring data. The instantaneous state information acquired by the data acquisition unit can be transmitted to the sports timing system server in real time, or it can be transmitted to the sports timing system server all at once after acquisition is completed. The data storage unit of the sports timing system server can store each instantaneous state information in a time sequence.

[0053] In step 220, after the data storage unit stores the instantaneous state information of each moment according to the time sequence, the computing unit can retrieve and process the instantaneous state information of each moment sequentially according to the time sequence. Specifically, taking a certain moment as an example, the computing unit retrieves the instantaneous state information of this moment and calculates the state difference between the instantaneous state information of this moment and the instantaneous state information of the previous moment; if the target object is in a stationary state at this moment, the state difference is theoretically zero; if the target object is in a moving state at this moment, the state difference is not zero.

[0054] Furthermore, after the computational unit determines the state differences at each moment, it can compare these state differences sequentially with the critical values ​​to determine the start and end times of the target object's motion. It should be noted that the critical values ​​can be determined based on all the state differences of the target object within its stationary state range. The critical value is used to characterize the critical state difference between a stationary and moving target object. When the state difference at a certain moment is less than or equal to the critical value, it indicates that the target object is still stationary at that moment. When the state difference at a certain moment exceeds the critical value, it indicates that the target object is in motion at that moment.

[0055] Understandably, by finding the state difference at each moment that first exceeds the critical value, we can determine when the target object began moving; conversely, by finding the state difference at each moment that last exceeds the critical value, we can determine when the target object ended moving. Thus, by observing subtle differences in state information, we can accurately pinpoint the start and end times of motion, thereby obtaining the precise duration of the target object's movement.

[0056] It is worth mentioning that the higher the fixed frequency of data acquisition by the data acquisition device, the more instantaneous state information is collected, and the higher the accuracy of the final motion time.

[0057] Typically, the instantaneous state information of a target object may not be easy to calculate directly. Therefore, it can be converted into an analyzable numerical object, such as a state feature array.

[0058] In some implementations, after obtaining the instantaneous state information of the target object at each moment during its motion in step 210, the motion timing method further includes: converting the instantaneous state information at each moment to obtain state parameters at each moment. Step 220, for any given moment, determining the state difference based on the instantaneous state information at that moment and the instantaneous state information at the previous moment, may include: performing a subtraction operation between the state parameters at that moment and the state parameters at the previous moment to obtain the state difference at that moment.

[0059] In this embodiment, after the sports timing system obtains the instantaneous state information at each moment, the computing unit in the sports timing system server can first convert the instantaneous state information at each moment into state parameters with state characteristics according to the time sequence. It should be noted that the state parameters can be represented by a sequence or a matrix; the specific representation of the state parameters is not limited here.

[0060] As an example, if the instantaneous state information acquired by the data acquisition device is the color channel values ​​in the image data, the motion timing system server can arrange the image data at each moment in chronological order as an image sequence p. i The data is stored in the form of (i = 1, 2, ..., N), where i represents the sequence value and N represents the number of image data. Furthermore, each image data can be extracted using a processing unit to obtain the corresponding state parameter S. i State parameter S i It can be defined as a 3D array [m,n,k] i ], where (m,n) are the coordinates of a pixel in the image data, k i =[r i ,g i ,b i ]|(m,n) represents the color channel value of this pixel. It should be noted that the state parameter can include the state values ​​of all pixels in the image data, the state values ​​of some pixels, or the state value of only one pixel, as long as the position of the pixel in the state parameter is the same at each time step.

[0061] Therefore, by transforming instantaneous state information into state parameters with state feature arrays, it becomes easier to use instantaneous state information to calculate motion time.

[0062] Furthermore, after obtaining the state parameters at each moment, the difference between the current state parameter and the previous state parameter can be calculated to obtain the state difference value at the current moment. The state difference value at the current moment can characterize the difference between the current state and the previous state. If the target object is still stationary at the current moment, the state difference value at the current moment should be zero or close to zero. If the target object just starts moving at the current moment, the state difference value at the current moment should change significantly. Therefore, by judging the state difference value, we can determine when the target object starts moving, and we can also determine when the target object stops moving.

[0063] Continuing with the example of using color channel values ​​in image data as instantaneous state information, the state parameters S at each time step are obtained. i The state difference can then be calculated using the following formula:

[0064] Δti =|avg(abs(S) i -S i-1 ))|(i=1,2,…N)

[0065] In the formula, Δt i Let S be the state difference at time i. i Let S be the state parameter at time i. i-1 Let be the state parameters at time i-1, avg be the average function, and abs be the absolute value function.

[0066] The following example will provide a detailed explanation of the principle behind the formula for this state difference.

[0067] For example, if the state parameters are represented in matrix form, then the state parameters may only include the color channel values ​​k of the pixels. i If the state parameters contain only the color channel values ​​of four pixels, then the state parameters can be represented as a 2*2 matrix, where each k... i Both are either a 1×3 matrix or a three-dimensional vector [r, g, b]. The state parameters at time 1 and time 2 can be specifically represented as follows:

[0068]

[0069]

[0070] In the formula, This represents the color channel value of a pixel at a specific position in the first row and first column of the state parameters at time 1. This represents the color channel value of a pixel at a specific position in the first row and first column of the state parameters at time 2. Furthermore, the difference between state parameters S1 and S2 yields the state difference value at time 2:

[0071]

[0072] However, since this data is in matrix form, it cannot be directly used for control charts. Therefore, the average state difference for each color channel can be calculated by averaging the state differences for each color channel.

[0073]

[0074] In the formula, y represents the number of rows in the state parameter matrix, z represents the number of columns in the state parameter matrix, and X i,j Let r, g, and b be the color channel value in the i-th row and j-th column, where r, g, and b are the color channels. Further, the magnitude of the vector obtained through averaging can be used as the final state difference value.

[0075]

[0076] Ultimately, the state difference Δt2 at time 2 is 9.233093.

[0077] Figure 3 This is the second flowchart of the motion timing method according to an embodiment of this application. Figure 3 As shown, in some embodiments, determining the start and end times of the target object's motion in step 230 based on the state differences and critical values ​​at various times may include the following steps:

[0078] Step 310: Determine the interval of stationary time of the target object during its motion based on the state difference at each moment.

[0079] Step 320: Determine the critical value based on all state differences corresponding to the interval of rest time.

[0080] Step 330: Compare the state difference at each moment with the critical value in chronological order, and take the moment when the state difference first exceeds the critical value as the start moment of the motion, and take the moment when the state difference last exceeds the critical value as the end moment of the motion.

[0081] Specifically, after obtaining the state differences at each moment, the continuous interval where the state differences remain almost unchanged can be taken as the interval of stationary moments of the target object during its motion. It can be understood that when collecting instantaneous state information of the target object, instantaneous state information before and after the target object's motion is also collected. Therefore, the state differences at each moment, in chronological order, can basically present three stages: "static-dynamic-static". Consequently, there exists a continuous interval in which the state differences hardly fluctuate.

[0082] After determining the static time interval, the critical value can be calculated using all the state differences within the static time interval, i.e., the state differences within the static time interval are used as a control group. In some implementations, determining the critical value based on all state differences corresponding to the static time interval may include the following steps: determining the state mean and state variance of all state differences within the static time interval; and determining the critical value using a preset formula based on the state mean and state variance.

[0083] Specifically, we can first calculate the mean M and variance S of all state differences within the static time interval. The method for calculating the mean and variance can be an existing one, which will not be elaborated here. After obtaining the mean M and variance S of all state differences within the static time interval, we can then use a preset formula, the mean M, and the variance S to calculate the critical value.

[0084] In some implementations, the preset formula may be:

[0085] L = M + nS

[0086] Where L is the critical value, M is the state mean, S is the state variance, and n is the coefficient of the state variance. It should be noted that the value of n can be 2 or 3, or it can be determined manually according to the actual environmental conditions and accuracy requirements; no specific restrictions are imposed here.

[0087] It is understood that this application's embodiments borrow (but are not limited to) the method of using Statistical Process Control (SPC) to determine control limits to define the static time interval. That is, a control group representing the static state is found, whose static state difference fluctuation range is [0, M+nS]. When the target object is in a static state, the probability of the state difference changing within this range is highest. Theoretically, exceeding the upper bound is a low-probability event; if it occurs, it can be considered that the original static state has changed; otherwise, it indicates that the object remains static.

[0088] In this embodiment, after obtaining the critical value, we can first use the critical value to analyze whether there are any cases exceeding the critical value in the static time interval, and to determine whether the state difference follows a normal distribution. If there are cases exceeding the critical value in the static time interval, we need to analyze the cause and make certain adjustments. As an example, the cause may be that abnormal motion of the target object or the movement of other foreign objects is observed in the static time interval (i.e., the control group). In this case, the abnormal instantaneous state information data segment can be directly clipped. As another example, the cause may also be abnormal fluctuations caused by continuous external factors such as ambient light sources and vibrations. In this case, after eliminating these external influencing factors, we can restart the acquisition of instantaneous state information during the target object's motion process.

[0089] Figure 4 This is a schematic diagram illustrating the state difference distribution as a specific example of this application. (For reference...) Figure 4 The state differences at each moment, arranged chronologically, can present a graph resembling a normal distribution. In this embodiment, the normality of fluctuations within the static time interval can be determined by observing whether the state difference distribution diagram conforms to a normal distribution. If the state differences at each moment do not conform to a quasi-normal distribution, the reasons need to be analyzed and adjustments made.

[0090] In some implementations, after obtaining the state differences at each time point, the motion timing method may further include: denoising the state differences at each time point using a moving average algorithm. Specifically, when a large amount of noise is observed in the static time interval through the state difference distribution diagram, a moving average algorithm can be used to denoise all state differences, making the changes in state differences more gradual. This allows for a more accurate determination of the start and end times of the target object's motion, and thus enables the calculation of more precise motion time.

[0091] In step 240, after obtaining the start time and end time of the motion, the motion time of the target object is determined based on the start time and end time of the motion. It should be noted that the time in this embodiment can be represented by a sequence value.

[0092] Specifically, if the sequence value at the start of the motion is Ts and the sequence value at the end of the motion is Te, then the number of sequences passed through during the motion process can be calculated first as T = Te - Ts. After obtaining the number of sequences passed through during the motion process, the motion time can be obtained by dividing the number of sequences T by the fixed frequency f when the data acquisition device collects the data.

[0093] As an example, the data acquisition device collects the instantaneous state information of the target object at a fixed frequency of 60fps, that is, it collects instantaneous state information once every 1 / 60th of a second. The instantaneous state information obtained at each moment can be stored in time series, i.e., p i (i = 1, 2, ..., N), if the instantaneous state information p is determined based on the state difference and the critical value. 15 The corresponding time is the start of motion, and the instantaneous state information p 65 The corresponding time is the end time of the motion. The sequence value of the start time of the motion is 15, and the sequence value of the end time of the motion is 195. Furthermore, the number of sequences T passed through during the motion process can be calculated to be 180. Dividing the number of sequences T passed through during the motion process by the fixed frequency of 60fps, the motion time is 3 seconds.

[0094] Therefore, the motion timing method of this application yields an error of 1 / f seconds in motion time, meaning that the higher the fixed frequency of data acquisition by the data collector, the higher the accuracy of motion time, thereby effectively improving the accuracy of detecting the motion time of an object.

[0095] Figure 5 This is the third flowchart of the motion timing method according to an embodiment of this application. Figure 5 As shown, in some embodiments, obtaining the instantaneous state information of the target object at various moments during its motion in step 210 may include the following steps:

[0096] Step 510: Acquire image data of the target object at various moments during its motion.

[0097] Step 520: Determine the instantaneous state information at each moment based on the image data at each moment.

[0098] It should be noted that the instantaneous state information at any given moment includes the position information and color channel value of at least one pixel in the image data, and the position information in the instantaneous state information at each moment is the same.

[0099] In this embodiment of the application, the data acquisition device can be a camera device. The camera device can acquire image data of the target object at a fixed frequency and output the image data to the motion timing system server. The motion timing system server determines the instantaneous state information at each moment based on the image data at each moment. Here, the instantaneous state information can be the color channel value of the pixel in the image data.

[0100] The motion time timing method of this application embodiment will be further described below in the application scenario of detecting the retraction and extension time of aircraft landing gear, taking image data as an example.

[0101] First, a tripod-mounted camera can be installed on the aircraft. Figure 6 This is a schematic diagram illustrating the positional relationship between the landing gear and the camera, as a specific example of this application. Figure 6 Includes landing gear 610 and camera 620, such as Figure 6 As shown, the position of the camera 620 can be set to any position that can capture the entire process of the landing gear 610 retracting and extending.

[0102] In this embodiment, the camera 620 may only film the landing gear 610 retraction and extension process. Other surrounding objects and backgrounds should remain stationary during the filming process, or they can be isolated using a barrier or screen. In addition, the color of the far end of the landing gear 610 should be significantly different from the color of the aircraft body and the background, which is more conducive to identifying the retraction and extension time of the landing gear 610.

[0103] Furthermore, the camera 620 can be set to record at fixed time intervals. For example, if f is the number of frames per second (i.e., a fixed frequency) (FPS), then the fixed time interval is 1 / f seconds. In this case, the time interval between two adjacent frames during video recording is fixed.

[0104] In this embodiment, the motion timing system server and the camera 620 can establish a communication connection via wired / wireless means.

[0105] The control unit in the motion timing system server can control the camera 620 to start or stop recording. When the camera 620 starts recording, each frame of the recording can be considered a record of the object's motion state at fixed time intervals. After recording is complete, each frame of image data is marked in chronological order.

[0106] The camera 620 stores each frame of image data on the memory card in chronological order, and then exports and outputs each frame of image data to the motion timing system server via wired / wireless means. The motion timing system server further processes each image data.

[0107] In this embodiment, the video recording can be observed first, and image data showing obvious foreign object movement before and after the landing gear 610 begins to move can be deleted. Furthermore, for abnormal movements outside the landing gear 610's movement path during the movement, the corresponding data can be marked or masked using the same color. Finally, the image data sequence p can be obtained. i (i = 1, 2, ..., N).

[0108] Furthermore, the computing unit in the motion timing system server can determine the corresponding state parameters S based on the image data of each frame. i State parameter S i It can be defined as a 3D array [m,n,k] i ], where (m,n) are the coordinates of a pixel in the image data, k i =[r i ,g i ,b i ]|(m,n) represents the color channel value of this pixel.

[0109] After obtaining the state parameter S corresponding to each frame of image data i Then, based on the state parameters of the current frame and the previous frame, the state difference of the current frame can be calculated:

[0110] Δt i =|avg(abs(S) i -S i-1 (i = 1, 2, ..., N)

[0111] It's understandable that, in an image where the landing gear is stationary and the lighting is stable, the color change of corresponding pixels between adjacent frames should be minimal. When represented by a variable (e.g., Δt)... i The fluctuation range of this variable can be roughly considered fixed; therefore, the Δt within this time period can be considered as... i Defined as the control group. When the landing gear moves, the color of some pixels on the trajectory changes drastically, Δt i The fluctuation range will increase significantly. Therefore, whether the landing gear is moving is transformed into the variable Δt. i The question is whether it falls within the fluctuation range when at rest.

[0112] The state difference Δt corresponding to each frame i A similar result can be obtained by drawing a graph. Figure 4 The graph clearly shows three regions: "static-moving-static". Furthermore, from... Figure 4 It can also be seen that when i∈[1,100], the landing gear 610 is in a stationary state, and then it can be determined from Δt1 to Δt 100By calculating the mean M and variance S of the state difference during this static time interval, the critical value L = M + nS can be calculated.

[0113] After calculating the critical value L, we can first use L to analyze whether there are situations where the critical value is exceeded between two static time intervals. If so, we can analyze the reasons and make adjustments. If the adjustment measures involve environmental changes in the state recording, we can restart the acquisition of image data.

[0114] Furthermore, the state difference corresponding to the first frame can be compared with the critical value in chronological order to find the sequence value Ts corresponding to the first state difference exceeding the critical value and the sequence value Te corresponding to the last state difference exceeding the critical value; and the number of sequences T = Te - Ts passed during the movement of the landing gear 610 can be calculated using Ts and Te.

[0115] After obtaining the sequence number T during the movement of the landing gear 610, the movement time of the landing gear 610 can be obtained by dividing the sequence number T during the movement of the landing gear 610 by the fixed frequency f.

[0116] Therefore, by analyzing the changes in the landing gear's state during the minimum interval, the start and end times of the landing gear's movement can be quickly determined, thus achieving high timing accuracy.

[0117] Figure 7 This is a schematic diagram of the structure of the motion timing device according to an embodiment of this application.

[0118] like Figure 7 As shown, the motion timing device 700 may include an acquisition module 710, a first determination module 720, a second determination module 730, and a motion time determination module 740. The acquisition module 710 acquires instantaneous state information of the target object at various moments during its motion, including both a stationary state and a moving state. The first determination module 720 determines the state difference between any given moment and the instantaneous state information of the previous moment. The second determination module 730 determines the start and end times of the target object's motion based on the state differences at each moment and a critical value, where the critical value is determined by the state difference when the target object is stationary. The motion time determination module 740 determines the motion time of the target object based on the start and end times of the motion.

[0119] In some implementations, the acquisition module 710 is further configured to: convert the instantaneous state information at each moment into data to obtain the state parameters at each moment; the first determination module 720 is specifically configured to: perform a subtraction operation between the state parameters at each moment and the state parameters at the previous moment to obtain the state difference value at each moment.

[0120] In some implementations, the second determining module 730 is specifically used to: determine the static time interval of the target object during the motion process based on the state difference at each time; determine the critical value based on all the state differences corresponding to the static time interval; compare the state difference at each time with the critical value in chronological order, and take the time corresponding to the state difference that first exceeds the critical value as the motion start time, and take the time corresponding to the state difference that last exceeds the critical value as the motion end time.

[0121] In some implementations, the second determining module 730 is further specifically used to: determine the mean and variance of all state differences within the time interval of rest; and determine a critical value using a preset formula and based on the mean and variance of the state.

[0122] In some implementations, the preset formula is:

[0123] L = M + nS

[0124] Where L is the critical value, M is the state mean, S is the state variance, and n is the coefficient of the state variance.

[0125] In some implementations, the first determining module 720 is further specifically used to: perform noise reduction processing on the state difference at each time point using a moving average algorithm.

[0126] In some embodiments, the acquisition module 710 is further specifically used to: acquire image data of the target object at each moment during its motion; determine the instantaneous state information at each moment based on the image data at each moment; for any instantaneous state information at any moment, the instantaneous state information includes the position information and color channel value of at least one pixel in the image data, and the position information in the instantaneous state information at each moment corresponds to the same value.

[0127] Therefore, by acquiring instantaneous state information of the target object before, during, and after the motion process through the acquisition module 710, the first determination module 720 then determines the state difference between the instantaneous state information at each moment and the instantaneous state information at the corresponding previous moment, the second determination module 730 determines the change in the motion state of the target object through the state difference at each moment, thereby determining the starting moment and ending moment of the motion of the target object, and finally the motion time determination module 740 determines the motion time of the target object through the starting moment and ending moment of the motion, thereby improving the accuracy of detecting the motion time of the moving object.

[0128] It should be noted that for details not disclosed in the sports timing device of this embodiment, please refer to the details disclosed in the embodiments of the sports timing method in this specification, which will not be repeated here.

[0129] Based on the above embodiments, Figure 8An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 8 As shown, the electronic device may include a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute a motion timing method, which includes: acquiring instantaneous state information of the target object at each moment during its motion, the motion process including the target object's stationary state; for any given moment, determining the state difference between the instantaneous state information at that moment and the instantaneous state information at the previous moment; determining the start and end times of the target object's motion based on the state differences at each moment and a critical value, the critical value being determined based on the state difference when the target object is stationary; and determining the motion time of the target object based on the start and end times of the motion.

[0130] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0131] Based on the above embodiments, the present invention also provides a computer program product, which includes a computer program that 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 motion timing method provided by the above methods. The method includes: acquiring instantaneous state information of a target object at various moments during its motion, the motion process including the static state of the target object; for any given moment, determining the state difference between the instantaneous state information at that moment and the instantaneous state information at the previous moment; determining the start time and end time of the motion of the target object based on the state differences at each moment and a critical value, the critical value being determined based on the state difference when the target object is in a static state; and determining the motion time of the target object based on the start time and end time of the motion.

[0132] Based on the above embodiments, in another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program is implemented to perform the motion timing method provided by the above methods. The method includes: acquiring instantaneous state information of a target object at various moments during its motion, the motion process including the static state of the target object; for any given moment, determining a state difference between the instantaneous state information of that moment and the instantaneous state information of the previous moment; determining the start moment and end moment of the motion of the target object based on the state differences at each moment and a critical value, the critical value being determined based on the state difference when the target object is in a static state; and determining the motion time of the target object based on the start moment and end moment of the motion.

[0133] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

Claims

1. A method for timing sports, characterized in that, include: Acquire instantaneous state information of a target object at various moments during its motion, wherein the motion process includes the stationary state of the target object, the target object being a landing gear, and the instantaneous state information includes at least color channel values ​​from image data, pitch and volume values ​​from audio data, or displacement data; For any given moment, the state difference at that moment is determined based on the instantaneous state information at that moment and the instantaneous state information at the previous moment; The start and end times of the motion of the target object are determined based on the state difference and critical value at each time point, wherein the critical value is determined based on the state difference when the target object is at rest. The motion time of the target object is determined based on the motion start time and the motion end time; Determining the start and end times of the target object's motion based on the state differences and critical values ​​at each moment includes: The interval of the target object's stationary moments during the motion process is determined based on the state differences at each moment. Determine the mean and variance of all state differences within the static time interval, and determine the critical value using a preset formula based on the mean and variance of the states; The state difference at each moment is compared with the critical value in chronological order. The moment when the state difference first exceeds the critical value is taken as the start moment of the movement, and the moment when the state difference last exceeds the critical value is taken as the end moment of the movement.

2. The motion timing method according to claim 1, characterized in that, After acquiring the instantaneous state information of the target object at each moment during its motion, the method further includes: The instantaneous state information at each moment is converted into data to obtain the state parameters at each moment; Determining the state difference at any given moment based on the instantaneous state information at that moment and the instantaneous state information at the previous moment includes: The state parameter at the given time is subtracted from the state parameter at the previous time to obtain the state difference value at the given time.

3. The motion timing method according to claim 1, characterized in that, The preset formula is: L=M+nS Wherein, L is the critical value, M is the state mean, S is the state variance, and n is the coefficient of the state variance.

4. The motion timing method according to claim 1, characterized in that, After determining the state difference at any given time based on the instantaneous state information at that time and the instantaneous state information at the previous time, the method further includes: The state difference at each time point is denoised using a moving average algorithm.

5. The motion timing method according to any one of claims 1-4, characterized in that, The acquisition of instantaneous state information of the target object at various moments during its motion includes: Acquire image data of the target object at each moment during the motion; The instantaneous state information at each moment is determined based on the image data at each moment; for any instantaneous state information at any moment, the instantaneous state information includes the position information and color channel value of at least one pixel in the image data, and the position information in the instantaneous state information at each moment is the same.

6. A sports timing device, characterized in that, include: The acquisition module is used to acquire instantaneous state information of the target object at various moments during the motion process. The motion process includes the static state and the motion state of the target object. The target object is a landing gear. The instantaneous state information includes at least the color channel values ​​in the image data, the pitch and volume values ​​in the audio data, or displacement data. The first determining module is used to determine the state difference at any given time based on the instantaneous state information at that time and the instantaneous state information at the previous time. The second determining module is used to determine the start time and end time of the motion of the target object based on the state difference and critical value at each time, wherein the critical value is determined based on the state difference when the target object is in a stationary state. A motion time determination module is used to determine the motion time of the target object based on the motion start time and the motion end time. The second determining module is specifically used to: determine the static time interval of the target object during the motion process based on the state difference at each time; determine the state mean and state variance of all the state differences within the static time interval, and determine the critical value using a preset formula and based on the state mean and state variance; compare the state difference at each time with the critical value in chronological order, and take the time corresponding to the state difference that first exceeds the critical value as the motion start time, and take the time corresponding to the state difference that last exceeds the critical value as the motion end time.

7. 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, it implements the motion timing method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the motion timing method as described in any one of claims 1 to 5.

Images