Football juggling examination counting method and device and storage medium

Abstract

The invention relates to the field of sports visual identification, and discloses a football juggling examination counting method and device and a storage medium. The method comprises the following steps: reading a motion video of an examinee, and carrying out frame disassembly processing on the motion video to obtain N ordered motion frame images; according to a preset target detection algorithm, performing target framing processing on the ith motion frame image to obtain an ith examinee foot frame and an ith football frame; calculating the i-th intersection area between the i-th football frame and the i-th examinee foot frame; when the i-th intersection area is larger than a preset touch threshold value, calculating the (i + M)-th foot ball distance; if yes, adding 1 to the effective frame number of the effective counter; and when the effective frame number is greater than the preset frame number threshold value, adding 1 to the juggling count of the juggling counter, and resetting the effective frame number of the effective counter to be zero. In the embodiment of the invention, juggling is identified through the geometrical relationship between the football frame and the foot frame, so that the identification calculation amount is reduced, and the counting stability is improved.

Description

Technical Field

[0001] The present invention relates to the field of sports visual recognition, and in particular to a football juggling test counting method, device and storage medium. Background Art

[0002] Juggling is a fundamental technique in soccer. It requires players to continuously juggle the ball using various parts of the body (such as the instep, thigh, and head) to keep it in the air. Through juggling practice, players can significantly improve their perception of the ball, known as their "ball sense," which is crucial for precisely controlling the direction, force, and rhythm of the ball during play.

[0003] During training and competition, accurately counting the number of juggles is a key indicator for assessing a player's skill level. The number of juggles, to a certain extent, reflects a player's ability to control the ball and their physical coordination. However, traditional juggling counting methods typically rely on manual counting, which presents numerous problems. Manual counting is inefficient, particularly when the number of juggles is high, as the counter can easily become distracted or fatigued, leading to missed or double-counted counts. Manual counting is also susceptible to interference from external factors, such as noise from the training ground or cheers from the audience, which can affect the accuracy of the count and make it impossible to objectively assess a player's skill level. To overcome the inaccuracy of manual juggling counting, Chinese invention CN119540840B proposes a method for counting juggles using human skeletal points. However, this method requires a high computational workload and high cost for image processing. Furthermore, the skeletal point method is prone to distortion in juggling counts when multiple human figures are included in the image, and the juggling counting lacks stability. Therefore, to address the current technical issues of visual recognition of soccer juggling counting, which require a high computational workload and lack stability, a new technology is needed to address these issues. Summary of the Invention

[0004] The main purpose of the present invention is to solve the technical problems of large computational complexity and insufficient stability in the current visual recognition of football juggling counting.

[0005] A first aspect of the present invention provides a method for counting soccer juggling tests, comprising the steps of: Reading a motion video of the examinee, and performing frame decomposition processing on the motion video to obtain N ordered motion frame images, where N is a positive integer; According to the preset target detection algorithm, target framing is performed on the i-th motion frame image to obtain the i-th candidate's foot frame and the i-th football frame, where i is a positive integer, i=1, 2, 3..., N; Calculating the i-th intersection area between the i-th football frame and the i-th examinee's foot frame; When the i-th intersection area is greater than the preset touch threshold, the i+M-th foot-ball distance between the i+M-th examinee's foot frame and the i+M-th football frame corresponding to the i+M-th motion frame image is calculated, where M=i+1, i+2, ..., Ni; When the (i+M)th foot-ball distance is greater than a preset analysis threshold, the valid frame number of a preset valid counter is increased by 1; When the valid frame number is greater than a preset frame number threshold, the juggling count of the preset juggling counter is increased by 1, and the valid frame number of the valid counter is reset to zero.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the step of performing target framing processing on the i-th motion frame image according to a preset target detection algorithm to obtain the i-th examinee's foot frame and the i-th football frame includes: According to the preset target detection algorithm, target framing is performed on the i-th motion frame image to obtain the j-th i-th human body frame, the k-th i-th foot frame, and the i-th football frame, where i, j, and k are positive integers, i = 1, 2, 3, ..., N; Traversing and comparing the j i-th human frames with the preset examination area to obtain the i-th candidate's human frame; The k i-th foot frames are traversed and compared with the i-th examinee's body frame to obtain at least one i-th examinee's foot frame.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the step of traversing and comparing the j i-th body frames with a preset examination area to obtain the i-th candidate's body frame includes: Calculating the intersection area ratios of j i-th human body frames and the preset examination area respectively to obtain j i-th overlap rates; The i-th human body frame corresponding to the maximum overlap rate among the j i-th overlap rates is screened out to obtain the i-th candidate's human body frame.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the step of respectively calculating the ratio of the intersection areas of the j i-th human body frames and the preset examination area to obtain the j i-th overlap rates includes: Calculating the intersection areas of the j i-th human body frames and the preset examination area respectively, to obtain the intersection areas corresponding to the j i-th human body frames; The intersection area mappings corresponding to the j i-th human body frames are divided by the frame areas of the j i-th human body frames to obtain the j i-th overlap rate.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, the step of traversing and comparing the k i-th foot frames with the i-th candidate's body frame to obtain at least one i-th candidate's foot frame includes: Calculate the intersection area ratios of the k i-th foot frames and the examinee's body frame respectively to obtain the k i-th correlation overlap rates; Traversing and determining whether the k i-th association overlap rates are greater than a preset association threshold; When it is greater than a preset correlation threshold, the i-th foot frame corresponding to the i-th correlation overlap rate greater than the preset correlation threshold is determined as the i-th examinee's foot frame.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the step of respectively calculating the intersection area ratios of the k i-th foot frames and the examinee's body frame to obtain k i-th association overlap rates includes: Calculate the intersection areas of the k i-th foot frames and the examinee's body frame to obtain the intersection areas corresponding to the k i-th foot frames; The intersection area mappings corresponding to the k i-th foot frames are divided by the frame areas of the k i-th foot frames to obtain the k i-th association overlap rates.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the step of calculating the i-th intersection area between the i-th football frame and the i-th examinee's foot frame includes: Determine whether the i-th football frame and the i-th examinee's foot frame have an intersection; When there is no intersection, it is determined whether the i+1th football frame corresponding to the i+1th motion frame image and the i+1th examinee's foot frame corresponding to the i+1th motion frame image have an intersection; When there is an intersection, the i-th intersection area is calculated based on the intersection coordinates of the i-th football frame and the i-th examinee's foot frame.

[0012] Optionally, in a seventh implementation of the first aspect of the present invention, the step of calculating the i-th intersection area based on the intersection coordinates of the i-th football frame and the i-th examinee's foot frame includes: I=max(X a2 -X b1 +1,0)*max(Y a2 -Y b1 +1,0); Where I is the area of ​​the ith intersection, (X b1 , Y b1 ) is the coordinate of the upper left corner of the intersection of the i-th football frame and the i-th candidate’s foot frame, (X a2 , Y a2 ) is the coordinate of the lower right corner of the intersection of the i-th football frame and the i-th candidate's foot frame.

[0013] A second aspect of the present invention provides a football juggling test counting device, comprising: a memory and at least one processor, wherein the memory stores instructions, and the memory and the at least one processor are interconnected via a line; the at least one processor calls the instructions in the memory so that the football juggling test counting device executes the above-mentioned football juggling test counting method.

[0014] A third aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which, when executed on a computer, causes the computer to execute the above-mentioned soccer juggling test counting method.

[0015] In an embodiment of the present invention, the examinee's foot frame and ball frame are identified in a captured sports video. The intersection of these frames simplifies the triggering of juggling counting. Once the distance between the foot frame and ball frame exceeds a threshold, the system adds the number of frames during which the foot and ball are separated. This eliminates interference caused by invalid touches (e.g., stepping on the ball), and resets the valid frame count after a valid juggle is completed. This reduces the computational complexity of visual recognition for juggling counting and increases counting stability, ensuring it is reliably monitored despite variations in the examinee's juggling postures and the frame rate of the captured image. This solution identifies juggling by combining the spatial relationship at the moment of contact with the ball with the geometric relationship between the ball frame and foot frame before and after contact, effectively addressing the current technical issues of high computational complexity and insufficient stability in visual recognition of juggling counting. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an embodiment of a method for counting football juggling in an examination according to an embodiment of the present invention; Figure 2 102 is a schematic diagram of a specific embodiment of the method for counting football juggling in an examination according to an embodiment of the present invention; Figure 3a A schematic diagram of content identified by an object detection algorithm according to an embodiment of the present invention; Figure 3b Schematic diagram of the implementation of the target detection algorithm recognition of an embodiment of the present invention; Figure 4 A schematic diagram of the overlapping of a football frame and a test taker's foot frame in a football juggling test counting method according to an embodiment of the present invention; Figure 5 Schematic diagram of an embodiment of a football juggling test counting device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The embodiment of the present invention provides a method, device and storage medium for counting soccer juggling tests.

[0018] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0019] In the description of the embodiments disclosed herein, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to." The term "based on" should be understood as "based, at least in part, on." The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment." The terms "first," "second," etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0020] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 An embodiment of a method for counting football juggling in an examination according to an embodiment of the present invention comprises the steps of: 101. Reading a motion video of the examinee and performing frame decomposition processing on the motion video to obtain N ordered motion frame images, where N is a positive integer; In this embodiment, a camera can be used to capture a motion video of the examinee. This motion video can be a real-time video captured during the examinee's examination, or it can be a video that is captured first and then analyzed. The motion video can be decomposed according to a set frame rate. For example, if the frame rate is 120 frames per second and the motion video is one minute long, 7200 orderly motion frame images can be obtained by decomposing the video frame by frame. Alternatively, a motion frame image can be extracted and decomposed every three frames, resulting in 2400 orderly motion frame images. The decomposition of the motion video can be performed by selecting specific decomposition parameters based on the frame rate video generated by the camera capture image, which will not be described in detail here.

[0021] 102. Perform target framing processing on the i-th motion frame image according to a preset target detection algorithm to obtain the i-th examinee's foot frame and the i-th football frame, where i is a positive integer, i=1, 2, 3, ..., N; In this embodiment, the deep learning YOLO-V8 target detection algorithm can be used to perform target frame identification processing on the first motion frame image of the 2400 disassembled motion frame images, and the corresponding first candidate's foot frame and first football frame can be identified from the first motion frame image. By traversing the 2400 motion frame images, the i-th candidate's foot frame and the i-th football frame can be identified, where i=1, 2, 3..., 2400.

[0022] For details, please refer to Figure 2 , Figure 2 FIG. 1 is a schematic diagram of a specific embodiment of step 102 of the soccer juggling test counting method according to an embodiment of the present invention. Step 102 includes the following specific implementation methods: 1021. Perform target framing processing on the i-th motion frame image according to a preset target detection algorithm to obtain the j-th i-th human body frame, the k-th i-th foot frame, and the i-th football frame, where i, j, and k are positive integers, and i = 1, 2, 3, ..., N; 1022. Traverse and compare the j i-th human body frames with the preset examination area to obtain the i-th candidate's human body frame; 1023. Traverse and compare the k i-th foot frames with the i-th examinee's body frame to obtain at least one i-th examinee's foot frame.

[0023] In steps 1021-1023, the test area is introduced to assist in identifying the test taker object, which can increase the recognition accuracy of the football juggling object. Figure 3a 、 3b , Figure 3a This is a schematic diagram of the content identified by the target detection algorithm according to an embodiment of the present invention. Figure 3b Schematic diagram of the implementation of the target detection algorithm recognition according to an embodiment of the present invention. Figure 3a 、 3b In the figure, 0 represents the human body frame, 1 represents the foot frame, 2 represents the football frame, and A represents the test area.

[0024] Using the target detection algorithm, the first motion frame image is subjected to target framing, resulting in two first-person frames, four first-foot frames, and a first ball frame. In Figure 3, Area A represents the predefined test area. The overlap ratio between the two first-person frames and Area A is calculated sequentially, and the first-person frame with the highest overlap ratio is identified as the first candidate's frame. This mechanism effectively eliminates interference from onlookers and ensures that the candidate and the ball being juggled remain locked. Similarly, the correlation between the four first-foot frames and the first candidate's frame is calculated sequentially, and the first-foot frame that meets the required correlation ratio is identified as the first candidate's foot frame.

[0025] Furthermore, step 1022 includes the following specific implementations: 10221. Calculate the ratio of the intersection area between the j i-th human body frames and the preset examination area to obtain the j i-th overlap rates; 10222. Filter out the i-th body frame corresponding to the maximum overlap rate among the j i-th overlap rates to obtain the i-th candidate's body frame.

[0026] In steps 10221 and 10222, the intersection areas of the two first body frames and the preset examination area are calculated to obtain a first area and a second area. The first area and the second area are respectively calculated with the total area corresponding to the two first body frames to obtain two first overlap rates, which are 92% and 0%, respectively. The maximum overlap rate of the two first overlap rates is compared, and the first body frame corresponding to the 92% overlap rate is determined as the first candidate's body frame.

[0027] Specifically, step 10221 includes the following specific implementation methods: 102211. Calculate the intersection areas of the j i-th human body frames and the preset examination area respectively to obtain the intersection areas corresponding to the j i-th human body frames; 102212. Divide the intersection area mappings corresponding to the j i-th human body frames by the frame areas of the j i-th human body frames to obtain the j i-th overlap rate.

[0028] In steps 102211 and 102212, the intersection areas of the two first human frames and the preset test area are calculated, resulting in intersection areas of 0 and 35 corresponding to the two first human frames. Next, the areas of the two first human frames are calculated as 31 and 85, respectively. The intersection areas of the two first human frames are divided by the areas of the two first human frames, resulting in the values ​​0 / 31 and 35 / 85, respectively, to obtain the two first overlap rates of 0% and 41.176%.

[0029] Furthermore, step 1023 includes the following specific implementations: 10231. Calculate the intersection area ratios of the k i-th foot frames and the examinee's body frame respectively to obtain k i-th correlation overlap rates; 10232. Determine whether the k i-th association overlap rates are greater than a preset association threshold; 10233. When the value is greater than a preset association threshold, the i-th foot frame corresponding to the i-th association overlap rate greater than the preset association threshold is determined as the i-th candidate's foot frame.

[0030] In steps 10231-10233, the intersection area ratios of the four first foot frames and the candidate's body frame are calculated, resulting in four first correlation overlap rates: 0%, 0%, 99%, and 96%, respectively. The correlation threshold is 80%, and the first foot frame corresponding to the four first correlation overlap rates greater than 80% is determined as the first candidate's foot frame.

[0031] Furthermore, step 10231 includes the following specific implementations: 102311. Calculate the intersection areas of the k i-th foot frames and the examinee's body frame to obtain the intersection areas corresponding to the k i-th foot frames; 102312. Divide the intersection area mappings corresponding to the k i-th foot frames by the frame areas of the k i-th foot frames to obtain the k i-th associated overlap rates.

[0032] In steps 102311-102312, the intersection area of ​​the four first foot frames and the candidate's body frame is first calculated, and the intersection areas corresponding to the four first foot frames are 0, 0, 9.9, and 9.6. The box areas corresponding to the four first foot frames are 8.9, 9.7, 10, and 9.8. According to the linked list, the mappings of 0, 0, 9.9, and 9.6 can be divided by 8.9, 9.7, 10, and 9.8 to obtain the four first association overlap rates of 0%, 0%, 99%, and 97.95%. The data to be calculated can be stored and calculated in the form of lists, arrays, etc., and the mapping relationship can be implemented using linked lists and indexes, which will not be explained here.

[0033] 103. Calculate the i-th intersection area between the i-th football frame and the i-th examinee's foot frame; In this embodiment, the overlapping area between the first soccer ball frame and the first examinee's foot frame in the first frame of image data is calculated as the first intersection area.

[0034] Specifically, step 103 includes the following specific implementation methods: 1031. Determine whether the i-th football frame and the i-th examinee's foot frame have an intersection; 1032. When there is no intersection, determining whether the (i+1)th football frame corresponding to the (i+1)th motion frame image and the (i+1)th examinee's foot frame corresponding to the (i+1)th motion frame image have an intersection; 1033. When there is an intersection, the i-th intersection area is calculated based on the intersection coordinates of the i-th football frame and the i-th examinee's foot frame.

[0035] In steps 1031-1033, it is first analyzed whether there is any overlapping intersection between the first football frame and the first candidate's foot frame. This intersection analysis can be a coordinate data relationship analysis, or collision detection or space segmentation analysis.

[0036] If the qualitative analysis shows that there is no intersection, then analyze whether the second football frame and the second candidate's foot frame have an overlapping intersection, and then continue the analysis until a football frame and a candidate's foot frame with an intersection are encountered.

[0037] Please refer to Figure 4 , Figure 4 Schematic diagram of the football frame and the examinee's foot frame overlapping in the football juggling test counting method according to an embodiment of the present invention. The coordinates of the upper left corner, lower right corner, lower left corner, and upper right corner of the examinee's foot frame are (X a1 , Y a1 )、(Xa2 , Y a2 )、(X a1 , Y a2 )、(X a2 , Y a1 ), the coordinates of the upper left corner, lower right corner, lower left corner, and upper right corner of the football box are (X b1 , Y b1 )、(X b2 , Y b2 )、(X b1 , Y b2 )、(X b2 , Y b1 ). After qualitative analysis of the intersection, there are two intersections. The coordinates of the upper left corner of the intersection are: X b1 =max(X a1 , X b1 ), Y b1 =max(Y a1 , Y b1 ), the coordinates of the lower right corner are: X a2 =min(X a2 , X b2 ), Y b2 =min(Y a2 , Y b2 ).

[0038] Calculation of the intersection of two boxes: I=max(X a2 -X b1 +1,0)*max(Y a2 -Y b1 +1,0); Where I is the area of ​​the i-th intersection, (X b1 , Y b1 ) is the coordinate of the upper left corner of the intersection of the i-th football frame and the i-th candidate’s foot frame, (X a2 , Y a2 ) is the coordinate of the lower right corner of the intersection of the i-th football frame and the i-th candidate's foot frame.

[0039] Import the data analysis before calculation, then the overall calculation is actually: I=max(min(X a2 , X b2 )-max(X a1 , X b1 )+1,0)*max(min(Y a2 , Y b2 )-max(Y a1 , Y b1 )+1,0), where I is the area of ​​the i-th intersection, (X b1 , Y b1) is the coordinate of the upper left corner of the intersection of the i-th football frame and the i-th candidate’s foot frame, (X a2 , Y a2 ) is the coordinate of the lower right corner of the intersection of the i-th football frame and the i-th candidate’s foot frame; Lead to the two frame intersection judgment condition: min(X a2 , X b2 )-max(X a1 , X b1 ) or min(Y a2 , Y b2 )-max(Y a1 , Y b1 ) are both greater than zero. If they are both greater than zero, they intersect. If they are not both greater than zero, they do not intersect.

[0040] 104. When the i-th intersection area is greater than a preset touch threshold, the i+M-th foot-ball distance between the i+M-th examinee's foot frame and the i+M-th football frame corresponding to the i+M-th motion frame image is calculated, where M=i+1, i+2, ..., Ni; In this embodiment, when the first intersection area is greater than the preset touch threshold 20, it is considered that the actual objects corresponding to the two frames have touched, and then the distances between the center points of the examinee's foot frame and the center points of the football frame in the N-1 motion frame images after the first motion frame image are calculated one by one to obtain the second, third,..., N-1 foot-to-ball distances.

[0041] 105. When the (i+M)th foot-ball distance is greater than a preset analysis threshold, the valid frame number of a preset valid counter is increased by 1; In this embodiment, after the touch threshold is triggered, subsequent motion frames 2, 3, ..., and N-1 are continuously analyzed for instances where the foot-ball distance exceeds a preset analysis threshold. If this occurs, it indicates that after contact with the foot, the ball has moved away from the foot. The number of frames in which the foot-ball distance exceeds the preset analysis threshold is continuously counted. If the number of valid frames exceeds 5-10, the juggling is considered valid. This approach, which continuously monitors the number of valid frames in which the ball is away from the foot, prevents invalid juggling, such as stepping on the ball, from being recorded.

[0042] 106. When the valid frame number is greater than a preset frame number threshold, the juggling count of a preset juggling counter is increased by 1, and the valid frame number of the valid counter is reset to zero.

[0043] In this embodiment, after the valid frame count exceeds 5-10, the juggling count in the preset juggling counter is incremented by 1, and the valid frame count in the valid counter is reset to zero, completing a cycle. The next time the juggling count is incremented, the contact state between the foot and the ball is determined. The number of frames separating the foot and the ball after contact is continuously monitored, and the total number of juggling attempts is cyclically counted.

[0044] In an embodiment of the present invention, the examinee's foot frame and ball frame are identified in a captured sports video. The intersection of these frames simplifies the triggering of juggling counting. Once the distance between the foot frame and ball frame exceeds a threshold, the system adds the number of frames during which the foot and ball are separated. This eliminates interference caused by invalid touches (e.g., stepping on the ball), and resets the valid frame count after a valid juggle is completed. This reduces the computational complexity of visual recognition for juggling counting and increases counting stability, ensuring it is reliably monitored despite variations in the examinee's juggling postures and the frame rate of the captured image. This solution identifies juggling by combining the spatial relationship at the moment of contact with the ball with the geometric relationship between the ball frame and foot frame before and after contact, effectively addressing the current technical issues of high computational complexity and insufficient stability in visual recognition of juggling counting.

[0045] Figure 5 This is a schematic diagram of the structure of a soccer juggling test counting device provided by an embodiment of the present invention. The soccer juggling test counting device 500 may vary significantly depending on configuration or performance. It may include one or more central processing units (CPUs) 510 (e.g., one or more processors), memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing application programs 533 or data 532. The memory 520 and storage media 530 may be either transient or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of instructions operating on the soccer juggling test counting device 500. Furthermore, the processor 510 may be configured to communicate with the storage medium 530 to execute the series of instructions stored in the storage medium 530 on the soccer juggling test counting device 500.

[0046] The soccer ball-jumping-based test counting device 500 may further include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, Free BSD, etc. It will be appreciated by those skilled in the art that Figure 5The structure of the football juggling test counting device shown does not constitute a limitation on the football juggling-based test counting device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0047] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, cause the computer to execute the steps of the football juggling examination counting method.

[0048] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0049] In addition, although adopting specific order to describe each operation, this should be understood as requiring such operation to be carried out in the specific order shown or in sequential order, or requiring that all illustrated operations should be carried out to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although comprising some specific implementation details in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation also can be implemented in a plurality of implementations individually or in the mode of any suitable subcombination.

[0050] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for counting football juggling in an examination, characterized in that: Including steps: Reading a motion video of the examinee, and performing frame decomposition processing on the motion video to obtain N ordered motion frame images, where N is a positive integer; According to the preset target detection algorithm, target framing is performed on the i-th motion frame image to obtain the i-th candidate's foot frame and the i-th football frame, where i is a positive integer, i=1, 2, 3..., N; Calculating the i-th intersection area between the i-th football frame and the i-th examinee's foot frame; When the i-th intersection area is greater than the preset touch threshold, the i+M-th foot-ball distance between the i+M-th examinee's foot frame and the i+M-th football frame corresponding to the i+M-th motion frame image is calculated, where M=i+1, i+2, ..., Ni; When the (i+M)th foot-ball distance is greater than a preset analysis threshold, the valid frame number of a preset valid counter is increased by 1; When the valid frame number is greater than a preset frame number threshold, the juggling count of the preset juggling counter is increased by 1, and the valid frame number of the valid counter is reset to zero.

2. The soccer juggling test counting method according to claim 1, wherein: The step of performing target framing processing on the i-th motion frame image according to the preset target detection algorithm to obtain the i-th examinee's foot frame and the i-th football frame includes: According to the preset target detection algorithm, target framing is performed on the i-th motion frame image to obtain the j-th i-th human body frame, the k-th i-th foot frame, and the i-th football frame, where i, j, and k are positive integers, i = 1, 2, 3, ..., N; Traversing and comparing the j i-th human frames with the preset examination area to obtain the i-th candidate's human frame; The k i-th foot frames are traversed and compared with the i-th examinee's body frame to obtain at least one i-th examinee's foot frame.

3. The soccer juggling test counting method according to claim 2, wherein: The step of traversing and comparing the j i-th human body frames with the preset examination area to obtain the i-th candidate's human body frame comprises: Calculating the intersection area ratios of j i-th human body frames and the preset examination area respectively to obtain j i-th overlap rates; The i-th human body frame corresponding to the maximum overlap rate among the j i-th overlap rates is screened out to obtain the i-th candidate's human body frame.

4. The soccer juggling test counting method according to claim 3, wherein: The step of respectively calculating the intersection area ratios of the j i-th human body frames and the preset examination area to obtain the j i-th overlap rates includes: Calculating the intersection areas of the j i-th human body frames and the preset examination area respectively, to obtain the intersection areas corresponding to the j i-th human body frames; The intersection area mappings corresponding to the j i-th human body frames are divided by the frame areas of the j i-th human body frames to obtain the j i-th overlap rate.

5. The soccer juggling test counting method according to claim 2, wherein: The step of traversing and comparing the k i-th foot frames with the i-th examinee's body frame to obtain at least one i-th examinee's foot frame comprises: Calculate the intersection area ratios of the k i-th foot frames and the examinee's body frame respectively to obtain the k i-th correlation overlap rates; Traversing and determining whether the k i-th association overlap rates are greater than a preset association threshold; When it is greater than a preset correlation threshold, the i-th foot frame corresponding to the i-th correlation overlap rate greater than the preset correlation threshold is determined as the i-th examinee's foot frame.

6. The soccer juggling test counting method according to claim 5, characterized in that: The step of respectively calculating the intersection area ratios of the k i-th foot frames and the examinee's body frame to obtain the k i-th correlation overlap rates includes: Calculate the intersection areas of the k i-th foot frames and the examinee's body frame to obtain the intersection areas corresponding to the k i-th foot frames; The intersection area mappings corresponding to the k i-th foot frames are divided by the frame areas of the k i-th foot frames to obtain the k i-th association overlap rates.

7. The soccer juggling test counting method according to claim 1, wherein: The step of calculating the i-th intersection area between the i-th football frame and the i-th examinee's foot frame comprises: Determine whether the i-th football frame and the i-th examinee's foot frame have an intersection; When there is no intersection, it is determined whether the i+1th football frame corresponding to the i+1th motion frame image and the i+1th examinee's foot frame corresponding to the i+1th motion frame image have an intersection; When there is an intersection, the i-th intersection area is calculated based on the intersection coordinates of the i-th football frame and the i-th examinee's foot frame.

8. The soccer juggling test counting method according to claim 7, wherein: The step of calculating the i-th intersection area based on the intersection coordinates of the i-th football frame and the i-th examinee's foot frame includes: I=max(X a2 -X b1 +1,0)*max(Y a2 -Y b1 +1,0); Where I is the area of ​​the ith intersection, (X b1 , Y b1 ) is the coordinate of the upper left corner of the intersection of the i-th football frame and the i-th candidate’s foot frame, (X a2 , Y a2 ) is the coordinate of the lower right corner of the intersection of the i-th football frame and the i-th candidate's foot frame.

9. A soccer juggling test counting device, characterized in that: The soccer juggling test counting device comprises: a memory and at least one processor, wherein the memory stores instructions, and the memory and the at least one processor are interconnected via a circuit; The at least one processor calls the instructions in the memory to enable the football juggling test counting device to execute the football juggling test counting method according to any one of claims 1 to 8.

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 soccer juggling test counting method according to any one of claims 1 to 8 is implemented.

Images