Football dribbling and rod winding compliance judgment method and system based on image recognition

Abstract

The invention relates to the technical field of football pole winding testing, and provides a football dribbling pole winding compliance judgment method and system based on image recognition, and the method comprises the steps: constructing a time interval through the detection signal receiving time between marker poles, taking a time point in the time interval to correspondingly obtain an image frame in a pole winding video, the obtained pole-winding image reflects the relative positions of the football and the athlete with the marker pole, whether the football pole-winding route is in compliance or not is judged by judging the consistency of the corresponding football relative position and the athlete relative position at the associated time point, and the football dribbling pole-winding detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of football dribbling around a pole test, and in particular to a method and system for judging compliance of football dribbling around a pole based on image recognition. Background Art

[0002] Currently, the soccer pole-circling event is the main content of sports testing. However, general refereeing work requires manual monitoring of the entire process of the pole-circling event, which is very labor-intensive when there are many testers, and human errors may occur in the judgment. The existing image detection technology needs to identify the movement trajectory of athletes and soccer balls throughout the entire process, which is not only costly and difficult to develop, but also inefficient in generating trajectories for judgment. Summary of the invention

[0003] The present invention provides a method for judging compliance of football dribbling around a pole based on image recognition, which is used to solve the problem of low efficiency of judging compliance of football dribbling around a pole in the prior art.

[0004] The first aspect of the present invention provides a method for judging compliance of a soccer dribbling around a pole based on image recognition, comprising: Acquire a first detection signal and a second detection signal, sort the detection signals according to the receiving time and establish a first detection time interval and a second detection time interval; compare the first detection time interval with the second detection time interval, and associate the first detection time interval with the most similar time period with the second detection time interval; Acquire a first pole-winding video, where the first pole-winding video is shot along the pole placement direction; extract time points in the associated first detection time interval and second detection time interval to obtain first time points and second time points, and acquire corresponding images in the first pole-winding video at the first time points and the second time points to obtain first pole-winding images and second pole-winding images; The relative positions of the football and the sign pole are identified in the first pole-wrapping image, and based on the time point sequence of the first pole-wrapping image, it is determined whether the corresponding relative positions are staggered; if so, the relative positions of the human body and the sign pole are identified in the second pole-wrapping image, and based on the correlation between the first detection time interval and the second detection time interval, it is determined whether the relative positions of the human body and the sign pole are consistent with the relative positions of the associated football and the sign pole; if so, it is determined that the football dribbling around the pole is compliant.

[0005] Optionally, also include: A second pole-wrapping video is obtained, where the second pole-wrapping video is shot perpendicular to the pole placement direction; a corresponding third time point and a fourth time point are obtained according to the first detection signal and the second detection signal, and a third pole-wrapping image and a fourth pole-wrapping image corresponding to the third time point and the fourth time point are obtained in the second pole-wrapping video; each marker pole and a football are identified in the third pole-wrapping image, the marker poles are sorted, and a first marker pole interval where the football is located is identified; each marker pole and a human body are identified in the fourth pole-wrapping image, the marker poles are sorted, and a second marker pole interval where the human body is located is identified; and whether the first marker pole interval is consistent with the associated second marker pole interval is determined based on the association relationship, and if not, it is deemed that the football dribbling around the pole is in violation of the regulations.

[0006] Optionally, after obtaining the first rod-winding image and the second rod-winding image, the method further includes: The first rod-wrapped image and the second rod-wrapped image are segmented using a preset region of interest frame, and images not within the region of interest frame are eliminated.

[0007] The second aspect of the present application provides a football dribbling compliance judgment system based on image recognition, comprising: A detection signal time processing module, used to obtain the first detection signal and the second detection signal, sort the detection signals according to the receiving time and establish the first detection time interval and the second detection time interval; compare the first detection time interval with the second detection time interval, and associate the first detection time interval with the most similar time period with the second detection time interval; An image acquisition module is used to acquire a first pole-winding video, wherein the first pole-winding video is shot along the pole placement direction; extract time points in the associated first detection time interval and second detection time interval to obtain first time points and second time points, and acquire corresponding images in the first pole-winding video at the first time points and the second time points to obtain first pole-winding images and second pole-winding images; The image analysis and judgment module is used to identify the relative positions of the football and the marker pole in the first pole-wrapping image, and judge whether the corresponding relative positions are staggered according to the time point sequence of the first pole-wrapping image; if so, identify the relative positions of the human body and the marker pole in the second pole-wrapping image, and judge whether the relative positions of the human body and the marker pole are consistent with the relative positions of the associated football and the marker pole according to the correlation between the first detection time interval and the second detection time interval; if so, judge that the football dribbling around the pole is compliant.

[0008] Optionally, also include: The pole-circling route judgment module is used to obtain a second pole-circling video, which is shot perpendicular to the pole placement direction; obtain the corresponding third time point and fourth time point according to the first detection signal and the second detection signal, and obtain the third pole-circling image and the fourth pole-circling image corresponding to the third time point and the fourth time point in the second pole-circling video; identify each marker pole and the football in the third pole-circling image, sort each marker pole and identify the first marker pole interval where the football is located; identify each marker pole and the human body in the fourth pole-circling image, sort each marker pole and identify the second marker pole interval where the human body is located; determine whether the first marker pole interval is consistent with the associated second marker pole interval based on the association relationship, and if not, it is regarded as a violation of the football dribbling around the pole.

[0009] Optionally, after obtaining the first rod-wrapped image and the second rod-wrapped image, the image acquisition module further includes: The first rod-wrapped image and the second rod-wrapped image are segmented using a preset region of interest frame, and images not within the region of interest frame are eliminated.

[0010] In a third aspect, the present application provides a method and device for judging compliance of dribbling a football around a pole based on image recognition, the device comprising a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the method for determining compliance of dribbling a soccer ball around a pole based on image recognition according to the instructions in the program code as described in any one of the first aspects of the present invention.

[0011] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to execute a method for determining compliance of a football dribbling around a pole based on image recognition as described in any one of the first aspects of the present invention.

[0012] It can be seen from the above technical scheme that the present invention has the following advantages: a time interval is constructed by the detection signal reception time between the marker poles, and a time point is taken in the time interval to obtain the image frame in the pole-circling video. The obtained pole-circling image reflects the relative positions of the football, the athlete and the marker pole. By judging whether the corresponding relative position of the football and the relative position of the athlete at the associated time point are consistent, it is judged whether the route of the football around the pole is compliant, thereby improving the efficiency of the detection of football dribbling around the pole. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 It is a flowchart of a method for judging compliance of soccer dribbling around a pole based on image recognition; Figure 2 This is a structural diagram of a football dribbling compliance judgment system based on image recognition. DETAILED DESCRIPTION

[0015] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] The present invention provides a method for judging compliance of football dribbling around a pole based on image recognition, which is used to solve the problem of low efficiency of judging compliance of football dribbling around a pole in the prior art.

[0017] See also Figure 1 , Figure 1 A first flow chart of a method for determining compliance of a soccer dribbling around a pole based on image recognition provided by an embodiment of the present invention.

[0018] S100, obtaining a first detection signal and a second detection signal, sorting the detection signals according to the receiving time and establishing a first detection time interval and a second detection time interval; comparing the first detection time interval with the second detection time interval, and associating the first detection time interval with the most similar time period with the second detection time interval; It should be noted that an infrared sensor is provided on the sign pole of the winding pole, which is used to detect objects passing through the area between the two sign poles. At least two beams of infrared light can be used to establish an infrared grating. When an athlete or an object blocks the infrared light, a detection signal will be triggered. The infrared light is divided into two categories according to different infrared light setting heights. The infrared light detection signal within the height range of 0-30cm can be set as the first detection signal to detect the football passing signal, and the infrared light detection signal within the height range of 1m-1.5m can be set as the second detection signal to detect the human body passing signal; because the first detection signal is triggered not only by the football passing, but also by the human foot passing, and the second detection signal is triggered by the arm in addition to the torso, so the first detection signal and the second detection signal are only triggered once in a short period of time, or the first detection signal and the second detection signal are only triggered once between two adjacent sign poles; During the test of an athlete dribbling around a pole, bypassing multiple marker poles will trigger multiple first detection signals and second detection signals. The time interval between each two first detection signals can be regarded as the football moving around the pole, and the time interval between each two second detection signals can be regarded as the athlete moving around the pole. The athlete and the football are two separate individuals. Due to different dribbling postures of the athletes, the torso may pass first and the ball later, or the ball may pass first and the torso later. Therefore, the first detection time interval and the second detection time interval may not be exactly the same. However, because it is the athlete dribbling, the difference between the two time intervals will not be too far. Therefore, the association relationship between the first detection time interval and the second detection time interval can be established based on the time similarity between the time intervals. The associated first detection time interval and second detection time interval reflect the corresponding process of the athlete dribbling around the pole.

[0019] S200, obtaining a first pole-winding video, wherein the first pole-winding video is shot along the pole placement direction; extracting time points in the associated first detection time interval and the second detection time interval to obtain first time points and second time points, and obtaining corresponding images in the first pole-winding video at the first time points and the second time points to obtain first pole-winding images and second pole-winding images; It should be noted that a camera is set up in the venue to film the process of athletes dribbling around the pole, and the start and end time of the video recording is consistent with the start and end time of dribbling around the pole. The camera is started and stopped according to the start signal and the end signal, so that the time of the first video around the pole is consistent with the time point of the detection signal at the marker pole; the marker poles are generally placed at intervals along a straight line, and the camera shooting direction is consistent with the straight line. The camera's line of sight is horizontal and the field of view should capture the ground near the nearest marker pole to the farthest marker pole. In order not to affect the athlete's dribbling, the nearest marker pole to be filmed should be the starting marker pole for dribbling around the pole. When extracting time points in the associated first detection time interval and second detection time interval, time points in the middle of the time interval can be extracted as much as possible. When extracting images captured at time points close to the endpoints of the time interval, the first signal may be triggered by the movement of the legs and feet of the athlete in the manner of pulling the football, resulting in the football not passing between the two marker poles at the corresponding endpoint of the time interval, or the athlete's torso not passing between the two marker poles when the second detection signal is triggered by the arm swing, resulting in subsequent incorrect recognition and judgment. Therefore, in this embodiment, the midpoint of the time interval can be selected according to the two time endpoints of the time interval to extract the time point. For example, if a first time interval is from time t1 to time t2, the time (t1+t2) / 2 can be taken as the corresponding first time point; because the shooting timeline of the first pole-circling video is consistent with the timeline of the infrared detection signal of the marker pole, when the corresponding image frame is extracted in the video at the time point selected according to the time interval of the detection signal, the first pole-circling image and the second pole-circling image accurately record the football picture and the athlete picture at the corresponding moment.

[0020] S300, identifying the relative positions of the football and the sign pole in the first pole-wrapping image, and judging whether the corresponding relative positions are staggered according to the time point sequence of the first pole-wrapping image; if so, identifying the relative positions of the human body and the sign pole in the second pole-wrapping image, and judging whether the relative positions of the human body and the sign pole are consistent with the relative positions of the associated football and the sign pole according to the correlation relationship between the first detection time interval and the second detection time interval; if so, judging that the football dribbling around the pole is compliant; It should be noted that in the first pole-wrapping image, multiple sign poles overlap and divide the screen into two parts, the left and right parts, and the object contour is obtained according to the edge of the grayscale eigenvalue in the image. The object is identified based on the conformity of the contour of the object to the characteristics of the sign pole. For example, after the contour is obtained, the relationship between the longitudinal height and the lateral length of the object is identified. Given the slender appearance of the sign pole, the longitudinal height should be several times the lateral length. In addition, goal posts may also be captured in the image and may be identified as pole-shaped objects, which can be further identified based on the color of the sign pole. Generally, there are red or yellow stripes on the sign pole, while the goal pole is only pure white. The first pole-wrapping image corresponds to the first detection time interval, which corresponds to the situation of the football wrapping around the pole. Therefore, in addition to the sign pole, the football needs to be identified in the first pole-wrapping image. The football is identified according to the circular contour of the object, the midpoint coordinates of the football are calculated according to the edge contour coordinates of the football, and the midpoint coordinates of the sign post are calculated according to the edge contour coordinates of the sign post, which can be the centroid or the center of gravity, and then the relative position of the football and the sign post is identified by comparing the midpoint coordinates of the football and the sign post, and the football is on the left or right side of the sign post by comparing the size of the horizontal coordinate; the corresponding relative position can be obtained in a number of first pole-circling images, and then it is determined whether the relative position appears alternately left and right according to the first time point sequence corresponding to the first pole-circling images. If so, it can be determined that the football has correctly bypassed the sign post, if not, it is possible that the football has not correctly bypassed the pole, for example, the ball continues to dribble on the same side after just touching the infrared beam, and at this time it can be determined that the dribbling route is wrong; In dribbling a football around the pole, it is also necessary to ensure that the athlete and the football are on the same route. Therefore, the athlete's body can be identified according to the outline in the second pole-around-the-pole image to obtain the coordinates of the midpoint of the torso. Similarly, the coordinates of the midpoint of the marker pole can be identified in the second pole-around-the-pole image, and then the coordinates of the midpoint of the torso and the midpoint of the marker pole are compared to identify the relative position of the human body and the marker pole. The midpoint of the torso can be the center of gravity of the athlete. When the limbs pass the pole but the center of gravity does not pass the marker pole, it can be regarded that the athlete has not actually passed the pole. By comparing the magnitude of the horizontal coordinates of the midpoint of the torso and the midpoint of the marker pole, it can be determined whether the athlete is on the left or right side of the marker pole. In the aforementioned step S100, the first detection time interval is associated with the second detection time interval, and there are correspondingly associated first and second time points, that is, there should be correspondingly associated first pole-around-the-pole images and second pole-around-the-pole images. Since the athlete and the football are on the same route, the relative positions in the associated images should be consistent. When it is determined whether the relative position of the human body and the marker pole is consistent with the relative position of the associated football and the marker pole, it can be determined that the football dribbling around the pole is compliant.

[0021] In this embodiment, a time interval is constructed by the detection signal reception time between the marker poles, and a time point is taken in the time interval to obtain the image frame in the pole-circling video. The obtained pole-circling image reflects the relative positions of the football, the athlete and the marker poles. By judging whether the corresponding relative position of the football and the relative position of the athlete at the associated time point are consistent, it is judged whether the route of the football around the pole is compliant, thereby improving the efficiency of the detection of football dribbling around the pole.

[0022] The above is a detailed description of the first embodiment of a method for determining compliance of a football dribbling around a pole based on image recognition provided by the present application. The following is a detailed description of the second embodiment of a method for determining compliance of a football dribbling around a pole based on image recognition provided by the present application.

[0023] In this embodiment, a method for judging compliance of dribbling a soccer ball around a pole based on image recognition is further provided, and further includes: Acquire a second pole-wrapping video, wherein the second pole-wrapping video is shot perpendicular to the pole placement direction; obtain corresponding third and fourth time points according to the first detection signal and the second detection signal, and obtain a third pole-wrapping image and a fourth pole-wrapping image corresponding to the third and fourth time points in the second pole-wrapping video; identify each marker pole and a football in the third pole-wrapping image, sort each marker pole and identify a first marker pole interval where the football is located; identify each marker pole and a human body in the fourth pole-wrapping image, sort each marker pole and identify a second marker pole interval where the human body is located; determine whether the first marker pole interval is consistent with the associated second marker pole interval according to the association relationship, and if not, it is deemed that the football dribbling around the pole is in violation of the rules; It should be noted that the camera is placed on the side of the dribbling pole field, and all the marker poles can be captured in the second dribbling pole video, and the marker poles are distributed along horizontal intervals in the picture; in the second dribbling pole video, it can be recorded between which two marker poles the football and the athlete are passing, and the reception time of the first detection signal and the second detection signal corresponds to the time point. At the third time point, the football is passing through the line between the two marker poles, and at the fourth time point, the athlete is passing through the line between the two marker poles; in the third dribbling pole image and the fourth dribbling pole image, each marker pole is identified and sorted. In this embodiment, there are 4 marker poles that can be sorted as marker poles 1-4. According to the identified football and human body, it is determined between which two marker poles, for example, in a third dribbling pole image, the football is between marker poles No. 2 and No. 3. 1 and 2, and in the associated fourth pole-circling image, the athlete is in the second marker pole interval between marker poles 1 and 2, then the two marker pole intervals are inconsistent, and the athlete may be dribbling the ball so that the football passes between marker poles 2 and 3 from left to right, while the athlete himself also passes between marker poles 1 and 2 from left to right. In this case, although the same-side judgment of the aforementioned step S300 can be satisfied, in fact, the movement paths of the athlete and the football are different, and therefore it is considered that the football dribbled around the pole in violation of the regulations; further, if the sources of the first detection signal and the second detection signal emitted by different marker poles can be distinguished in the infrared sensor signal of the marker pole, the first marker pole interval and the second marker pole interval can also be identified according to the marker pole interval triggered by the detection signal.

[0024] Further, in the aforementioned step S200, after obtaining the first pole-circling image and the second pole-circling image, it also includes: performing image segmentation on the first pole-circling image and the second pole-circling image with a preset region of interest frame, and eliminating images not in the region of interest frame; it should be noted that, in order to ensure that the time spent is as short as possible during the dribbling process of the athlete around the pole, the athlete and the football will try to dribble as close to the marker pole as possible to shorten the dribble route. Therefore, within the shooting field of view of the camera, the athlete and the football actually only move back and forth in a narrow area on the left and right sides of the marker pole. Therefore, in order to reduce the subsequent recognition of irrelevant image parts, the region of interest frame can be preset for image cropping and segmentation, thereby improving the efficiency of subsequent analysis and recognition and computing power resource consumption; when the camera is placed to shoot the first pole-circling video, the marker pole can be set at the vertical center line of the image, and the length and width of the region of interest are set according to empirical values, and the central area of ​​the first pole-circling image and the second pole-circling image is segmented out to reduce the influence of surrounding irrelevant pictures on recognition; further, when the camera position is not accurately set, the image segmentation can be performed with the region of interest frame after the marker pole position is identified.

[0025] The above is a detailed description of a method for judging the compliance of dribbling a football around the pole based on image recognition according to the first aspect of the present application. The following is a detailed description of an embodiment of a system for judging the compliance of dribbling a football around the pole based on image recognition according to the second aspect of the present application.

[0026] See also Figure 2 , Figure 2 This is a structural diagram of a football dribbling around the pole compliance judgment system based on image recognition. This embodiment provides a football dribbling around the pole compliance judgment system based on image recognition, including: The detection signal time processing module 10 is used to obtain the first detection signal and the second detection signal, sort the detection signals according to the receiving time and establish the first detection time interval and the second detection time interval; compare the first detection time interval with the second detection time interval, and associate the first detection time interval with the most similar time period with the second detection time interval; The image acquisition module 20 is used to acquire a first pole-winding video, where the first pole-winding video is shot along the pole placement direction; extract time points in the associated first detection time interval and second detection time interval to obtain first time points and second time points, and acquire corresponding images in the first pole-winding video at the first time points and the second time points to obtain first pole-winding images and second pole-winding images; The image analysis and judgment module 30 is used to identify the relative position of the football and the marker pole in the first pole-wrapping image, and judge whether the corresponding relative positions are staggered according to the time point sequence of the first pole-wrapping image; if so, identify the relative position of the human body and the marker pole in the second pole-wrapping image, and judge whether the relative position of the human body and the marker pole is consistent with the relative position of the associated football and the marker pole according to the correlation between the first detection time interval and the second detection time interval; if so, judge that the football dribbling around the pole is compliant.

[0027] Furthermore, it also includes: The pole-circling route judgment module 40 is used to obtain a second pole-circling video, which is shot perpendicular to the pole placement direction; obtain the corresponding third time point and fourth time point according to the first detection signal and the second detection signal, and obtain the third pole-circling image and the fourth pole-circling image corresponding to the third time point and the fourth time point in the second pole-circling video; identify each marker pole and the football in the third pole-circling image, sort each marker pole and identify the first marker pole interval where the football is located; identify each marker pole and the human body in the fourth pole-circling image, sort each marker pole and identify the second marker pole interval where the human body is located; determine whether the first marker pole interval is consistent with the associated second marker pole interval based on the association relationship, and if not, it is regarded as a violation of the football dribbling around the pole.

[0028] Furthermore, after obtaining the first rod-wrapped image and the second rod-wrapped image in the image acquisition module 20, the following further comprises: The first rod-wrapped image and the second rod-wrapped image are segmented using a preset region of interest frame, and images not within the region of interest frame are eliminated.

[0029] The third aspect of the present application also provides a method and device for judging the compliance of dribbling a football around a pole based on image recognition, including a processor and a memory: the memory is used to store program code and transfer the program code to the processor; the processor is used to execute the above-mentioned method for judging the compliance of dribbling a football around a pole based on image recognition according to the instructions in the program code.

[0030] A fourth aspect of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, and the program code is used to execute the above-mentioned method for determining the compliance of a football dribbling around a pole based on image recognition.

[0031] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0032] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0033] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0034] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0035] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0036] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for judging compliance of soccer dribbling around a pole based on image recognition, characterized in that include: Acquire a first detection signal and a second detection signal, sort the detection signals according to reception time and establish a first detection time interval and a second detection time interval; Compare the first detection time interval with the second detection time interval, and associate the first detection time interval with the second detection time interval whose time period is most similar; Acquire a first pole-winding video, where the first pole-winding video is shot along the pole placement direction; extract time points in the associated first detection time interval and second detection time interval to obtain first time points and second time points, and acquire corresponding images in the first pole-winding video at the first time points and the second time points to obtain first pole-winding images and second pole-winding images; The relative positions of the football and the sign pole are identified in the first pole-wrapping image, and based on the time point sequence of the first pole-wrapping image, it is determined whether the corresponding relative positions are staggered; if so, the relative positions of the human body and the sign pole are identified in the second pole-wrapping image, and based on the correlation between the first detection time interval and the second detection time interval, it is determined whether the relative positions of the human body and the sign pole are consistent with the relative positions of the associated football and the sign pole; if so, it is determined that the football dribbling around the pole is compliant.

2. A method for judging compliance of soccer dribbling around a pole based on image recognition according to claim 1, characterized in that: Also includes: A second pole-wrapping video is obtained, where the second pole-wrapping video is shot perpendicular to the pole placement direction; a corresponding third time point and a fourth time point are obtained according to the first detection signal and the second detection signal, and a third pole-wrapping image and a fourth pole-wrapping image corresponding to the third time point and the fourth time point are obtained in the second pole-wrapping video; each marker pole and a football are identified in the third pole-wrapping image, the marker poles are sorted, and a first marker pole interval where the football is located is identified; each marker pole and a human body are identified in the fourth pole-wrapping image, the marker poles are sorted, and a second marker pole interval where the human body is located is identified; and whether the first marker pole interval is consistent with the associated second marker pole interval is determined based on the association relationship, and if not, it is deemed that the football dribbling around the pole is in violation of the regulations.

3. The method for judging compliance of soccer dribbling around a pole based on image recognition according to claim 1, characterized in that: After obtaining the first rod-wrapped image and the second rod-wrapped image, the method further includes: The first rod-wrapped image and the second rod-wrapped image are segmented using a preset region of interest frame, and images not within the region of interest frame are eliminated.

4. A football dribbling compliance judgment system based on image recognition, characterized in that: include: A detection signal time processing module, used to obtain the first detection signal and the second detection signal, sort the detection signals according to the receiving time and establish the first detection time interval and the second detection time interval; compare the first detection time interval with the second detection time interval, and associate the first detection time interval with the most similar time period with the second detection time interval; An image acquisition module is used to acquire a first pole-winding video, wherein the first pole-winding video is shot along the pole placement direction; extract time points in the associated first detection time interval and second detection time interval to obtain first time points and second time points, and acquire corresponding images in the first pole-winding video at the first time points and the second time points to obtain first pole-winding images and second pole-winding images; The image analysis and judgment module is used to identify the relative positions of the football and the marker pole in the first pole-wrapping image, and judge whether the corresponding relative positions are staggered according to the time point sequence of the first pole-wrapping image; if so, identify the relative positions of the human body and the marker pole in the second pole-wrapping image, and judge whether the relative positions of the human body and the marker pole are consistent with the relative positions of the associated football and the marker pole according to the correlation between the first detection time interval and the second detection time interval; if so, judge that the football dribbling around the pole is compliant.

5. A football dribbling around the pole compliance judgment system based on image recognition according to claim 4, characterized in that: Also includes: The pole-circling route judgment module is used to obtain a second pole-circling video, which is shot perpendicular to the pole placement direction; obtain the corresponding third time point and fourth time point according to the first detection signal and the second detection signal, and obtain the third pole-circling image and the fourth pole-circling image corresponding to the third time point and the fourth time point in the second pole-circling video; identify each marker pole and the football in the third pole-circling image, sort each marker pole and identify the first marker pole interval where the football is located; identify each marker pole and the human body in the fourth pole-circling image, sort each marker pole and identify the second marker pole interval where the human body is located; determine whether the first marker pole interval is consistent with the associated second marker pole interval based on the association relationship, and if not, it is regarded as a violation of the football dribbling around the pole.

6. A football dribbling around the pole compliance judgment system based on image recognition according to claim 4, characterized in that: In the image acquisition module, after obtaining the first rod-wrapped image and the second rod-wrapped image, the module further includes: The first rod-wrapped image and the second rod-wrapped image are segmented using a preset region of interest frame, and images not within the region of interest frame are eliminated.

7. A soccer dribbling compliance judgment device based on image recognition, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the method for determining compliance of dribbling a football around a pole based on image recognition according to the instructions in the program code as described in any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program codes, and the program codes are used to execute the method for determining compliance of a soccer dribbling around a pole based on image recognition as described in any one of claims 1 to 3.

Images