Rope skipping counting method, device, system, electronic device and storage medium

Abstract

The present application relates to a rope skipping counting method, apparatus, system, electronic device, and storage medium. The rope skipping counting method includes acquiring image information, obtaining at least one target detection result based on the image information, performing preparation gesture recognition on the target detection result using a well-trained preparation gesture recognition model to obtain a first recognition result, and, if the first recognition result indicates that the preparation gesture recognition has passed, performing rope skipping detection processing on the target detection result using the well-trained rope skipping counting model to generate a target rope skipping detection result. This application solves the problems of low accuracy and efficiency in rope skipping counting, achieving efficient and accurate automated rope skipping counting.

Description

Technical Field

[0001] The present application relates to the field of rope skipping counting, and in particular to a rope skipping counting method, device, system, electronic device and storage medium. Background Art

[0002] Rope skipping has become a key activity in many recreational and competitive settings. With the continuous development of physical education, many primary and secondary schools have included rope skipping as part of their physical education exams, using it as a criterion for measuring physical fitness. Rope skipping requires counting as a performance indicator. Related technologies typically employ manual counting, dedicated rope skipping shaft counting, infrared counting, or audio-based counting methods. However, manual counting methods are not only time-consuming and labor-intensive, but also susceptible to subjective factors. Dedicated rope skipping shaft counting methods require dedicated rope skipping equipment and, after extended use, can wear out significantly, rendering it unusable. Infrared counting methods require expensive equipment and rely on specific environments and constraints. Audio counting methods are highly dependent on the environment and can be difficult to identify when multiple people are skipping simultaneously. Furthermore, when multiple people are skipping, all of these methods require manual participation in final tallying, resulting in low accuracy and efficiency in rope skipping counting.

[0003] Currently, no effective solution has been proposed for the problems of low accuracy and efficiency of rope skipping counting in related technologies. Summary of the Invention

[0004] The embodiments of the present application provide a rope skipping counting method, device, system, electronic device and storage medium to at least solve the problems of low accuracy and efficiency of rope skipping counting in the related art.

[0005] In a first aspect, an embodiment of the present application provides a rope skipping counting method, the method comprising:

[0006] Acquiring image information, and obtaining at least one target detection result based on the image information;

[0007] Performing preparation gesture recognition on the target detection result using a well-trained preparation gesture recognition model to obtain a first recognition result;

[0008] When the first recognition result indicates that the preparation gesture recognition is passed, a rope skipping detection process is performed on the target detection result using a well-trained rope skipping counting model to generate a target rope skipping detection result.

[0009] In some embodiments, when the first recognition result indicates that the preparation gesture recognition is passed, the method further includes:

[0010] Obtain the preset first rope skipping detection area;

[0011] Calculating an overlapping result based on the first rope skipping detection area and the first recognition result;

[0012] In a case where the overlapping result is greater than or equal to a preset overlapping value, the rope skipping detection process is performed on the target detection result using the rope skipping counting model to generate the target rope skipping detection result.

[0013] In some embodiments, the size of the first rope skipping detection area is a first size, and the first size includes first scale information and first feature point coordinates, and the overlapping result calculated based on the first rope skipping detection area and the first recognition result includes:

[0014] Acquire position frame information according to the first recognition result; the size of the position frame information is a second size, and the second size includes second scale information and second feature point coordinates;

[0015] Calculating an overlapping area according to the first scale information, the first feature point coordinates, the second scale information, and the second feature point coordinates;

[0016] Overlapping rate information is calculated according to the first scale information, the second scale information, and the overlapping area, and the overlapping rate information is used as the overlapping result.

[0017] In some embodiments, after calculating the overlap result based on the first rope skipping detection area and the first recognition result, the method further includes:

[0018] When the overlap result is less than the preset overlap value, a first prompt message is sent to the reminder device, so that the reminder device prompts the user to enter the first rope skipping detection area based on the first prompt message.

[0019] In some embodiments, when the first recognition result indicates that the preparation gesture recognition is passed, the method further includes:

[0020] Performing confirmation gesture recognition on the first recognition result using a well-trained confirmation gesture recognition model to obtain a second recognition result;

[0021] If the time taken to obtain the second recognition result exceeds a preset recognition time period, or the second recognition result indicates that the confirmation gesture recognition fails, reusing the preparation gesture recognition model to perform preparation gesture recognition on all the target detection results to obtain the first recognition result;

[0022] In a case where the time when the second recognition result is obtained is within the preset recognition time period, the rope skipping detection processing is performed on the target detection result using the rope skipping counting model to generate the target rope skipping detection result.

[0023] In some embodiments, performing rope skipping detection processing on the target detection result using a well-trained rope skipping counting model to generate a target rope skipping detection result includes:

[0024] Performing face comparison processing on the target detection result to obtain a face comparison result, and performing rope skipping detection processing on the target detection result using the rope skipping counting model to obtain a rope skipping counting result;

[0025] The target rope skipping detection result is generated according to the face comparison result and the rope skipping counting result.

[0026] In some embodiments, performing face comparison processing on the target detection result to obtain a face comparison result includes:

[0027] Obtain the detection database;

[0028] Performing face recognition processing on the target detection results using a well-trained face recognition model to obtain facial feature information;

[0029] The facial feature information is compared with the stored information in the detection database to obtain the facial comparison result.

[0030] In some embodiments, generating the target rope skipping detection result according to the face comparison result and the rope skipping counting result includes:

[0031] Get the preset comparison threshold;

[0032] generating the target rope skipping detection result according to the facial feature information and the rope skipping counting result, when the face comparison result indicates that the comparison information between the facial feature information and the stored information is greater than or equal to the comparison threshold;

[0033] When the face comparison result indicates that the comparison information is less than the comparison threshold, the facial feature information is stored in the detection database to generate a new face object, and the target rope skipping detection result is generated according to the new face object and the rope skipping counting result.

[0034] In some embodiments, performing rope skipping detection processing on the target detection result using a well-trained rope skipping counting model to generate a target rope skipping detection result includes:

[0035] Obtain the second rope skipping detection area and the preset rope skipping time;

[0036] When it is detected that the target detection result is located within the second rope skipping detection area and the current time is within the preset rope skipping time range, performing rope skipping detection processing on the target detection result using the rope skipping counting model to generate the target rope skipping detection result;

[0037] When it is detected that the target detection result leaves the second rope skipping detection area, or the current time exceeds the preset rope skipping time, a second prompt message is sent to the reminder device, so that the reminder device prompts the user to end the rope skipping counting process based on the second prompt message.

[0038] In a second aspect, an embodiment of the present application provides a rope skipping counting device, the device comprising: an acquisition module, an identification module, and a generation module;

[0039] The acquisition module is configured to acquire image information and obtain at least one target detection result based on the image information;

[0040] The recognition module is configured to perform preparation gesture recognition on the target detection result using a well-trained preparation gesture recognition model to obtain a first recognition result;

[0041] The generating module is configured to perform rope skipping detection processing on the target detection result using a well-trained rope skipping counting model to generate a target rope skipping detection result when the first recognition result indicates that the preparation gesture recognition has passed.

[0042] In a third aspect, an embodiment of the present application provides a rope skipping counting system, the system comprising: an image acquisition device and a control device;

[0043] The image acquisition device is used to send the acquired image information to the control device;

[0044] The control device is used to execute the rope skipping counting method as described in the first aspect above.

[0045] In a fourth aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the rope skipping counting method as described in the first aspect above is implemented.

[0046] In a fifth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored. When the program is executed by a processor, the skipping rope counting method described in the first aspect above is implemented.

[0047] Compared with the related art, the skipping rope counting method, device, system, electronic device and storage medium provided in the embodiments of the present application obtain image information and obtain at least one target detection result based on the image information; use a well-trained preparation gesture recognition model to perform preparation gesture recognition on the target detection result to obtain a first recognition result; when the first recognition result indicates that the preparation gesture recognition is passed, use the well-trained skipping rope counting model to perform skipping rope detection processing on the target detection result to generate a target skipping rope detection result, which solves the problems of low accuracy and efficiency of skipping rope counting and realizes efficient and accurate automatic skipping rope counting.

[0048] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0050] Figure 1 This is a diagram of an application environment of a rope skipping counting method according to an embodiment of the present application;

[0051] Figure 2 is a flow chart of a rope skipping counting method according to an embodiment of the present application;

[0052] Figure 3 is a flow chart of an application method for preparing a gesture recognition model according to an embodiment of the present application;

[0053] Figure 4 is a flow chart of a method for confirming an application of a gesture recognition model according to an embodiment of the present application;

[0054] Figure 5 is a flowchart of a method for applying a face recognition model according to an embodiment of the present application;

[0055] Figure 6 is a flow chart of an application method of a rope skipping counting model according to an embodiment of the present application;

[0056] Figure 7 is a flow chart of a rope skipping counting method according to a preferred embodiment of the present application;

[0057] Figure 8 This is a structural block diagram of a rope skipping counting device according to an embodiment of the present application;

[0058] Figure 9 This is a structural diagram of the interior of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means and should not be understood as the contents disclosed in the present application being insufficient.

[0060] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0061] Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by a person of ordinary skill in the technical field to which this application belongs. The words "one", "a", "the" and the like used in this application do not indicate a limit on quantity and may indicate the singular or plural. The terms "include", "comprise", "have" and any variations thereof used in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units that are inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The word "multiple" used in this application means greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in this application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0062] The rope skipping counting method provided in this application can be applied to Figure 1 In the application environment shown, the image acquisition device 12 communicates with the server device 14 via a network. The server device 14 acquires image information from the image acquisition device 12, obtains at least one target detection result based on the image information, and performs preparation gesture recognition on the target detection result using a well-trained preparation gesture recognition model to obtain a first recognition result. The server device 14 then performs rope skipping detection processing on the target detection result using a well-trained rope skipping counting model to generate a target rope skipping detection result. The image acquisition device 12 can be, but is not limited to, various binocular cameras, dome cameras, video recording devices, or other devices for capturing images. The server device 14 can be implemented as an independent server or a server cluster consisting of multiple servers.

[0063] This embodiment provides a rope skipping counting method. Figure 2 This is a flow chart of a rope skipping counting method according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0064] Step S220: Acquire image information, and acquire at least one target detection result based on the image information.

[0065] The image information refers to an image of a human body to be detected during rope skipping. The image information can be obtained by extracting continuous video frames from a video stream captured by the image acquisition device at the rope skipping deployment site using a control device such as the server device or processing chip. The control device can use a human body detection model to detect each frame of image information, obtain the rectangular position information of all detected human targets, and use a target tracking algorithm to track the motion position of the detected human targets to update the target position in real time, thereby obtaining the target detection results for the human targets. It is understood that when a multi-person rope skipping competition or training is conducted at the rope skipping deployment site, at least two target detection results can be detected.

[0066] In step S240 , a well-trained preparation gesture recognition model is used to perform preparation gesture recognition on the target detection result to obtain a first recognition result.

[0067] The preparatory gesture recognition model is used to identify gestures, such as waving, raising, or nodding, that indicate a jumper is in preparation. These preparatory gestures can be pre-set by staff. The preparatory gesture recognition model can be trained by obtaining multiple sample images containing these preparatory gestures as a training set; inputting these training sets into a neural network model for training, ultimately generating an accurate gesture recognition model. The control device can then extract the portion of the image containing each target detection result from the image information and input this into the accurate gesture recognition model to determine whether any target detection result has executed a preparatory gesture, thereby generating a first recognition result indicating whether any human target has executed a preparatory gesture.

[0068] Step S260 , when the first recognition result indicates that the preparation gesture recognition is passed, the target detection result is processed by skipping rope detection using a well-trained skipping rope counting model to generate a target skipping rope detection result.

[0069] Among them, the above-mentioned rope skipping counting model refers to a model for automatically counting rope skipping based on the above-mentioned image information. The training method of the rope skipping counting model can be: obtaining multiple sample images including different rope skipping states such as take-off, mid-air, and landing, and generating different training sets accordingly; inputting each training set into the classification model for training, and finally training to generate a rope skipping counting model. It is understandable that the rope skipping counting model can also be generated based on human body key point detection, which will not be repeated here. The continuous frame video stream where the above-mentioned target detection result is located is respectively input into the rope skipping counting model, and automatic rope skipping counting can be achieved to generate the above-mentioned target rope skipping detection result.

[0070] It is understood that in actual application scenarios, if the jump rope counting is for a single person, the user can be instructed to perform a preparation gesture after being ready. That is, the accurate gesture recognition model is used to perform accurate gesture recognition for the only existing target detection result. Automatic jump rope counting begins when it is detected that the first recognition result generated is that the user performed the preparation gesture. If the jump rope counting is for multiple people at the same time, each user can be instructed to perform an accurate gesture. That is, the accurate gesture recognition model is used to perform accurate gesture recognition for each target detection result. Automatic jump rope counting begins when the number of successful preparation gesture recognitions equals the number of target detection results. Alternatively, one user can be pre-assigned to perform an accurate gesture on behalf of the user. In this case, only the first recognition result of a successful preparation gesture recognition is required to start the automatic jump rope counting. Through the above-mentioned step S260, automatic jump rope counting begins only when the successful preparation gesture recognition is detected. This can avoid false detections caused by users not being ready or other unrelated people accidentally entering the process, and reduce interference signals that may occur during the jump rope process.

[0071] Through the above steps S220 to S260, human body recognition is performed on the image information, and gesture recognition is performed on the human body recognition results obtained, and automatic rope skipping counting is performed based on the results of gesture recognition, thereby reducing the interference of human participation in counting, reducing the detection cost, and improving the efficiency of rope skipping detection; in addition, since the present application is based on rope skipping detection generated based on image information, it avoids interference such as sound and empty jumps, and can effectively improve the accuracy of rope skipping technology, thereby solving the problems of accuracy and low efficiency of rope skipping counting, and realizing an efficient and accurate automated rope skipping counting method.

[0072] In some embodiments, when the first recognition result indicates that the preparation gesture recognition is passed, the rope skipping counting method further includes the following steps:

[0073] Step S261: Acquire a preset first rope skipping detection area.

[0074] The first rope skipping detection area is an area used to specify the range of motion of the user representing the execution of the preparation gesture. For example, the first rope skipping detection area can be drawn as a specific shape such as a rectangle or a circle. It is understandable that the first rope skipping detection area can be directly drawn as a rectangle or other area by the staff at the rope skipping deployment site; or, the first rope skipping detection area can also be drawn in advance by the staff on the video frame image captured by the image acquisition device, and the staff can mark a cross or other symbol at the rope skipping deployment site to remind the representative of the standing position during the subsequent rope skipping count, thereby improving the calculation efficiency of the control device.

[0075] Step S262: Calculate an overlapping result based on the first rope skipping detection area and the first recognition result.

[0076] The first recognition result includes location frame information representing the location of the user performing the preparation gesture. The overlap result may be the overlap between the location frame information and the first rope skipping detection area, or the overlap ratio between the overlapped portion and the first rope skipping detection area. The overlap result may be calculated based on the first rope skipping detection area and the location frame information in the first recognition result.

[0077] Step S263 , when the overlap result is greater than or equal to a preset overlap value, performing rope skipping detection processing on the target detection result using the rope skipping counting model to generate the target rope skipping detection result.

[0078] The preset overlap value refers to an overlap threshold value pre-set by the staff. This preset overlap value should match the calculation method of the overlap result. For example, if the overlap result is obtained by calculating the area of ​​the overlap between the location box information of the representative's location and the first rope skipping detection area, the preset overlap value can be set as a threshold value in dpi. Alternatively, if the overlap result is obtained by calculating the ratio of the overlap area between the overlapped area and the first rope skipping detection area, the preset overlap value can be set as a threshold value in the form of a ratio, such as 0.8. By comparing the overlap result with the preset overlap value, if the overlap result is greater than the preset overlap value, it indicates that the overlap between the representative's location and the first rope skipping detection area is large, and it can be determined that the representative has entered the first rope skipping detection area. At this time, the target detection result is input into the rope skipping counting model and the target rope skipping detection result is output to improve the accuracy of the subsequent detection results of the rope skipping counting model.

[0079] Through the above steps S261 to S263, when it is detected that the preparation gesture recognition is passed, it is further detected whether the user who performs the preparation gesture enters the pre-designated first skipping rope detection area, thereby avoiding false detection caused by other unrelated personnel making the same gesture when mistakenly entering the skipping rope deployment site, and effectively improving the accuracy of skipping rope counting.

[0080] In some embodiments, the size of the first rope skipping detection area is a first size, and the first size includes first scale information and first feature point coordinates. The calculating of the overlapping result based on the first rope skipping detection area and the first recognition result further includes the following steps:

[0081] Position frame information is obtained based on the first recognition result; the size of the position frame information is a second size, and the second size includes second scale information and second feature point coordinates; the overlapping area is calculated based on the first scale information, the first feature point coordinates, the second scale information, and the second feature point coordinates; overlapping rate information is calculated based on the first scale information, the second scale information, and the overlapping area, and the overlapping rate information is used as the overlapping result.

[0082] The first scale information may include the width, height, diagonal, or other characteristic line segments of the first rope skipping detection area; the first feature point coordinates may include the coordinates of the center point, corner points, side center, or other characteristic points of the first rope skipping detection area. The second scale information may include the width, height, diagonal, or other characteristic line segments of the area indicated by the location frame information; the second feature point coordinates may include the coordinates of the center point, corner points, side center, or other characteristic points of the location frame. Using the line segments and feature point coordinates of each characteristic area, the area of ​​the overlap between the location frame information and the first rope skipping detection area can be calculated. The areas of the corresponding areas can then be calculated based on the first and second scale information. The overlap ratio information can then be calculated by calculating the ratio of the overlap area to one of the areas, or the ratio of the overlap area to the area with the smallest area. This overlap ratio information is then used as the overlap result for subsequent steps.

[0083] Specifically, taking the case where the first scale information includes the width w1 and height h1 of the first rope skipping detection area, the first feature point coordinates include the upper left corner coordinates (R1.x, R1.y) and the lower right corner coordinates (R2.x, R2.y) of the first rope skipping detection area, and the second scale information includes the width w2 and height h2 of the position frame information, and the second feature point coordinates include the upper left corner coordinates (R3.x, R3.y) and the lower right corner coordinates (R4.x, R4.y) of the position frame information as an example, the calculation formula for the overlap rate is as follows:

[0084] W = w1 + w2 - (max {R1.x + w1, R3.x + w2} - min {R1.x, R3.x}) Formula 1

[0085] H=h1+h2-(max{R1.y+h1, R3.y+h2}-min{R1.y, R3.y}) Formula 2

[0086]

[0087] Among them, W is used to represent the width of the above-mentioned overlapping part, and H is used to represent the height of the overlapping part. Substituting the width and height values ​​of the overlapping part obtained in the above-mentioned formula 1 and the above-mentioned formula 2 into the above-mentioned formula 3, the overlap rate rare can be calculated. It should be noted that if W>0 and H>0 are calculated, it means that there is an overlap between the above-mentioned position frame information and the above-mentioned first rope skipping detection area. At this time, the overlap rate rare can be obtained by comparing the minimum value between the position frame information and the first rope skipping detection area, and calculating the ratio between the overlap and the minimum value; by taking the smaller value of the two rectangular areas, it avoids the problem that the overlap rate value range is very large when a fixed rectangular frame is used to calculate the overlap rate when the areas of the two rectangles differ greatly, thereby making the subsequent comparison result of the overlap rate and the preset overlap value low in calculation accuracy. If the calculated width W or height H of the overlapping part is 0, it means that the sides of the two rectangular boxes are connected but not overlapping; if the calculated W<0 or H<0, it means that there is no overlapping part between the two rectangular boxes. Therefore, when these two situations occur, that is, when W≤0 or H≤0 is first calculated, there is no need to continue calculating the subsequent formulas to obtain the calculation result of the overlap rate rare=0, so as to improve the calculation efficiency.

[0088] Through the above embodiment, the above-mentioned overlapping rate information is calculated through the position box information and the characteristic line segments, coordinate points and other information of the first rope skipping detection area, which improves the calculation efficiency and accuracy, and the overlapping rate information is selected as the overlapping result, so that the judgment of whether the representative user who performs the above-mentioned accurate gesture enters the first rope skipping detection area is more intuitive, thereby improving the accuracy and efficiency of rope skipping counting.

[0089] In some embodiments, after step S262, the rope skipping counting method further includes the following steps:

[0090] Step S264: When the overlap result is less than the preset overlap value, a first prompt message is sent to the reminder device, so that the reminder device prompts the user to enter the first rope skipping detection area based on the first prompt message.

[0091] Specifically, when the control device calculates that the overlap result is less than the preset overlap value, it indicates that the representative who performed the preparation gesture has not yet entered the first rope skipping detection area. At this time, the control device can generate a first prompt message and send it to the reminder device connected thereto, and the reminder device can display a reminder message to the user to prompt the user to enter the first rope skipping detection area. The reminder device can be a display screen device deployed on site, and based on the first prompt message, it displays the words "Please enter the designated area!"; or, the reminder device can be an LED light deployed above the first rope skipping detection area on site, and based on the first prompt message, it displays a red light; the reminder device can also be a speaker or other sound and light device for reminder, which will not be described in detail here.

[0092] Through the above step S264, when it is detected based on the above overlapping result that the user has not entered the first rope skipping detection area, the reminder device is instructed to automatically send a prompt signal to the user based on the generated first prompt information without the need for human assistance, thereby effectively improving the degree of automation in the rope skipping counting process.

[0093] It should be noted that this embodiment also provides an application method for preparing a gesture recognition model. For example, the gesture recognition model adopts a waving detection model to recognize a waving gesture. Figure 3 is a flow chart of an application method for preparing a gesture recognition model according to an embodiment of the present application. Figure 3 As shown, the application method of preparing the gesture recognition model includes the following steps:

[0094] Step S301: Obtain video stream information.

[0095] Step S302: performing target detection on each frame of image extracted from the video stream information.

[0096] Step S303: Acquire the position of the human target in the image and track it to generate a target detection result.

[0097] Step S304: Detect the target detection result using the hand waving detection model.

[0098] Step S305: Determine whether the target is waving. If the determination result of step S304 is no, then execute step S304 again.

[0099] Step S306: If the determination result of the above step S304 is yes, the overlapping rate between the waving target and the first rope skipping detection area is calculated.

[0100] Step S307: Determine whether the overlap ratio is greater than a preset overlap value. If the determination result of step S307 is no, then re-execute step S306.

[0101] Step S308: If the determination result of the above step S307 is yes, a determination result indicating that the target has entered the first rope skipping detection area is generated.

[0102] In some embodiments, when the first recognition result indicates that the preparation gesture recognition is passed, the rope skipping counting method further includes the following steps:

[0103] Step S265 : Using a well-trained confirmation gesture recognition model, perform confirmation gesture recognition on the first recognition result to obtain a second recognition result.

[0104] The confirmation gesture recognition model is used to identify gestures, such as an OK sign, a "V" sign, or a fist, that indicate a jumper has reconfirmed their correctness. This confirmation gesture can be pre-set by staff as a specific gesture distinct from the preparatory gesture. The training method for the confirmation gesture recognition model may include obtaining multiple sample images containing the confirmation gesture as a training set; inputting this training set into a neural network model for training, ultimately generating a confirmation gesture recognition model. The control device can then extract the portion of the image containing each target detection result from the image information and input it into the confirmation gesture recognition model to determine whether a target detection result has executed a confirmation gesture, thereby generating a second recognition result indicating whether a human target has executed a confirmation gesture.

[0105] Step S266: When the time for obtaining the second recognition result exceeds the preset recognition time period, or the second recognition result indicates that the confirmation gesture recognition fails, the preparation gesture recognition model is reused to perform preparation gesture recognition on all the target detection results to obtain the first recognition result.

[0106] The preset recognition time period refers to a pre-set time period for specifying the duration of the confirmation gesture recognition; for example, the preset recognition time period can be set to 30 seconds. Specifically, if the control device fails to identify the second recognition result within the preset recognition time period, or the time it takes to identify the second recognition result exceeds the preset recognition time period, it indicates that no human target performing the confirmation gesture was detected within the preset recognition time period. In this case, the control device can use the preparation gesture recognition model to re-detect whether a human target has performed the preparation gesture, thereby avoiding the problem of false detection of the target performing the preparation gesture in step S240 by repeatedly recognizing the preparation gesture.

[0107] Step S267: When the time when the second recognition result is obtained is within the preset recognition time period, the target detection result is processed by skipping rope detection using the skipping rope counting model to generate the target skipping rope detection result.

[0108] Specifically, if a human target performing the above-mentioned confirmation gesture is successfully identified within the above-mentioned preset recognition time period, the skipping rope counting model is automatically started, the skipping rope counting detection is performed on the above-mentioned target detection result, and finally the above-mentioned target skipping rope detection result is generated.

[0109] Through the above steps S265 to S267, the gesture recognition model is used to identify whether the human target performs the confirmation gesture, thereby ensuring that the automatic start of the skipping rope counting process will not go wrong due to interference factors such as irrelevant personnel accidentally entering through multiple different gesture recognitions, thereby further improving the accuracy of the skipping rope counting.

[0110] It should be noted that this embodiment also provides an application method of a confirmation gesture recognition model. Taking the confirmation gesture recognition model using an OK gesture detection model to recognize an OK gesture as an example, Figure 4 is a flow chart of a method for confirming the application of a gesture recognition model according to an embodiment of the present application. Figure 4 As shown, the application method of the confirmation gesture recognition model includes the following steps:

[0111] Step S401: Obtain video stream information.

[0112] Step S402: Perform OK gesture recognition on the target detection result using the OK gesture detection model.

[0113] Step S403: determine whether the recognition time exceeds a preset recognition time period.

[0114] Step S404: If the determination result of step S403 is no, determine whether there is a human target performing an OK gesture. If the determination result of step S404 is no, then re-execute step S403.

[0115] Step S405: If the judgment result of the above step S404 is yes, a judgment result that the human target is ready is generated, and a countdown of ten seconds is prompted. After the countdown ends, the automatic rope skipping counting begins.

[0116] Step S406: If the judgment result of the above step S403 is yes, the hand waving detection model is started and the detection is restarted.

[0117] In some embodiments, the above-mentioned use of a fully trained skipping rope counting model to perform skipping rope detection processing on the target detection result, and generating the target skipping rope detection result also includes the following steps: performing face comparison processing on the target detection result to obtain a face comparison result, and using the skipping rope counting model to perform skipping rope detection processing on the target detection result to obtain a skipping rope counting result; generating the target skipping rope detection result based on the face comparison result and the skipping rope counting result.

[0118] The above-mentioned face comparison processing of the target detection result to obtain the face comparison result also includes the following steps: obtaining a detection database; using a well-trained face recognition model to perform face recognition processing on the target detection result to obtain face feature information; comparing the face feature information with the stored information in the detection database to obtain the face comparison result.

[0119] It is understood that the above-mentioned detection database refers to a pre-stored database that includes facial information of known users and rope skipping record information. Specifically, the above-mentioned facial recognition model is used to perform facial recognition processing on the above-mentioned tracked target detection results to obtain corresponding facial feature information, and then the facial feature information is compared one by one with the facial information corresponding to each piece of stored information in the above-mentioned detection database to obtain the above-mentioned facial comparison result. It should be noted that the above-mentioned facial comparison result can also be a comparison of the facial feature information of the target detection result with the face-specific database stored in the storage space of the above-mentioned control device, which will not be repeated here.

[0120] Furthermore, after obtaining the face comparison result, in the multi-person skipping rope counting scenario, the skipping rope counting result obtained by performing the skipping rope detection processing on the target detection result using the skipping rope counting model can be matched one by one with each human target, so as to finally generate a multi-person matching target skipping rope detection result.

[0121] Through the above embodiment, by utilizing the face recognition model to perform face comparison on the target detection results, and finally generating the above target rope skipping detection results based on the obtained face comparison results, the detection errors caused by the disorder of matching between the human target and the rope skipping count value during the rope skipping counting process of multiple people are avoided, and the accuracy of rope skipping counting is effectively improved.

[0122] In some embodiments, generating the target rope skipping detection result based on the face comparison result and the rope skipping counting result further includes the following steps:

[0123] Step S268: Obtain a preset comparison threshold.

[0124] The comparison threshold may be pre-set by the staff, for example, it may be set to a value such as 80%.

[0125] Step S269, when the face comparison result indicates that the comparison information between the facial feature information and the stored information is greater than or equal to the comparison threshold, the target rope skipping detection result is generated based on the facial feature information and the rope skipping count result; when the face comparison result indicates that the comparison information is less than the comparison threshold, the facial feature information is stored in the detection database to generate a new face object, and the target rope skipping detection result is generated based on the new face object and the rope skipping count result.

[0126] If the comparison information is detected to be greater than or equal to the comparison threshold, it indicates that the face comparison is successful, and the facial feature information of the human target matches the facial information stored in the detection database, indicating that they belong to the same user. In this case, there is no need to add a new user, and a target rope skipping detection result associated with the facial information stored in the detection database can be directly generated. If the comparison information is detected to be less than the comparison threshold, it indicates that the face comparison has failed, and the facial feature information of the human target has not yet been stored in the detection database. In this case, the facial feature information can be updated to the detection database, and the rope skipping count result can be added to the detection database.

[0127] It is understandable that in a multi-person rope skipping competition scenario, if the above-mentioned face comparison is successful, the number of rope jumps can be compared with the number of rope jumps stored in the detection database for the corresponding human target at the end of the rope skipping. If the number of rope jumps is greater than the number of rope jumps stored, the number of rope jumps will be updated to the detection database, otherwise it will not be updated. Finally, after all processes are completed, the detection database is traversed, and the rope jump count is used as the sorting condition to select the top M results and display them as the results of this competition. M is a positive integer greater than 1. Alternatively, in a rope skipping training scenario, the number of rope jumps in each training session can also be stored in the above-mentioned detection database, and then used as a historical record for users to review.

[0128] Through the above steps S268 to S269, the facial feature information and the rope skipping counting results are stored in the above detection database based on the above comparison information, thereby facilitating user retrieval and improving the efficiency of generating target rope skipping detection results.

[0129] It should be noted that this embodiment also provides an application method of the face recognition model. Figure 5 is a flow chart of a method for applying a face recognition model according to an embodiment of the present application. Figure 5 As shown, the application method of the face recognition model includes the following steps:

[0130] Step S501: Obtain video stream information.

[0131] Step S502: using a face recognition model to identify the target detection result.

[0132] Step S503: Determine whether facial feature information is detected. If the determination result of step S503 is no, then re-execute step S502.

[0133] Step S504: If the judgment result of the above step S503 is yes, then perform face comparison in the detection database and determine whether the comparison is successful.

[0134] Step S505: If the determination result of the above step S504 is yes, it is determined whether to update the rope skipping count data when the rope skipping is finished.

[0135] Step S506: If the judgment result of the above step S04 is no, then at the end of the rope skipping, the facial feature information of the target detection result and the rope skipping count data are inserted into the above detection database.

[0136] In some embodiments, the above-mentioned skipping rope detection processing is performed on the target detection result using a well-trained skipping rope counting model, and generating the target skipping rope detection result also includes the following steps: obtaining a second skipping rope detection area and a preset skipping rope time; when it is detected that the target detection result is within the second skipping rope detection area and the current time is within the range of the preset skipping rope time, using the skipping rope counting model to perform skipping rope detection processing on the target detection result to generate the target skipping rope detection result; when it is detected that the target detection result leaves the second skipping rope detection area, or the current time exceeds the preset skipping rope time, sending a second prompt message to the reminder device, so that the reminder device prompts the user that the skipping rope counting process ends based on the second prompt message.

[0137] The second rope skipping detection area is a pre-designated exercise area for each user. It is understood that the first rope skipping detection area can be the same as or different from the second rope skipping detection area. For example, in a single-person rope skipping counting scenario, the first rope skipping detection area can be set to the same area as the second rope skipping detection area. The preset rope skipping time is a pre-set time limit for the rope skipping session. For example, the preset rope skipping time can be set to 1 minute.

[0138] Specifically, the control device can continuously track the target detection result using a target tracking algorithm. When the control device tracks that the target detection result has been within the second rope skipping detection area and the current time has not exceeded the preset rope skipping time, it means that the rope skipping has not ended. The control device can then use the rope skipping counting model to continuously count the rope skipping for the target detection result during this time period. When the control device tracks and detects that the target detection result has left the second rope skipping detection area, or the current time has timed out, it means that the rope skipping has ended. At this time, the control device can instruct the reminder device to remind the user that the rope skipping counting process has ended based on the generated second prompt information. The second prompt information can be information such as "This rope skipping has ended, please leave".

[0139] Through the above embodiment, by setting the second skipping rope detection area and the preset skipping rope time, it is determined whether the jumper has left the designated skipping rope area or whether the skipping rope time has timed out, thereby realizing accurate control of the automatic start and end functions of the automated skipping rope detection process, and improving the accuracy of the skipping rope counting; at the same time, when the end of the process is detected, the reminder device is instructed to automatically send a prompt signal to the user, further improving the degree of automation in the skipping rope counting process.

[0140] It should be noted that this embodiment also provides an application method of the rope skipping counting model. Figure 6 is a flow chart of an application method of a rope skipping counting model according to an embodiment of the present application. Figure 6 As shown, the application method of the rope skipping counting model includes the following steps:

[0141] Step S601: Obtain video stream information.

[0142] Step S602: Perform rope skipping counting detection on the target detection result using the rope skipping counting model.

[0143] Step S603: Tracking the human target in the target detection result.

[0144] Step S604: Based on the above tracking results, it is determined whether the human target has changed, that is, whether it has left the designated rope skipping area.

[0145] Step S605: If the judgment result of the above step S604 is no, continue to perform rope skipping counting detection.

[0146] Step S606: Determine whether the rope skipping timer has expired.

[0147] Step S607: If the judgment result of the above step S606 is yes, the process ends, and the hand-waving configuration is performed, and the above-mentioned hand-waving detection model is turned on to enter the next round of rope skipping counting process.

[0148] Step S608: If the judgment result of the above step S604 is yes, the hand waving configuration is performed and the above hand waving detection model is turned on to enter the next round of rope skipping counting process.

[0149] The following describes the embodiments of this application in detail in conjunction with actual application scenarios. Figure 7 This is a flow chart of a rope skipping counting method according to a preferred embodiment of the present application. Figure 7 As shown, the process includes the following steps:

[0150] Step S701: Obtain video stream information.

[0151] Step S702: Use the hand waving detection model to lock the rope skipping human target.

[0152] Step S703: Track whether the target enters the first rope skipping detection area.

[0153] Step S704: Using the OK gesture detection model, determine whether the rope skipping human target is ready.

[0154] Step S705: Use the face recognition model to determine whether the rope skipping human target is successfully matched.

[0155] Step S706: Utilize the rope skipping counting model to detect the rope skipping human target to obtain a rope skipping counting result.

[0156] Step S707: Save the rope skipping counting result to the detection database based on the facial feature information obtained in the above step S705.

[0157] Step S708, completing the current rope skipping counting detection process.

[0158] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0159] This embodiment also provides a skipping rope counting device, which is used to implement the above-mentioned embodiments and preferred embodiments. The details that have been described will not be repeated here. As used below, the terms "module," "unit," "subunit," etc. may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0160] Figure 8 This is a structural block diagram of a rope skipping counting device according to an embodiment of the present application. Figure 8 As shown, the device includes: an acquisition module 82, a recognition module 84 and a generation module 86; the acquisition module 82 is used to acquire image information and obtain at least one target detection result based on the image information; the recognition module 84 is used to use a well-trained preparation gesture recognition model to perform preparation gesture recognition on the target detection result to obtain a first recognition result; the generation module 86 is used to use a well-trained skipping rope counting model to perform skipping rope detection processing on the target detection result when the first recognition result indicates that the preparation gesture recognition has passed, and generate a target skipping rope detection result.

[0161] Through the above embodiment, the acquisition module 82 performs human body recognition on the image information, the recognition module 84 performs gesture recognition on the human body recognition result obtained, and the generation module 86 automatically counts the skipping rope based on the gesture recognition result, thereby reducing the interference of human participation in counting, reducing the detection cost, and improving the skipping rope detection efficiency; in addition, since the present application is based on the skipping rope detection generated by image information, it avoids interference such as sound and empty jumps, and can effectively improve the accuracy of the skipping rope technique, thereby solving the problems of accuracy and low efficiency of skipping rope counting, and realizing an efficient and accurate automatic skipping rope counting device.

[0162] In some embodiments, the above-mentioned generation module 86 is also used to obtain a preset first rope skipping detection area; the generation module 86 calculates an overlapping result based on the first rope skipping detection area and the first recognition result; when the overlapping result is greater than or equal to the preset overlap value, the generation module 86 uses the rope skipping counting model to perform rope skipping detection processing on the target detection result to generate the target rope skipping detection result.

[0163] In some embodiments, the size of the first rope skipping detection area is a first size, and the first size includes first scale information and first feature point coordinates. The generation module 86 is also used to obtain position frame information based on the first recognition result; the size of the position frame information is a second size, and the second size includes second scale information and second feature point coordinates; the generation module 86 calculates the overlapping area based on the first scale information, the first feature point coordinates, the second scale information and the second feature point coordinates; the generation module 86 calculates the overlapping rate information based on the first scale information, the second scale information and the overlapping area, and uses the overlapping rate information as the overlapping result.

[0164] In some embodiments, the generation module 86 is further configured to send a first prompt message to the reminder device when the overlap result is less than the preset overlap value, so that the reminder device prompts the user to enter the first rope skipping detection area based on the first prompt message.

[0165] In some embodiments, the above-mentioned generation module 86 is also used to use a well-trained confirmation gesture recognition model to perform confirmation gesture recognition on the first recognition result to obtain a second recognition result; when the time for obtaining the second recognition result exceeds the preset recognition time period, or the second recognition result indicates that the confirmation gesture recognition fails, the generation module 86 reuses the preparation gesture recognition model to perform preparation gesture recognition on all the target detection results to obtain the first recognition result; when the time for obtaining the second recognition result is within the preset recognition time period, the generation module 86 uses the skipping rope counting model to perform skipping rope detection processing on the target detection result to generate the target skipping rope detection result.

[0166] In some embodiments, the above-mentioned generation module 86 is also used to perform face comparison processing on the target detection result to obtain a face comparison result, and use the skipping rope counting model to perform skipping rope detection processing on the target detection result to obtain a skipping rope counting result; the generation module 86 generates the target skipping rope detection result based on the face comparison result and the skipping rope counting result.

[0167] In some embodiments, the above-mentioned generation module 86 is also used to obtain a detection database; the generation module 86 uses a well-trained face recognition model to perform face recognition processing on the target detection result to obtain face feature information; the generation module 86 compares the face feature information with the stored information in the detection database to obtain the face comparison result.

[0168] In some embodiments, the above-mentioned generation module 86 is also used to obtain a preset comparison threshold; when the face comparison result indicates that the comparison information between the facial feature information and the stored information is greater than or equal to the comparison threshold, the generation module 86 generates the target rope skipping detection result based on the facial feature information and the rope skipping count result; when the face comparison result indicates that the comparison information is less than the comparison threshold, the generation module 86 stores the facial feature information to the detection database to generate a new face object, and generates the target rope skipping detection result based on the new face object and the rope skipping count result.

[0169] In some embodiments, the above-mentioned generation module 86 is also used to obtain a second skipping rope detection area and a preset skipping rope time; when the generation module 86 detects that the target detection result is within the second skipping rope detection area and the current time is within the preset skipping rope time, the generation module 86 uses the skipping rope counting model to perform skipping rope detection processing on the target detection result to generate the target skipping rope detection result; when the generation module 86 detects that the target detection result leaves the second skipping rope detection area, or the current time exceeds the preset skipping rope time, the generation module 86 sends a second prompt message to the reminder device, so that the reminder device prompts the user to end the skipping rope counting process based on the second prompt message.

[0170] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0171] This embodiment also provides a rope skipping counting system, comprising: an image acquisition device and a control device; the image acquisition device is configured to send the acquired image information to the control device; the control device is configured to acquire the image information and obtain at least one target detection result based on the image information; the control device uses a well-trained preparation gesture recognition model to perform preparation gesture recognition on the target detection result to obtain a first recognition result; and when the first recognition result indicates that the preparation gesture recognition has passed, the control device uses the well-trained rope skipping counting model to perform rope skipping detection processing on the target detection result to generate a target rope skipping detection result. The control device includes, but is not limited to, various server devices, processing chips, single-chip microcomputers, personal computers, or other devices configured to control the rope skipping counting process to generate a target rope skipping detection result. Through the above embodiments, the control device performs human body recognition on image information and gesture recognition on the human body recognition results obtained, and automatically counts rope skipping based on the results of gesture recognition, thereby reducing the interference of human participation in counting, reducing detection costs, and improving rope skipping detection efficiency; in addition, since the present application is based on rope skipping detection generated based on image information, it avoids interference such as sound and empty jumps, and can effectively improve the accuracy of rope skipping technology, thereby solving the problems of accuracy and low efficiency of rope skipping counting, and realizing an efficient and accurate automated rope skipping counting system.

[0172] In some embodiments, the skipping rope counting system further includes a reminder device. The control device is further configured to obtain a second skipping rope detection area and a preset skipping rope time; upon detecting that the target detection result is within the second skipping rope detection area and the current time is within the preset skipping rope time range, the control device performs skipping rope detection processing on the target detection result using the skipping rope counting model to generate the target skipping rope detection result; upon detecting that the target detection result leaves the second skipping rope detection area or the current time exceeds the preset skipping rope time, the control device sends a second reminder message to the reminder device, so that the reminder device notifies the user of the end of the skipping rope counting process based on the second reminder message.

[0173] In some embodiments, a computer device is provided, which may be a server. Figure 9 This is a structural diagram of the internal structure of a computer device according to an embodiment of the present application. Figure 9As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store target rope skipping detection results. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above-mentioned rope skipping counting method is implemented.

[0174] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0175] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0176] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0177] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0178] S1, obtaining image information, and obtaining at least one target detection result based on the image information.

[0179] S2, performing preparation gesture recognition on the target detection result using a well-trained preparation gesture recognition model to obtain a first recognition result.

[0180] S3. When the first recognition result indicates that the preparation gesture recognition is passed, a rope skipping detection process is performed on the target detection result using a well-trained rope skipping counting model to generate a target rope skipping detection result.

[0181] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be repeated here.

[0182] In addition, in conjunction with the rope skipping counting method in the above embodiments, the present application can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any of the rope skipping counting methods in the above embodiments is implemented.

[0183] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0184] Those skilled in the art should understand that the various technical features of the above-described embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0185] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A rope skipping counting method, characterized in that: The method comprises: Acquiring image information, and obtaining at least one target detection result based on the image information; Performing preparation gesture recognition on the target detection result using a well-trained preparation gesture recognition model to obtain a first recognition result; When the first recognition result indicates that the preparation gesture recognition is passed, performing rope skipping detection processing on the target detection result using a well-trained rope skipping counting model to generate a target rope skipping detection result, including: Obtain the preset first rope skipping detection area; Calculating an overlapping result based on the first rope skipping detection area and the first recognition result; In a case where the overlapping result is greater than or equal to a preset overlapping value, the rope skipping detection process is performed on the target detection result using the rope skipping counting model to generate the target rope skipping detection result.

2. The rope skipping counting method according to claim 1, wherein: The size of the first rope skipping detection area is a first size, and the first size includes first scale information and first feature point coordinates. The overlapping result calculated based on the first rope skipping detection area and the first recognition result includes: Acquire position frame information according to the first recognition result; the size of the position frame information is a second size, and the second size includes second scale information and second feature point coordinates; Calculating an overlapping area according to the first scale information, the first feature point coordinates, the second scale information, and the second feature point coordinates; Overlapping rate information is calculated according to the first scale information, the second scale information, and the overlapping area, and the overlapping rate information is used as the overlapping result.

3. The rope skipping counting method according to claim 1, wherein: After calculating the overlap result based on the first rope skipping detection area and the first recognition result, the method further includes: When the overlap result is less than the preset overlap value, a first prompt message is sent to the reminder device, so that the reminder device prompts the user to enter the first rope skipping detection area based on the first prompt message.

4. The rope skipping counting method according to claim 1, wherein: When the first recognition result indicates that the preparation gesture recognition is passed, the method further includes: Performing confirmation gesture recognition on the first recognition result using a well-trained confirmation gesture recognition model to obtain a second recognition result; If the time taken to obtain the second recognition result exceeds a preset recognition time period, or the second recognition result indicates that the confirmation gesture recognition fails, reusing the preparation gesture recognition model to perform preparation gesture recognition on all the target detection results to obtain the first recognition result; In a case where the time when the second recognition result is obtained is within the preset recognition time period, the rope skipping detection processing is performed on the target detection result using the rope skipping counting model to generate the target rope skipping detection result.

5. The rope skipping counting method according to claim 1, wherein: The step of performing rope skipping detection processing on the target detection result by using the well-trained rope skipping counting model to generate the target rope skipping detection result includes: Performing face comparison processing on the target detection result to obtain a face comparison result, and performing rope skipping detection processing on the target detection result using the rope skipping counting model to obtain a rope skipping counting result; The target rope skipping detection result is generated according to the face comparison result and the rope skipping counting result.

6. The rope skipping counting method according to claim 5, characterized in that: The performing face comparison processing on the target detection result to obtain the face comparison result includes: Obtain the detection database; Performing face recognition processing on the target detection results using a well-trained face recognition model to obtain facial feature information; The facial feature information is compared with the stored information in the detection database to obtain the facial comparison result.

7. The rope skipping counting method according to claim 6, characterized in that: Generating the target rope skipping detection result according to the face comparison result and the rope skipping counting result includes: Get the preset comparison threshold; generating the target rope skipping detection result according to the facial feature information and the rope skipping counting result, when the face comparison result indicates that the comparison information between the facial feature information and the stored information is greater than or equal to the comparison threshold; When the face comparison result indicates that the comparison information is less than the comparison threshold, the facial feature information is stored in the detection database to generate a new face object, and the target rope skipping detection result is generated according to the new face object and the rope skipping counting result.

8. The rope skipping counting method according to any one of claims 1 to 7, characterized in that: The step of performing rope skipping detection processing on the target detection result by using the well-trained rope skipping counting model to generate the target rope skipping detection result includes: Obtain the second rope skipping detection area and the preset rope skipping time; When it is detected that the target detection result is located within the second rope skipping detection area and the current time is within the preset rope skipping time range, performing rope skipping detection processing on the target detection result using the rope skipping counting model to generate the target rope skipping detection result; When it is detected that the target detection result leaves the second rope skipping detection area, or the current time exceeds the preset rope skipping time, a second prompt message is sent to the reminder device, so that the reminder device prompts the user to end the rope skipping counting process based on the second prompt message.

9. A skipping rope counting device, characterized in that: The device includes: an acquisition module, an identification module and a generation module; The acquisition module is configured to acquire image information and obtain at least one target detection result based on the image information; The recognition module is configured to perform preparation gesture recognition on the target detection result using a well-trained preparation gesture recognition model to obtain a first recognition result; The generating module is configured to, when the first recognition result indicates that the preparation gesture recognition has passed, perform rope skipping detection processing on the target detection result using a well-trained rope skipping counting model to generate a target rope skipping detection result; The generation module is also used to obtain a preset first rope skipping detection area; calculate an overlapping result based on the first rope skipping detection area and the first recognition result; and when the overlapping result is greater than or equal to a preset overlap value, use the rope skipping counting model to perform rope skipping detection processing on the target detection result to generate the target rope skipping detection result.

10. A skipping rope counting system, characterized in that: The system includes: an image acquisition device and a control device; The image acquisition device is used to send the acquired image information to the control device; The control device is used to execute the rope skipping counting method according to any one of claims 1 to 8.

11. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the rope skipping counting method according to any one of claims 1 to 8.

12. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the rope skipping counting method according to any one of claims 1 to 8 when running.

Images