CN113378713B - Skip counting method, device, terminal equipment and storage medium - Google Patents
Skip counting method, device, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN113378713B CN113378713B CN202110649785.5A CN202110649785A CN113378713B CN 113378713 B CN113378713 B CN 113378713B CN 202110649785 A CN202110649785 A CN 202110649785A CN 113378713 B CN113378713 B CN 113378713B
- Authority
- CN
- China
- Prior art keywords
- key point
- count
- state
- value
- target parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Television Signal Processing For Recording (AREA)
- Measurement Of Unknown Time Intervals (AREA)
- Image Analysis (AREA)
Abstract
The application is applicable to the technical field of artificial intelligence, and provides a jump counting method, a jump counting device, terminal equipment and a storage medium, wherein the jump counting method comprises the following steps: according to a preset image acquisition period, acquiring a rope skipping video image, extracting key point coordinates of a target key point from the rope skipping video image, and storing the key point coordinates into a key point coordinate set, wherein the abscissa of the key point coordinates is the acquisition time of the rope skipping video image, and the ordinate is the longitudinal height value of the target key point in the rope skipping video image; in response to reaching a preset fitting condition, fitting the key point coordinates in the key point coordinate set to generate a parabola, and obtaining target parameters of the parabola; determining an adding state of the jump count according to the value of the target parameter, and updating the value of the jump count according to the adding state, wherein the adding state comprises a count increasing state and a count unchanged state. Furthermore, the present application relates to blockchain techniques.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a jump counting method, apparatus, terminal device, and storage medium.
Background
The jump rope is a relatively warm exercise at present, is a systemic exercise integrating upper limbs, lower limbs, waist and buttocks exercise, and can effectively burn heat and reduce fat. The teenagers can jump ropes, so that the bone strength can be increased, and the bone cell growth can be promoted, and the growth can be promoted.
In practical applications, a user may shoot a rope skipping video through a shooting device, such as a mobile phone, and then count the hops in the rope skipping video in a macroscopic manner. The counting method for the skip count in the rope skipping video by means of naked eyes is low in efficiency and easy to make mistakes.
Disclosure of Invention
In view of the above, the embodiments of the present application provide a skip count method, apparatus, terminal device, and storage medium, so as to solve the problems of low efficiency and easy error in counting skip counts in a skip rope video by means of naked eye viewing in the related art.
A first aspect of an embodiment of the present application provides a hop counting method, including:
according to a preset image acquisition period, acquiring a rope skipping video image, extracting key point coordinates of a target key point from the rope skipping video image, and storing the key point coordinates into a key point coordinate set, wherein the abscissa of the key point coordinates is the acquisition time of the rope skipping video image, and the ordinate is the longitudinal height value of the target key point in the rope skipping video image;
in response to reaching a preset fitting condition, fitting the key point coordinates in the key point coordinate set to generate a parabola, and obtaining target parameters of the parabola;
determining an adding state of the jump count according to the value of the target parameter, and updating the value of the jump count according to the adding state, wherein the adding state comprises a count increasing state and a count unchanged state.
Further, extracting key point coordinates of a target key point from the rope skipping video image includes:
inputting the rope skipping video image into a pre-trained key point prediction model to obtain a key point set aiming at the rope skipping video image;
and taking the acquisition time of the rope skipping video image as an abscissa and the longitudinal height value of the target key point in the key point set in the rope skipping video image as an ordinate to obtain the key point coordinates of the target key point.
Further, determining the adding state of the skip count according to the value of the target parameter includes:
if the value of the target parameter belongs to a preset range and the target parameter is the parabolic target parameter obtained by first fitting, determining that the adding state is a counting increasing state;
if the value of the target parameter belongs to the preset range and the target parameter is a parabolic target parameter obtained by non-first fitting, determining that the adding state is a counting increasing state when the polarity of the value of the target parameter obtained by fitting at the previous moment is opposite to the polarity of the value of the target parameter.
Further, updating the value of the skip count according to the addition state includes:
if the addition state is the count increasing state, the value of the jump count is increased by 1, and if the addition state is the count unchanged state, the value of the jump count is unchanged.
Further, the method further comprises:
and updating the coordinate set of the key points according to the adding state of the jump count.
Further, updating the set of key point coordinates according to the addition status of the skip count, including:
if the adding state of the jump count is the count increasing state, clearing the key point coordinate set;
and if the adding state of the jump count is a count-unchanged state, deleting the earliest stored key point coordinate in the key point coordinate set.
Further, preset fitting conditions include at least one of the following: receiving a fitting instruction; reaching a fitting period; the number of the key point coordinates in the key point coordinate set is greater than or equal to a preset number, and the preset number is greater than or equal to three.
A second aspect of an embodiment of the present application provides a skip count apparatus, including:
the information acquisition unit is used for acquiring a rope skipping video image according to a preset image acquisition period, extracting key point coordinates of a target key point from the rope skipping video image, and storing the key point coordinates into a key point coordinate set, wherein the abscissa of the key point coordinates is the acquisition time of the rope skipping video image, and the ordinate is the longitudinal height value of the target key point in the rope skipping video image;
the information fitting unit is used for generating a parabola by fitting key point coordinates in the key point coordinate set in response to the preset fitting condition, so as to obtain a target parameter of the parabola;
and the count updating unit is used for determining the adding state of the jump count according to the value of the target parameter and updating the value of the jump count according to the adding state, wherein the adding state comprises a count increasing state and a count unchanged state.
A third aspect of the embodiments of the present application provides a terminal device comprising a memory, a processor and a computer program stored in the memory and operable on the terminal device, the processor implementing the steps of the hop count method provided in the first aspect when the computer program is executed.
A fourth aspect of the embodiments of the present application provides a storage medium storing a computer program which, when executed by a processor, implements the steps of the hop count method provided by the first aspect.
The embodiment of the application provides a jump counting method, a jump counting device, terminal equipment and a storage medium, which have the following beneficial effects: because the change of each jump of a person along with time is nearly a parabola with a downward opening in the rope skipping process, the target key points of the rope skipping person, such as shoulder key points, and part or all of the key point coordinates of the corresponding key point coordinate set are fitted to generate the parabola, the accurate description of the rope skipping process can be realized, and therefore, the jump counting increment condition can be determined by analyzing the target parameters of the parabola obtained by fitting, and the rapid and accurate jump counting can be realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the related technical descriptions will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an implementation of a skip count method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a theoretical jump waveform provided by an embodiment of the present application;
FIG. 3 is a schematic diagram of an actual jump waveform provided by an embodiment of the present application;
fig. 4 is a schematic distribution diagram of key points of a human body according to an embodiment of the present application;
FIG. 5 is a block diagram of a jump counting device according to an embodiment of the present application;
fig. 6 is a block diagram of a terminal device according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The hop counting method according to the embodiment of the present application may be executed by a control device or a terminal (hereinafter referred to as a "terminal device"). When the jump counting method is executed by the terminal equipment, the execution main body is the terminal equipment.
Referring to fig. 1, fig. 1 shows a flowchart of implementing a skip counting method according to an embodiment of the present application, including:
and step 101, acquiring a rope skipping video image according to a preset image acquisition period, extracting key point coordinates of a target key point from the rope skipping video image, and storing the key point coordinates into a key point coordinate set.
Where the keypoint coordinates are typically coordinates of the target keypoint. The abscissa of the coordinates of the key points is the acquisition time of the rope skipping video image, and the ordinate is the longitudinal height value of the target key points in the rope skipping video image.
The preset image capturing period is generally a preset period for capturing an image. In practice, since the duration of one jump period is usually short, the above-mentioned preset image acquisition period is usually a small value, for example, may be 0.1 seconds, 0.05 seconds, or the like. It should be noted that, since each person can jump about 100-150 rope per minute, the single rope jump time is between 400ms and 600ms, and since at least three data points are needed to fit and generate a parabola, in order to achieve accurate jump counting, the value of the preset image acquisition period is usually less than 133ms, where 133=400+.3.
The target key points are usually predetermined key points of the human body. As an example, the target key points may be hip key points, shoulder key points, or the like.
The execution body may collect the video image of the rope skipping from the video of the rope skipping currently being recorded or from the video of the rope skipping already recorded according to a preset image collection period. Then, the executing body may extract the key point coordinates of the target key point from the rope skipping video image. As an example, if the target key point is a shoulder key point, the shoulder of the rope skipping person may wear a specific object, such as wearing a red cloth head, so that the executing body may identify the target key point from the rope skipping video image by identifying the worn red cloth head, and extract the key point coordinates of the target key point. Finally, the execution body may store the extracted coordinates of the key points in the set of coordinates of the key points.
And step 102, in response to reaching a preset fitting condition, fitting and generating a parabola by adopting the key point coordinates in the key point coordinate set, and obtaining target parameters of the parabola.
The preset fitting condition is usually a preset condition for triggering the fitting operation.
Optionally, the preset fitting condition may include, but is not limited to, at least one of the following three:
first, a fitting instruction is received.
And secondly, the fitting period is reached. The fitting period is usually a preset period value.
Here, the fitting period is generally greater than the preset image acquisition period and less than one rope skipping period.
Thirdly, the number of the key point coordinates in the key point coordinate set is larger than or equal to the preset number, and the preset number is larger than or equal to three.
The target parameters are usually preset parameters, and in practice, the parameters of the parabola generally have three parameters, namely, a parameter a, a parameter b and a parameter c. The target parameter of the parabola is typically parameter a.
In practical application, when the rope jumpers jump, each jump changes along time to be nearly a parabola with downward opening, for example, y=at 2 +bt+c, where a, b and c are parameters of a parabola. Theoretically, if a person keeps constant jump with the same frequency and the same height, the jump waveform corresponding to the change of the jump height with time approximates to the parabola shown in fig. 2. In practice, however, the jump rope height will vary each time as the jump physical effort is spent, the actual jump waveform of which is shown in fig. 3.
Fig. 2 is a theoretical hopping waveform provided by an embodiment of the present application, and fig. 3 is an actual hopping waveform provided by an embodiment of the present application.
As can be seen from comparison between fig. 2 and fig. 3, in the practical application scenario, the peak corresponding to each jump will change more significantly, and the distance between every two peaks will also change more significantly. The opening size of the parabola corresponding to each wave is almost the same, namely, the value of the parameter a of the parabola is basically the same. In fact, since the gravitational acceleration experienced during the jump is kept unchanged, the value of the parameter a in the parabola corresponding to each wave is theoretically also approximately equal. Therefore, taking the parameter a as the target parameter of the parabola, and determining the jump count increase condition by analyzing the target parameter, it is possible to realize fast and accurate jump count.
Here, when the preset fitting condition is reached, the execution body may use some or all of the coordinates of the key points in the set of coordinates of the key points to fit and generate a parabola, so that the target parameter in the parabola may be obtained.
Step 103, determining the adding state of the jump count according to the value of the target parameter, and updating the value of the jump count according to the adding state.
Wherein the adding state includes a count increasing state and a count unchanged state.
Here, since the value of the target parameter of the parabola corresponding to each jump is substantially unchanged and the value of the target parameter corresponding to each person's jump is substantially the same when the rope is jumped, the execution subject may determine the addition state of the jump count by analyzing the value of the target parameter. For example, if the value of the target parameter is significantly greater than the value of the target parameter corresponding to the rope skipping action, the adding state of the skip count may be determined to be the count-unchanged state.
According to the method provided by the embodiment, as the change of each jump along with time of a person in the rope skipping process is almost a parabola with a downward opening, the target key points of the rope skipping person, such as the shoulder key points, are fitted and generated into the parabola by the corresponding key point coordinate sets, so that the rope skipping process can be accurately described, and therefore, the jump counting increment condition can be determined by analyzing the target parameters of the fitted parabola, and the rapid and accurate jump counting can be realized.
In some optional implementations of this embodiment, extracting keypoint coordinates of the target keypoint from the rope-skipping video image includes:
firstly, inputting a rope skipping video image into a pre-trained key point prediction model to obtain a key point set aiming at the rope skipping video image. That is, a set of coordinates of each key point in the rope skipping video image is obtained.
The key point prediction model can be used for analyzing the corresponding relation between the image and the human body gesture key points. In practice, the keypoint prediction model may be a model obtained by training an initial model (for example, convolutional neural network (Convolutional Neural Network, CNN), residual network (res net), etc.) using a machine learning method based on training samples.
Fig. 4 is a schematic distribution diagram of key points of a human body according to an embodiment of the present application. As shown in fig. 4, there may be 17 key points, their numbers may be 0-16 in sequence, and the positions indicated by 0-16 may be: 0-nose, 1-left eye, 2-right eye, 3-left ear, 4-right ear, 5-left shoulder, 6-right shoulder, 7-left elbow, 8-right elbow, 9-left wrist, 10-right wrist, 11-left crotch joint, 12-right crotch joint, 13-left knee, 14-right knee, 15-left ankle, 16-right ankle.
Here, the rope skipping video image is input into the key point prediction model, and a set of key points for the rope skipping video image can be obtained. In this set of keypoints, 17 keypoints may be included.
And then, taking the acquisition time of the rope skipping video image as an abscissa and taking the longitudinal height value of the target key point in the key point set in the rope skipping video image as an ordinate to obtain the key point coordinates of the target key point.
Here, the target key point may be a shoulder key point, for example, may be a key point numbered 5 as shown in fig. 4. The execution subject can directly take the acquisition time of the rope skipping video image as an abscissa and take the longitudinal height value of the target key point in the rope skipping video image as an ordinate to obtain the key point coordinate of the target key point.
In the implementation mode, the key point prediction model is a pre-trained neural network model, the key point detection is carried out by directly inputting the rope skipping video image into the key point prediction model, then the longitudinal height value corresponding to the longitudinal coordinate of one key point obtained by detection is directly taken as the longitudinal coordinate, and the acquisition time of the rope skipping video image is taken as the horizontal coordinate, so that the key point coordinate of the target key point is obtained. The method can directly extract the key point coordinates of the target key points from the rope skipping video image, and is convenient, practical and high in accuracy.
In some optional implementations of the present embodiment, determining the adding state of the skip count according to the value of the target parameter includes: if the value of the target parameter belongs to the preset range and the target parameter is the target parameter of the parabola obtained by first fitting, determining that the adding state is a counting increasing state. If the value of the target parameter belongs to the preset range and the target parameter is a parabolic target parameter obtained by non-first fitting, determining that the adding state is a counting increasing state when the polarity of the value of the target parameter obtained by fitting at the previous moment is opposite to the polarity of the value of the target parameter.
Wherein the preset range is a throwing obtained by fitting the rope skipping actionThe range of the target parameter of the object line. In practice, the value of the target parameter is usually small. In practice, when the abscissa of the key point is in the dimension of millisecond and the ordinate is the number of pixels, the preset range may be 2×10 -3 Up to 4X 10 -3 。
Here, if the value of the currently obtained target parameter belongs to the preset range and the target parameter is the first target parameter obtained by fitting the rope skipping video, the adding state is determined to be the counting increasing state.
In addition, if the value of the currently obtained target parameter belongs to the preset range, but the target parameter is not the first target parameter obtained by fitting, the polarity of the value of the target parameter obtained by fitting at the previous moment is continuously analyzed. The addition state is determined to be the count-up state only when the polarity of the value of the target parameter at the previous time is opposite to the polarity of the value of the target parameter at the current time.
For example, if the polarity of the target parameter at the previous time is positive, the polarity of the target parameter at the current time is negative, and the polarities are opposite, the addition state may be determined to be the count-up state. Otherwise, if the polarity of the target parameter at the previous moment is negative, and the polarity of the target parameter at the current moment is negative, the polarities are the same, and at this time, the adding state can be determined to be the counting unchanged state.
It should be noted that, since the parabola generated by the segment fitting of the falling phase point of the last jump and the current jump phase is generally upward in opening, the polarity of the value of the parameter a is positive. When the value polarity of the previous parameter a is positive and the value polarity of the current parameter a is negative, the last jump is ended, and a new jump is started, and the adding state is determined to be the count increasing state at the moment, so that more accurate jump counting can be realized.
In an optional implementation manner of the embodiments of the present application, updating the value of the skip count according to the addition state may include: if the addition state is the count increasing state, the value of the jump count is increased by 1, and if the addition state is the count unchanged state, the value of the jump count is unchanged.
Here, the skip count is updated according to the addition state, and accurate skip count can be realized.
In an optional implementation manner of the various embodiments of the present application, the jump counting method may further include: and updating the coordinate set of the key points according to the adding state of the jump count.
Here, the execution body may update the key point coordinate set according to the addition state of the skip count, thereby implementing more accurate skip count.
Optionally, updating the key point coordinate set according to the adding state of the skip count may include: and if the adding state of the jump count is a count increasing state, clearing the coordinate set of the key point. And if the adding state of the jump count is a count-unchanged state, deleting the earliest stored key point coordinate in the key point coordinate set.
Here, when the addition state is the count increasing state, it indicates that the current jump is one, and the jump count is currently required to be increased. At this time, the set of key point coordinates may be emptied and recording restarted. When the adding state is the state with unchanged count, it indicates that the current jump cannot be recorded, at this time, the earliest stored key point coordinate in the key point coordinate set can be deleted, the key point coordinate at the current moment is added, and analysis is continued until the jump count is increased. The jump counting is realized more accurately.
In all embodiments of the present application, the terminal device may collect the rope skipping video image according to a preset image collection period, extract the key point coordinates of the target key point from the rope skipping video image, and store the key point coordinates in the key point coordinate set. And the abscissa of the coordinates of the key points is the acquisition time of the rope skipping video image, and the ordinate is the longitudinal height value of the target key points in the rope skipping video image. And then, in response to reaching a preset fitting condition, fitting and generating a parabola by adopting the key point coordinates in the key point coordinate set, and obtaining the target parameters of the parabola. And finally, determining the adding state of the jump count according to the value of the target parameter, and updating the value of the jump count according to the adding state. Wherein the addition state includes a count up state and a count unchanged state. The terminal device can upload the value of the finally obtained jump count to the blockchain, so that the safety and the fairness and transparency to users can be ensured. The user device may download the data information from the blockchain to verify whether the data information has been tampered with. The blockchain referred to in this example is a novel mode of application for computer technology such as distributed data storage, point-to-point transmission, consensus mechanisms, encryption algorithms, and the like. The Blockchain (Blockchain), which is essentially a decentralised storage server, is a string of data blocks that are generated in association using cryptographic methods, each of which contains a batch of information for network transactions, for verifying the validity (anti-counterfeiting) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Referring to fig. 5, fig. 5 is a block diagram illustrating a jump counting device 500 according to an embodiment of the application. The jump counting means in this embodiment comprise units for performing the steps in the corresponding embodiment of fig. 1. Refer specifically to fig. 1 and the related description in the embodiment corresponding to fig. 1. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 5, the skip count apparatus 500 includes:
the information collection unit 501 is configured to collect a rope skipping video image according to a preset image collection period, extract a key point coordinate of a target key point from the rope skipping video image, and store the key point coordinate in a key point coordinate set, where an abscissa of the key point coordinate is a collection time of the rope skipping video image, and an ordinate is a longitudinal height value of the target key point in the rope skipping video image;
the information fitting unit 502 is configured to generate a parabola by fitting the key point coordinates in the key point coordinate set in response to reaching a preset fitting condition, so as to obtain a target parameter of the parabola;
the count updating unit 503 is configured to determine an addition state of the skip count according to the value of the target parameter, and update the value of the skip count according to the addition state, where the addition state includes a count increasing state and a count unchanged state.
As an embodiment of the present application, the information acquisition unit 501 is specifically configured to:
inputting the rope skipping video image into a pre-trained key point prediction model to obtain a key point set aiming at the rope skipping video image;
and taking the acquisition time of the rope skipping video image as an abscissa and the longitudinal height value of the target key point in the key point set in the rope skipping video image as an ordinate to obtain the key point coordinates of the target key point.
As an embodiment of the present application, the count updating unit 503 is specifically configured to:
if the value of the target parameter belongs to a preset range and the target parameter is the parabolic target parameter obtained by first fitting, determining that the adding state is a counting increasing state;
if the value of the target parameter belongs to the preset range and the target parameter is a parabolic target parameter obtained by non-first fitting, determining that the adding state is a counting increasing state when the polarity of the value of the target parameter obtained by fitting at the previous moment is opposite to the polarity of the value of the target parameter.
As an embodiment of the present application, the count updating unit 503 is specifically configured to:
if the addition state is the count increasing state, the value of the jump count is increased by 1, and if the addition state is the count unchanged state, the value of the jump count is unchanged.
The apparatus may further comprise a data update unit (not shown in the figure) as an embodiment of the present application. And the data updating unit is used for updating the coordinate set of the key points according to the adding state of the jump count.
As an embodiment of the present application, the data updating unit is specifically configured to:
if the adding state of the jump count is the count increasing state, clearing the key point coordinate set;
and if the adding state of the jump count is a count-unchanged state, deleting the earliest stored key point coordinate in the key point coordinate set.
As an embodiment of the present application, the preset fitting conditions include at least one of the following: receiving a fitting instruction; reaching a fitting period; the number of the key point coordinates in the key point coordinate set is greater than or equal to a preset number, and the preset number is greater than or equal to three.
According to the device provided by the embodiment, as the change of each jump along with time of a person in the rope skipping process is almost a parabola with a downward opening, the target key points of the rope skipping person, such as the shoulder key points, are fitted and generated into the parabola by the corresponding key point coordinate sets, so that the accurate description of the rope skipping process can be realized, and therefore, the jump counting increment condition can be determined by analyzing the target parameters of the parabola obtained by fitting, and the rapid and accurate jump counting can be realized.
It should be understood that, in the block diagram of the jump counting device shown in fig. 5, each unit is configured to execute each step in the embodiment corresponding to fig. 1, and each step in the embodiment corresponding to fig. 1 has been explained in detail in the foregoing embodiment, and reference is specifically made to fig. 1 and the related description in the embodiment corresponding to fig. 1, which are not repeated herein.
Fig. 6 is a block diagram of a terminal device according to another embodiment of the present application. As shown in fig. 6, the terminal device 600 of this embodiment includes: a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601, such as a program of a jump counting method. The steps of the various embodiments of the hop count method described above, such as steps 101 through 103 shown in fig. 1, are implemented when the processor 601 executes the computer program 603. Alternatively, the processor 601 may implement the functions of each unit in the embodiment corresponding to fig. 5 when executing the computer program 603, for example, the functions of the units 501 to 503 shown in fig. 5, refer to the related descriptions in the embodiment corresponding to fig. 5, which are not repeated here.
By way of example, the computer program 603 may be partitioned into one or more units, one or more units being stored in the memory 602 and executed by the processor 601 to complete the application. One or more of the elements may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program 603 in the terminal device 600. For example, the computer program 603 may be divided into an information acquisition unit, an information fitting unit, a count updating unit, each unit functioning specifically as above.
The terminal device may include, but is not limited to, a processor 601, a memory 602. It will be appreciated by those skilled in the art that fig. 6 is merely an example of a terminal device 600 and is not limiting of the terminal device 600, and may include more or fewer components than shown, or may combine certain components, or different components, such as a turntable device may also include an input-output device, a network access device, a bus, etc.
The processor 601 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 602 may be an internal storage unit of the terminal device 600, such as a hard disk or a memory of the terminal device 600. The memory 602 may also be an external storage device of the terminal device 600, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device 600. Further, the memory 602 may also include both internal storage units and external storage devices of the terminal device 600. The memory 602 is used to store computer programs and other programs and data required by the turntable device. The memory 602 may also be used to temporarily store data that has been output or is to be output.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Wherein the computer readable storage medium may be nonvolatile or volatile. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of each method embodiment described above may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable storage medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable storage medium may be appropriately scaled according to the requirements of jurisdictions in which such computer readable storage medium does not include electrical carrier signals and telecommunication signals, for example, according to jurisdictions and patent practices.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (9)
1. A skip count method, the method comprising:
according to a preset image acquisition period, acquiring a rope skipping video image, extracting key point coordinates of a target key point from the rope skipping video image, and storing the key point coordinates into a key point coordinate set, wherein the abscissa of the key point coordinates is the acquisition time of the rope skipping video image, and the ordinate is the longitudinal height value of the target key point in the rope skipping video image;
in response to reaching a preset fitting condition, fitting the key point coordinates in the key point coordinate set to generate a parabola, and obtaining a target parameter of the parabola, wherein the target parameter is a square term coefficient of a quadratic function corresponding to the parabola;
determining an adding state of the jump count according to the value of the target parameter, and updating the value of the jump count according to the adding state, wherein the adding state comprises a count increasing state and a count unchanged state;
wherein, the determining the adding state of the jump count according to the value of the target parameter includes:
if the value of the target parameter belongs to a preset range and the target parameter is a parabolic target parameter obtained by first fitting, determining that the adding state is a counting increasing state;
if the value of the target parameter belongs to a preset range and the target parameter is a parabolic target parameter obtained by non-first fitting, determining that the adding state is a counting increasing state when the polarity of the value of the target parameter obtained by fitting at the previous moment is opposite to the polarity of the value of the target parameter.
2. The skip count method of claim 1 wherein the extracting key point coordinates of a target key point from the skip rope video image comprises:
inputting the rope skipping video image into a pre-trained key point prediction model to obtain a key point set aiming at the rope skipping video image;
and taking the acquisition time of the rope skipping video image as an abscissa and the longitudinal height value of the target key point in the key point set in the rope skipping video image as an ordinate to obtain the key point coordinates of the target key point.
3. The hop count method according to claim 1, wherein updating the value of the hop count according to the addition state includes:
if the adding state is a counting increasing state, the value of the jump count is increased by 1, and if the adding state is a counting unchanged state, the value of the jump count is unchanged.
4. The hop count method of claim 1, wherein the method further comprises:
and updating the key point coordinate set according to the adding state of the jump count.
5. The hop-counting method of claim 4, wherein updating the set of keypoint coordinates based on the state of addition of the hop-count comprises:
if the adding state of the jump count is a count increasing state, the key point coordinate set is emptied;
and if the adding state of the jump count is a count-unchanged state, deleting the earliest stored key point coordinate in the key point coordinate set.
6. The hop count method of any of claims 1-5 wherein the preset fitting conditions include at least one of: receiving a fitting instruction; reaching a fitting period; the number of the key point coordinates in the key point coordinate set is greater than or equal to a preset number, and the preset number is greater than or equal to three.
7. A skip count apparatus, the apparatus comprising:
the information acquisition unit is used for acquiring a rope skipping video image according to a preset image acquisition period, extracting key point coordinates of a target key point from the rope skipping video image, and storing the key point coordinates into a key point coordinate set, wherein the abscissa of the key point coordinates is the acquisition time of the rope skipping video image, and the ordinate is the longitudinal height value of the target key point in the rope skipping video image;
the information fitting unit is used for generating a parabola by fitting the key point coordinates in the key point coordinate set in response to the preset fitting condition, and obtaining a target parameter of the parabola, wherein the target parameter is a square term coefficient of a quadratic function corresponding to the parabola;
a count updating unit, configured to determine an addition state of the skip count according to the value of the target parameter, and update the value of the skip count according to the addition state, where the addition state includes a count increment state and a count unchanged state;
wherein, the determining the adding state of the jump count according to the value of the target parameter includes:
if the value of the target parameter belongs to a preset range and the target parameter is a parabolic target parameter obtained by first fitting, determining that the adding state is a counting increasing state;
if the value of the target parameter belongs to a preset range and the target parameter is a parabolic target parameter obtained by non-first fitting, determining that the adding state is a counting increasing state when the polarity of the value of the target parameter obtained by fitting at the previous moment is opposite to the polarity of the value of the target parameter.
8. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110649785.5A CN113378713B (en) | 2021-06-10 | 2021-06-10 | Skip counting method, device, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110649785.5A CN113378713B (en) | 2021-06-10 | 2021-06-10 | Skip counting method, device, terminal equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113378713A CN113378713A (en) | 2021-09-10 |
| CN113378713B true CN113378713B (en) | 2023-08-29 |
Family
ID=77573783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110649785.5A Active CN113378713B (en) | 2021-06-10 | 2021-06-10 | Skip counting method, device, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113378713B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115282589A (en) * | 2022-08-31 | 2022-11-04 | 深圳十米网络科技有限公司 | Somatosensory game method based on rope skipping action |
| CN115361438B (en) * | 2022-10-19 | 2023-02-28 | 山东远联信息科技有限公司 | Service processing method and system for cloud computing and big data positioning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103386181A (en) * | 2013-07-25 | 2013-11-13 | Tcl通讯（宁波）有限公司 | Mobile terminal and rope skipping counting method adopting same |
| CN109737952A (en) * | 2018-12-12 | 2019-05-10 | 安徽华米信息科技有限公司 | Rope skipping data processing method, device and wearable device |
| WO2019244153A1 (en) * | 2018-06-21 | 2019-12-26 | Baseline Vision Ltd. | Device, system, and method of computer vision, object tracking, image analysis, and trajectory estimation |
| CN112634400A (en) * | 2020-12-21 | 2021-04-09 | 浙江大华技术股份有限公司 | Rope skipping counting method, terminal and computer readable storage medium thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200302187A1 (en) * | 2015-07-17 | 2020-09-24 | Origin Wireless, Inc. | Method, apparatus, and system for people counting and recognition based on rhythmic motion monitoring |
-
2021
- 2021-06-10 CN CN202110649785.5A patent/CN113378713B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103386181A (en) * | 2013-07-25 | 2013-11-13 | Tcl通讯（宁波）有限公司 | Mobile terminal and rope skipping counting method adopting same |
| WO2019244153A1 (en) * | 2018-06-21 | 2019-12-26 | Baseline Vision Ltd. | Device, system, and method of computer vision, object tracking, image analysis, and trajectory estimation |
| CN109737952A (en) * | 2018-12-12 | 2019-05-10 | 安徽华米信息科技有限公司 | Rope skipping data processing method, device and wearable device |
| CN112634400A (en) * | 2020-12-21 | 2021-04-09 | 浙江大华技术股份有限公司 | Rope skipping counting method, terminal and computer readable storage medium thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113378713A (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113378713B (en) | Skip counting method, device, terminal equipment and storage medium | |
| CN104794462B (en) | A kind of character image processing method and processing device | |
| CN111667420B (en) | Image processing method and device | |
| CN110659581B (en) | Image processing method, device, equipment and storage medium | |
| CN109063584B (en) | Facial feature point positioning method, device, equipment and medium based on cascade regression | |
| CN109525771B (en) | Video distribution device, video distribution system, and video distribution method | |
| JPWO2019208703A1 (en) | Information processing device | |
| CN113239875B (en) | Method, system and device for acquiring face characteristics and computer readable storage medium | |
| CN109561257A (en) | Picture focusing method, device, terminal and corresponding storage medium | |
| CN109117635A (en) | Method for detecting virus, device, computer equipment and the storage medium of application program | |
| CN106419821A (en) | Method and device for arthroscopically measuring intra-articular structure | |
| CN110163265A (en) | Data processing method, device and computer equipment | |
| CN110599520B (en) | Open field experiment data analysis method, system and terminal equipment | |
| CN108205708A (en) | A kind of novel expansible deep learning system and data identification method | |
| CN111191558B (en) | Robot and face recognition teaching method and storage medium thereof | |
| CN107885318A (en) | A kind of virtual environment exchange method, device, system and computer-readable medium | |
| CN107992816A (en) | Photographing search method and device and electronic equipment | |
| CN111750919A (en) | Identity authentication method and apparatus using multi-axis sensor and accelerometer | |
| CN108263074A (en) | Localization method, device, terminal device and the readable storage medium storing program for executing of silk-screen halftone | |
| CN112166435A (en) | Target tracking method and device, electronic equipment and storage medium | |
| EP3330674A1 (en) | Method and apparatus for realizing step counting | |
| CN112717343B (en) | Method and device for processing sports data, storage medium and computer equipment | |
| CN108053031A (en) | A kind of deep learning system and deep learning recognition methods | |
| CN115227468A (en) | Training method of intelligent artificial limb, intelligent artificial limb and storage medium | |
| CN113206956A (en) | Image processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |