CN111539294B - Shooting detection method and device, electronic equipment and computer readable storage medium - Google Patents
Shooting detection method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111539294B CN111539294B CN202010307279.3A CN202010307279A CN111539294B CN 111539294 B CN111539294 B CN 111539294B CN 202010307279 A CN202010307279 A CN 202010307279A CN 111539294 B CN111539294 B CN 111539294B
- Authority
- CN
- China
- Prior art keywords
- user
- shooting
- information
- video frame
- position information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Abstract
The application provides a shooting detection method, a shooting detection device, electronic equipment and a computer-readable storage medium, which are applied to the technical field of image processing, wherein the shooting detection method comprises the following steps: when the fact that the user in the target video frame has the shooting intention is detected, the subsequent frame is detected, when the position information of the basketball in the subsequent frame and the target human body part of the user meet a certain relation, the fact that the user completes shooting once is determined, therefore, the problem of detection omission possibly occurring in infrared detection can be avoided, and the accuracy of shooting detection is improved.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a shooting detection method, device, electronic device, and computer-readable storage medium.
Background
The basketball shooting machine is also called a basketball machine or a street basketball machine, and is sports leisure equipment with the latest trend formed by independently shooting actions in basketball sports, players need to shoot as many shots as possible within a certain time to score, and the players can enter the next stage when the scores exceed a certain score, so that the basketball shooting machine is a new sports mode.
When a player plays a game by using a shooting machine, the shooting times of the player are generally required to be counted, and currently, the shooting detection of the player is realized by infrared ray detection, however, the detection method by infrared ray has the problem of low detection accuracy.
Disclosure of Invention
The application provides a shooting detection method, a shooting detection device, electronic equipment and a computer-readable storage medium, which are used for improving the accuracy of shooting times detection of a user, and the technical scheme adopted by the application is as follows:
in a first aspect, there is provided a shot detection method, the method comprising,
determining whether a user in the target video frame has an intention to shoot a basket based on the gesture recognition model;
if the user in the target video frame has the shooting intention, detecting and identifying a subsequent frame of the target video frame based on a YOLO target detection model, and determining the position information of a basketball in the subsequent frame and the position information of the target human body part of the user;
and determining whether the user in the target video frame finishes shooting once or not based on the determined position information of the basketball and the position information of the target human body part of the user.
Optionally, determining whether the user in the target video frame has an intention to shoot based on the gesture recognition model comprises:
determining human body part key points of a user based on the gesture recognition model, wherein the human body part key points comprise a head, shoulders, elbows, wrists and arms;
and determining whether the user has the shooting intention or not based on the determined human body part key points of the user.
Optionally, the position information includes center coordinate information, width information, and height information.
Optionally, the determining whether the user in the target video frame has finished shooting one time based on the determined position information of the basketball and the position information of the target human body part of the user includes:
determining the position relation between the basketball and the target human body part based on the determined position information of the basketball and the position information of the target human body part of the user;
and if the basketball is positioned at the upper preset threshold distance of the target human body part, determining that the user finishes shooting one time.
Optionally, the method further comprises:
and if the user finishes shooting once, updating shooting record information of the user, wherein the shooting record information comprises shooting times of the user and shooting time information.
Optionally, the method further comprises:
determining shooting times information in a preset time based on the shooting record information;
obtaining the information of the goal times in the preset time;
and determining the shooting score of the user based on the shooting frequency information in the preset time and the goal frequency information in the preset time.
Optionally, the method further comprises:
carrying out image recognition on the target video frame to determine identity information of a user;
and storing the identity information of the user and the shooting score of the user in an associated manner.
In a second aspect, there is provided a shot detection apparatus, the apparatus comprising,
a first determination module for determining whether a user in a target video frame has an intention to shoot based on a gesture recognition model;
a second determining module, configured to detect and identify a subsequent frame of the target video frame based on a YOLO target detection model if the user in the target video frame has an intention to shoot a basketball, and determine location information of the basketball in the subsequent frame and location information of a target human body part of the user;
and the third determining module is used for determining whether the user in the target video frame finishes shooting once based on the determined position information of the basketball and the position information of the target human body part of the user.
Optionally, the first determining module includes:
a first determining unit, configured to determine human body part key points of a user based on the gesture recognition model, where the human body part key points include a head, shoulders, elbows, wrists, and arms;
and a second determination unit which determines whether the user has the intention of shooting based on the determined key points of the human body parts of the user.
Optionally, the position information includes center coordinate information, width information, and height information.
Optionally, the third determining module includes:
a third determining unit, configured to determine a position relationship between the basketball and the target human body part based on the determined position information of the basketball and the position information of the target human body part of the user;
a fourth determination unit, configured to determine that the user has completed shooting if the basketball is located at an upper portion of the target human body part by a predetermined threshold distance.
Optionally, the apparatus further comprises:
and the updating module is used for updating the shooting record information of the user if the user is determined to complete one shooting, wherein the shooting record information comprises the shooting times of the user and the shooting time information.
Optionally, the apparatus further comprises:
the fourth determining module is used for determining shooting times information in a preset time based on the shooting record information;
the acquisition module is used for acquiring the information of the ball-entering times in the preset time;
and the fifth determining module is used for determining the shooting score of the user based on the shooting frequency information in the preset time and the goal frequency information in the preset time.
Optionally, the apparatus further comprises:
the identification module is used for carrying out image identification on the target video frame to determine the identity information of the user;
and the storage module is used for storing the identity information of the user and the shooting score of the user in a correlation manner.
In a third aspect, an electronic device is provided, which includes:
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the shot detection method of the first aspect is performed.
In a fourth aspect, there is provided a computer-readable storage medium for storing computer instructions which, when run on a computer, cause the computer to perform the shot detection method of the first aspect.
Compared with the prior art of shooting detection by infrared rays, the shooting detection method and device, the electronic equipment and the computer-readable storage medium determine whether a user in a target video frame has the shooting intention or not based on a posture recognition model; if the user in the target video frame has the shooting intention, detecting and identifying a subsequent frame of the target video frame based on a YOLO target detection model, and determining the position information of a basketball in the subsequent frame and the position information of a target human body part of the user; and determining whether the user in the target video frame finishes shooting once or not based on the determined position information of the basketball and the position information of the target human body part of the user. The method comprises the steps of detecting a subsequent frame when the user in a target video frame is detected to have shooting intention, and determining that the user finishes shooting once when the position information of the basketball in the subsequent frame and the target human body part of the user meet a certain relation, so that the detection omission problem possibly caused by infrared detection can be avoided, and the shooting detection accuracy is improved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flow chart of a shot detection method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a shot detection device according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Example one
The embodiment of the application provides a shooting detection method, and as shown in fig. 1, the method may include the following steps:
step S101, whether the user in the target video frame has the shooting intention or not is determined based on the gesture recognition model.
The posture recognition refers to a computer vision technology for detecting a human image in an image or a video, and can determine a position where a certain body part of a person appears in the image, that is, a positioning problem of joints of the person in the image or the video, and can also be understood as a search for a specific posture in a space of all joint postures, in short, a task of posture estimation is to reconstruct joints and limbs of the person.
Specifically, it is determined whether the user in the target video frame has an intention to shoot a basket based on the gesture recognition model. The target video frame can be acquired by an image acquisition device configured by the shooting machine, wherein a certain trigger condition can be set, and the acquisition and detection of the user video can be carried out if the user clicks to start the shooting game. When the video frame is analyzed, the video frame can be preprocessed, wherein the preprocessing comprises the steps of cutting the image, only keeping the image within the width range of the shooting machine, and discarding the image outside the width range of the shooting machine, so that the data processing amount of image analysis can be reduced.
The gesture recognition model may be a 2D gesture recognition model or a 3D gesture recognition model based on different specific scenes.
Step S102, if the user in the target video frame has the shooting intention, detecting and identifying a subsequent frame of the target video frame based on a YOLO target detection model, and determining the position information of the basketball in the subsequent frame and the position information of the target human body part of the user.
Specifically, if the user has the shooting intention, the subsequent frames of the target video frames are detected and identified through the YOLO target detection model, and the position information of the basketball in the subsequent frames and the position information of the target human body part of the user are determined. The output of the YOLO target detection model may be the position information of the target and the probability of the corresponding category. Wherein the position information includes center coordinate information (X, Y), width information W, and height information H.
The task of object detection is, among other things, to identify which objects are in the image and their location in the image. The YOLO (You Only Look one) target detection realizes target detection classification by using a simple regression network, one network simultaneously classifies and positions a plurality of objects, and the one-stage real-time detection network is a milestone of the one-stage real-time detection network without the concept of proposal.
The YOLO target detection model may be a model based on any one of YOLOv1, YOLOv2, and YOLOv 3.
The YOLO model may be obtained based on a plurality of collected video frames with tag data of a shooting game performed by a user, where the tag data is corresponding position information (center coordinate information (X, Y), width information W, and height information H) in an image, and the tag data may include one or more position information, that is, a plurality of objects correspond to the video frames.
And step S103, determining whether the user in the target video frame finishes shooting once or not based on the determined position information of the basketball and the position information of the target human body part of the user.
Specifically, whether the user in the target video frame finishes shooting once is determined based on the determined position information of the basketball and the position information of the target human body part of the user. And if the determined result is that the shooting is not finished, detecting and identifying another subsequent frame of the target video frame.
Compared with the shooting detection by infrared rays in the prior art, the shooting detection method based on the gesture recognition model determines whether a user in a target video frame has shooting intention or not; if the user in the target video frame has the shooting intention, detecting and identifying a subsequent frame of the target video frame based on a YOLO target detection model, and determining the position information of a basketball in the subsequent frame and the position information of a target human body part of the user; and determining whether the user in the target video frame finishes shooting once or not based on the determined position information of the basketball and the position information of the target human body part of the user. The method comprises the steps of detecting a subsequent frame when it is detected that a user in a target video frame has shooting intention, and determining that the user finishes shooting once when the position information of a basketball in the subsequent frame and a target human body part of the user meet a certain relation, so that the problem of missed detection possibly occurring in infrared detection can be avoided, and the accuracy of shooting detection is improved.
The embodiment of the present application provides a possible implementation manner, and step S101 includes:
step S1011 (not shown in the figure), determining human body part key points of the user based on the gesture recognition model, wherein the human body part key points include a head, a shoulder, an elbow, a wrist, and an arm;
step S1012 (not shown in the drawing), it is determined whether the user has an intention to shoot a basket based on the determined human body part key point of the user.
Specifically, the gesture recognition model is a human skeleton key point detection model, and the detection process is as follows:
1) Calculating key points; 2) Calculating all the associated areas;
3) And carrying out vector connection according to the key points and the associated regions to obtain the bone structure of the user.
In the embodiment of the application, the shooting intention of the user is identified only by identifying the bone structure of the upper body of the user, and correspondingly, the key points are head diagram, shoulders, elbows, wrists and arms, so that all key points of the human body do not need to be identified, and the data processing amount can be reduced.
The embodiment of the present application provides a possible implementation manner, and specifically, step S103 includes:
step S1031 (not shown in the figure) of determining a positional relationship between the basketball and the target human body part based on the determined positional information of the basketball and the positional information of the target human body part of the user;
step S1032 (not shown), if the basketball is located at the upper predetermined threshold distance of the target human body part, it is determined that the user has finished shooting one time.
Specifically, the position relationship between the basketball and the target human body part (for example, the basketball is located on the upper part or the lower part of the target human body part) can be determined based on the determined position information of the basketball and the position information of the target human body part of the user. The basketball includes football, volleyball and other balls. Wherein, the target human body part can be any one of the head, eyes, nose bridge and the like of the user.
And when the basketball is positioned at the upper part of the target human body part by the preset threshold distance, the basketball is shot by the user, and the user is determined to finish shooting one time.
Further, if the user completes one shot, the detection of the shot taken by the user can be continued, wherein, since the user cannot shoot a shot immediately after completing one shot, the shooting intention detection of the user can be performed on the video frames six frames later. Thereby enabling to reduce the data processing amount.
With the embodiment of the application, the problem of how to determine that the user finishes shooting is solved.
The embodiment of the present application provides a possible implementation manner, and further, the method includes,
step S104 (not shown in the figure), if it is determined that the user completes one shooting, the shooting record information of the user is updated, and the shooting record information includes the shooting times of the user and the shooting time information.
Specifically, if the user finishes shooting once, the shooting record information of the user is updated, and the shooting record information comprises the shooting times of the user and shooting time information. The shooting times information of the user can be displayed on a screen configured by the shooting machine.
For the embodiment of the application, the problem of statistics of the shooting times of the user is solved.
The embodiment of the present application provides a possible implementation manner, and further, the method further includes:
step S105 (not shown in the figure) of determining shooting frequency information within a predetermined time based on the shooting record information;
step S106 (not shown in the figure), obtaining the information of the ball inlet times in the preset time;
step S107 (not shown in the figure) of determining a shooting score of the user based on the shooting frequency information in the predetermined time and the goal frequency information in the predetermined time.
For example, the number of shots and the number of goals of the user within one minute may be determined based on the shooting record information, and then the shooting score of the user may be determined according to the number of shots and the number of goals.
For the embodiment of the application, the problem of determining the shooting score of the user is solved, and the shooting times are detected more accurately than in an infrared mode, so that the shooting score of the user determined by the application is also more accurate than the shooting score of the user determined in the infrared mode.
The embodiment of the present application provides a possible implementation manner, and the method further includes:
step S108 (not shown in the figure) of carrying out image recognition on the target video frame to determine identity information of the user;
step S109 (not shown in the figure) stores the identity information of the user and the shooting score of the user in association with each other.
Specifically, the identity of the user in the target video can be identified and determined through an image identification method, such as a face identification algorithm, and then the identity information of the user is associated with the shooting score of the user and stored.
Specifically, the user may query the historical score conditions by a corresponding data query method.
Fig. 2 is a shooting detection apparatus provided in an embodiment of the present application, where the apparatus 20 includes: a first determining module 201, a second determining module 202, and a third determining module 203, wherein,
a first determination module 201, configured to determine whether a user in a target video frame has an intention to shoot a basket based on a gesture recognition model;
a second determining module 202, configured to detect and identify a subsequent frame of the target video frame based on the YOLO target detection model if the user in the target video frame has an intention to shoot a basketball, and determine location information of the basketball in the subsequent frame and location information of a target human body part of the user;
the position information comprises center coordinate information, width information and height information.
And a third determining module 203, configured to determine whether the user in the target video frame completes one shooting based on the determined position information of the basketball and the position information of the target human body part of the user.
Compared with the prior art that shooting detection is carried out through infrared rays, the shooting detection device determines whether a user in a target video frame has shooting intention or not based on a gesture recognition model; if the user in the target video frame has the shooting intention, detecting and identifying a subsequent frame of the target video frame based on a YOLO target detection model, and determining the position information of a basketball in the subsequent frame and the position information of a target human body part of the user; and determining whether the user in the target video frame finishes shooting once or not based on the determined position information of the basketball and the position information of the target human body part of the user. The method comprises the steps of detecting a subsequent frame when it is detected that a user in a target video frame has shooting intention, and determining that the user finishes shooting once when the position information of a basketball in the subsequent frame and a target human body part of the user meet a certain relation, so that the problem of missed detection possibly occurring in infrared detection can be avoided, and the accuracy of shooting detection is improved.
The shooting detection device of this embodiment can execute the shooting detection method provided in the above embodiments of this application, and the implementation principles thereof are similar, and are not described herein again.
The embodiment of the present application provides a possible implementation manner, and further, the first determining module 201 includes:
a first determining unit, configured to determine human body part key points of a user based on the gesture recognition model, where the human body part key points include a head, shoulders, elbows, wrists, and arms;
and a second determination unit which determines whether the user has the intention of shooting based on the determined key points of the human body parts of the user.
The embodiment of the present application provides a possible implementation manner, where the third determining module 203 includes:
a third determining unit, configured to determine a position relationship between the basketball and the target human body part based on the determined position information of the basketball and the position information of the target human body part of the user;
and the fourth determination unit is used for determining that the user finishes shooting once if the basketball is positioned at the upper part of the target human body part by the preset threshold distance.
The embodiment of the present application provides a possible implementation manner, and further, the apparatus 20 further includes:
and the updating module is used for updating the shooting record information of the user if the user is determined to complete one shooting, wherein the shooting record information comprises the shooting times of the user and the shooting time information.
The embodiment of the present application provides a possible implementation manner, and further, the apparatus 20 further includes:
the fourth determining module is used for determining shooting frequency information in a preset time based on the shooting record information;
the acquisition module is used for acquiring the information of the ball-entering times in the preset time;
and the fifth determining module is used for determining the shooting score of the user based on the shooting frequency information in the preset time and the goal frequency information in the preset time.
The embodiment of the present application provides a possible implementation manner, and further, the apparatus 20 further includes:
the identification module is used for carrying out image identification on the target video frame to determine the identity information of the user;
and the storage module is used for storing the identity information of the user and the shooting score of the user in a correlation manner.
The embodiment of the application provides a shooting detection device, which is suitable for the shooting detection method shown in the embodiment and is not repeated herein.
An embodiment of the present application provides an electronic device, as shown in fig. 3, an electronic device 30 shown in fig. 3 includes: a processor 301 and a memory 303. Wherein processor 301 is coupled to memory 303, such as via bus 302. Further, the electronic device 30 may also include a transceiver 304. It should be noted that the transceiver 304 is not limited to one in practical applications, and the structure of the electronic device 30 is not limited to the embodiment of the present application. The processor 301 is applied to the embodiment of the present application, and is configured to implement the functions of the first determining module, the second determining module, and the third determining module shown in fig. 2. The transceiver 304 includes a receiver and a transmitter.
The processor 301 may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 301 may also be a combination of computing functions, e.g., comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
The memory 303 is used for storing application program codes for executing the scheme of the application, and the processor 301 controls the execution. The processor 301 is configured to execute application program code stored in the memory 303 to implement the functions of the shot detection apparatus provided by the embodiment shown in fig. 2.
Compared with the prior art that shooting detection is carried out through infrared rays, the electronic equipment determines whether a user in a target video frame has shooting intention or not based on a gesture recognition model; if the user in the target video frame has the shooting intention, detecting and identifying a subsequent frame of the target video frame based on a YOLO target detection model, and determining the position information of a basketball in the subsequent frame and the position information of a target human body part of the user; and determining whether the user in the target video frame finishes shooting once or not based on the determined position information of the basketball and the position information of the target human body part of the user. The method comprises the steps of detecting a subsequent frame when the user in a target video frame is detected to have shooting intention, and determining that the user finishes shooting once when the position information of the basketball in the subsequent frame and the target human body part of the user meet a certain relation, so that the detection omission problem possibly caused by infrared detection can be avoided, and the shooting detection accuracy is improved.
The embodiment of the application provides an electronic device suitable for the method embodiment. And will not be described in detail herein.
Embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method shown in the above embodiments.
Compared with the prior art of shooting detection by infrared rays, the method for detecting the shooting of the target video frame based on the gesture recognition model determines whether a user in the target video frame has the intention of shooting or not; if the user in the target video frame has the shooting intention, detecting and identifying a subsequent frame of the target video frame based on a YOLO target detection model, and determining the position information of a basketball in the subsequent frame and the position information of a target human body part of the user; and determining whether the user in the target video frame finishes shooting once or not based on the determined position information of the basketball and the position information of the target human body part of the user. The method comprises the steps of detecting a subsequent frame when the user in a target video frame is detected to have shooting intention, and determining that the user finishes shooting once when the position information of the basketball in the subsequent frame and the target human body part of the user meet a certain relation, so that the detection omission problem possibly caused by infrared detection can be avoided, and the shooting detection accuracy is improved.
The embodiment of the application provides a computer-readable storage medium which is suitable for the method embodiment. And will not be described in detail herein.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.
Claims (10)
1. A shooting detection method is characterized by being applied to a shooting machine and comprising the following steps:
determining whether a user in the target video frame has an intention to shoot a basket based on the gesture recognition model;
the gesture recognition model is a human skeleton key point detection model, and the determining whether the user in the target video frame has the shooting intention or not based on the gesture recognition model comprises the following steps: calculating key points; calculating all the associated areas; performing vector connection according to the key points and the associated regions to obtain a bone structure of the user; wherein the skeletal structure comprises only upper body skeletal structure;
if the user in the target video frame has the shooting intention, detecting and identifying a subsequent frame of the target video frame based on a YOLO target detection model, and determining the position information of the basketball in the subsequent frame and the position information of the target human body part of the user;
and determining whether the user in the target video frame finishes shooting once or not based on the determined position information of the basketball and the position information of the target human body part of the user.
2. The method of claim 1, wherein determining whether a user in a target video frame has an intention to shoot a basket based on a gesture recognition model comprises:
determining human body part key points of a user based on the gesture recognition model, wherein the human body part key points comprise a head, shoulders, elbows, wrists and arms;
and determining whether the user has the shooting intention or not based on the determined human body part key points of the user.
3. The method of claim 1, wherein the position information comprises center coordinate information, width information, and height information.
4. The method of any one of claims 1-3, wherein determining whether the user has completed a shot in the target video frame based on the determined position information of the basketball and the position information of the user's target human body part comprises:
determining the position relation between the basketball and the target human body part based on the determined position information of the basketball and the position information of the target human body part of the user;
and if the basketball is positioned at the upper preset threshold distance of the target human body part, determining that the user finishes shooting one time.
5. The method of claim 4, further comprising:
and if the user finishes one shooting, updating shooting record information of the user, wherein the shooting record information comprises shooting times of the user and shooting time information.
6. The method of claim 5, further comprising:
determining shooting times information in a preset time based on the shooting record information;
acquiring the information of the number of ball entries in the preset time;
and determining the shooting score of the user based on the shooting times information in the preset time and the goal times information in the preset time.
7. The method of claim 6, further comprising:
carrying out image recognition on the target video frame to determine identity information of a user;
and storing the identity information of the user and the shooting score of the user in an associated manner.
8. A shooting detection device, characterized in that is applied to a shooting machine, comprising:
a first determination module for determining whether a user in a target video frame has an intention to shoot based on a gesture recognition model;
the gesture recognition model is a human skeleton key point detection model, and the determining whether the user in the target video frame has the shooting intention or not based on the gesture recognition model comprises the following steps: calculating key points; calculating all the associated areas; performing vector connection according to the key points and the associated regions to obtain a bone structure of the user; wherein the skeletal structure comprises only upper body skeletal structure;
a second determining module, configured to detect and identify a subsequent frame of the target video frame based on a YOLO target detection model if the user in the target video frame has an intention to shoot a basketball, and determine position information of the basketball in the subsequent frame and position information of a target human body part of the user;
and the third determining module is used for determining whether the user in the target video frame finishes shooting once based on the determined position information of the basketball and the position information of the target human body part of the user.
9. An electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: performing a shot detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing computer instructions which, when run on a computer, cause the computer to perform the shot detection method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010307279.3A CN111539294B (en) | 2020-04-17 | 2020-04-17 | Shooting detection method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010307279.3A CN111539294B (en) | 2020-04-17 | 2020-04-17 | Shooting detection method and device, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111539294A CN111539294A (en) | 2020-08-14 |
| CN111539294B true CN111539294B (en) | 2022-11-15 |
Family
ID=71979994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010307279.3A Active CN111539294B (en) | 2020-04-17 | 2020-04-17 | Shooting detection method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111539294B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011310B (en) * | 2021-03-15 | 2022-03-11 | 中国地质大学（武汉） | Method and device for collecting shooting exercise amount, computer equipment and storage medium |
| CN116109981B (en) * | 2023-01-31 | 2024-04-12 | 北京智芯微电子科技有限公司 | Shooting recognition method, basketball recognition device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701460A (en) * | 2016-01-07 | 2016-06-22 | 王跃明 | Video-based basketball goal detection method and device |
| CN106991357A (en) * | 2016-01-20 | 2017-07-28 | 上海慧体网络科技有限公司 | The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video |
| CN107305138A (en) * | 2016-04-20 | 2017-10-31 | 李斌 | Basketball action identification method and system based on wrist attitude detection |
| CN109821243A (en) * | 2019-01-25 | 2019-05-31 | 丰羽教育科技（上海）有限公司 | A method of simulation reappears shooting process |
| CN109961039A (en) * | 2019-03-20 | 2019-07-02 | 上海者识信息科技有限公司 | A kind of individual's goal video method for catching and system |
-
2020
- 2020-04-17 CN CN202010307279.3A patent/CN111539294B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701460A (en) * | 2016-01-07 | 2016-06-22 | 王跃明 | Video-based basketball goal detection method and device |
| CN106991357A (en) * | 2016-01-20 | 2017-07-28 | 上海慧体网络科技有限公司 | The shooting of automatic identification Basketball Match and the algorithm scored based on panoramic video |
| CN107305138A (en) * | 2016-04-20 | 2017-10-31 | 李斌 | Basketball action identification method and system based on wrist attitude detection |
| CN109821243A (en) * | 2019-01-25 | 2019-05-31 | 丰羽教育科技（上海）有限公司 | A method of simulation reappears shooting process |
| CN109961039A (en) * | 2019-03-20 | 2019-07-02 | 上海者识信息科技有限公司 | A kind of individual's goal video method for catching and system |
Non-Patent Citations (2)
| Title |
|---|
| "Detecting events and key actors in multi-person videos";Vignesh Ramanathan et al.;《arxiv》;20160331;全文 * |
| "基于视频图像处理的罚篮技术动作辅助训练系统";孙锐兴;《中国优秀博硕士学位论文全文数据库(硕士) 社会科学Ⅱ辑》;20170715(第07期);第15-39页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111539294A (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107301370B (en) | Kinect three-dimensional skeleton model-based limb action identification method | |
| US7899206B2 (en) | Device, system and method for determining compliance with a positioning instruction by a figure in an image | |
| RU2628155C2 (en) | Device, method and computer program for reconstruction of object motion | |
| CN111539294B (en) | Shooting detection method and device, electronic equipment and computer readable storage medium | |
| EP3798978A1 (en) | Ball game video analysis device and ball game video analysis method | |
| CN101533528B (en) | Optical motion capture data processing method based on module piecewise linear model | |
| CN104778465B (en) | A kind of matched method for tracking target of distinguished point based | |
| Elaoud et al. | Skeleton-based comparison of throwing motion for handball players | |
| CN108919943A (en) | A kind of real-time hand method for tracing based on depth transducer | |
| CN108830170A (en) | A kind of end-to-end method for tracking target indicated based on layered characteristic | |
| Tsai et al. | Enhancing accuracy of human action Recognition System using Skeleton Point correction method | |
| Naik et al. | DeepPlayer-track: player and referee tracking with jersey color recognition in soccer | |
| JP4465150B2 (en) | System and method for measuring relative position of an object with respect to a reference point | |
| CN111368787A (en) | Video processing method and device, equipment and computer readable storage medium | |
| Ohri et al. | On-device realtime pose estimation & correction | |
| CN109758154B (en) | Motion state determination method, device, equipment and storage medium | |
| CN114155557A (en) | Positioning method, positioning device, robot and computer-readable storage medium | |
| Terroba et al. | Finding optimal strategies in tennis from video sequences | |
| CN116311523A (en) | Fancy rope skipping recognition algorithm based on image recognition | |
| CN111353347A (en) | Motion recognition error correction method, electronic device, and storage medium | |
| CN113947757A (en) | Volleyball sport touch screen detection method based on OpenPose | |
| CN104680134B (en) | Quick human body detecting method | |
| CN111210424B (en) | Bone age X-ray film RUS bone block near contour point positioning method | |
| CN112883862B (en) | Shooting identification method, shooting identification device, computer equipment and storage medium | |
| Zeng et al. | Machine learning based automatic sport event detection and counting |
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 |