CN110059653A - A kind of method of data capture and device, electronic equipment, storage medium - Google Patents
A kind of method of data capture and device, electronic equipment, storage medium Download PDFInfo
- Publication number
- CN110059653A CN110059653A CN201910335557.3A CN201910335557A CN110059653A CN 110059653 A CN110059653 A CN 110059653A CN 201910335557 A CN201910335557 A CN 201910335557A CN 110059653 A CN110059653 A CN 110059653A
- Authority
- CN
- China
- Prior art keywords
- data
- scene
- target
- data collection
- positioning
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000013481 data capture Methods 0.000 title abstract 2
- 238000013480 data collection Methods 0.000 claims description 83
- 238000012545 processing Methods 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 230000015654 memory Effects 0.000 claims description 20
- 230000009471 action Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 22
- 230000006870 function Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000004807 localization Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- 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
-
- 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
- G06V40/23—Recognition of whole body movements, e.g. for sport training
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present disclosure discloses a kind of method of data capture, this method comprises: receiving at least one scene video；Using image recognition model, motion information identification is carried out to the object for including at least one scene video, is collected at least one object identification data, motion information includes: object identity, movement and tracing positional；The scenario objects data of target scene are generated according at least one object identification data.By implementing above scheme, the collection of related data is carried out to the object under application scenarios based on image recognition technology and location technology, not only collection efficiency is higher, but also full-featured.
Description
Technical Field
The present disclosure relates to the field of machine vision technologies, and in particular, to a data collection method and apparatus, an electronic device, and a storage medium.
Background
Currently, in match training scenes such as football matches and basketball matches, it is generally necessary to collect relevant match data to determine player motion tracks, football motion tracks, and court thermodynamic diagrams, so as to provide a basis for subsequent tactical guidance and arrangement.
In the prior art, two ways of collecting match data are mainly included, one way is manual statistics, however, in a large-scale sports match, not only the field range is large, but also too many athletes are on the field, the efficiency of data collection is low due to manual statistics, the other way is that different types of data are collected respectively by adopting a door line technology, an eagle eye system and the like, one kind of equipment can only realize the collection of one type of data, and the function is single.
Disclosure of Invention
The embodiment of the disclosure is expected to provide a data collection method and device, an electronic device, and a storage medium, where relevant data is collected for an object in an application scene based on an image recognition technology and a positioning technology, and the collection efficiency is high and the functions are comprehensive.
The technical scheme of the embodiment of the disclosure is realized as follows:
the embodiment of the disclosure provides a data collection method, which comprises the following steps:
receiving at least one scene video;
identifying, by using an image identification model, motion information of an object included in the at least one scene video, and collecting at least one object identification data, where the motion information includes: object identity, action, and tracking location;
scene object data of the target scene is generated according to the at least one object identification data.
In the above data collection method, after receiving at least one scene video, the method further includes:
carrying out space positioning processing on the object included in the at least one scene video by using a space positioning algorithm, and collecting at least one object positioning data;
generating scene object data of a target scene from the at least one object recognition data comprises:
and generating scene object data of the target scene according to the at least one object identification data and the at least one object positioning data.
In the data collecting method, before the identifying the motion information of the object included in the at least one scene video by using the image identification model and collecting at least one object identification data, the method further includes:
and acquiring the image recognition model generated by training based on a preset model training method.
In the above data collecting method, the generating scene object data of the target scene according to the at least one object identification data includes:
receiving a target request sent by a client;
according to the target request, selecting data to be processed from the at least one object identification data, and determining a target data processing mode;
and performing data processing on the data to be processed according to the target data processing mode to generate the scene object data.
In the above data collection method, after the generating the scene object data, the method further includes:
and sending the target providing information to the client.
In the data collection method, the image recognition model at least comprises a target detection tracking model and a motion recognition model.
An embodiment of the present invention provides a data collection device, including:
a receiving module, configured to receive at least one scene video;
an identification module, configured to perform motion information identification on an object included in the at least one scene video by using an image identification model, and collect at least one object identification data, where the motion information includes: object identity, action, and tracking location;
and the generating module is used for generating scene object data of the target scene according to the at least one object identification data.
The data collecting device also comprises a positioning module;
the positioning module is used for performing spatial positioning processing on an object included in the at least one scene video by using a spatial positioning algorithm and collecting at least one object positioning data;
the generating module is configured to generate scene object data of the target scene according to the at least one object identification data and the at least one object positioning data.
The data acquisition device further comprises an acquisition module, and the acquisition module is specifically used for acquiring the image recognition model generated by training based on a preset model training method.
In the data collecting apparatus, the generating module is specifically configured to receive a target request sent by a client; according to the target request, selecting data to be processed from the at least one object identification data, and determining a target data processing mode; and performing data processing on the data to be processed according to the target data processing mode to generate the scene object data.
The data collecting device further comprises a sending module;
the sending module is used for sending the scene object data to the client.
In the above data collection apparatus, the image recognition model includes at least a target detection tracking model and a motion recognition model.
An embodiment of the present invention provides an electronic device, including: a processor, a memory, and a communication bus; wherein,
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is used for executing the data collection program stored in the memory so as to realize the data collection method.
Optionally, the electronic device is a server.
Embodiments of the present invention provide a computer-readable storage medium storing one or more programs, which are executable by one or more processors to implement the above-described data collection method.
The embodiment of the invention provides a data collection method, which comprises the steps of receiving at least one scene video; identifying, by using an image identification model, an object included in at least one scene video with motion information, and collecting at least one object identification data, wherein the motion information includes: object identity, action, and tracking location; scene object data of the target scene is generated from the at least one object recognition data. Compared with the prior art that data are collected manually or data of a single type are collected by a door line technology, an eagle eye system and the like respectively, the technical scheme of the invention collects related data of an object under an application scene based on an image recognition technology, and has the advantages of high collection efficiency and comprehensive functions.
Drawings
Fig. 1 is a first schematic flow chart of a data collection method according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart illustrating a data collection method according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of an exemplary data collection method applied to a soccer scene according to an embodiment of the present invention;
FIG. 4 is a diagram of an exemplary soccer ball trajectory provided by an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a data collection device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure.
Fig. 1 is a first flowchart illustrating a data collection method according to an embodiment of the present disclosure. As shown in fig. 1, the method mainly comprises the following steps:
s101, receiving at least one scene video.
In an embodiment of the invention, the data collection device may receive at least one scene video.
It should be noted that, in the embodiment of the present invention, at least one camera device, for example, a camera, is installed in a target scene, and the number of the specifically installed cameras may be determined according to whether the target scene can be completely covered, that is, the installed cameras need to ensure that a formed shooting range does not cover a dead angle in the target scene, and the installation positions and angles of the different cameras are different, so that at least one scene video generated by the target scene at least one angle may be actually acquired by the installed cameras, and the at least one camera may upload the at least one scene video to a data collection device as a basis for data collection, and the specific number of the scene videos is not limited in the embodiment of the present invention.
It should be noted that, in the embodiment of the present invention, the target scene may be a football match scene or a football training scene on a football field, or may also be a basketball match scene or a basketball training scene on a basketball field, and the specific target scene is not limited in the embodiment of the present invention.
Illustratively, in the embodiment of the present invention, the target scene is a football training scene, for which three cameras are installed at different positions at different angles around the football court, and the three cameras completely cover the football court, so that when a football player trains on the football court, for the football training scene, the three cameras will generate three scene videos at three angles and upload the three scene videos to the data collection device, and the data collection device can receive the input three scene videos.
S102, identifying the motion information of the object included in at least one scene video by using an image identification model, and collecting at least one object identification datum, wherein the motion information comprises: object identity, action, and tracking location.
In an embodiment of the present invention, after receiving the at least one scene video, the data collection device may perform motion information recognition on the object included in the at least one scene video by using the image recognition model, and collect the at least one object recognition data.
In the embodiment of the present invention, the object in the target scene includes a person, an article, and the like in the target scene, for example, a player, a football, a teaching aid, and the like in a football training scene, and the specific object data included in the target scene is not limited in the embodiment of the present invention.
It should be noted that, in the embodiment of the present invention, the image recognition model at least includes a target detection tracking model and a motion recognition model, where the target detection tracking model can detect a target object, for example, a specific person, from a certain frame of image of a video, so as to track the target object in another image, and the motion recognition model can automatically recognize the motion of different persons in the image, of course, the image recognition model may also include other models based on an image recognition technology, and the specific image recognition model is not limited in the embodiment of the present invention.
It should be noted that, in the embodiment of the present invention, at least one scene video actually includes multiple frames of images, and for each frame of image, the data collection apparatus may perform identification, motion recognition, and tracking position of an object by using the object detection tracking model and the motion recognition model included in the image recognition model, so as to obtain at least one object recognition data.
It is understood that, in the embodiment of the present invention, the data collection apparatus may perform object detection on a certain frame image in at least one scene video by using a target detection tracking model in an image recognition model, that is, identify an identity of an object, and after the object detection is performed, perform tracking in other frame images according to characteristics of the object, to obtain tracking positions of the object, which all belong to the object recognition data.
It is understood that, in the embodiment of the present invention, the data collection apparatus may perform motion recognition on the object in each frame of image in at least one scene video by using the motion recognition model in the image recognition model, that is, obtain motion data of the object, which also belongs to the above object recognition data.
It should be noted that, in the embodiment of the present invention, the image recognition model may also include other types of models, for example, a face recognition model, and the data collection device may perform face recognition by using the face recognition model, but these models are all based on image recognition technology and all belong to the image recognition model.
For example, in an embodiment of the present invention, the target scene is a football training scene, and the data collection device may receive at least one football scene video, and further perform identity, action, and tracking recognition on a player and a football included in the at least one football scene video by using the target detection tracking model and the action recognition model in the image recognition model, to obtain object recognition data such as a player number, player action data, player motion tracking data, and football motion tracking data of the player.
It should be noted that, in the embodiment of the present invention, before the motion information recognition is performed by using the image recognition model, the data collection apparatus actually further includes the following steps: and acquiring an image recognition model generated by training based on a preset model training method.
It should be noted that, in the embodiment of the present invention, an image recognition model may be trained according to a preset model training mode by using a large number of sample images according to an artificial intelligence technique and an image recognition technique, and a specific model training mode is not limited in the embodiment of the present invention.
S103, generating scene object data of the target scene according to at least one object identification datum.
In an embodiment of the present invention, after the data collecting device collects the at least one object identification data, the data collecting device may generate scene object data of the target scene according to the at least one object identification data.
Specifically, in an embodiment of the present invention, a data collection device generates scene object data of a target scene according to at least one object identification data, including: receiving a target request sent by a client; according to the target request, selecting data to be processed from at least one object identification data, and determining a target data processing mode; and performing data processing on the data to be processed according to the target data processing mode to generate scene object data.
It should be noted that, in the embodiment of the present invention, data processing manners corresponding to different types of requests may be stored in advance in the data collection device, for example, the target request is a request for providing a motion trajectory of a player, the data collection device may obtain a data processing manner for determining the motion trajectory of the player according to the target request, and select player tracking data from at least one object identification data, and the specific target data processing manner is not limited in the embodiment of the present invention.
It should be noted that, in the embodiment of the present invention, the at least one object identification data includes diversified data, for example, for a goal scene being a football training scene, the scene object data may include data such as player identity, player motion tracking, football tracking, and teaching aid type, wherein, for the goal providing information corresponding to the goal request generation, part of the information is not needed, therefore, the data collection device may determine data to be used for the goal request, and select data to be processed from the at least one object identification data, and the specific data to be processed is not limited in the embodiment of the present invention.
Illustratively, in the embodiment of the present invention, the target scene is a football training scene, and the target request provides a football motion trajectory for the request, so the data collection device selects football tracking data from at least one object identification data according to the target request, that is, image positions of a football in each frame of at least one scene video, combines all the football tracking positions, and sequentially connects according to a corresponding target data processing mode, that is, according to a time sequence of the frames, so as to generate a football motion trajectory map, where the football motion trajectory map is scene object data.
It is to be understood that, in the embodiment of the present invention, the data collecting device generates scene object data of the target scene according to at least one object identification data, where the scene object data may be a thermodynamic diagram, a motion trajectory of an object in the target scene, and the like, and the specific scene object data is not limited by the embodiment of the present invention.
It should be noted that, in the embodiment of the present invention, after the data collection device generates the scene object data, the data collection device may send the scene object data to the client.
It can be understood that, in the embodiment of the present invention, the target scene may be a soccer scene or a basketball scene, and under these scenes, the coach and the player need to know the relevant information in the sport process for tactical improvement and training, so that, in practice, the coach and the player can send the information of the actual demand to the data collection device in a target request manner through the client, the data collection device can generate scene object data, and send the scene object data to the client, and the coach and the player can analyze and adjust the tactical situation according to the scene object data, that is, a data support service is provided for the sport teaching and match scenes.
The embodiment of the invention provides a data collection method, which comprises the steps of receiving at least one scene video; identifying, by using an image identification model, an object included in at least one scene video with motion information, and collecting at least one object identification data, wherein the motion information includes: object identity, action, and tracking location; scene object data of the target scene is generated from the at least one object recognition data. Compared with the prior art that data are collected manually or data of a single type are collected by a door line technology, an eagle eye system and the like respectively, the technical scheme of the invention collects related data of an object under an application scene based on an image recognition technology, and has the advantages of high collection efficiency and comprehensive functions.
Fig. 2 is a schematic flow chart diagram of a data collection method according to an embodiment of the present invention. As shown in fig. 2, the method mainly comprises the following steps:
s201, receiving at least one scene video.
In an embodiment of the present invention, the data collection device may receive at least one scene video acquired by at least one camera device overlaying the target scene.
It should be noted that, in the embodiment of the present invention, step S201 is completely the same as step S101 in the first embodiment, and is not described herein again.
S202, identifying the motion information of the object included in at least one scene video by using an image identification model, and collecting at least one object identification datum, wherein the motion information comprises: object identity, action, and tracking location.
In an embodiment of the present invention, after receiving the at least one scene video, the data collection device may perform motion information recognition on an object included in the at least one scene video using an image recognition model, for example, an object detection tracking model and a motion recognition model, so as to collect the at least one object recognition data.
It should be noted that, in the embodiment of the present invention, the step S202 is completely the same as the step S102 in the first embodiment, and is not described herein again.
S203, carrying out space positioning processing on the object included in the at least one scene video by using a space positioning algorithm, and collecting at least one object positioning data.
In an embodiment of the present invention, after receiving the at least one scene video, the data collection device may perform a spatial positioning process on an object included in the at least one scene video by using a spatial positioning algorithm, so as to collect the at least one object positioning data.
It should be noted that, in the embodiment of the present invention, the data collection device may specifically obtain an image position of an object included in each frame of image in the at least one scene video in the image, and then perform spatial positioning calculation on the image position by using a spatial positioning algorithm, so as to obtain at least one object positioning data.
In the embodiment of the present invention, if the data collection device receives three scene videos, corresponding three frames of images may be acquired at the same time in the three scene videos, the data collection device acquires the same target object from the three frames of images, the image positions of the target object in the three frames of images are a1, a2, and A3, and the spatial location of the target object at the time may be acquired by performing spatial location calculation on a1, a2, and A3 using a spatial location algorithm. If the data collection device obtains a scene video, a frame of image can be obtained at a moment in the scene video, the image position of the target player in the frame of image is B1, and the spatial positioning algorithm is used for carrying out spatial mapping on B1, so that the spatial position of the target object at the moment can be obtained, wherein the spatial position is the object positioning data.
Illustratively, in the embodiment of the invention, the target scene is a basketball training scene, the data collection device receives three basketball scene videos transmitted by three cameras covering the basketball training scene, so that the spatial positioning algorithm is utilized to perform spatial positioning processing on players, basketballs and teaching aids in the three basketball scene videos, and data such as the positions of players, the positions of football and the positions of teaching aids in the basketball training scene are collected, namely object positioning data is obtained, wherein the positions of players, the positions of football and the positions of teaching aids are spatial positions in a three-dimensional space.
It should be noted that, in the embodiment of the present invention, the data collection device may respectively perform spatial positioning processing on the objects included in each frame of at least one scene video by using a spatial positioning algorithm, of course, some frames may be selected from the objects according to a certain rule or an actual requirement to perform the spatial positioning processing, and a specific spatial positioning manner is not limited in the embodiment of the present invention.
It should be noted that, in the embodiment of the present invention, the data collection is derived from at least one scene video obtained by at least one camera installed in the corresponding area, so that, based on the hardware configuration of the at least one camera and the configuration information of the camera device, such as the installation angle and the installation position, the corresponding spatial positioning algorithm can be determined, and the specific spatial positioning algorithm and the determination process of the spatial positioning algorithm are not limited in the embodiment of the present invention.
It is understood that, in the embodiment of the present invention, the image recognition model and the spatial location algorithm may be generated by a model training device or other devices, and then transmitted to a data collection device, and the data collection device may obtain the image recognition model and the spatial location algorithm.
It should be noted that, in the embodiment of the present invention, for the situation that at least one object identification data and at least one object positioning data are collected by using the image identification model and the spatial positioning algorithm, a complete collection system may be designed according to the image identification model and the spatial positioning algorithm, that is, the image identification model and the spatial positioning algorithm may be packaged in some way according to a certain system design rule, and normalized input and output are designed, for example, a video that needs to be subjected to a scene screening may be firstly performed, and a portion of a video with poor effect may be deleted, and further, a comprehensive consideration design may be performed from the aspects of structural elements, functional requirements, time series, and the like to perform data collection more optimally, but the basis of the system design comes from the image identification model and the spatial positioning algorithm, that is, the collection system actually has an image identification function and a spatial positioning function, the specific image recognition model and the spatial localization algorithm are provided in a form that is not limited by the embodiments of the present invention.
S204, generating scene object data of the target scene according to the at least one object identification data and the at least one object positioning data.
In an embodiment of the invention, after the data collecting device collects the at least one object identification data and the at least one object positioning data, the data collecting device may generate the scene object data of the target scene according to the at least one object identification data and the at least one object positioning data.
It can be understood that, in the embodiment of the present invention, the scene object data is used to implement a data support service for a target scene, and statistical analysis may be performed according to at least one object identification data and at least one object positioning data according to specific requirements to obtain related scene object data.
It should be noted that, in the embodiment of the present invention, the at least one object identification data and the at least one object positioning data are both for objects in the target scene, for example, players and pieces of golf equipment in a sports game, and the specific at least one object identification data and at least one object positioning data are not limited in the embodiment of the present invention.
Specifically, in the embodiment of the present invention, the data collection device may further receive a target request sent by the client, so as to generate scene object data of the target scene according to the target request and the at least one object identification data and the at least one object positioning data, where the scene object data is used to represent a motion state of an object included in the target scene.
It should be noted that, in the embodiment of the present invention, the goal request may be a request for some type of scene object data, for example, a motion trajectory of a certain player in a football training scene, or motion amount data of each player, and the specific goal request is not limited in the embodiment of the present invention.
Illustratively, in the embodiment of the invention, the target scene is a football training scene, and the target request may be one or more of a request for court thermal information, a request for player trajectory, a request for player motion amount data, a request for player physical consumption data, and a request for football trajectory.
Illustratively, in the embodiment of the invention, the at least one object identification data and the at least one object positioning data collected by the data collection device may specifically include data of types such as player identity, player position, player motion tracking, football position, football tracking, teaching aid position, etc., the target request provides player motion amount data for the request, and the corresponding target data processing mode is to multiply the motion amount of a preset unit distance according to the motion distance of the player, namely, the object positioning data is involved, therefore, the data collection device selects the player position data from the scene object data as the data to be processed, and then generates the player motion amount data, namely, the scene object data according to the motion distance of the player determined according to the player position and the motion amount of the preset unit distance according to the target data processing mode, and when the target request further includes the goal of providing the thermal power data of the court, a course thermodynamic diagram, which is also scene object data, may also be generated.
It should be noted that, in the embodiment of the present invention, the scene object data generated according to the at least one object identification data and the at least one object positioning data may include various types of data, and the scene object data may be in a form of data, a form of a table, or an image, and the specific form of the scene object data is not limited in the embodiment of the present invention.
It is understood that, in the embodiment of the present invention, after the data collection device generates the scene object data, the scene object data can be sent to the client as in step S103 in the first embodiment, which is not described herein again.
Fig. 3 is a schematic flow chart illustrating an exemplary data collection method applied to a soccer scene according to an embodiment of the present invention. As shown in fig. 3, the data collection device includes an image recognition model and a spatial localization algorithm, wherein the image recognition model and the spatial localization algorithm are designed as a system, arranging camera devices around the court to collect scene videos, importing the videos into a data collection device, enabling the data collection device to utilize an image recognition model and a spatial positioning algorithm, processing the scene video to obtain scene object data such as player identity, position, motion tracking, football position, teaching aid position and the like, then according to actual requirements, namely a target request, generates a thermodynamic diagram, a player motion trail diagram, a motion amount and a physical ability diagram by using scene object data, and a soccer ball trajectory diagram, fig. 4 is an exemplary soccer ball trajectory diagram provided by an embodiment of the present invention, as shown in fig. 4, the soccer balls move from location 1 to location 5 in turn, and the data collection device may provide these maps to the client.
An embodiment of the present disclosure further provides a data collection device, and fig. 5 is a schematic structural diagram of the data collection device according to the embodiment of the present disclosure. As shown in fig. 5, the data collection apparatus includes:
a receiving module 501, configured to receive at least one scene video;
an identifying module 502, configured to perform motion information identification on an object included in the at least one scene video by using an image identification model, and collect at least one object identification data, where the motion information includes: object identity, action, and tracking location;
a generating module 503, configured to generate scene object data of the target scene according to the at least one object identification data.
Optionally, the data collection module further comprises a positioning module 504;
the positioning module 504 is configured to perform spatial positioning processing on an object included in the at least one scene video by using a spatial positioning algorithm, and collect at least one object positioning data;
the generating module 503 is configured to generate scene object data of the target scene according to the at least one object identification data and the at least one object positioning data.
Optionally, the data collection apparatus further includes an obtaining module 505;
the obtaining module 505 is specifically configured to obtain the image recognition model generated based on training by a preset model training method.
Optionally, the generating module 503 is specifically configured to receive a target request sent by a client; according to the target request, selecting data to be processed from the at least one object identification data, and determining a target data processing mode; and performing data processing on the data to be processed according to the target data processing mode to generate the scene object data.
Optionally, the data collection device further includes a sending module;
the sending module 506 is configured to send the scene object data to the client.
Optionally, the image recognition model at least includes a target detection tracking model and a motion recognition model.
The embodiment of the invention provides a data collection device, which receives at least one scene video; identifying, by using an image identification model, an object included in at least one scene video with motion information, and collecting at least one object identification data, wherein the motion information includes: object identity, action, and tracking identification; scene object data of the target scene is generated from the at least one object recognition data. Compared with the prior art that data are collected manually or data of a single type are collected by a door line technology, an eagle eye system and the like, the data collection device collects relevant data of an object under an application scene based on an image recognition technology, and is high in collection efficiency and comprehensive in function.
An embodiment of the present disclosure provides an electronic device, and fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 6, the electronic apparatus includes: a processor 601, memory 602, and a communication bus 603; wherein,
the communication bus 603 is used for realizing connection communication between the processor 601 and the memory 602;
the processor 601 is configured to execute the data collection program stored in the memory 602 to implement the data collection method.
In the embodiment of the present invention, the electronic device may be a server, or may be another terminal having a data processing capability, and the specific electronic device is not limited in the embodiment of the present invention.
Embodiments of the present disclosure also provide a computer-readable storage medium storing one or more programs, which may be executed by one or more processors to implement the above-described data collection method. The computer-readable storage medium may be a volatile Memory (volatile Memory), such as a Random-Access Memory (RAM); or a non-volatile Memory (non-volatile Memory) such as a Read-Only Memory (ROM), a flash Memory (flash Memory), a Hard Disk (HDD) or a Solid-State Drive (SSD); or may be a respective device, such as a mobile phone, computer, tablet device, personal digital assistant, etc., that includes one or any combination of the above-mentioned memories.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable signal processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable signal processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable signal processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable signal processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the preferred embodiment of the present disclosure, and is not intended to limit the scope of the present disclosure.
Claims (10)
1. A method of data collection, the method comprising:
receiving at least one scene video;
identifying, by using an image identification model, motion information of an object included in the at least one scene video, and collecting at least one object identification data, where the motion information includes: object identity, action, and tracking location;
scene object data of the target scene is generated according to the at least one object identification data.
2. The method of claim 1, wherein after receiving at least one scene video, the method further comprises:
carrying out space positioning processing on the object included in the at least one scene video by using a space positioning algorithm, and collecting at least one object positioning data;
generating scene object data of a target scene from the at least one object recognition data comprises:
and generating scene object data of the target scene according to the at least one object identification data and the at least one object positioning data.
3. The data collection method according to claim 1 or 2, wherein before the motion information recognition of the object included in the at least one scene video using the image recognition model is performed, the method further comprises:
and acquiring the image recognition model generated by training based on a preset model training method.
4. A data collection method according to claim 1 or 2, wherein said generating scene object data of the target scene from said at least one object recognition data comprises:
receiving a target request sent by a client;
according to the target request, selecting data to be processed from the at least one object identification data, and determining a target data processing mode;
and performing data processing on the data to be processed according to the target data processing mode to generate the scene object data.
5. The data collection method of claim 4, wherein after the generating the scene object data, the method further comprises:
and sending the scene object data to the client.
6. A method for data collection according to any one of claims 1 to 5, wherein the image recognition model comprises at least an object detection tracking model and a motion recognition model.
7. A data collection device, the data collection device comprising:
a receiving module, configured to receive at least one scene video;
an identification module, configured to perform motion information identification on an object included in the at least one scene video by using an image identification model, and collect at least one object identification data, where the motion information includes: object identity, action, and tracking location;
and the generating module is used for generating scene object data of the target scene according to the at least one object identification data.
8. The data collection device of claim 7, further comprising a positioning module;
the positioning module is used for performing spatial positioning processing on an object included in the at least one scene video by using a spatial positioning algorithm and collecting at least one object positioning data;
the generating module is configured to generate scene object data of the target scene according to the at least one object identification data and the at least one object positioning data.
9. An electronic device, characterized in that the electronic device comprises: a processor, a memory, and a communication bus; wherein,
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is configured to execute the data collection program stored in the memory to implement the data collection method of any one of claims 1 to 6.
10. A computer-readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the data collection method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910335557.3A CN110059653A (en) | 2019-04-24 | 2019-04-24 | A kind of method of data capture and device, electronic equipment, storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910335557.3A CN110059653A (en) | 2019-04-24 | 2019-04-24 | A kind of method of data capture and device, electronic equipment, storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110059653A true CN110059653A (en) | 2019-07-26 |
Family
ID=67320635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910335557.3A Pending CN110059653A (en) | 2019-04-24 | 2019-04-24 | A kind of method of data capture and device, electronic equipment, storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059653A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627039A (en) * | 2020-05-09 | 2020-09-04 | 北京小狗智能机器人技术有限公司 | Interaction system and interaction method based on image recognition |
| CN115475373A (en) * | 2022-09-14 | 2022-12-16 | 浙江大华技术股份有限公司 | Motion data display method and device, storage medium and electronic device |
| WO2023178921A1 (en) * | 2022-03-23 | 2023-09-28 | 上海商汤智能科技有限公司 | Interaction method and apparatus, and device, storage medium and computer program product |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909887A (en) * | 2017-01-19 | 2017-06-30 | 南京邮电大学盐城大数据研究院有限公司 | A kind of action identification method based on CNN and SVM |
| CN108229294A (en) * | 2017-09-08 | 2018-06-29 | 北京市商汤科技开发有限公司 | A kind of motion capture method, apparatus, electronic equipment and storage medium |
| CN108985263A (en) * | 2018-08-08 | 2018-12-11 | 北京旷视科技有限公司 | A kind of collecting method, device, electronic equipment and computer-readable medium |
-
2019
- 2019-04-24 CN CN201910335557.3A patent/CN110059653A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909887A (en) * | 2017-01-19 | 2017-06-30 | 南京邮电大学盐城大数据研究院有限公司 | A kind of action identification method based on CNN and SVM |
| CN108229294A (en) * | 2017-09-08 | 2018-06-29 | 北京市商汤科技开发有限公司 | A kind of motion capture method, apparatus, electronic equipment and storage medium |
| CN108985263A (en) * | 2018-08-08 | 2018-12-11 | 北京旷视科技有限公司 | A kind of collecting method, device, electronic equipment and computer-readable medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627039A (en) * | 2020-05-09 | 2020-09-04 | 北京小狗智能机器人技术有限公司 | Interaction system and interaction method based on image recognition |
| WO2023178921A1 (en) * | 2022-03-23 | 2023-09-28 | 上海商汤智能科技有限公司 | Interaction method and apparatus, and device, storage medium and computer program product |
| CN115475373A (en) * | 2022-09-14 | 2022-12-16 | 浙江大华技术股份有限公司 | Motion data display method and device, storage medium and electronic device |
| CN115475373B (en) * | 2022-09-14 | 2024-02-02 | 浙江大华技术股份有限公司 | Display method and device of motion data, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10391378B2 (en) | Smart-court system and method for providing real-time debriefing and training services of sport games | |
| CN107871120B (en) | Sports event understanding system and method based on machine learning | |
| CN108229294B (en) | Motion data acquisition method and device, electronic equipment and storage medium | |
| Scott et al. | SoccerTrack: A dataset and tracking algorithm for soccer with fish-eye and drone videos | |
| CN109326310B (en) | Automatic editing method and device and electronic equipment | |
| CN101639354B (en) | Method and apparatus for object tracking | |
| WO2018223554A1 (en) | Multi-source video clipping and playing method and system | |
| US9367746B2 (en) | Image processing apparatus for specifying an image relating to a predetermined moment from among a plurality of images | |
| US11551428B2 (en) | Methods and apparatus to generate photo-realistic three-dimensional models of a photographed environment | |
| JP2017531979A (en) | System and method for visual player tracking in a sports arena | |
| US20070064975A1 (en) | Moving object measuring apparatus, moving object measuring system, and moving object measurement | |
| JP6720587B2 (en) | Video processing device, video processing method, and video processing program | |
| WO2021130546A1 (en) | Target object identification system, method and apparatus, electronic device and storage medium | |
| CN110059653A (en) | A kind of method of data capture and device, electronic equipment, storage medium | |
| US20170201723A1 (en) | Method of providing object image based on object tracking | |
| CN110270078B (en) | Football game special effect display system and method and computer device | |
| CN105245845A (en) | Method for controlling camera to follow and shoot automatically based on gathering trend in match field | |
| CN114025183B (en) | Live broadcast method, device, equipment, system and storage medium | |
| CN104182959B (en) | target searching method and device | |
| CN109460077B (en) | Automatic tracking method, automatic tracking equipment and automatic tracking system | |
| Yoo et al. | Painless tennis ball tracking system | |
| US20190164298A1 (en) | System and Method for Tracking the Speed of an Object Using Video | |
| CN108449362A (en) | Interactive system based on virtual reality imaging | |
| Kim et al. | Robust multi-object tracking to acquire object oriented videos in indoor sports | |
| CN112668435A (en) | Video-based key target image snapshot method, device 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190726 |