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
- identification
- transacter
- 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
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
This disclosure relates to technical field of machine vision more particularly to a kind of method of data capture and device, electronic equipment, deposit
Storage media.
Background technique
Currently, under the competition trainings scene such as football match and Basketball Match, it usually needs relevant competition data is collected,
To determine Athletess track, football track and court thermodynamic chart, for subsequent tactical instruction and arrangement provide according to
According to.
In the prior art, main includes two kinds of modes for collecting competition data, and one kind is artificial statistics, however, big
In type athletic competition, not only competition field range is larger, and the sportsman on competition field is excessive, and artificial statistics leads to the efficiency of data collection
Lower, another kind is to carry out the collection of different types of data respectively using door line technology, hawkeye system etc., and a kind of equipment is only capable of reality
A kind of collection of existing categorical data, has a single function.
Summary of the invention
The embodiment of the present disclosure is intended to provide a kind of method of data capture and device, electronic equipment, storage medium, is based on image
Identification technology and location technology carry out the collection of related data to the object under application scenarios, and not only collection efficiency is higher, but also
It is full-featured.
The technical solution of the embodiment of the present disclosure is achieved in that
The embodiment of the present disclosure provides a kind of method of data capture, which comprises
Receive at least one scene video；
Using image recognition model, motion information identification is carried out to the object for including at least one described scene video,
It is collected at least one object identification data, the motion information includes: object identity, movement and tracing positional；
The scenario objects data of target scene are generated according at least one described object identification data.
In above-mentioned method of data capture, after described at least one scene video of reception, the method also includes:
Using space orientation algorithm, space orientation processing is carried out to the object for including at least one described scene video,
It is collected at least one object locating data；
At least one object identification data described in the foundation generate target scene scenario objects data include:
Target scene is generated according at least one described object identification data and at least one described object locating data
Scenario objects data.
It is described to utilize image recognition model in above-mentioned method of data capture, to being wrapped at least one described scene video
The object included carries out motion information identification, is collected into before at least one object identification data, the method also includes:
Obtain the described image identification model generated based on the training of preset model training method.
In above-mentioned method of data capture, at least one object identification data described in the foundation generates the field of target scene
Scape object data, comprising:
Receive the destination request that client is sent；
According to the destination request, pending data is selected from least one described object identification data, and is determined
Target data processing mode；
Data processing is carried out to the pending data according to the target data processing mode, generates the scenario objects
Data.
In above-mentioned method of data capture, after the generation scenario objects data, the method also includes:
It provides the target to information and is sent to the client.
In above-mentioned method of data capture, described image identification model includes at least target detection trace model and movement is known
Other model.
The embodiment of the invention provides a kind of transacter, the transacter includes:
Receiving module, for receiving at least one scene video；
Identification module carries out the object for including at least one described scene video for utilizing image recognition model
Motion information identification is collected at least one object identification data, and the motion information includes: object identity, acts, and with
Track position；
Generation module, for generating the scenario objects data of target scene according at least one described object identification data.
It further include locating module in above-mentioned transacter；
The locating module, for utilizing space orientation algorithm, to the object for including at least one described scene video
Space orientation processing is carried out, at least one object locating data is collected into；
The generation module, for positioning number according at least one described object identification data and at least one described object
According to the scenario objects data for generating target scene.
Further include obtaining module in above-mentioned transacter, is specifically used for obtaining based on preset model training method
The described image identification model that training generates.
In above-mentioned transacter, the generation module, the destination request sent specifically for receiving client；Root
According to the destination request, pending data is selected from least one described object identification data, and is determined at target data
Reason mode；Data processing is carried out to the pending data according to the target data processing mode, generates the scenario objects
Data.
It further include sending module in above-mentioned transacter；
The sending module, for the scenario objects data to be sent to the client.
In above-mentioned transacter, described image identification model includes at least target detection trace model and movement is known
Other model.
The embodiment of the invention provides a kind of electronic equipment, the electronic equipment includes: that processor, memory and communication are total
Line；Wherein,
The communication bus, for realizing the connection communication between the processor and the memory；
The processor, for executing the data collection program stored in the memory, to realize above-mentioned data collection
Method.
Optionally, the electronic equipment is server.
The embodiment of the invention provides a kind of computer readable storage medium, the computer-readable recording medium storage has
One or more program, one or more of programs can be executed by one or more processor, above-mentioned to realize
Method of data capture.
The embodiment of the invention provides a kind of method of data capture, at least one scene video is received；Utilize image recognition
Model carries out motion information identification to the object for including at least one scene video, is collected at least one Object identifying number
According to motion information includes: object identity, movement and tracing positional；Target field is generated according at least one object identification data
The scenario objects data of scape.Technical solution of the present invention, middle use artificially collects data or door line skill compared with the prior art
Art, hawkeye system etc. carry out the collection of single type data respectively, based on image recognition technology to the object under application scenarios into
The collection of row related data, not only collection efficiency is higher, but also full-featured.
Detailed description of the invention
Fig. 1 is a kind of flow diagram one for method of data capture that the embodiment of the present disclosure provides；
Fig. 2 is a kind of flow diagram two of method of data capture provided in an embodiment of the present invention；
Fig. 3 is the process that a kind of illustrative method of data capture provided in an embodiment of the present invention is applied in football scene
Schematic diagram；
Fig. 4 is a kind of illustrative football trajectory diagram provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of transacter provided in an embodiment of the present invention；
Fig. 6 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present disclosure, the technical solution in the embodiment of the present disclosure is carried out clear, complete
Site preparation description.
A kind of embodiment of the disclosure provides a kind of method of data capture, and Fig. 1 is a kind of number that the embodiment of the present disclosure provides
According to the flow diagram one of collection method.As shown in Figure 1, mainly comprising the steps that
S101, at least one scene video is received.
In an embodiment of the present invention, transacter can receive at least one scene video.
It should be noted that it is mounted at least one photographic device in an embodiment of the present invention, in target scene, such as
Camera, the camera quantity specifically installed can be to be determined according to whether target scene can be completely covered, that is, that installs takes the photograph
The coverage for needing guarantee to constitute as head covers target scene without dead angle, and the position of different camera installations and angle are not
Together, therefore, can actually get that target scene generates under at least one angle by the camera of installation at least one
At least one scene video can be uploaded to transacter by a scene video, at least one camera, be received as data
The foundation of collection, the specific scene video quantity embodiment of the present invention are not construed as limiting.
It should be noted that in an embodiment of the present invention, target scene can be the football match scene on football pitch
Or football training scene, or Basketball Match scene or basketball training scene on basketball court etc., specific target scene
The embodiment of the present invention is not construed as limiting.
Illustratively, in an embodiment of the present invention, target scene is football training scene, for the scene, in football
The different angle different location on field periphery is mounted with that three cameras, these three cameras are covered completely for football pitch
Lid, therefore, in football player when being trained on football pitch, for football training scene, three cameras will be at three
Three scene videos are generated under angle, and three scene videos are uploaded to transacter, and transacter can connect
Receive three scene videos of input.
S102, using image recognition model, motion information identification is carried out to the object for including at least one scene video,
It is collected at least one object identification data, motion information includes: object identity, movement and tracing positional.
In an embodiment of the present invention, transacter is after receiving at least one scene video, i.e., available
Image recognition model carries out motion information identification to the object for including at least one scene video, it is right to be collected at least one
As identifying data.
It should be noted that in an embodiment of the present invention, the object in target scene includes the personage in target scene
With article etc., for example, sportsman, football and teaching aid etc. in football training scene, the object for including in specific target scene
The data embodiment of the present invention is not construed as limiting.
It should be noted that in an embodiment of the present invention, image recognition model includes at least target detection trace model
And action recognition model, wherein target detection trace model can detect target object, example from a certain frame image of video
Such as, some specific personage, to track in other images to the target object, action recognition model can be automatic
Identify the movement of different personages in image, certainly, image recognition model also may include other based on image recognition technology
Model, the specific image recognition model embodiment of the present invention are not construed as limiting.
It should be noted that in an embodiment of the present invention, at least one scene video actually includes multiple image,
For each frame image, transacter may be by the target detection trace model and movement that image recognition model includes
Identification model carries out identification, action recognition and the tracing positional of object, so that at least one Object identifying number will be obtained
According to.
It is understood that in an embodiment of the present invention, transacter can use mesh in image recognition model
The detection that detecting and tracking model carries out object to a certain frame image at least one scene video is marked, that is, identifies the body of object
Part, after detected, according to the feature of object, is tracked in other frame images, obtain the tracing positional of object,
Belong to above-mentioned object identification data.
It is understood that in an embodiment of the present invention, transacter can use in image recognition model and move
Make identification model and action recognition is carried out to the object in each frame image at least one scene video, i.e., acquisition object is dynamic
Make data, also belongs to above-mentioned object identification data.
It should be noted that in an embodiment of the present invention, image recognition model can also include other types of model,
For example, human face recognition model, transacter can use human face recognition model and carry out recognition of face, but these models are equal
Based on image recognition technology, image recognition model is belonged to.
Illustratively, in an embodiment of the present invention, target scene is football training scene, and transacter can connect
At least one football scene video is received, and further utilizes target detection trace model and action recognition in image recognition model
Model carries out identity, movement to the sportsman for including at least one football scene video and football, and tracks and identifies, and obtains
The object identification datas such as sportsman's number of sportsman, sportsman's action data, sportsman's motion tracking data, football tracking data.
It should be noted that in an embodiment of the present invention, transacter is transported using image recognition model
It is actually further comprising the steps of before dynamic information identification: to obtain the image generated based on the training of preset model training method and know
Other model.
It should be noted that in an embodiment of the present invention, can first according to artificial intelligence technology and image recognition technology,
Using a large amount of sample image, image recognition model, specific model training side are trained according to preset model training mode
The formula embodiment of the present invention is not construed as limiting.
S103, the scenario objects data that target scene is generated according at least one object identification data.
In an embodiment of the present invention, transacter is after being collected at least one object identification data
The scenario objects data of target scene are generated according at least one object identification data.
Specifically, in an embodiment of the present invention, transacter generates mesh according at least one object identification data
Mark the scenario objects data of scene, comprising: receive the destination request that client is sent；It is right from least one according to destination request
As selecting pending data in identification data, and determine target data processing mode；It is treated according to target data processing mode
It handles data and carries out data processing, generate scenario objects data.
It should be noted that in an embodiment of the present invention, different type can be previously stored in transacter
Corresponding data processing method is requested, for example, destination request provides Athletess track for request, then transacter can
According to the destination request, to get the data processing method of determining Athletess track, and from least one Object identifying
Player tracking data are selected in data, the specific target data processing mode embodiment of the present invention is not construed as limiting.
It should be noted that in an embodiment of the present invention, at least one object identification data includes diversified data,
For example, being football training scene for target scene, scenario objects data may include sportsman's identity, sportsman's motion tracking, foot
The data such as ball tracking and teaching aid type, wherein for generating the corresponding target of destination request and providing information, part is believed
Breath be it is unwanted, therefore, transacter can be determined for destination request needs the data that use, right from least one
As selecting pending data in identification data, the specific pending data embodiment of the present invention is not construed as limiting.
Illustratively, in an embodiment of the present invention, target scene is football training scene, and destination request provides for request
Football track, therefore, transacter according to destination request, chosen from least one object identification data football with
The picture position of track data, i.e. football at least one scene video in each frame is combined whole football tracing positionals, is pressed
It is successively attached according to corresponding target data processing mode that is, according to the time sequencing of frame, to generate football track
Figure, wherein football trajectory diagram is scenario objects data.
It is understood that in an embodiment of the present invention, transacter is according at least one object identification data
Generate the scenario objects data of target scene, wherein scenario objects data can be thermodynamic chart, the movement of object in target scene
Track etc., the specific scenario objects data embodiment of the present invention are not construed as limiting.
It should be noted that in an embodiment of the present invention, transacter is after generating scenario objects data, i.e.,
Scenario objects data can be sent to client.
It is understood that in an embodiment of the present invention, target scene can be football scene or basketball movement
Scene, under these scenes, coach and sportsman need to know that the relevant information in motion process carries out tactics improvement and training, because
This, actually coach and sportsman can be by the information of actual demand to be sent to data in a manner of destination request by client
Collection device, transacter produce scenario objects data, to be sent to client, coach and sportsman can bases
Tactics are analyzed and adjusted to scenario objects data, and as the scenes such as movement teaching and match provide data and support service.
The embodiment of the invention provides a kind of method of data capture, at least one scene video is received；Utilize image recognition
Model carries out motion information identification to the object for including at least one scene video, is collected at least one Object identifying number
According to motion information includes: object identity, movement and tracing positional；Target field is generated according at least one object identification data
The scenario objects data of scape.Technical solution of the present invention, middle use artificially collects data or door line skill compared with the prior art
Art, hawkeye system etc. carry out the collection of single type data respectively, based on image recognition technology to the object under application scenarios into
The collection of row related data, not only collection efficiency is higher, but also full-featured.
A kind of embodiment of the disclosure provides a kind of method of data capture, and Fig. 2 is a kind of number provided in an embodiment of the present invention
According to the flow diagram two of collection method.As shown in Fig. 2, mainly comprising the steps that
S201, at least one scene video is received.
In an embodiment of the present invention, transacter can receive at least one camera shooting dress of coverage goal scene
Set at least one scene video got.
It should be noted that in an embodiment of the present invention, the step S101 complete one in step S201 and embodiment one
It causes, details are not described herein.
S202, using image recognition model, motion information identification is carried out to the object for including at least one scene video,
It is collected at least one object identification data, motion information includes: object identity, movement and tracing positional.
In an embodiment of the present invention, transacter can use after receiving at least one scene video
Image recognition model, for example, target detection trace model and action recognition model, the object for including at least one scene video
Motion information identification is carried out, to be collected at least one object identification data.
It should be noted that in an embodiment of the present invention, the step S102 complete one in step S202 and embodiment one
It causes, details are not described herein.
S203, using space orientation algorithm, space orientation processing is carried out to the object for including at least one scene video,
It is collected at least one object locating data.
In an embodiment of the present invention, transacter can use after receiving at least one scene video
Space orientation algorithm carries out space orientation processing to the object for including at least one scene video, it is right to be collected at least one
As location data.
It should be noted that in an embodiment of the present invention, transacter specifically can first get at least one
The object that each frame image includes in scene video picture position in the picture utilize space orientation algorithm pair later
Picture position carries out space orientation calculating, to obtain at least one object locating data.
It should be noted that in an embodiment of the present invention, if transacter receives three scene videos, three
Synchronization in a scene video, available to three frame images are corresponded to, transacter obtains respectively from three frame images
The same target object is got, picture position of the target object in three frame images is A1, A2 and A3, is calculated using space orientation
Method carries out spatial position calculating to A1, A2 and A3, can be obtained the spatial position of the moment target object.If transacter
A scene video is obtained, at a moment in a scene video, available to a frame image, target sportsman is in a frame
Picture position in image is B1, carries out space reflection to B1 using space orientation algorithm, can be obtained the moment target object
Spatial position, spatial position is object locating data.
Illustratively, in an embodiment of the present invention, target scene is basketball training scene, and transacter receives
Three basketball scene videos for covering three thecamera heads of basketball training scene, thus using space orientation algorithm, to three
Sportsman, basketball and teaching aid in a basketball scene video carry out space orientation processing, are collected into ball in the basketball training scene
The data such as member position, football position and teaching aid position, i.e. acquisition object locating data, wherein position of Player, football position,
And teaching aid position is the spatial position in three-dimensional space.
It should be noted that in an embodiment of the present invention, transacter can use space orientation algorithm, to extremely
The object that each frame includes in a few scene video carries out space orientation processing respectively, it is of course also possible to according to certain rule
Then or actual demand, some frames are therefrom chosen and carry out space orientation processing, the specific space orientation mode present invention is implemented
Example is not construed as limiting.
It should be noted that in an embodiment of the present invention, the source of data collection is at least one scene obtained
Video, and at least one scene video is obtained by least one camera for being mounted on corresponding region, therefore, based at least
The hardware configuration of one camera itself, and installation the photographic devices such as angles and positions configuration information, can determine
The determination process embodiment of the present invention of corresponding space orientation algorithm, specific space orientation algorithm and space orientation algorithm is not made
It limits.
It is understood that in an embodiment of the present invention, image recognition model and space orientation algorithm can be by models
Training device or other devices generate, and are then transmit to transacter, transacter can be obtained image recognition mould
Type and space orientation algorithm, certainly, transacter itself can also have model training function and algorithm systematic function, from
Main acquisition image recognition model and space orientation algorithm, specific image recognition model and the space orientation algorithm embodiment of the present invention
It is not construed as limiting.
It should be noted that in an embodiment of the present invention, for being received using image recognition model and space orientation algorithm
It the case where collecting at least one object identification data and at least one object locating data, can also be according to image recognition model and sky
Between location algorithm design a complete collection system, it can according to certain system design rule to image recognition model
Be packaged with space orientation algorithm using certain modes, design specification is output and input, for example, can first to need into
Row scene video is screened, and ineffective partial video is deleted, further, it is also possible to from structural element, functional requirement, when
Between sequence etc. carry out comprehensively considering design, more preferably to carry out data collection, but the basis source of system design in
Image recognition model and space orientation algorithm, that is to say, that collection system actually has image identification function and space orientation
The offer form embodiment of the present invention of function, specific image recognition model and space orientation algorithm is not construed as limiting.
S204, the scene that target scene is generated according at least one object identification data and at least one object locating data
Object data.
In an embodiment of the present invention, transacter is being collected at least one object identification data and at least one
After object locating data, target field can be generated according at least one object identification data and at least one object locating data
The scenario objects data of scape.
It is understood that in an embodiment of the present invention, scenario objects data are for realizing the number for being directed to target scene
According to supporting to service, can according at least one object identification data and at least one object locating data according to specific demand into
Row statistical analysis, obtains relevant scenario objects data.
It should be noted that in an embodiment of the present invention, at least one object identification data and at least one object are fixed
For position data are both for the object in target scene, for example, sportsman and ball etc. in athletic competition, specifically at least
One object identification data and at least one object locating data embodiment of the present invention are not construed as limiting.
Specifically, in an embodiment of the present invention, the target that transacter can also receive client transmission is asked
It asks, to generate target field according at least one object identification data and at least one object locating data according to destination request
The scenario objects data of scape, scenario objects data are used to characterize the motion state for the object that target scene includes.
It should be noted that in an embodiment of the present invention, destination request can be the certain type of scenario objects of request
Data, for example, in football training scene a certain sportsman motion profile, alternatively, the amount of exercise data etc. of each sportsman, specifically
The destination request embodiment of the present invention be not construed as limiting.
Illustratively, in an embodiment of the present invention, target scene is football training scene, and destination request can be request
Court thermal information, request sportsman track, request sportsman's amount of exercise data, request sportsman's physical consumption data, request football fortune
One or more in dynamic rail mark.
Illustratively, in an embodiment of the present invention, at least one object identification data that transacter is collected into
With at least one object locating data, sportsman's identity, position of Player, sportsman's motion tracking, football position, foot can specifically include
The categorical datas such as ball tracking, teaching aid position, destination request provide sportsman's amount of exercise data for request, at corresponding target data
Reason mode is to be related to object locating data multiplied by the amount of exercise of preset unit distance according to the move distance of sportsman, because
This, transacter selects position of Player data from scenario objects data, as pending data, later, according to mesh
Data processing method is marked, it is raw multiplied by the amount of exercise of preset unit distance according to the move distance for the sportsman that position of Player determines
At sportsman's amount of exercise data, i.e. scene object data, in addition, destination request further includes when asking to provide court heating power data, together
Court thermodynamic chart can be generated in sample, and court thermodynamic chart is also scenario objects data.
It should be noted that in an embodiment of the present invention, according at least one object identification data and at least one is right
It may include various types of data as the scenario objects data that location data generates, also, scenario objects data can be number
According to form, or the form embodiment of the present invention of the form of table or image, specific scenario objects data is not made
It limits.
It is understood that in an embodiment of the present invention, transacter is after generating scenario objects data, together
Step S103 is the same in embodiment one, scenario objects data can be sent to client, details are not described herein.
Fig. 3 is the process that a kind of illustrative method of data capture provided in an embodiment of the present invention is applied in football scene
Schematic diagram.As shown in figure 3, including image recognition model and space orientation algorithm in transacter, wherein image recognition mould
Type and space orientation algorithm are designed as a system, and on court periphery, arrangement photographic device imported into number to acquire scene video
According in collection device, transacter is i.e. using image recognition model and space orientation algorithm, at scene video
Reason obtains the scenario objects data such as sportsman's identity, position, movement, motion tracking, football position and teaching aid position, later,
According to actual needs, i.e. destination request utilizes scenario objects data to generate thermodynamic chart, sportsman's motion profile figure, amount of exercise and body
It can scheme and football trajectory diagram, Fig. 4 are a kind of illustrative football trajectory diagram provided in an embodiment of the present invention, as shown in figure 4,
Football successively moves to position 5 by position 1, these figures can be supplied to client by transacter.
A kind of embodiment of the disclosure additionally provides a kind of transacter, and Fig. 5 is one kind provided in an embodiment of the present invention
The structural schematic diagram of transacter.As shown in figure 5, transacter includes:
Receiving module 501, for receiving at least one scene video；
Identification module 502, for utilize image recognition model, to the object for including at least one described scene video into
The identification of row motion information is collected at least one object identification data, and the motion information includes: object identity, acts, and
Tracing positional；
Generation module 503, for generating the scenario objects number of target scene according at least one described object identification data
According to.
Optionally, the data collection module further includes locating module 504；
The locating module 504, for utilizing space orientation algorithm, to pair for including at least one described scene video
As carrying out space orientation processing, it is collected at least one object locating data；
The generation module 503, for fixed according at least one described object identification data and at least one described object
Position data generate the scenario objects data of target scene.
Optionally, the transacter further includes obtaining module 505；
The acquisition module 505 is known specifically for obtaining the described image generated based on the training of preset model training method
Other model.
Optionally, the generation module 503 is specifically also used to receive the destination request of client transmission；According to the mesh
Mark request selects pending data from least one described object identification data, and determines target data processing mode；It presses
Data processing is carried out to the pending data according to the target data processing mode, generates the scenario objects data.
Optionally, the transacter further includes sending module；
The sending module 506, for the scenario objects data to be sent to the client.
Optionally, described image identification model includes at least target detection trace model and action recognition model.
The embodiment of the invention provides a kind of transacter, at least one scene video is received；Utilize image recognition
Model carries out motion information identification to the object for including at least one scene video, is collected at least one Object identifying number
According to motion information includes: object identity, movement, and is tracked and identified；Target field is generated according at least one object identification data
The scenario objects data of scape.Transacter of the invention, middle use artificially collects data, Huo Zhemen compared with the prior art
Line technology, hawkeye system etc. carry out the collection of single type data respectively, based on image recognition technology to pair under application scenarios
Collection as carrying out related data, not only collection efficiency is higher, but also full-featured.
A kind of embodiment of the disclosure provides a kind of electronic equipment, and Fig. 6 is that a kind of electronics provided in an embodiment of the present invention is set
Standby structural schematic diagram.As shown in fig. 6, the electronic equipment includes: processor 601, memory 602 and communication bus 603；Its
In,
The communication bus 603, for realizing the connection communication between the processor 601 and the memory 602；
The processor 601, for executing the data collection program stored in the memory 602, to realize above-mentioned number
According to collection method.
It should be noted that in an embodiment of the present invention, electronic equipment can be server, or other to have
The terminal etc. of data-handling capacity, the specific electronic equipment embodiment of the present invention are not construed as limiting.
The embodiment of the present disclosure additionally provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is one or more program, one or more of programs can be executed by one or more processor, on realizing
State method of data capture.It is volatile memory (volatile memory) that computer readable storage medium, which can be, such as with
Machine accesses memory (Random-Access Memory, RAM)；Or nonvolatile memory (non-volatile
Memory), such as read-only memory (Read-Only Memory, ROM), flash memory (flash memory), hard disk
(Hard Disk Drive, HDD) or solid state hard disk (Solid-State Drive, SSD)；It is also possible to include above-mentioned memory
One of or any combination respective equipment, such as mobile phone, computer, tablet device, personal digital assistant.
It should be understood by those skilled in the art that, embodiment of the disclosure can provide as method, system or computer program
Product.Therefore, the shape of hardware embodiment, software implementation or embodiment combining software and hardware aspects can be used in the disclosure
Formula.Moreover, the disclosure, which can be used, can use storage in the computer that one or more wherein includes computer usable program code
The form for the computer program product implemented on medium (including but not limited to magnetic disk storage and optical memory etc.).
The disclosure is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present disclosure
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable signal processing equipments to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable signal processing equipments execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable signal processing equipments with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions can also be loaded into computer or other programmable signal processing equipments, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The above, the only preferred embodiment of the disclosure, are not intended to limit the protection scope of the disclosure.
Claims (10)
1. a kind of method of data capture, which is characterized in that the described method includes:
Receive at least one scene video；
Using image recognition model, motion information identification is carried out to the object for including at least one described scene video, is collected
To at least one object identification data, the motion information includes: object identity, movement and tracing positional；
The scenario objects data of target scene are generated according at least one described object identification data.
2. method of data capture according to claim 1, which is characterized in that described at least one scene video of reception it
Afterwards, the method also includes:
Using space orientation algorithm, space orientation processing is carried out to the object for including at least one described scene video, is collected
To at least one object locating data；
At least one object identification data described in the foundation generate target scene scenario objects data include:
The scene of target scene is generated according at least one described object identification data and at least one described object locating data
Object data.
3. method of data capture according to claim 1 or 2, which is characterized in that it is described to utilize image recognition model, to institute
State include at least one scene video object carry out motion information identification, be collected at least one object identification data it
Before, the method also includes:
Obtain the described image identification model generated based on the training of preset model training method.
4. method of data capture according to claim 1 or 2, which is characterized in that at least one object described in the foundation
Identify that data generate the scenario objects data of target scene, comprising:
Receive the destination request that client is sent；
According to the destination request, pending data is selected from least one described object identification data, and determines target
Data processing method；
Data processing is carried out to the pending data according to the target data processing mode, generates the scenario objects number
According to.
5. method of data capture according to claim 4, which is characterized in that it is described generate the scenario objects data it
Afterwards, the method also includes:
The scenario objects data are sent to the client.
6. method of data capture according to claim 1-5, which is characterized in that described image identification model is at least
Including target detection trace model and action recognition model.
7. a kind of transacter, which is characterized in that the transacter includes:
Receiving module, for receiving at least one scene video；
Identification module moves the object for including at least one described scene video for utilizing image recognition model
Information identification, is collected at least one object identification data, and the motion information includes: object identity, movement and trace bit
It sets；
Generation module, for generating the scenario objects data of target scene according at least one described object identification data.
8. transacter according to claim 7, which is characterized in that the transacter further includes positioning mould
Block；
The locating module carries out the object for including at least one described scene video for utilizing space orientation algorithm
Space orientation processing, is collected at least one object locating data；
The generation module, for raw according at least one described object identification data and at least one described object locating data
At the scenario objects data of target scene.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes: processor, memory and communication bus；Wherein,
The communication bus, for realizing the connection communication between the processor and the memory；
The processor, for executing the data collection program stored in the memory, to realize any one of claim 1-6
The method of data capture.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage have one or
Multiple programs, one or more of programs can be executed by one or more processor, to realize that claim 1-6 appoints
Method of data capture described in one.
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 | |
| US11638854B2 (en) | Methods and systems for generating sports analytics with a mobile device | |
| CN108229294B (en) | Motion data acquisition method and device, electronic equipment and storage medium | |
| CN109190508B (en) | Multi-camera data fusion method based on space coordinate system | |
| US11310418B2 (en) | Computer-implemented method for automated detection of a moving area of interest in a video stream of field sports with a common object of interest | |
| CN102735100B (en) | Individual light weapon shooting training method and system by using augmented reality technology | |
| Kohl et al. | The mta dataset for multi-target multi-camera pedestrian tracking by weighted distance aggregation | |
| CN110059653A (en) | A kind of method of data capture and device, electronic equipment, storage medium | |
| CN113850248B (en) | Motion attitude evaluation method and device, edge calculation server and storage medium | |
| CN105262942B (en) | Distributed automatic image and video processing | |
| WO2018223554A1 (en) | Multi-source video clipping and playing method and system | |
| Scott et al. | SoccerTrack: A dataset and tracking algorithm for soccer with fish-eye and drone videos | |
| US10796448B2 (en) | Methods and systems for player location determination in gameplay with a mobile device | |
| CN107766788A (en) | Information processor, its method and computer-readable recording medium | |
| CN105744223B (en) | Video data handling procedure and device | |
| CN109961039B (en) | Personal goal video capturing method and system | |
| US10652449B2 (en) | Information processing apparatus, information processing method, and program | |
| CN106228218A (en) | The intelligent control method of a kind of destination object based on movement and system | |
| CN112465855B (en) | Passenger flow statistical method, device, storage medium and equipment | |
| CN105450911A (en) | Image processing apparatus and image processing method | |
| CN108970091B (en) | Badminton action analysis method and system | |
| CN110111364A (en) | Method for testing motion, device, electronic equipment and storage medium | |
| CN109089058A (en) | Video pictures processing method, electric terminal and device | |
| US20160127617A1 (en) | System for tracking the position of the shooting camera for shooting video films | |
| CN109460077B (en) | Automatic tracking method, automatic tracking equipment and automatic tracking system |
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 |