CN110177256A - A kind of tracking video data acquisition methods and device - Google Patents
A kind of tracking video data acquisition methods and device Download PDFInfo
- Publication number
- CN110177256A CN110177256A CN201910522906.2A CN201910522906A CN110177256A CN 110177256 A CN110177256 A CN 110177256A CN 201910522906 A CN201910522906 A CN 201910522906A CN 110177256 A CN110177256 A CN 110177256A
- Authority
- CN
- China
- Prior art keywords
- target
- video
- high definition
- equipment
- video frame
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The embodiment of the invention discloses a kind of acquisition methods and device for tracking video data, wherein, the described method includes: acquiring the corresponding relationship in equipment and object detection area between physical location according to the video object, the target position that target object is located in the object detection area is determined；According to the corresponding relationship in the target position and high definition video collecting equipment and the object detection area between physical location, the target high definition video collecting equipment for corresponding to the target position in the high definition video collecting equipment is obtained, the video frame that the target high definition video collecting equipment acquires is merged into processing and obtains tracking video data.Using method of the present invention, equipment can be acquired by the video object of setting and comprehensive positioning and tracking are carried out to multiple target objects, fast and accurately obtained corresponding HD video data, improve the collecting efficiency of tracking video.
Description
Technical field
The present embodiments relate to field of artificial intelligence, and in particular to a kind of tracking video data acquisition methods and dress
It sets.
Background technique
With the fast development of artificial intelligence technology, the function of existing video capture device is stronger and stronger, and user can be with
Realize that the tracking to specific objective object in video data is shot by video capture device.However, in current some big models
In the tracking shooting process for enclosing the multiple target object in region, such as: football match, ice hockey competition, large parking lot and time
In the video capture scheme of the extensive areas such as vehicle hall, it usually needs more video capture devices, which match, carries out video bat
It takes the photograph.However, existing focal length video capture device field range is limited, and short focus video capture device cannot obtain distant object
The clear image of object leads to be easy that there are blind areas in actual application therefore, it is impossible to combine entire monitoring scene.
In order to solve the above-mentioned technical problem, the technological means generallyd use in the prior art is a large amount of video acquisition of setting
Equipment removes to track the different target object in place respectively, and then obtains the tracking video for different target object.This side
Method equipment dosage is huge, and often has the problem of blocking mutually between rocker arm, reduces monitoring efficiency, and it is difficult to increase monitoring
Degree, therefore, is still unable to satisfy the demand of active user.
Summary of the invention
For this purpose, the embodiment of the present invention provides a kind of tracking video data acquisition methods, it is existing in the prior art to solve
For in the tracking shooting process of the multiple target object in extensive area, equipment dosage is huge, the low problem of monitoring efficiency.
To achieve the goals above, the embodiment of the present invention provides the following technical solutions:
A kind of tracking video data acquisition methods provided according to embodiments of the present invention, comprising: building the video object acquisition
The first corresponding relationship in position corresponding to the pickup area of equipment and object detection area between physical location, and building
In position corresponding to the pickup area of high definition video collecting equipment and the object detection area between physical location second
Corresponding relationship；It determines the target object in the video frame of the video object acquisition equipment acquisition, and extracts the target object
Target signature information, according to the target signature information, obtained from the video frame include the target object target
Video frame；It is located at the location information and first corresponding relationship in the target video frame according to the target object, determines
Target position of the target object in the object detection area；According to the target position and the second corresponding pass
System, obtains the target high definition video collecting equipment that the target position is corresponded in the high definition video collecting equipment；Described in acquisition
The full dose HD video frame is merged processing by target high definition video collecting equipment full dose HD video frame collected,
Obtain the tracking video data for being directed to the target object.
Further, the tracking video data acquisition methods, further includes: when the determining target object is described
When position in object detection area contains at least two different location, the probability value of at least two different location is obtained；
According to the probability value, the target position of the target object in the object detection area is determined；Wherein, described general
Rate value is the probability value that the target object is located at the position.
Further, described according to the target position and second corresponding relationship, obtain the high definition video collecting
The target high definition video collecting equipment that the target position is corresponded in equipment, specifically includes: according to the target position and described
Second corresponding relationship obtains at least two high definition video collectings that the target position is corresponded in the high definition video collecting equipment
Equipment；It obtains in at least two high definition video collectings equipment between the center and the target position of pickup area
Distance parameter；It is determined in at least two high definition video collectings equipment according to the distance parameter and corresponds to the target position
The target high definition video collecting equipment.
Further, the tracking video data acquisition methods, further includes: the target is obtained from the video frame
The global feature information of object；The target object and the object detection area midfield are obtained from the global feature information
The distance of ground horizontal plane is less than the local feature information of the part of pre-determined distance threshold value；According to the local feature information,
Location information of the part of the target object in the target video frame is obtained, by the local portion of the target object
Position is located at as the target object location information in the target video frame in the location information in the target video frame.
Further, the probability value for obtaining at least two different location, specifically includes: obtaining described at least two
The characteristic information of the corresponding target object of a different location；It is sent to using the characteristic information as sample preset
In feature identification model, the probability value of at least two different location is obtained；Wherein, the feature identification model is used for basis
The matching result of the characteristic information and target signature information determines the probability value of target object position.
Correspondingly, the application also provides a kind of tracking video data acquisition device, comprising: construction unit, for constructing view
Frequency object acquires the first corresponding pass corresponding to the pickup area of equipment between position and physical location in object detection area
Physical location in system, and position corresponding to the pickup area of building high definition video collecting equipment and the object detection area
Between the second corresponding relationship；Target video frame acquiring unit, for determining the video of the video object acquisition equipment acquisition
Target object in frame, and the target signature information of the target object is extracted, according to the target signature information, from the view
The target video frame comprising the target object is obtained in frequency frame；Target position determination unit, for according to the target object
Location information and first corresponding relationship in the target video frame, determine that the target object is examined in the target
Survey the target position in region；Target high definition video collecting equipment determination unit, for according to the target position and described the
Two corresponding relationships obtain the target high definition video collecting equipment that the target position is corresponded in the high definition video collecting equipment；
Video data obtaining unit is tracked, for obtaining target high definition video collecting equipment full dose HD video frame collected,
The full dose HD video frame is merged into processing, obtains the tracking video data for being directed to the target object.
Further, described according to the target position and second corresponding relationship, obtain the high definition video collecting
The target high definition video collecting equipment that the target position is corresponded in equipment, specifically includes: according to the target position and described
Second corresponding relationship obtains at least two high definition video collectings that the target position is corresponded in the high definition video collecting equipment
Equipment；It obtains in at least two high definition video collectings equipment between the center and the target position of pickup area
Distance parameter；It is determined in at least two high definition video collectings equipment according to the distance parameter and corresponds to the target position
The target high definition video collecting equipment.
Further, the tracking video data acquisition device, further includes: complete characterization obtaining unit is used for from institute
State the global feature information that the target object is obtained in video frame；
Local feature acquiring unit is examined for obtaining the target object and the target from the global feature information
The distance of place horizontal plane is less than the local feature information of the part of pre-determined distance threshold value in survey region；
Location information determination unit, for obtaining the local feature of the target object according to the local feature information
Location information of the information in the target video frame, by the local feature information of the target object in the target video frame
In location information be located at the location information in the target video frame as the target object.
Further, the tracking video data acquisition methods, further includes: when the determining target object is described
When position in object detection area contains at least two different location, the probability value of at least two different location is obtained；
According to the probability value, the target position of the target object in the object detection area is determined.
Further, the probability value for obtaining at least two different location, specifically includes: obtaining described at least two
The characteristic information of the corresponding target object of a different location；It is sent to using the characteristic information as sample preset
In feature identification model, the probability value of at least two different location is obtained；Wherein, the feature identification model is used for basis
The matching result of the characteristic information and target signature information determines the probability value of target object position.
Correspondingly, the application also provides a kind of electronic equipment, comprising: processor and memory；Wherein, the memory,
For storing the program of tracking video data acquisition methods, which is powered and runs the tracking video counts by the processor
After the program of acquisition methods, following step is executed:
Construct in position and object detection area corresponding to the pickup area of the video object acquisition equipment physical location it
Between the first corresponding relationship, and position and the target detection corresponding to the pickup area of building high definition video collecting equipment
The second corresponding relationship in region between physical location；Determine the target in the video frame of the video object acquisition equipment acquisition
Object, and the target signature information of the target object is extracted, according to the target signature information, obtained from the video frame
Target video frame comprising the target object；According to the target object be located at location information in the target video frame and
First corresponding relationship determines target position of the target object in the object detection area；According to the target
Position and second corresponding relationship obtain the target high definition view that the target position is corresponded in the high definition video collecting equipment
Frequency acquisition equipment；Target high definition video collecting equipment full dose HD video frame collected is obtained, by the full dose high definition
Video frame merges processing, obtains the tracking video data for being directed to the target object.
Correspondingly, the application also provides a kind of storage equipment, it is stored with the program of tracking video data acquisition methods, the journey
Sequence is run by processor, executes following step:
Construct in position and object detection area corresponding to the pickup area of the video object acquisition equipment physical location it
Between the first corresponding relationship, and position and the target detection corresponding to the pickup area of building high definition video collecting equipment
The second corresponding relationship in region between physical location；Determine the target in the video frame of the video object acquisition equipment acquisition
Object, and the target signature information of the target object is extracted, according to the target signature information, obtained from the video frame
Target video frame comprising the target object；According to the target object be located at location information in the target video frame and
First corresponding relationship determines target position of the target object in the object detection area；According to the target
Position and second corresponding relationship obtain the target high definition view that the target position is corresponded in the high definition video collecting equipment
Frequency acquisition equipment；Target high definition video collecting equipment full dose HD video frame collected is obtained, by the full dose high definition
Video frame merges processing, obtains the tracking video data for being directed to the target object.
Using method of the present invention, equipment can be acquired by the video object of setting in advance to each target object
Comprehensive positioning and tracking are carried out, and then fast and accurately obtains the height of the high definition video collecting equipment of corresponding position deployment
Clear video data improves the collecting efficiency of tracking video, avoids huge equipment dosage and more rocker arm equipment are mutually blocked
The problem of, to improve the usage experience of user.
Detailed description of the invention
It, below will be to embodiment party in order to illustrate more clearly of embodiments of the present invention or technical solution in the prior art
Formula or attached drawing needed to be used in the description of the prior art are briefly described.It should be evident that the accompanying drawings in the following description is only
It is merely exemplary, it for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer, which is extended, obtains other implementation attached drawings.
Structure depicted in this specification, ratio, size etc., only to cooperate the revealed content of specification, for
Those skilled in the art understands and reads, and is not intended to limit the invention enforceable qualifications, therefore does not have technical
Essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the function of the invention that can be generated
Under effect and the purpose that can reach, should all still it fall in the range of disclosed technology contents obtain and can cover.
Fig. 1 is a kind of flow chart of acquisition methods for tracking video data provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of acquisition device for tracking video data provided in an embodiment of the present invention；
Fig. 3 is the schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book is understood other advantages and efficacy of the present invention easily, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Below based on the acquisition methods of tracking video data of the present invention, embodiment is described in detail.Such as
Shown in Fig. 1, for a kind of flow chart for the acquisition methods for tracking video data provided in an embodiment of the present invention, process is implemented
The following steps are included:
Step S101: real in position corresponding to the pickup area of building the video object acquisition equipment and object detection area
The first corresponding relationship between the position of border, and building high definition video collecting equipment pickup area corresponding to position with it is described
The second corresponding relationship in object detection area between physical location.
In embodiments of the present invention, the described the video object acquisition equipment, which can refer to, a set of is completely covered target detection area
The wide-angle video in domain acquires equipment group.For example it can be made of two or three wide-angle video acquisition equipment.The wide-angle view
Frequency acquisition equipment can refer to that the acquisition of the wide-angle videos data such as wide angle cameras, wide-angle video recorder and wide angle picture sensor is set
It is standby.
The pickup area is that the video object acquisition equipment can take the region model in the object detection area
It encloses.Acquiring equipment by the video object of setting may be implemented the whole object detection area of pickup area covering.
It should be noted that acquiring the splicing of pickup area coverage goal detection zone between equipment in the video object
Place needs the reserved repeated acquisition region for meeting preset range threshold value, meanwhile, the video object acquisition equipment coverage area
Shooting required precision at least guarantees that each target object should occupy the no less than pixel wide of 16x16.
The high definition video collecting equipment can refer to a set of high definition video collecting that object detection area is completely covered
Equipment group.The high definition video collecting equipment group can refer to the set being made of multiple high-resolution pick-up devices, each
The complete object detection area of pickup area overlapped coverage of photographic device, and guarantee in its pickup area, each target
Object should occupy the width not less than 300 pixels.
It in the specific implementation process, can when disposing the high definition video collecting equipment and the video object acquisition equipment
To be measured in advance, so that practical in position corresponding to the pickup area of the video object acquisition equipment and object detection area
In position corresponding to the pickup area of position and high definition video collecting equipment and the object detection area physical location it
Between correspond, and the corresponding relationship of the two is stored in advance in the data-storage system to server.
Step S102: the target object in the video frame of the video object acquisition equipment acquisition is determined, and described in extraction
The target signature information of target object, according to the target signature information, obtaining from the video frame includes the target pair
The target video frame of elephant.
It is disposed after the video object acquisition equipment and the high definition video collecting equipment in step s101, this step
The target object for determining and needing in the video frame of equipment acquisition can be acquired by the video object, pass through feature extraction algorithm
The target signature information of the target object is extracted, is further set according to the target signature information from the video object acquisition
The video frame of standby acquisition obtains the target video frame comprising the target object.
In embodiments of the present invention, the target pair in the video frame of the determination the video object acquisition equipment acquisition
As can specifically refer to target object included in any one video frame acquired from the video object acquisition equipment.
The target object can refer to people or object etc. to be tracked, such as: the sportsman on automobile or football pitch in parking lot
Deng.
The target signature information can refer to the biological characteristic, shape feature, structure of target object described in unique identification
Make feature and color characteristic etc..The target video frame can refer to all views of the video object acquisition equipment acquisition
It include the video frame of the target object in frequency frame.
Step S103: the location information and described first in the target video frame is located at according to the target object and is corresponded to
Relationship determines target position of the target object in the object detection area.
After obtaining the first corresponding relationship in above-mentioned steps S101, determine that the target object is examined in the target for this step
Data Preparation is done in the target position surveyed in region.In step s 102, can be located at according to the target object described
Location information and first corresponding relationship in target video frame further determine that the target object in the target detection
Target position in region.
In the actual implementation process, the position when the determining target object in the object detection area includes extremely
When few two different locations, the corresponding mesh of at least two different location can be obtained by feature extraction algorithm
The characteristic information for marking object, is sent to the characteristic information as sample in preset feature identification model, and then respectively
To the probability value of at least two different location.According to the probability value size of at least two different location, by probability value
Maximum position determines only one target position of the target object in the object detection area.Wherein, the spy
Sign identification model is used to determine target object position according to the matching result of the characteristic information and target signature information
Probability value.
It should be noted that the location information that the target object is located in the target video frame specifically can be by such as
Under type determines: the complete characterization information of the target object is obtained from the video frame using feature extraction algorithm, from institute
It states and obtains the target object in global feature information at a distance from place horizontal plane in the object detection area less than default
The local feature information of the part of distance threshold identifies target object and is chased after according to the local feature information
Track obtains location information of the part of the target object in the target video frame in turn, by the target object
Part is located at as the target object position in the target video frame in the location information in the target video frame
Confidence breath.Specifically, can identify network implementations by Faster RCNN in the identification of target object, using based on nerve net
The matched mode of network characteristic similarity is positioned and is tracked to multiple target object.In addition, in embodiment of the present invention
Identification and tracking of the other modes realization to the target object can be used, be not specifically limited herein.
In embodiments of the present invention, the object detection area is the acquisition region of the target object to be detected,
Such as: the football pitch of athlete's, the parking lot etc. of automobile are not specifically limited herein.Usual the video object acquires equipment
Pickup area realization the object detection area is completely covered.The target position can refer to the target object position
Physical location in the object detection area.It should be noted that the target position is continuous during atual detection
Variation, so the target high definition video collecting equipment is also continually changing.
Step S104: according to the target position and second corresponding relationship, the high definition video collecting equipment is obtained
The target high definition video collecting equipment of the middle correspondence target position.
After obtaining the second corresponding relationship in above-mentioned steps S101, it is right in the high definition video collecting equipment to obtain for this step
The target high definition video collecting equipment of the target position is answered to do Data Preparation.It in step s 102, can be according to institute
It states target position and second corresponding relationship further obtains in the high definition video collecting equipment and corresponds to the target position
Target high definition video collecting equipment.
In the actual implementation process, according to the target position and second corresponding relationship, when the high definition of acquisition
When corresponding to the target position in video capture device and containing at least two high definition video collecting equipment, can further it obtain
The distance between center Yu the target position of pickup area parameter in at least two high definition video collectings equipment,
It is right in at least two high definition video collectings equipment to be determined according to the distance of center of the target position apart from pickup area
Answer the unique one target high definition video collecting equipment of the target position.Specifically, can also be by judging the mesh
Whether the distance between center of pickup area is less than preset distance in cursor position and the high definition video collecting equipment
Range threshold, if so, using the high definition video collecting equipment as the target high definition video collecting equipment.
In embodiments of the present invention, the target high definition video collecting equipment is apart from the target object positioned at described
A nearest high definition video collecting equipment in object detection area.
Step S105: obtaining target high definition video collecting equipment full dose HD video frame collected, will be described complete
Amount HD video frame merges processing, obtains the tracking video data for being directed to the target object.
After the target high definition video collecting equipment for determining the corresponding target object in above-mentioned steps S104, in step,
Available target high definition video collecting equipment full dose HD video frame collected.By the full dose HD video frame into
Row merging treatment can obtain the full trace video data for the target object.The merging treatment specifically includes:
Target position where shearing the target object in the full dose HD video frame, then the HD video frame target position
It is connected into tracking video.
In embodiments of the present invention, it can guarantee the stability of network-in-dialing, institute by preset local time server
Stating the delay between equipment and the local time server such as high definition video collecting equipment, the video object acquisition equipment can
With setting stablize preset time threshold (such as: 15ms or 20ms etc.) in.
It should be noted that the target position be during atual detection it is continually changing, so target HD video
It is also continually changing for acquiring equipment.Therefore, the target high definition video collecting equipment can refer to that a HD video is adopted
Collect equipment, may also mean that the combination of more high definition video collecting equipment.
Correspondingly, the full dose HD video frame finally acquired can refer to the acquisition of high definition video collecting equipment include
The video frame of the target object may also mean that the combination of more high definition video collecting equipment is collected comprising the target
The video frame of object.
Using method of the present invention, equipment can be acquired by the video object of setting in advance to each target object
Comprehensive positioning and tracking are carried out, and then fast and accurately obtains the high definition view of the high definition video collecting equipment of corresponding position
Frequency evidence improves the collecting efficiency of tracking video, avoids huge equipment dosage, to improve the use body of user
It tests.
Corresponding with a kind of acquisition methods of tracking video data of above-mentioned offer, the present invention also provides a kind of tracking videos
The acquisition device of data.Since the embodiment of the device is similar to above method embodiment, so be described relatively simple, it is related
Place refers to the explanation of above method embodiment part, the embodiment of tracking video data acquisition device described below
It is only illustrative.It please refers to shown in Fig. 2, is a kind of acquisition device for tracking video data provided in an embodiment of the present invention
Schematic diagram.
A kind of tracking video data acquisition device of the present invention includes following part:
Construction unit 201, for constructing position and target detection corresponding to the pickup area of the video object acquisition equipment
The first corresponding relationship in region between physical location, and position corresponding to the pickup area of building high definition video collecting equipment
It sets and the second corresponding relationship in the object detection area between physical location.
In embodiments of the present invention, the described the video object acquisition equipment, which can refer to, a set of is completely covered target detection area
The wide-angle video in domain acquires equipment group.For example it can be made of two or three wide-angle video acquisition equipment.The wide-angle view
Frequency acquisition equipment can refer to that the acquisition of the wide-angle videos data such as wide angle cameras, wide-angle video recorder and wide angle picture sensor is set
It is standby.The pickup area is that the video object acquisition equipment can take the regional scope in the object detection area.It is logical
The whole object detection area of pickup area covering may be implemented in the video object acquisition equipment for crossing setting.It should be noted that
The stitching portion of pickup area coverage goal detection zone needs the default model of reserved satisfaction between the video object acquisition equipment
The repeated acquisition region of threshold value is enclosed, meanwhile, the shooting required precision of the video object acquisition equipment coverage area at least guarantees
Each target object should occupy the no less than pixel wide of 16x16.
The high definition video collecting equipment can refer to a set of high definition video collecting that object detection area is completely covered
Equipment group.The high definition video collecting equipment group can refer to the set being made of multiple high-resolution pick-up devices, each
The complete object detection area of pickup area overlapped coverage of photographic device, and guarantee in its pickup area, each target
Object should occupy the width not less than 300 pixels.
It in the specific implementation process, can when disposing the high definition video collecting equipment and the video object acquisition equipment
To be measured in advance, so that practical in position corresponding to the pickup area of the video object acquisition equipment and object detection area
In position corresponding to the pickup area of position and high definition video collecting equipment and the object detection area physical location it
Between correspond, and the corresponding relationship of the two is stored in advance in the data-storage system to server.
Target video frame acquiring unit 202, the mesh in video frame for determining the video object acquisition equipment acquisition
Object is marked, and extracts the target signature information of the target object, according to the target signature information, is obtained from the video frame
Take the target video frame comprising the target object.
Target position determination unit 203, the position letter for being located in the target video frame according to the target object
Breath and first corresponding relationship, determine target position of the target object in the object detection area.
In the actual implementation process, the position when the determining target object in the object detection area includes extremely
When few two different locations, the corresponding mesh of at least two different location can be obtained by feature extraction algorithm
The characteristic information for marking object, is sent to the characteristic information as sample in preset feature identification model, and then respectively
To the probability value of at least two different location.According to the probability value size of at least two different location, by probability value
Maximum position determines only one target position of the target object in the object detection area.Wherein, the spy
Sign identification model is used to determine target object position according to the matching result of the characteristic information and target signature information
Probability value.
It should be noted that the location information that the target object is located in the target video frame specifically can be by such as
Under type determines: the complete characterization information of the target object is obtained from the video frame using feature extraction algorithm, from institute
It states and obtains the target object in global feature information at a distance from place horizontal plane in the object detection area less than default
The local feature information of the part of distance threshold identifies target object and is chased after according to the local feature information
Track obtains location information of the part of the target object in the target video frame in turn, by the target object
Part is located at as the target object position in the target video frame in the location information in the target video frame
Confidence breath.Specifically, can identify network implementations by Faster RCNN in the identification of target object, using based on nerve net
The matched mode of network characteristic similarity is positioned and is tracked to multiple target object.
Target high definition video collecting equipment determination unit 204, for according to the target position and the second corresponding pass
System, obtains the target high definition video collecting equipment that the target position is corresponded in the high definition video collecting equipment.
In the actual implementation process, according to the target position and second corresponding relationship, when the high definition of acquisition
When corresponding to the target position in video capture device and containing at least two high definition video collecting equipment, can further it obtain
The distance between center Yu the target position of pickup area parameter in at least two high definition video collectings equipment,
It is right in at least two high definition video collectings equipment to be determined according to the distance of center of the target position apart from pickup area
Answer the unique one target high definition video collecting equipment of the target position.Specifically, can also be by judging the mesh
Whether the distance between center of pickup area is less than preset distance in cursor position and the high definition video collecting equipment
Range threshold, if so, using the high definition video collecting equipment as the target high definition video collecting equipment.
Video data obtaining unit 205 is tracked, for obtaining the target high definition video collecting equipment full dose collected
The full dose HD video frame is merged processing, obtains the tracking video counts for being directed to the target object by HD video frame
According to.
In embodiments of the present invention, it can guarantee the stability of network-in-dialing, institute by preset local time server
Stating the delay between equipment and the local time server such as high definition video collecting equipment, the video object acquisition equipment can
With setting stablize preset time threshold (such as: 15ms or 20ms etc.) in.
Using device of the present invention, equipment can be acquired by the video object of setting in advance to each target object
Comprehensive positioning and tracking are carried out, and then fast and accurately obtains the high definition view of the high definition video collecting equipment of corresponding position
Frequency evidence improves the collecting efficiency of tracking video, avoids huge equipment dosage, to improve the use body of user
It tests.
Corresponding with a kind of acquisition methods of tracking video data of above-mentioned offer, the present invention also provides a kind of electronics to set
It is standby.Since the embodiment of the electronic equipment is similar to above method embodiment, so being described relatively simple, related place please join
See that the explanation of above method embodiment part, electronic device described below are only illustrative.It please refers to shown in Fig. 3,
It is the schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
The present invention provides a kind of electronic equipment and specifically includes: processor 301 and memory 302；Wherein, the memory
302, for storing the program of tracking video data acquisition methods, which is powered and runs tracking view by the processor
After the program of frequency data capture method, following step is executed:
Construct in position and object detection area corresponding to the pickup area of the video object acquisition equipment physical location it
Between the first corresponding relationship, and position and the target detection corresponding to the pickup area of building high definition video collecting equipment
The second corresponding relationship in region between physical location；Determine the target in the video frame of the video object acquisition equipment acquisition
Object, and the target signature information of the target object is extracted, according to the target signature information, obtained from the video frame
Target video frame comprising the target object；According to the target object be located at location information in the target video frame and
First corresponding relationship determines target position of the target object in the object detection area；According to the target
Position and second corresponding relationship obtain the target high definition view that the target position is corresponded in the high definition video collecting equipment
Frequency acquisition equipment；Target high definition video collecting equipment full dose HD video frame collected is obtained, by the full dose high definition
Video frame merges processing, obtains the tracking video data for being directed to the target object.
Correspondingly, being stored with the program of tracking video data acquisition methods, the journey the present invention also provides a kind of storage equipment
Sequence is run by processor, executes following step:
Construct in position and object detection area corresponding to the pickup area of the video object acquisition equipment physical location it
Between the first corresponding relationship, and position and the target detection corresponding to the pickup area of building high definition video collecting equipment
The second corresponding relationship in region between physical location；Determine the target in the video frame of the video object acquisition equipment acquisition
Object, and the target signature information of the target object is extracted, according to the target signature information, obtained from the video frame
Target video frame comprising the target object；According to the target object be located at location information in the target video frame and
First corresponding relationship determines target position of the target object in the object detection area；According to the target
Position and second corresponding relationship obtain the target high definition view that the target position is corresponded in the high definition video collecting equipment
Frequency acquisition equipment；Target high definition video collecting equipment full dose HD video frame collected is obtained, by the full dose high definition
Video frame merges processing, obtains the tracking video data for being directed to the target object.
Although above having used general explanation and specific embodiment, the present invention is described in detail, at this
On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore,
These modifications or improvements without departing from theon the basis of the spirit of the present invention are fallen within the scope of the claimed invention.
Claims (10)
1. a kind of acquisition methods for tracking video data characterized by comprising
It constructs in position corresponding to the pickup area of the video object acquisition equipment and object detection area between physical location
First corresponding relationship, and position and the object detection area corresponding to the pickup area of building high definition video collecting equipment
The second corresponding relationship between middle physical location；
It determines the target object in the video frame of the video object acquisition equipment acquisition, and extracts the target of the target object
Characteristic information obtains the target video frame comprising the target object according to the target signature information from the video frame；
Be located at the location information and first corresponding relationship in the target video frame according to the target object, determine described in
Target position of the target object in the object detection area；
According to the target position and second corresponding relationship, obtains in the high definition video collecting equipment and correspond to the target
The target high definition video collecting equipment of position；
Obtain target high definition video collecting equipment full dose HD video frame collected, by the full dose HD video frame into
Row merging treatment obtains the tracking video data for being directed to the target object.
2. the acquisition methods of tracking video data according to claim 1, which is characterized in that further include:
When position of the determining target object in the object detection area contains at least two different location, obtain
The probability value of at least two different location；
According to the probability value, the target position of the target object in the object detection area is determined；Wherein, institute
Stating probability value is the probability value that the target object is located at the position.
3. the acquisition methods of tracking video data according to claim 1, which is characterized in that described according to the target position
Set with second corresponding relationship, obtain the target HD video that the target position is corresponded in the high definition video collecting equipment
Equipment is acquired, is specifically included:
According to the target position and second corresponding relationship, obtain in the high definition video collecting equipment comprising the target
At least two high definition video collecting equipment of position；
It obtains in at least two high definition video collectings equipment between the center and the target position of pickup area
Distance parameter；
It is determined in at least two high definition video collectings equipment and is corresponded to described in the target position according to the distance parameter
Target high definition video collecting equipment.
4. the acquisition methods of tracking video data according to claim 1, which is characterized in that further include:
The global feature information of the target object is obtained from the video frame；
From obtaining the target object in the global feature information at a distance from place horizontal plane in the object detection area
Less than the local feature information of the part of pre-determined distance threshold value；
According to the local feature information, position letter of the part of the target object in the target video frame is obtained
Breath, is located at institute for location information of the part of the target object in the target video frame as the target object
State the location information in target video frame.
5. the acquisition methods of tracking video data according to claim 2, which is characterized in that at least two described in the acquisition
The probability value of a different location, specifically includes:
Obtain the characteristic information of the corresponding target object of at least two different location；
It is sent to the characteristic information as sample in preset feature identification model, obtains at least two different location
Probability value；Wherein, the feature identification model is used for true according to the matching result of the characteristic information and target signature information
Set the goal the probability value of object position.
6. a kind of acquisition device for tracking video data characterized by comprising
Construction unit, it is real in position corresponding to the pickup area of the video object acquisition equipment and object detection area for constructing
The first corresponding relationship between the position of border, and building high definition video collecting equipment pickup area corresponding to position with it is described
The second corresponding relationship in object detection area between physical location；
Target video frame acquiring unit, the target object in video frame for determining the video object acquisition equipment acquisition,
And the target signature information of the target object is extracted, according to the target signature information, is obtained from the video frame and include
The target video frame of the target object；
Target position determination unit, location information for being located in the target video frame according to the target object and described
First corresponding relationship determines target position of the target object in the object detection area；
Target high definition video collecting equipment determination unit, for obtaining according to the target position and second corresponding relationship
The target high definition video collecting equipment of the target position is corresponded in the high definition video collecting equipment；
Video data obtaining unit is tracked, for obtaining target high definition video collecting equipment full dose HD video collected
The full dose HD video frame is merged processing, obtains the tracking video data for being directed to the target object by frame.
7. the acquisition device of tracking video data according to claim 6, which is characterized in that described according to the target position
Set with second corresponding relationship, obtain the target HD video that the target position is corresponded in the high definition video collecting equipment
Equipment is acquired, is specifically included:
According to the target position and second corresponding relationship, obtains in the high definition video collecting equipment and correspond to the target
At least two high definition video collecting equipment of position；
It obtains in at least two high definition video collectings equipment between the center and the target position of pickup area
Distance parameter；
It is determined in at least two high definition video collectings equipment and is corresponded to described in the target position according to the distance parameter
Target high definition video collecting equipment.
8. the acquisition device of tracking video data according to claim 6, which is characterized in that further include:
Complete characterization obtaining unit, for obtaining the global feature information of the target object from the video frame；
Local feature acquiring unit, for obtaining the target object and the target detection area from the global feature information
The distance of place horizontal plane is less than the local feature information of the part of pre-determined distance threshold value in domain；
Location information determination unit, for obtaining the local feature information of the target object according to the local feature information
Location information in the target video frame, by the local feature information of the target object in the target video frame
Location information is located at the location information in the target video frame as the target object.
9. a kind of electronic equipment characterized by comprising
Processor；And
Memory, the program of the acquisition methods for storing tracking video data, the equipment are powered and pass through the processor and transports
After the program of the acquisition methods of the row tracking video data, following step is executed:
It constructs in position corresponding to the pickup area of the video object acquisition equipment and object detection area between physical location
First corresponding relationship, and position and the object detection area corresponding to the pickup area of building high definition video collecting equipment
The second corresponding relationship between middle physical location；
It determines the target object in the video frame of the video object acquisition equipment acquisition, and extracts the target of the target object
Characteristic information obtains the target video frame comprising the target object according to the target signature information from the video frame；
Be located at the location information and first corresponding relationship in the target video frame according to the target object, determine described in
Target position of the target object in the object detection area；
According to the target position and second corresponding relationship, obtains in the high definition video collecting equipment and correspond to the target
The target high definition video collecting equipment of position；
Obtain target high definition video collecting equipment full dose HD video frame collected, by the full dose HD video frame into
Row merging treatment obtains the tracking video data for being directed to the target object.
10. a kind of storage equipment, which is characterized in that be stored with the program of the acquisition methods of tracking video data, which is located
Device operation is managed, following step is executed:
It constructs in position corresponding to the pickup area of the video object acquisition equipment and object detection area between physical location
First corresponding relationship, and position and the object detection area corresponding to the pickup area of building high definition video collecting equipment
The second corresponding relationship between middle physical location；
It determines the target object in the video frame of the video object acquisition equipment acquisition, and extracts the target of the target object
Characteristic information obtains the target video frame comprising the target object according to the target signature information from the video frame；
Be located at the location information and first corresponding relationship in the target video frame according to the target object, determine described in
Target position of the target object in the object detection area；
According to the target position and second corresponding relationship, obtains in the high definition video collecting equipment and correspond to the target
The target high definition video collecting equipment of position；
Obtain target high definition video collecting equipment full dose HD video frame collected, by the full dose HD video frame into
Row merging treatment obtains the tracking video data for being directed to the target object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910522906.2A CN110177256B (en) | 2019-06-17 | 2019-06-17 | Tracking video data acquisition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910522906.2A CN110177256B (en) | 2019-06-17 | 2019-06-17 | Tracking video data acquisition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110177256A true CN110177256A (en) | 2019-08-27 |
| CN110177256B CN110177256B (en) | 2021-12-14 |
Family
ID=67697293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910522906.2A Active CN110177256B (en) | 2019-06-17 | 2019-06-17 | Tracking video data acquisition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110177256B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222509A (en) * | 2020-01-17 | 2020-06-02 | 北京字节跳动网络技术有限公司 | Target detection method and device and electronic equipment |
Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090002489A1 (en) * | 2007-06-29 | 2009-01-01 | Fuji Xerox Co., Ltd. | Efficient tracking multiple objects through occlusion |
| CN100456827C (en) * | 2003-06-18 | 2009-01-28 | 松下电器产业株式会社 | Video surveillance system, surveillance video composition apparatus, and video surveillance server |
| US20090067670A1 (en) * | 2007-09-07 | 2009-03-12 | Edh Sa (Pty) Ltd. | Methods and processes for detecting a mark on a playing surface and for tracking an object |
| CN102148965A (en) * | 2011-05-09 | 2011-08-10 | 上海芯启电子科技有限公司 | Video monitoring system for multi-target tracking close-up shooting |
| CN102256108A (en) * | 2011-05-30 | 2011-11-23 | 四川省电力公司 | Automatic tracking positioning system for multiple paths of video for personnel in intelligent transformer substation |
| CN102902884A (en) * | 2012-09-24 | 2013-01-30 | 天津市亚安科技股份有限公司 | PTZ (pan/tilt/zoom) camera automatic positioning and angle calculating method |
| CN103259962A (en) * | 2013-04-17 | 2013-08-21 | 深圳市捷顺科技实业股份有限公司 | Target tracking method and related device |
| US20130287250A1 (en) * | 2012-04-25 | 2013-10-31 | Electronics And Telecommunications Research Institute | Method and apparatus for tracking object in image data, and storage medium storing the same |
| CN203399223U (en) * | 2013-08-19 | 2014-01-15 | 中国能源建设集团广东省电力设计研究院 | Video monitoring system of direct current power transmission system |
| CN104301669A (en) * | 2014-09-12 | 2015-01-21 | 重庆大学 | Suspicious target detection tracking and recognition method based on dual-camera cooperation |
| CN104537659A (en) * | 2014-12-23 | 2015-04-22 | 金鹏电子信息机器有限公司 | Automatic two-camera calibration method and system |
| CN104680559A (en) * | 2015-03-20 | 2015-06-03 | 青岛科技大学 | Multi-view indoor pedestrian tracking method based on movement behavior mode |
| CN104925055A (en) * | 2014-03-18 | 2015-09-23 | 福特全球技术公司 | Method and device for detecting moving objects in area surrounding vehicle |
| CN105070098A (en) * | 2015-07-14 | 2015-11-18 | 安徽清新互联信息科技有限公司 | Vehicle distance detection method based on license plate position |
| US20150332093A1 (en) * | 2014-05-15 | 2015-11-19 | Postech Academy-Industry Foundation | Object tracking apparatus and method thereof |
| CN105182320A (en) * | 2015-07-14 | 2015-12-23 | 安徽清新互联信息科技有限公司 | Depth measurement-based vehicle distance detection method |
| CN105933678A (en) * | 2016-07-01 | 2016-09-07 | 湖南源信光电科技有限公司 | Multi-focal length lens linkage imaging device based on multi-target intelligent tracking |
| CN107093188A (en) * | 2017-04-12 | 2017-08-25 | 湖南源信光电科技股份有限公司 | A kind of intelligent linkage and tracking based on panoramic camera and high-speed ball-forming machine |
| WO2018044731A1 (en) * | 2016-09-02 | 2018-03-08 | Vid Scale, Inc. | Systems and methods for hybrid network delivery of objects of interest in video |
| CN108111818A (en) * | 2017-12-25 | 2018-06-01 | 北京航空航天大学 | Moving target active perception method and apparatus based on multiple-camera collaboration |
| CN108174152A (en) * | 2017-12-28 | 2018-06-15 | 深圳英飞拓科技股份有限公司 | A kind of target monitoring method and target monitor system |
| CN108419014A (en) * | 2018-03-20 | 2018-08-17 | 北京天睿空间科技股份有限公司 | The method for capturing face using panoramic camera and the linkage of Duo Tai candid cameras |
| CN108734780A (en) * | 2017-04-17 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | Method, apparatus and equipment for generating map |
| CN108876806A (en) * | 2018-05-07 | 2018-11-23 | 广东省电信规划设计院有限公司 | Method for tracking target and system, storage medium and equipment based on big data analysis |
| CN109146912A (en) * | 2018-07-26 | 2019-01-04 | 湖南人文科技学院 | A kind of visual target tracking method based on Objective analysis |
| CN109685002A (en) * | 2018-12-21 | 2019-04-26 | 创新奇智(广州)科技有限公司 | A kind of dataset acquisition method, system and electronic device |
| CN109685062A (en) * | 2019-01-02 | 2019-04-26 | 南方科技大学 | A kind of object detection method, device, equipment and storage medium |
| CN109788208A (en) * | 2019-01-30 | 2019-05-21 | 华通科技有限公司 | Target identification method and system based on multiple groups focal length images source |
-
2019
- 2019-06-17 CN CN201910522906.2A patent/CN110177256B/en active Active
Patent Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100456827C (en) * | 2003-06-18 | 2009-01-28 | 松下电器产业株式会社 | Video surveillance system, surveillance video composition apparatus, and video surveillance server |
| US20090002489A1 (en) * | 2007-06-29 | 2009-01-01 | Fuji Xerox Co., Ltd. | Efficient tracking multiple objects through occlusion |
| US20090067670A1 (en) * | 2007-09-07 | 2009-03-12 | Edh Sa (Pty) Ltd. | Methods and processes for detecting a mark on a playing surface and for tracking an object |
| CN102148965A (en) * | 2011-05-09 | 2011-08-10 | 上海芯启电子科技有限公司 | Video monitoring system for multi-target tracking close-up shooting |
| CN102256108A (en) * | 2011-05-30 | 2011-11-23 | 四川省电力公司 | Automatic tracking positioning system for multiple paths of video for personnel in intelligent transformer substation |
| US20130287250A1 (en) * | 2012-04-25 | 2013-10-31 | Electronics And Telecommunications Research Institute | Method and apparatus for tracking object in image data, and storage medium storing the same |
| CN102902884A (en) * | 2012-09-24 | 2013-01-30 | 天津市亚安科技股份有限公司 | PTZ (pan/tilt/zoom) camera automatic positioning and angle calculating method |
| CN103259962A (en) * | 2013-04-17 | 2013-08-21 | 深圳市捷顺科技实业股份有限公司 | Target tracking method and related device |
| CN203399223U (en) * | 2013-08-19 | 2014-01-15 | 中国能源建设集团广东省电力设计研究院 | Video monitoring system of direct current power transmission system |
| CN104925055A (en) * | 2014-03-18 | 2015-09-23 | 福特全球技术公司 | Method and device for detecting moving objects in area surrounding vehicle |
| US20150332093A1 (en) * | 2014-05-15 | 2015-11-19 | Postech Academy-Industry Foundation | Object tracking apparatus and method thereof |
| CN104301669A (en) * | 2014-09-12 | 2015-01-21 | 重庆大学 | Suspicious target detection tracking and recognition method based on dual-camera cooperation |
| CN104537659A (en) * | 2014-12-23 | 2015-04-22 | 金鹏电子信息机器有限公司 | Automatic two-camera calibration method and system |
| CN104680559A (en) * | 2015-03-20 | 2015-06-03 | 青岛科技大学 | Multi-view indoor pedestrian tracking method based on movement behavior mode |
| CN105070098A (en) * | 2015-07-14 | 2015-11-18 | 安徽清新互联信息科技有限公司 | Vehicle distance detection method based on license plate position |
| CN105182320A (en) * | 2015-07-14 | 2015-12-23 | 安徽清新互联信息科技有限公司 | Depth measurement-based vehicle distance detection method |
| CN105933678A (en) * | 2016-07-01 | 2016-09-07 | 湖南源信光电科技有限公司 | Multi-focal length lens linkage imaging device based on multi-target intelligent tracking |
| WO2018044731A1 (en) * | 2016-09-02 | 2018-03-08 | Vid Scale, Inc. | Systems and methods for hybrid network delivery of objects of interest in video |
| CN107093188A (en) * | 2017-04-12 | 2017-08-25 | 湖南源信光电科技股份有限公司 | A kind of intelligent linkage and tracking based on panoramic camera and high-speed ball-forming machine |
| CN108734780A (en) * | 2017-04-17 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | Method, apparatus and equipment for generating map |
| CN108111818A (en) * | 2017-12-25 | 2018-06-01 | 北京航空航天大学 | Moving target active perception method and apparatus based on multiple-camera collaboration |
| CN108174152A (en) * | 2017-12-28 | 2018-06-15 | 深圳英飞拓科技股份有限公司 | A kind of target monitoring method and target monitor system |
| CN108419014A (en) * | 2018-03-20 | 2018-08-17 | 北京天睿空间科技股份有限公司 | The method for capturing face using panoramic camera and the linkage of Duo Tai candid cameras |
| CN108876806A (en) * | 2018-05-07 | 2018-11-23 | 广东省电信规划设计院有限公司 | Method for tracking target and system, storage medium and equipment based on big data analysis |
| CN109146912A (en) * | 2018-07-26 | 2019-01-04 | 湖南人文科技学院 | A kind of visual target tracking method based on Objective analysis |
| CN109685002A (en) * | 2018-12-21 | 2019-04-26 | 创新奇智(广州)科技有限公司 | A kind of dataset acquisition method, system and electronic device |
| CN109685062A (en) * | 2019-01-02 | 2019-04-26 | 南方科技大学 | A kind of object detection method, device, equipment and storage medium |
| CN109788208A (en) * | 2019-01-30 | 2019-05-21 | 华通科技有限公司 | Target identification method and system based on multiple groups focal length images source |
Non-Patent Citations (3)
| Title |
|---|
| 公安部第三研究所: "《多摄像机协同关注目标检测跟踪技术》", 30 June 2017, 南京：东南大学出版社 * |
| 熊伟，谢剑薇等著: "《光电跟踪控制系统导论》", 31 August 2009, 北京：国防工业出版社 * |
| 石皓: "用于全景与PTZ主从摄像机的标定方法研究", 《中国优秀硕士学位论文全文数据库（电子期刊）信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222509A (en) * | 2020-01-17 | 2020-06-02 | 北京字节跳动网络技术有限公司 | Target detection method and device and electronic equipment |
| CN111222509B (en) * | 2020-01-17 | 2023-08-18 | 北京字节跳动网络技术有限公司 | Target detection method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110177256B (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10489656B2 (en) | Methods and systems for ball game analytics with a mobile device | |
| US10372970B2 (en) | Automatic scene calibration method for video analytics | |
| JP6448223B2 (en) | Image recognition system, image recognition apparatus, image recognition method, and computer program | |
| Wheeler et al. | Face recognition at a distance system for surveillance applications | |
| CN111046752B (en) | Indoor positioning method, computer equipment and storage medium | |
| CN108200334B (en) | Image shooting method and device, storage medium and electronic equipment | |
| JP6077655B2 (en) | Shooting system | |
| CN111163259A (en) | Image capturing method, monitoring camera and monitoring system | |
| CN109345568A (en) | Sports ground intelligent implementing method and system based on computer vision algorithms make | |
| CN111241872B (en) | Video image shielding method and device | |
| CN106033601A (en) | Method and apparatus for detecting abnormal situation | |
| CN114120168A (en) | Target running distance measuring and calculating method, system, equipment and storage medium | |
| CN102867172B (en) | A kind of human-eye positioning method, system and electronic equipment | |
| CN112613568A (en) | Target identification method and device based on visible light and infrared multispectral image sequence | |
| CN115103120A (en) | Shooting scene detection method and device, electronic equipment and storage medium | |
| CN114037923A (en) | Target activity hotspot graph drawing method, system, equipment and storage medium | |
| CN109977796A (en) | Trail current detection method and device | |
| CN110177256A (en) | A kind of tracking video data acquisition methods and device | |
| CN112001224A (en) | Video acquisition method and video acquisition system based on convolutional neural network | |
| CN116797961A (en) | Picture acquisition method and device for moving sphere, computer equipment and storage medium | |
| KR20190134916A (en) | Method and apparatus for collecting floating population data on realtime road image | |
| Chiron et al. | Outdoor 3D Acquisition System for Small and Fast Targets. Application to honeybee monitoring at the beehive entrance | |
| CN117058767B (en) | Training field monitoring method, training field monitoring equipment, storage medium and training field monitoring device | |
| CN117934805B (en) | Object screening method and device, storage medium and electronic equipment | |
| WO2023063088A1 (en) | Method, apparatus, system and non-transitory computer readable medium for adaptively adjusting detection area |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Method and Device for Obtaining Tracking Video Data Effective date of registration: 20230713 Granted publication date: 20211214 Pledgee: Bank of Jiangsu Limited by Share Ltd. Beijing branch Pledgor: BEIJING MOVIEBOOK SCIENCE AND TECHNOLOGY Co.,Ltd. Registration number: Y2023110000278 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |