CN108230348A - A kind of method for tracking target and device - Google Patents
A kind of method for tracking target and device Download PDFInfo
- Publication number
- CN108230348A CN108230348A CN201611198905.XA CN201611198905A CN108230348A CN 108230348 A CN108230348 A CN 108230348A CN 201611198905 A CN201611198905 A CN 201611198905A CN 108230348 A CN108230348 A CN 108230348A
- Authority
- CN
- China
- Prior art keywords
- sprite
- target
- panorama
- section
- module
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The embodiment of the invention discloses a kind of method for tracking target and device, method includes：Obtain N number of sprite and its corresponding panorama；The first position of target is determined in panorama；According to first position, the corresponding target sprite of target is determined；According to the second position and the first position in the corresponding panorama of each target sprite, the third place of the target in each target sprite is determined；According to the third place, to the target into line trace in target sprite；That is, this programme is not the position for determining target in each sprite respectively in isolation, in this programme, position of the target in each sprite is interrelated, therefore, when the target is from a sub- screen switching to another sprite, the smoothness of screen switching can be improved.
Description
Technical field
The present invention relates to technical field of video monitoring, more particularly to a kind of method for tracking target and device.
Background technology
During video monitoring, it usually needs to the target that monitors into line trace.Existing tracking scheme is all base
Target in same video flowing picture is into line trace.
At present, multi-track system video stream technology is widely used.Multi-track system video flowing refers to that video flowing is set by more acquisitions
Multiple sub-video streams composition of standby acquisition, in this case, usually by this independent dissection process of multiple sub-video streams progress, and
During broadcasting, to treated, multiple sub-video streams carry out splicing broadcasting.
Target in the video flowing picture played using existing tracking scheme to splicing, can only be right respectively into during line trace
Target in each sub-video stream picture included in the video flowing is into line trace.In this way, when a certain target is regarded in each height
In frequency stream picture when switching over, since this programme is respectively to the target in each sub-video stream picture into line trace, also
It is to say, unrelated to the target following in each sub-video stream picture, therefore, the target is from a sub-video stream screen switching
During to another sub-video stream picture, the smoothness of screen switching is very low.
Invention content
A kind of smoothness for being designed to provide method for tracking target and device, improving between picture of the embodiment of the present invention.
In order to achieve the above objectives, the embodiment of the invention discloses a kind of method for tracking target, including：
Obtain N number of sprite and its corresponding panorama；Wherein, the panorama is N number of sprite splicing
Complete picture that treated, the N are more than 1；
The first position of target is determined in the panorama；
According to the first position, the corresponding target sprite of the target is determined, wherein, it is wrapped in the target sprite
Containing all or part of target；
The second position and the first position in the corresponding panorama of each target sprite determine
The third place of the target in each target sprite；
According to the third place, to the target into line trace in target sprite.
Optionally, described the step of obtaining N number of sprite and its corresponding panorama, can include：
Obtain N number of sprite of N platforms collecting device acquisition；
According to the orientation of the N platforms collecting device, determine in the acquired corresponding panorama of each sprite
The second position；
According to the corresponding second position of each sprite, N number of sprite is spliced, obtains the panorama
Face.
Optionally, described the step of obtaining N number of sprite that N platforms collecting device acquires, can include：
Obtain N number of sub-video stream of N platforms collecting device acquisition；
N number of sub-video stream is decoded and time synchronization, obtains N number of sprite.
Optionally, described according to the first position, the step of determining the target corresponding target sprite, can wrap
It includes：
Determine the aspect ratio that the first position occupies in each sprite；
The sprite that aspect ratio is more than to predetermined threshold value is determined as target sprite.
Optionally, described the step of determining the aspect ratio that the first position occupies in each sprite, can wrap
It includes：
Determine the first width section and the first height section of the corresponding tracking box in the first position；
Determine the second width section and the second height section of each sprite；
For each sprite, the second width section and the first of the first width section of the sprite is determined
Second intersection in the second height section of intersection and the sprite and the first height section；
According to first intersection and second intersection, the picture that the first position occupies in the sprite is determined
Ratio.
Optionally, it is described according to the third place, in target sprite to the target into the step of line trace can
To include：
Panorama displaying is carried out, and in each target sprite, positioned at the third place to the panorama
Target carries out feature displaying.
In order to achieve the above objectives, the embodiment of the invention also discloses a kind of target tracker, including：
Acquisition module, for obtaining N number of sprite and its corresponding panorama；Wherein, the panorama is the N
A sub- picture splicing treated complete picture, the N are more than 1；
First determining module, for determining the first position of target in the panorama；
Second determining module, for according to the first position, determining the corresponding target sprite of the target, wherein,
All or part of target is included in the target sprite；
Third determining module, for the second position in the corresponding panorama of each target sprite and
The first position determines the third place of the target in each target sprite；
Tracking module, for according to the third place, to the target into line trace in target sprite.
Optionally, the acquisition module can include：
Acquisition submodule, for obtaining N number of sprite of N platforms collecting device acquisition；
First determination sub-module for the orientation according to the N platforms collecting device, determines acquired each sprite pair
The second position in the panorama answered；
Splice submodule, for according to the corresponding second position of each sprite, splicing to N number of sprite,
Obtain the panorama.
Optionally, the acquisition submodule, specifically can be used for：
Obtain N number of sub-video stream of N platforms collecting device acquisition；
N number of sub-video stream is decoded and time synchronization, obtains N number of sprite.
Optionally, second determining module, can include：
Second determination sub-module, for determining aspect ratio that the first position occupies in each sprite；
Third determination sub-module, the sprite for aspect ratio to be more than to predetermined threshold value are determined as target sprite.
Optionally, second determination sub-module, specifically can be used for：
Determine the first width section and the first height section of the corresponding tracking box in the first position；
Determine the second width section and the second height section of each sprite；
For each sprite, the second width section and the first of the first width section of the sprite is determined
Second intersection in the second height section of intersection and the sprite and the first height section；
According to first intersection and second intersection, the picture that the first position occupies in the sprite is determined
Ratio.
Optionally, the tracking module, specifically can be used for：
Panorama displaying is carried out, and in each target sprite, positioned at the third place to the panorama
Target carries out feature displaying.
Using illustrated embodiment of the present invention, first position of the target in panorama is combined, each sprite corresponds to
The panorama in the second position, determine the third place of the target in sprite；That is, this programme is not
The position of target is determined in each sprite respectively in isolation, in the present solution, position of the target in each sprite is mutual
Association, therefore, when the target is from a sub- screen switching to another sprite, can improve the smoothness of screen switching.
Certainly, it implements any of the products of the present invention or method must be not necessarily required to reach all the above excellent simultaneously
Point.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of method for tracking target provided in an embodiment of the present invention；
Fig. 2 is a kind of Image Acquisition schematic diagram of a scenario provided in an embodiment of the present invention；
Fig. 3 is a kind of panorama schematic diagram provided in an embodiment of the present invention；
Fig. 4 is the panorama schematic diagram under a kind of coordinate system provided in an embodiment of the present invention；
Fig. 5 is the sprite schematic diagram under a kind of coordinate system provided in an embodiment of the present invention；
Fig. 6 is a kind of structure diagram of target tracker provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
In order to solve the above-mentioned technical problem, an embodiment of the present invention provides a kind of method for tracking target and device, Ke Yiying
For the various electronic equipments such as computer, tablet computer, monitoring device, specifically it is not construed as limiting.The present invention is implemented first below
The method for tracking target that example provides is described in detail.
Fig. 1 is a kind of flow diagram of method for tracking target provided in an embodiment of the present invention, including：
S101：Obtain N number of sprite and its corresponding panorama；Wherein, the panorama is N number of sprite
Complete picture after splicing, the N are more than 1.
More collecting devices is set to carry out Image Acquisition to Same Scene, to realize to the better monitoring effect of the scene.
Here the collected N number of video flowing of N platform collecting devices that Image Acquisition is carried out for Same Scene is known as sub-video stream, it will be sub
Video flowing picture is known as sprite.
This programme can have real-time, the current sprite in this N number of sub-video stream be obtained in real time, in this way, just obtaining
To N number of sprite.The complete picture obtained after this N number of sprite splicing is known as panorama.
It should be noted that equipment of the executive agent of the embodiment of the present invention with this N number of sprite is carried out splicing
It can be identical or different.That is, directly can to obtain this from another equipment N number of for the executive agent of the embodiment of the present invention
The corresponding panorama of sprite.Alternatively, the executive agent of the embodiment of the present invention can also based on acquired N number of sprite into
Row splicing obtains the panorama.
Specifically, the process that this N number of sprite is carried out splicing can include：
Obtain N number of sprite of N platforms collecting device acquisition；According to the orientation of the N platforms collecting device, determine acquired
The second position in the corresponding panorama of each sprite；According to the corresponding second position of each sprite, to the N
A sprite is spliced, and obtains the panorama.
In the present embodiment, in order to distinguish description, position of the target in panorama is known as first position, by sub- picture
Position in the corresponding panorama in face is known as the second position, and position of the target in sprite is known as the third place.
It, can be by this N number of sub- picture during splicing is carried out to N number of sprite as a kind of embodiment
The resolution ratio in face is compressed, in this way, the pressure for the equipment for performing concatenation can be reduced, improves splicing speed, and should
The panorama resolution ratio spliced in this way is relatively low, when being transmitted, playing to panorama, can occupy smaller
Resource.In addition, when being shown to panorama, feature displaying will not be usually carried out, therefore, even if panorama resolution ratio
It is relatively low, practical bandwagon effect will not be caused significantly to influence.
It cites a plain example, it is assumed that as shown in Fig. 2, N is 4, this 4 collecting device rows are into a line to Same Scene
Carry out Image Acquisition.In this 4 collecting devices, the orientation of collecting device 1 is located at the leftmost side, therefore, is spelled in sprite
When connecing, the second position in the 1 corresponding panorama of sprite that collecting device 1 acquires should be the leftmost side, such as the panorama in Fig. 2
Shown in picture, the second position one in the orientation of collecting device panorama corresponding with the sprite that the collecting device acquires
It causes.
According to the position in this corresponding panorama of 4 sprites, using video-splicing technology to this 4 sprites into
Row splicing obtains a complete picture for the scene, that is, the panorama.
As a kind of embodiment, the step of N number of sprite for obtaining the acquisition of N platforms collecting device, can include：
Obtain N number of sub-video stream of N platforms collecting device acquisition；
N number of sub-video stream is decoded and time synchronization, obtains N number of sprite.
The time synchronization determines N number of sub- picture under synchronization it is to be understood that according to the timestamp of each sub-video stream
Face.That is, N number of sprite is the picture for synchronization, Same Scene.
As described above, this programme there can be real-time, N number of current sprite under current time can be obtained in real time.
For the convenience of description, each sprite acquired in S101 is known as original sprite in content below, it will be complete
The corresponding position of original sprite included in scape picture is known as splicing sprite.It is understood that original sprite is with spelling
The image content for connecing sprite is consistent, but the resolution ratio of original sprite can be greater than or equal to the resolution of splicing sprite
Rate." 1 corresponding position of sprite ", " 2 corresponding position of sprite ", " 3 corresponding position of sprite ", " sprite 4 in Fig. 2
Corresponding position " is splicing sprite.
S102：The first position of target is determined in the panorama.
As described above, the panorama is a complete picture, the mode of the position of target is determined in a picture to be had
It is a variety of, such as frame difference method, Gauss modeling, visible ray modeling etc..
S103：According to the first position, the corresponding target sprite of the target is determined.Wherein, target is drawn
All or part of target is included in face.
As a kind of embodiment, can include in this step：
Determine the aspect ratio that the first position occupies in each sprite；
The sprite that aspect ratio is more than to predetermined threshold value is determined as target sprite.
It is understood that the target should be a region in panorama, therefore, which can be the area
The coordinate section in domain, naturally it is also possible to for other, not limit herein.
In the present embodiment, it may be determined that the region first picture area for occupying and every in each splicing sprite
Second picture area of a splicing sprite, is determined as first position by the ratio of the first picture area and the second picture area and exists
The aspect ratio occupied in splicing sprite.
It should be noted that splicing sprite is consistent with the image content of original sprite, therefore, first position is original
The aspect ratio occupied in sprite is consistent with the aspect ratio that first position occupies in sprite is spliced.
Assuming that as shown in figure 3, in panorama, total picture area that the first position of target occupies is 40cm2,
In, the first picture area occupied in " 1 corresponding position of sprite " is 0cm2, accounted in " 2 corresponding position of sprite "
According to the first picture area be 20cm2, the first picture area occupied in " 3 corresponding position of sprite " is 20cm2, in " son
The first picture area that 4 corresponding position of picture " occupies is 0cm2." 1 corresponding position of sprite " in Fig. 3, " sprite 2 is right
The position answered ", " 3 corresponding position of sprite ", " 4 corresponding position of sprite " are splicing sprite.
Assuming that the second picture area of this 4 splicing sprites is identical, it is 400cm2, then in " 1 corresponding position of sprite
Put " in, the ratio of the first picture area and the second picture area is 0, that is, target first position " sprite 1 corresponds to
Position " in the aspect ratio that occupies be 0, that is, the aspect ratio that is occupied in sprite 1 of first position of target is 0.
Similarly, the aspect ratio that the first position of target occupies in sprite 2 is 20/400=0.05, and the first position of target is in son
The aspect ratio occupied in picture 3 is 20/400=0.05, and the aspect ratio that the first position of target occupies in sprite 4 is
0。
Assuming that predetermined threshold value is 0.0001, then sprite 2 and sprite 3 are determined as target sprite.
In the present embodiment, it may be determined that the first width section of the corresponding tracking box in the first position and first high
Spend section；Determine the second width section and the second height section of each sprite；For each sprite, determine
Second width section of the sprite and first intersection in the first width section and the second height section of the sprite
With second intersection in the first height section；According to first intersection and second intersection, the first position is determined
The aspect ratio occupied in the sprite.
It should be noted that above-mentioned width section, height section can be understood as：In a coordinate system, by starting point coordinate value
The coordinate section formed with end coordinate values.Optionally, the first width section is：Tracking box is in the corresponding change in coordinate axis direction of width
On the coordinate section that forms of starting point coordinate value and end coordinate values；First height section is：Tracking box is in the corresponding seat of height
The coordinate section that starting point coordinate value on parameter direction is formed with end coordinate values；Second width section is：Sprite is in width
The coordinate section that starting point coordinate value on corresponding change in coordinate axis direction is formed with end coordinate values；Second height section is：Son is drawn
The coordinate section that starting point coordinate value of the face on the corresponding change in coordinate axis direction of height is formed with end coordinate values.
Continue the example in Fig. 3, understand for convenience, Fig. 3 is placed into the coordinate system where it, as shown in Figure 4.
The corresponding tracking box in first position can be the frame where " target " being interpreted as in Fig. 3 or Fig. 4, it is assumed that the first of the tracking box
Width section is (15,25), and the first height section is (2,6).Assuming that the second width section of " 1 corresponding position of sprite " is
(0,10), the second height section are (0,8)；Assuming that the second width section of " 2 corresponding position of sprite " is (11,20), the
Two height sections are (0,8)；Assuming that the second width section of " 3 corresponding position of sprite " is (21,30), the second height section
For (0,8)；Assuming that the second width section of " 4 corresponding position of sprite " is (31,40), the second height section is (0,8).
Therefore, for " 1 corresponding position of sprite "：Its second width section and the first of the first width section
Intersection is 0, and second intersection in the second height section and the first height section is (2,6)；Since the first intersection is 0, then really
The aspect ratio that the first position to set the goal occupies in " 1 corresponding position of sprite " is 0, that is, the first position of target
The aspect ratio occupied in sprite 1 is 0.
For " 2 corresponding position of sprite "：First intersection in its second width section and the first width section
For (15,20), second intersection in the second height section and the first height section is (2,6)；With reference to the first intersection and second
Intersection, determine aspect ratio that the first position of target occupies in " 2 corresponding position of sprite " for (20-15) * (6-2)/
400=20/400=0.05, that is, the aspect ratio that is occupied in sprite 2 of first position of target is 0.05；
For " 3 corresponding position of sprite "：First intersection in its second width section and the first width section
For (21,25), second intersection in the second height section and the first height section is (2,6)；With reference to the first intersection and second
Intersection, determine aspect ratio that the first position of target occupies in " 3 corresponding position of sprite " for (25-21) * (6-2)/
400=16/400=0.04, that is, the aspect ratio that is occupied in sprite 3 of first position of target is 0.04；
For " 4 corresponding position of sprite "：First intersection in its second width section and the first width section
It is 0, second intersection in the second height section and the first height section is (2,6)；Since the first intersection is 0, it is determined that mesh
The aspect ratio that target first position occupies in " 4 corresponding position of sprite " be 0, that is, target first position in son
The aspect ratio occupied in picture 4 is 0.
Assuming that predetermined threshold value is 0.0001, then sprite 2 and sprite 3 are determined as target sprite.
It should be noted that according to the first position of target, there are many modes that determine the corresponding target sprite of target,
For example, in world coordinate system, the corresponding first coordinate section in first position and each original sprite that determine target correspond to
The second coordinate section, according to the first coordinate section and the second coordinate section with the presence or absence of intersection, determine whether the target occurs
In the original sprite.Alternatively, other modes can also be used, do not limit herein.
S104：The second position and the first position in the corresponding panorama of each target sprite,
Determine the third place of the target in each target sprite.
Continue the example in above-mentioned Fig. 3, sprite 2 and sprite 3 are determined as target sprite.
Fig. 3 is placed into the coordinate system where it, it is known that data are as follows：The corresponding tracking box in first position of target
First width section is (15,25), and the first height section is (2,6), and the second width section of " 2 corresponding position of sprite " is
(11,20), the second height section are (0,8), and the second width section of " 3 corresponding position of sprite " is (21,30), and second is high
It is (0,8) to spend section.
Sprite 2 and sprite 3 in Fig. 4 are the original sprite under local Coordinate System.Below it needs to be determined that target
The third place in sprite 2 and sprite 3.
It is understood using above-mentioned given data：The starting point " 15 " in the first width section is in the second width section of sprite 2
At four, the right side unit of starting point " 11 "；The terminal " 25 " in the first width section is in the terminal in the second width section of sprite 2
At five, the right side unit of " 20 ", that is to say, that the first width section some (21-25) has exceeded the second width section,
This part can not be shown in sprite 2；
The starting point " 2 " in the first height section is in two, the right side unit of the starting point " 0 " in the second height section of sprite 2
Place, the terminal " 6 " in the first height section is at two, the left side unit of the terminal " 8 " in the second height section of sprite 2；
The starting point " 15 " in the first width section is in six, the left side unit of the starting point " 21 " in the second width section of sprite 3
Place, that is to say, that the first width section some (15-20) has exceeded the second width section, this part can not be shown in son
In picture 3；The terminal " 25 " in the first width section is in five, the left side unit of the terminal " 30 " in the second width section of sprite 3
Place；
The starting point " 2 " in the first height section is in two, the right side unit of the starting point " 0 " in the second height section of sprite 3
Place, the terminal " 6 " in the first height section is at two, the left side unit of the terminal " 8 " in the second height section of sprite 3.
Hence, it can be determined that it is as shown in Figure 5 to go out the third place of the target in sprite 2 and sprite 3.
S105：According to the third place, to the target into line trace in target sprite.
As a kind of embodiment, panorama displaying can be carried out, and in each target sprite to the panorama
, positioned at the third place target carry out feature displaying.
That is, panorama and the close up view for target can be shown simultaneously, panorama and details are taken into account.The spy
Picture is write to can be understood as being amplified target or other treated pictures.
Moreover, only target sprite is shown, that is to say, that the sprite of target is not present in N number of sprite
Network and memory source can have been saved without the operation transmitted, decode, played.
Using embodiment illustrated in fig. 1 of the present invention, first position of the target in panorama, each sprite pair are combined
The third place of the target in sprite is determined in the second position in the panorama answered；That is, this programme is not
It is the position for determining target in each sprite respectively in isolation, in the present solution, position of the target in each sprite is mutual
It is associated, therefore, when the target is from a sub- screen switching to another sprite, the smoothness of screen switching can be improved.
Method for tracking target provided in an embodiment of the present invention can also be applied to the feelings there are multiple targets in panorama
Condition.That is, when performing S102, the first position of multiple targets is defined in panorama.In this case, respectively
For each target, S103, S104, S105 are performed, i.e.,：
For each target, according to the first position of the target, the corresponding target sprite of the target is determined, according to each
The first position of the second position and the target in the corresponding panorama of target sprite, determines the target in each target
The third place in sprite；According to the third place, to the target into line trace in target sprite.
Corresponding with above method embodiment, the embodiment of the present invention also provides a kind of target tracker.
Fig. 6 is a kind of structure diagram of target tracker provided in an embodiment of the present invention, including：
Acquisition module 601, for obtaining N number of sprite and its corresponding panorama；Wherein, the panorama is institute
The complete picture after N number of sprite splicing is stated, the N is more than 1；
First determining module 602, for determining the first position of target in the panorama；
Second determining module 603, for according to the first position, determining the corresponding target sprite of the target,
In, all or part of target is included in the target sprite；
Third determining module 604, in the corresponding panorama of each target sprite the second position,
And the first position, determine the third place of the target in each target sprite；
Tracking module 605, for according to the third place, to the target into line trace in target sprite.
In the present embodiment, acquisition module 601 can include：Acquisition submodule, the first determination sub-module and splicing submodule
Block (not shown), wherein,
Acquisition submodule, for obtaining N number of sprite of N platforms collecting device acquisition；
First determination sub-module for the orientation according to the N platforms collecting device, determines acquired each sprite pair
The second position in the panorama answered；
Splice submodule, for according to the corresponding second position of each sprite, splicing to N number of sprite,
Obtain the panorama.
In the present embodiment, the acquisition submodule, specifically can be used for：
Obtain N number of sub-video stream of N platforms collecting device acquisition；
N number of sub-video stream is decoded and time synchronization, obtains N number of sprite.
In the present embodiment, the second determining module 603 can include：Second determination sub-module and third determination sub-module
(not shown), wherein,
Second determination sub-module, for determining aspect ratio that the first position occupies in each sprite；
Third determination sub-module, the sprite for aspect ratio to be more than to predetermined threshold value are determined as target sprite.
In the present embodiment, second determination sub-module, specifically can be used for：
Determine the first width section and the first height section of the corresponding tracking box in the first position；
Determine the second width section and the second height section of each sprite；
For each sprite, the second width section and the first of the first width section of the sprite is determined
Second intersection in the second height section of intersection and the sprite and the first height section；
According to first intersection and second intersection, the picture that the first position occupies in the sprite is determined
Ratio.
In the present embodiment, tracking module 605 specifically can be used for：
Panorama displaying is carried out, and in each target sprite, positioned at the third place to the panorama
Target carries out feature displaying.
Using embodiment illustrated in fig. 6 of the present invention, first position of the target in panorama, each sprite pair are combined
The third place of the target in sprite is determined in the second position in the panorama answered；That is, this programme is not
It is the position for determining target in each sprite respectively in isolation, in the present solution, position of the target in each sprite is mutual
It is associated, therefore, when the target is from a sub- screen switching to another sprite, the smoothness of screen switching can be improved.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any this practical relationship or sequence.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only will including those
Element, but also including other elements that are not explicitly listed or further include as this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
Also there are other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is described using relevant mode, identical similar portion between each embodiment
Point just to refer each other, and the highlights of each of the examples are difference from other examples.Especially for device reality
For applying example, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
One of ordinary skill in the art will appreciate that all or part of step in realization above method embodiment is can
It is completed with instructing relevant hardware by program, the program can be stored in computer read/write memory medium,
The storage medium designated herein obtained, such as：ROM/RAM, magnetic disc, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (12)
1. a kind of method for tracking target, which is characterized in that including：
Obtain N number of sprite and its corresponding panorama；Wherein, the panorama is N number of sprite splicing
Complete picture afterwards, the N are more than 1；
The first position of target is determined in the panorama；
According to the first position, the corresponding target sprite of the target is determined, wherein, comprising complete in the target sprite
Portion or the part target；
The second position and the first position in the corresponding panorama of each target sprite determine described
The third place of the target in each target sprite；
According to the third place, to the target into line trace in target sprite.
2. according to the method described in claim 1, it is characterized in that, the N number of sprite of the acquisition and its corresponding panorama
The step of include：
Obtain N number of sprite of N platforms collecting device acquisition；
According to the orientation of the N platforms collecting device, the in the acquired corresponding panorama of each sprite is determined
Two positions；
According to the corresponding second position of each sprite, N number of sprite is spliced, obtains the panorama.
3. the according to the method described in claim 2, it is characterized in that, N number of sprite for obtaining the acquisition of N platforms collecting devices
Step includes：
Obtain N number of sub-video stream of N platforms collecting device acquisition；
N number of sub-video stream is decoded and time synchronization, obtains N number of sprite.
4. according to the method described in claim 1, it is characterized in that, described according to the first position, the target pair is determined
The step of target sprite answered, includes：
Determine the aspect ratio that the first position occupies in each sprite；
The sprite that aspect ratio is more than to predetermined threshold value is determined as target sprite.
5. according to the method described in claim 4, it is characterized in that, described determine that the first position accounts in each sprite
According to aspect ratio the step of include：
Determine the first width section and the first height section of the corresponding tracking box in the first position；
Determine the second width section and the second height section of each sprite；
For each sprite, determine that the second width section of the sprite is handed over the first of the first width section
Second intersection in the second height section of collection and the sprite and the first height section；
According to first intersection and second intersection, the picture ratio that the first position occupies in the sprite is determined
Example.
6. according to claim 1-5 any one of them methods, which is characterized in that it is described according to the third place, in target
The target was included into the step of line trace in sprite：
Panorama displaying is carried out, and to target in each target sprite, positioned at the third place to the panorama
Carry out feature displaying.
7. a kind of target tracker, which is characterized in that including：
Acquisition module, for obtaining N number of sprite and its corresponding panorama；Wherein, the panorama is N number of son
Picture splicing treated complete picture, the N are more than 1；
First determining module, for determining the first position of target in the panorama；
Second determining module, for according to the first position, determining the corresponding target sprite of the target, wherein, it is described
All or part of target is included in target sprite；
Third determining module, for the second position in the corresponding panorama of each target sprite and described
First position determines the third place of the target in each target sprite；
Tracking module, for according to the third place, to the target into line trace in target sprite.
8. device according to claim 7, which is characterized in that the acquisition module, including：
Acquisition submodule, for obtaining N number of sprite of N platforms collecting device acquisition；
First determination sub-module for the orientation according to the N platforms collecting device, determines that acquired each sprite is corresponding
The second position in the panorama；
Splice submodule, for according to the corresponding second position of each sprite, splicing to N number of sprite, obtaining
The panorama.
9. device according to claim 8, which is characterized in that the acquisition submodule is specifically used for：
Obtain N number of sub-video stream of N platforms collecting device acquisition；
N number of sub-video stream is decoded and time synchronization, obtains N number of sprite.
10. device according to claim 7, which is characterized in that second determining module, including：
Second determination sub-module, for determining aspect ratio that the first position occupies in each sprite；
Third determination sub-module, the sprite for aspect ratio to be more than to predetermined threshold value are determined as target sprite.
11. device according to claim 10, which is characterized in that second determination sub-module is specifically used for：
Determine the first width section and the first height section of the corresponding tracking box in the first position；
Determine the second width section and the second height section of each sprite；
For each sprite, determine that the second width section of the sprite is handed over the first of the first width section
Second intersection in the second height section of collection and the sprite and the first height section；
According to first intersection and second intersection, the picture ratio that the first position occupies in the sprite is determined
Example.
12. according to claim 6-11 any one of them devices, which is characterized in that the tracking module is specifically used for：
Panorama displaying is carried out, and to target in each target sprite, positioned at the third place to the panorama
Carry out feature displaying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611198905.XA CN108230348B (en) | 2016-12-22 | 2016-12-22 | Target tracking method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611198905.XA CN108230348B (en) | 2016-12-22 | 2016-12-22 | Target tracking method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108230348A true CN108230348A (en) | 2018-06-29 |
| CN108230348B CN108230348B (en) | 2022-01-21 |
Family
ID=62656161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611198905.XA Active CN108230348B (en) | 2016-12-22 | 2016-12-22 | Target tracking method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108230348B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080118107A1 (en) * | 2006-11-20 | 2008-05-22 | Rexee, Inc. | Method of Performing Motion-Based Object Extraction and Tracking in Video |
| CN103716594A (en) * | 2014-01-08 | 2014-04-09 | 深圳英飞拓科技股份有限公司 | Panorama splicing linkage method and device based on moving target detecting |
| CN103761514A (en) * | 2014-01-26 | 2014-04-30 | 公安部第三研究所 | System and method for achieving face recognition based on wide-angle gun camera and multiple dome cameras |
| CN103795978A (en) * | 2014-01-15 | 2014-05-14 | 浙江宇视科技有限公司 | Multi-image intelligent identification method and device |
| CN104268887A (en) * | 2014-09-30 | 2015-01-07 | 深圳市科松电子有限公司 | Method and device used for calibrating gestures of camera and suitable for multi-scene switching |
| CN104378582A (en) * | 2013-08-16 | 2015-02-25 | 北京博思廷科技有限公司 | Intelligent video analysis system and method based on PTZ video camera cruising |
| CN104660998A (en) * | 2015-02-16 | 2015-05-27 | 苏州阔地网络科技有限公司 | Relay tracking method and system |
| CN105407283A (en) * | 2015-11-20 | 2016-03-16 | 成都因纳伟盛科技股份有限公司 | Multi-target active recognition tracking and monitoring method |
-
2016
- 2016-12-22 CN CN201611198905.XA patent/CN108230348B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080118107A1 (en) * | 2006-11-20 | 2008-05-22 | Rexee, Inc. | Method of Performing Motion-Based Object Extraction and Tracking in Video |
| CN104378582A (en) * | 2013-08-16 | 2015-02-25 | 北京博思廷科技有限公司 | Intelligent video analysis system and method based on PTZ video camera cruising |
| CN103716594A (en) * | 2014-01-08 | 2014-04-09 | 深圳英飞拓科技股份有限公司 | Panorama splicing linkage method and device based on moving target detecting |
| CN103795978A (en) * | 2014-01-15 | 2014-05-14 | 浙江宇视科技有限公司 | Multi-image intelligent identification method and device |
| CN103761514A (en) * | 2014-01-26 | 2014-04-30 | 公安部第三研究所 | System and method for achieving face recognition based on wide-angle gun camera and multiple dome cameras |
| CN104268887A (en) * | 2014-09-30 | 2015-01-07 | 深圳市科松电子有限公司 | Method and device used for calibrating gestures of camera and suitable for multi-scene switching |
| CN104660998A (en) * | 2015-02-16 | 2015-05-27 | 苏州阔地网络科技有限公司 | Relay tracking method and system |
| CN105407283A (en) * | 2015-11-20 | 2016-03-16 | 成都因纳伟盛科技股份有限公司 | Multi-target active recognition tracking and monitoring method |
Non-Patent Citations (2)
| Title |
|---|
| OMAR JAVED ET AL.: "KNIGHTM: A REAL TIME SURVEILLANCE SYSTEM FOR MULTIPLE OVERLAPPING AND NON-OVERLAPPING CAMERAS", 《ICME 2003》 * |
| 孙超: "黑夜给了我"鹰"的眼睛我要用它看清世界—走进海康威视"鹰眼"视界", 《中国安防》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108230348B (en) | 2022-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104010225B (en) | The method and system of display panoramic video | |
| US8495697B1 (en) | Techniques to provide an enhanced video replay | |
| WO2019192509A1 (en) | Media data processing method and apparatus | |
| CN102215375B (en) | The system of selection of the video source of the sprite of more pictures and device in multimedia conferencing | |
| CN108882038A (en) | A kind of multi-channel video playback method based on Android | |
| CN103248941B (en) | A kind of method of multi-channel video source simultaneous display and device | |
| CN108449553A (en) | Instructor in broadcasting's control system and signal processing method | |
| CN102629460A (en) | Method and apparatus for controlling frame frequency of liquid crystal display | |
| CN108040277A (en) | For the subtitle switching method and device of the multi-language captions obtained after decoding | |
| CN108769824A (en) | A kind of video mixed flow method, apparatus, system, equipment and medium | |
| CN105430471A (en) | Method and device for displaying live commenting in video | |
| CN104936030B (en) | A kind of boot-strap menu display process, equipment and array terminal system | |
| CN106375835B (en) | A kind of flow media playing method and equipment | |
| CN106658030A (en) | Method and device for playing composite video comprising single-path audio and multipath videos | |
| CN109753145B (en) | Transition animation display method and related device | |
| CN111279687A (en) | Video subtitle processing method and director system | |
| CN107333144A (en) | Multichannel picture display process and device based on football race broadcast relay system | |
| CN106961624B (en) | A kind of video switching method, apparatus and system | |
| CN113014943A (en) | Video playing method, video player and video live broadcasting system | |
| CN107864393A (en) | The method and device that video is shown with captioning synchronization | |
| CN107317960A (en) | Video image acquisition methods and acquisition device | |
| CN104994429B (en) | A kind of method and device playing video | |
| CN109922230A (en) | Synchronous broadcast method, control method for playing back and the device of dynamic content | |
| CN115380539B (en) | Apparatus and system for processing video | |
| JP2013205821A (en) | Video display apparatus, method and program for multi-display 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |