CN106709957B - Method and system, the intelligent electronic device of polyphaser observed object - Google Patents
Method and system, the intelligent electronic device of polyphaser observed object Download PDFInfo
- Publication number
- CN106709957B CN106709957B CN201611258454.4A CN201611258454A CN106709957B CN 106709957 B CN106709957 B CN 106709957B CN 201611258454 A CN201611258454 A CN 201611258454A CN 106709957 B CN106709957 B CN 106709957B
- Authority
- CN
- China
- Prior art keywords
- camera
- target
- result
- amendment
- observed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses the method for polyphaser observed object, the system of polyphaser observed object and intelligent electronic devices.The method of the polyphaser observed object includes: the initial target observed result for obtaining each camera, and the initial target observed result of the camera is that the position of target that target detection obtains in the picture is carried out by the image shot to camera;Amendment is iterated to the target observation result of camera, until the target observation result of whole cameras meets uniform condition.The method of polyphaser observed object provided by the invention improves the consistency of multiple camera observed objects.
Description
Technical field
The present invention relates to polyphaser observation technologies, observe more particularly, to the method for polyphaser observed object, polyphaser
The system and intelligent electronic device of target.
Background technique
The research field that polyphaser observation technology is related to includes the fields such as data fusion, pattern-recognition.Polyphaser observes skill
Target location base technology of the art as multiple-camera can be applied to indoor virtual virtual reality device (handle, wearable biography
Sensor etc.) the scenes such as locating and tracking, robot localization.
In polyphaser observation technology, handles low-density Multi-target position and tracking problem has obtained considerable progress, but
Problems are still had for the positioning of high density target.Main problem includes target is blocked or target and target by other objects
Between block mutually cause detection error, target and target it is close to each other caused by target labels are chaotic, the throwing between polyphaser
Shadow error etc..A consequence caused by these problems is that same target is different in certain two or more magazine observed result
It causes, i.e., the observed result from different cameral cannot converge at a bit in the projection of same reference planes (such as ground level).Mesh
It includes characteristic matching, Epipolar geometric constraint, to target same in different cameral that preceding solution polyphaser, which observes inconsistent main method,
Appearance model etc..
Summary of the invention
The purpose of the present invention is to provide a kind of polyphaser observation technologies, observe the consistent of same target to improve polyphaser
Property.
According to the first aspect of the invention, a kind of method of polyphaser observed object is provided, comprising the following steps:
The initial target observed result of each camera is obtained, the initial target observed result of the camera is by camera
The position of the target that the image progress target detection of shooting obtains in the picture;
According to formulaTo the target observation knot of camera
Fruit is iterated amendment, until the target observation result of whole cameras meets uniform condition;
Wherein, 1≤i≤N, N are camera total number, and i represents i-th of camera, and j represents j-th of camera, i ≠ j, k >=1;The kth time revised target observation of i-th of camera as a result,It is kth -1 time amendment of i-th of camera
Rear target observation as a result,It is the mapping relations according to j-th of camera and i-th of camera, by j-th camera
Kth -1 time revised target observation result be mapped to the target observation obtained on i-th of camera as a result,It is i-th of phase
The initial target observed result of machine, ωj→iIt is j-th of camera to the amendment weight of i-th of camera, ε is convergence coefficient;
The uniform condition isξ is the threshold value of setting.
Optionally, the initial target observed result shows as the coordinate of the bottom edge central point of detection rectangle frame.
Optionally, amendment weights omega of j-th of the camera to i-th of cameraj→iIt is to calculate to obtain in the following manner:
According toJ-th of camera is calculated to the amendment Feasible degree H of i-th of cameraj→i, wherein Pj→iIt is j-th
The similarity of the grey level histogram of the image of the grey level histogram and i-th of camera shooting of the image of camera shooting, QjIt is j-th
The degree that target is blocked in the image of camera shooting;
Calculate other each cameras in addition to i-th of camera to the amendment Feasible degree of i-th of camera and value H;
According to ωj→i=Hj→i/ H calculates j-th of camera to the amendment weights omega of i-th of cameraj→i。
It optionally, further include using between camera before the target observation result to each camera is iterated amendment
Mapping relations from the initial target observed result of spatially debug the step of.
According to the second aspect of the invention, a kind of intelligent electronic device, including processor and memory are provided;
For storing instruction, described instruction is operated for controlling the processor to execute according to power the memory
The method that benefit requires the described in any item polyphaser observed objects of 1-4.
According to the third aspect of the invention we, a kind of system of polyphaser observed object is provided, is comprised the following modules:
Initial target observed result obtains module, for obtaining the initial target observed result of each camera, the camera
Initial target observed result be that the position of target that target detection obtains in the picture is carried out by the image that shoots to camera;
Target observation modified result module, for according to formulaAmendment is iterated to the target observation result of camera,
Until the target observation result of whole cameras meets uniform condition;
Wherein, 1≤i≤N, N are camera total number, and i represents i-th of camera, and j represents j-th of camera, i ≠ j, k >=1;The kth time revised target observation of i-th of camera as a result,It is kth -1 time amendment of i-th of camera
Rear target observation as a result,It is the mapping relations according to j-th of camera and i-th of camera, by j-th camera
Kth -1 time revised target observation result be mapped to the target observation obtained on i-th of camera as a result,It is i-th of phase
The initial target observed result of machine, ωj→iIt is j-th of camera to the amendment weight of i-th of camera, ε is convergence coefficient;
The uniform condition isξ is the threshold value of setting.
Optionally, the initial target observed result shows as the coordinate of the bottom edge central point of detection rectangle frame.
Optionally, the system also includes amendment weight calculation modules;
The amendment weight calculation module, for according toCalculate amendment of j-th of camera to i-th of camera
Feasible degree Hj→i, wherein Pj→iBe j-th of camera shooting image grey level histogram and i-th of camera shoot image ash
Spend the similarity of histogram, QjIt is the degree that target is blocked in the image of j-th of camera shooting;Calculate except i-th camera it
Outer other each cameras to the amendment Feasible degree of i-th camera and value H;According to ωj→i=Hj→i/ H calculates j-th of phase
Amendment weights omega of the machine to i-th of cameraj→i。
Optionally, the system also includes initial target observed result preprocessing modules;
The initial target observed result preprocessing module, for being modified in the target observation modified result module
Before, using the mapping relations between camera from the initial target observed result of spatially debug.
The technical solution of polyphaser observed object provided by the invention corrects target observation knot using weighting unification algorism
Fruit improves the consistency of multiple camera observed objects.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described.It should be appreciated that the following drawings illustrates only certain embodiments of the present invention, therefore it is not construed as pair
The restriction of range.It for those of ordinary skill in the art, without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows the flow diagram of the method for polyphaser observed object provided in an embodiment of the present invention.
Fig. 2 shows another embodiment of the present invention provides polyphaser observed object method flow diagram.
Fig. 3 shows the block diagram of the system of polyphaser observed object provided in an embodiment of the present invention.
Fig. 4 show another embodiment of the present invention provides polyphaser observed object system block diagram.
Fig. 5 shows the block diagram of the hardware configuration of intelligent electronic device provided in an embodiment of the present invention.
Specific embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of invention.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the present invention
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
Illustrate the method for polyphaser observed object provided in an embodiment of the present invention with reference to Fig. 1, comprising the following steps:
101, the initial target observed result of each camera is obtained, the initial target observed result of the camera is by right
The position of the target that the image progress target detection of camera shooting obtains in the picture.
In one embodiment, the initial target observed result shows as the seat of the bottom edge central point of detection rectangle frame
Mark.Target detection is carried out to the image of camera shooting and obtains the position of target in the picture, such as carries out target detection and draws
The detection rectangle frame for representing target out obtains the coordinate of the bottom edge central point of detection rectangle frame, with the bottom edge central point of rectangle frame
Position of the coordinate as target in the picture.The obtained target of target detection is carried out in the picture to the image of camera shooting
Position is technology commonly used in the art, and which is not described herein again.
102, according to the first formulaTo the mesh of camera
Mark observed result is iterated amendment, until the target observation result of whole cameras meets uniform condition;
Wherein, 1≤i≤N, N are camera total number, and i represents i-th of camera, and j represents j-th of camera, i ≠ j, k >=1;The kth time revised target observation of i-th of camera as a result,It is after kth -1 time of i-th of camera is corrected
Target observation as a result,It is the mapping relations according to j-th of camera and i-th of camera, by the of j-th camera
K-1 revised target observation result be mapped to the target observation obtained on i-th of camera as a result,It is i-th of camera
Initial target observed result, ωj→iIt is j-th of camera to the amendment weight of i-th of camera, ε is convergence coefficient, and ε is that experience is normal
Number, those skilled in the art can set according to practical application request.
The uniform condition isξ is the threshold value of setting, and ξ can be set according to actual needs
It is fixed.
Mapping relations between camera and another camera are homography matrix.
The main reason for inconsistency of the observed result of same target is the mapping error and camera itself between camera
Target detection error, wherein mapping error is caused since the mapping relations (homography matrix) between camera are not accurate enough,
Target detection error may be blocked due to target by other objects or the target is blocked mutually with other targets causes, it is also possible to
It is since the inaccuracy of detection algorithm causes.
J-th of camera can be calculated in the following manner to the amendment weights omega of i-th of cameraj→i:
(a) according toJ-th of camera is calculated to the amendment Feasible degree H of i-th of cameraj→i, wherein Pj→iIt is
The similarity of the grey level histogram of the image of the grey level histogram and i-th of camera shooting of the image of j camera shooting, QjIt is
The degree that target is blocked in the image of j camera shooting;
(b) calculate other each cameras in addition to i-th of camera to the amendment Feasible degree of i-th of camera and value H;
(c) according to ωj→i=Hj→i/ H calculates j-th of camera to the amendment weights omega of i-th of cameraj→i。
Hj→iIt is amendment Feasible degree of j-th of camera to i-th of camera, calculates Hj→iWhen from degree of blocking and grey level histogram
Two dimensions are measured, degree of blocking QjIt is bigger, illustrate that the object sensing result of j-th of camera may be more inaccurate, j-th of phase
Machine is smaller to the amendment Feasible degree of i-th of camera;Grey level histogram similarity Pj→iIt is bigger, illustrate the object sensing of j-th of camera
As a result more credible for i-th of camera, j-th of camera is bigger to the amendment Feasible degree of i-th of camera, in this way
It is comprehensive to measure j-th of camera to the amendment Feasible degree of i-th of camera.ωj→i=Hj→i/ H is equivalent to other each cameras to
The amendment Feasible degree of i camera has carried out normalized, so thatIt is other each i.e. in addition to i-th of camera
A camera to the amendment weight of i-th of camera and value be 1.
In step 102, ε control convergence speed, ε is bigger, and convergence rate is bigger.In kth time iteration, i-th of camera transmitting
Kth -1 time revised target observation result gives other each cameras, while also receiving kth -1 time from other each cameras
Revised target observation result.
Kth -1 time revised target observation result of other each cameras in addition to i-th of camera is mapped to i-th
On a camera, kth -1 time revised target observation result for obtaining other each cameras in addition to i-th of camera is mapped to
Target observation result on i-th of camera.It is revised using kth -1 time of other each cameras in addition to i-th of camera
The target observation that target observation result is mapped on i-th of camera is as a result, go the target observation result of i-th of camera of amendment.
Such as: one, which shares three cameras, is observed same target, then:
For First camera, the expansion of the first formula are as follows:
For second camera, the expansion of the first formula are as follows:
For third platform camera, the expansion of the first formula are as follows:
According to the first formula (1), the first formula (2), the first formula (3) of above-mentioned expansion respectively to the target of three cameras
Observed result is iterated amendment, until the target observation result of first camera meetsAnd the
The target observation result of two cameras meetsAnd the target observation result of third camera meetsI.e. whole cameras all meetThen think the observed result of whole cameras
Meet consistency.
The method of polyphaser observed object of the invention is iterated amendment to target observation result using unification algorism,
The projection information between different cameral is merged, until the target observation result of whole cameras meets uniform condition, is improved
The consistency of polyphaser observed object.Optionally, the present invention is iterated processing to the initial target observed result of polyphaser, from
The multiple dimensions of degree of blocking, gray scale are modified detection algorithm, alleviate detection algorithm and bring mistake, optimize target labels
Consistency provides good data input for the processing of subsequent target.
With reference to Fig. 2 illustrate another embodiment of the present invention provides polyphaser observed object method, comprising the following steps:
201, the image of each camera shooting is inputted.
202, the image of each camera shooting is detected, obtains the initial target observed result of each camera.
203, initial target observed result is pre-processed.
204, target observation result is further corrected with unification algorism.
As can be seen that this embodiment and previous implementation are very similar, the main distinction is, this embodiment is to initial
Target observation result is pre-processed, and the pretreatment refers to using the mapping relations between camera from spatially debug
Initial target observed result.The essence of this process is, the initial target observed result of each camera can be mapped to
In same reference planes (such as screen plane of ground level or some camera), easily can spatially it exclude not
Possible initial target observed result.
It to those skilled in the art, can be real by way of hardware mode, software mode or software and hardware combining
The method of existing forgoing multiphase machine observed object.Based on the same inventive concept, the more of the embodiment of the present invention are introduced with reference to Fig. 3 and Fig. 4
The system of camera observed object, the method to execute forgoing multiphase machine observed object.
The system for illustrating polyphaser observed object provided in an embodiment of the present invention with reference to Fig. 3, comprises the following modules:
Initial target observed result obtains module 11, for obtaining the initial target observed result of each camera, the phase
The initial target observed result of machine is that the position of target that target detection obtains in the picture is carried out by the image that shoots to camera
It sets;
Target observation modified result module 12, for according to formulaAmendment is iterated to the target observation result of camera,
Until the target observation result of whole cameras meets uniform condition;
Wherein, 1≤i≤N, N are camera total number, and i represents i-th of camera, and j represents j-th of camera, i ≠ j, k >=1;The kth time revised target observation of i-th of camera as a result,It is kth -1 time amendment of i-th of camera
Rear target observation as a result,It is the mapping relations according to j-th of camera and i-th of camera, by j-th camera
Kth -1 time revised target observation result be mapped to the target observation obtained on i-th of camera as a result,It is i-th of phase
The initial target observed result of machine, ωj→iIt is j-th of camera to the amendment weight of i-th of camera, ε is convergence coefficient;
The uniform condition isξ is the threshold value of setting.
Optionally, the initial target observed result shows as the coordinate of the bottom edge central point of detection rectangle frame.
With reference to Fig. 4 illustrate another embodiment of the present invention provides polyphaser observed object system, comprise the following modules:
Initial target observed result obtains module 21, for obtaining the initial target observed result of each camera, the phase
The initial target observed result of machine is that the position of target that target detection obtains in the picture is carried out by the image that shoots to camera
It sets.
Initial target observed result preprocessing module 22, for being modified it in the target observation modified result module
Before, using the mapping relations between camera from the initial target observed result of spatially debug.
Correct weight calculation module 24, for according toCalculating j-th of camera can to the amendment of i-th of camera
Row degree Hj→i, wherein Pj→iBe j-th of camera shooting image grey level histogram and i-th of camera shoot image gray scale
The similarity of histogram, QjIt is the degree that target is blocked in the image of j-th of camera shooting;It calculates in addition to i-th of camera
Other each cameras to the amendment Feasible degree of i-th camera and value H;According to ωj→i=Hj→i/ H calculates j-th of camera
To the amendment weights omega of i-th of cameraj→i。
Target observation modified result module 23, for according to formulaAmendment is iterated to the target observation result of camera,
Until the target observation result of whole cameras meets uniform condition;
Wherein, 1≤i≤N, N are camera total number, and i represents i-th of camera, and j represents j-th of camera, i ≠ j, k >=1;The kth time revised target observation of i-th of camera as a result,It is after kth -1 time of i-th of camera is corrected
Target observation as a result,It is the mapping relations according to j-th of camera and i-th of camera, by the of j-th camera
K-1 revised target observation result be mapped to the target observation obtained on i-th of camera as a result,It is i-th of camera
Initial target observed result, ωj→iIt is j-th of camera to the amendment weight of i-th of camera, ε is convergence coefficient;
The uniform condition isξ is the threshold value of setting.
Optionally, the initial target observed result shows as the coordinate of the bottom edge central point of detection rectangle frame.
Fig. 5 is the frame for showing the example of hardware configuration for the intelligent electronic device that can be used for realizing the embodiment of the present invention
Figure.Intelligent electronic device 300 includes processor 3010, memory 3020, interface arrangement 3030, communication device 3040, display dress
Set 3050, input unit 3060, loudspeaker 3070, microphone 3080, etc..
For storing instruction, described instruction is operated for control processor 3010 to execute before memory 3020
The method for stating described in any item polyphaser observed objects.
Processor 3010 is such as can be central processor CPU, Micro-processor MCV.Memory 3020 is for example including ROM
(read-only memory), RAM (random access memory), the nonvolatile memory of hard disk etc..Interface arrangement 3030 is for example
Including USB interface, earphone interface etc..Communication device 3040 is for example able to carry out wired or wireless communication.Display device 3050
Liquid crystal display, touch display screen in this way etc..Input unit 3060 is such as may include touch screen, keyboard.User can lead to
Cross 3080 inputting/outputting voice information of loudspeaker 3070 and microphone.
Intelligent electronic device shown in fig. 5 is only explanatory, and never be intended to limitation the present invention, its application or
Purposes.It will be appreciated by those skilled in the art that although multiple devices are shown in FIG. 5, the present invention can only relate to it
In partial devices.How those skilled in the art disclosed conceptual design instruction, instruction can control processing according to the present invention
It is techniques well known that device, which carries out operation, therefore is not described in detail herein.
The technical solution of polyphaser observed object of the invention, is iterated target observation result using unification algorism and repairs
Just, projection information of the fusion between different cameral improves until the target observation result of whole cameras meets uniform condition
The consistency of polyphaser observed object.Optionally, the present invention is iterated processing to the initial target observed result of polyphaser,
Detection algorithm is modified from degree of blocking, gray scale multiple dimensions, detection algorithm is alleviated and brings mistake, optimize target mark
Consistency is signed, provides good data input for the processing of subsequent target.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
But it will be clear for those skilled in the art that the various embodiments described above, which can according to need exclusive use or be combined with each other, to be made
With.In addition, for device embodiment, since it is corresponding with embodiment of the method, so describe fairly simple, it is related
Place referring to the corresponding part of embodiment of the method explanation.System embodiment described above is only schematical,
Wherein module can be or can also be and is not physically separated as illustrated by the separation member.
In addition, the flow chart and block diagram in the drawings show system, method and the meters of multiple embodiments according to the present invention
The architecture, function and operation in the cards of calculation machine program product.In this regard, each box in flowchart or block diagram
Can represent a part of a module, section or code, a part of the module, section or code include one or
Multiple executable instructions for implementing the specified logical function.It should also be noted that in some implementations as replacements, box
Middle marked function can also occur in a different order than that indicated in the drawings.For example, two continuous boxes are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of function or movement as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Computer program product provided by the embodiment of the present invention, the computer-readable storage including storing program code
Medium, the instruction that said program code includes can be used for executing previous methods method as described in the examples, and specific implementation can be joined
See embodiment of the method, details are not described herein.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.The apparatus embodiments described above are merely exemplary, for example, the division of the unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, in another example, multiple units or components can
To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for
The mutual coupling, direct-coupling or communication connection of opinion can be through some communication interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should be noted that, in this document, 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 actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for 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
There is also other identical elements in process, method, article or equipment including the element.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
Although some specific embodiments of the invention are described in detail by example, the skill of this field
Art personnel it should be understood that example above merely to being illustrated, the range being not intended to be limiting of the invention.The skill of this field
Art personnel are it should be understood that can without departing from the scope of the invention modify to above embodiments.Model of the invention
It encloses and is defined by the following claims.
Claims (9)
1. a kind of method of polyphaser observed object, which comprises the following steps:
The initial target observed result of each camera is obtained, the initial target observed result of the camera is by shooting to camera
Image carry out the position of the obtained target of target detection in the picture;
According to formulaTo the target observation result of camera into
Row iteration amendment, until the target observation result of whole cameras meets uniform condition;
Wherein, 1≤i≤N, 1≤j≤N, N are camera total number, and i represents i-th of camera, and j represents j-th of camera, i ≠ j, k >=
1;The kth time revised target observation of i-th of camera as a result,It is that kth -1 time of i-th of camera is repaired
Target observation after just as a result,It is the mapping relations according to j-th of camera and i-th of camera, by j-th of camera
Kth -1 time revised target observation result be mapped to the target observation obtained on i-th of camera as a result,It is i-th
The initial target observed result of camera, ωj→iIt is j-th of camera to the amendment weight of i-th of camera, ε is convergence coefficient;
The uniform condition isξ is the threshold value of setting.
2. the method according to claim 1, wherein the initial target observed result shows as detection rectangle frame
Bottom edge central point coordinate, wherein the detection rectangle frame is for representing the target.
3. the method according to claim 1, wherein amendment weight of j-th of the camera to i-th of camera
ωj→iIt is to calculate to obtain in the following manner:
According toJ-th of camera is calculated to the amendment Feasible degree H of i-th of cameraj→i, wherein Pj→iIt is j-th of camera
The similarity of the grey level histogram of the grey level histogram of the image of shooting and the image of i-th of camera shooting, QjIt is j-th of camera
The degree that target is blocked in the image of shooting;
Calculate other each cameras in addition to i-th of camera to the amendment Feasible degree of i-th of camera and value H;
According to ωj→i=Hj→i/ H calculates j-th of camera to the amendment weights omega of i-th of cameraj→i。
4. being repaired the method according to claim 1, wherein being iterated in the target observation result to each camera
Before just, further include the steps that the initial target observed result using the mapping relations between camera from spatially debug.
5. a kind of intelligent electronic device, which is characterized in that including processor and memory;
For storing instruction, described instruction is operated for controlling the processor to execute and be wanted according to right the memory
The method for seeking the described in any item polyphaser observed objects of 1-4.
6. a kind of system of polyphaser observed object, which is characterized in that comprise the following modules:
Initial target observed result obtains module, for obtaining the initial target observed result of each camera, the camera just
Beginning target observation is the result is that carry out the position of target that target detection obtains in the picture by the image that shoots to camera;
Target observation modified result module, for according to formula
Amendment is iterated to the target observation result of camera, until the target observation result of whole cameras meets uniform condition;
Wherein, 1≤i≤N, 1≤j≤N, N are camera total number, and i represents i-th of camera, and j represents j-th of camera, i ≠ j, k >=
1;The kth time revised target observation of i-th of camera as a result,It is kth -1 time amendment of i-th of camera
Rear target observation as a result,It is the mapping relations according to j-th of camera and i-th of camera, by j-th camera
Kth -1 time revised target observation result be mapped to the target observation obtained on i-th of camera as a result,It is i-th of phase
The initial target observed result of machine, ωj→iIt is j-th of camera to the amendment weight of i-th of camera, ε is convergence coefficient;
The uniform condition isξ is the threshold value of setting.
7. system according to claim 6, which is characterized in that the initial target observed result shows as detection rectangle frame
Bottom edge central point coordinate, wherein the detection rectangle frame is for representing the target.
8. system according to claim 6, which is characterized in that the system also includes amendment weight calculation modules;
The amendment weight calculation module, for according toIt is feasible to the amendment of i-th of camera to calculate j-th of camera
Spend Hj→i, wherein Pj→iIt is that the grey level histogram of the image of j-th of camera shooting and the gray scale of image that i-th of camera is shot are straight
The similarity of square figure, QjIt is the degree that target is blocked in the image of j-th of camera shooting;It calculates in addition to i-th of camera
Other each cameras to the amendment Feasible degree of i-th camera and value H;According to ωj→i=Hj→i/ H calculates j-th of camera pair
The amendment weights omega of i-th of cameraj→i。
9. system according to claim 6, which is characterized in that the system also includes the pretreatments of initial target observed result
Module;
The initial target observed result preprocessing module, for being modified it in the target observation modified result module
Before, using the mapping relations between camera from the initial target observed result of spatially debug.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611258454.4A CN106709957B (en) | 2016-12-30 | 2016-12-30 | Method and system, the intelligent electronic device of polyphaser observed object |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611258454.4A CN106709957B (en) | 2016-12-30 | 2016-12-30 | Method and system, the intelligent electronic device of polyphaser observed object |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106709957A CN106709957A (en) | 2017-05-24 |
CN106709957B true CN106709957B (en) | 2019-09-17 |
Family
ID=58905532
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611258454.4A Active CN106709957B (en) | 2016-12-30 | 2016-12-30 | Method and system, the intelligent electronic device of polyphaser observed object |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106709957B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111062313A (en) * | 2019-12-13 | 2020-04-24 | 歌尔股份有限公司 | Image identification method, image identification device, monitoring system and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008153721A1 (en) * | 2007-05-29 | 2008-12-18 | Cognex Corporation | System and method for locating a three-dimensional object using machine vison |
CN102831385A (en) * | 2011-06-13 | 2012-12-19 | 索尼公司 | Device and method for target identification in multiple-camera monitoring network |
CN103557841A (en) * | 2013-08-28 | 2014-02-05 | 陈天恩 | Method for improving photogrammetric precision of multi-camera resultant image |
-
2016
- 2016-12-30 CN CN201611258454.4A patent/CN106709957B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008153721A1 (en) * | 2007-05-29 | 2008-12-18 | Cognex Corporation | System and method for locating a three-dimensional object using machine vison |
CN102831385A (en) * | 2011-06-13 | 2012-12-19 | 索尼公司 | Device and method for target identification in multiple-camera monitoring network |
CN103557841A (en) * | 2013-08-28 | 2014-02-05 | 陈天恩 | Method for improving photogrammetric precision of multi-camera resultant image |
Also Published As
Publication number | Publication date |
---|---|
CN106709957A (en) | 2017-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11379287B2 (en) | System and method for error detection and correction in virtual reality and augmented reality environments | |
US11394872B2 (en) | Method and apparatus for jointly calibrating external parameters of multiple cameras, device and medium | |
US11199414B2 (en) | Method for simultaneous localization and mapping | |
Gordon et al. | What and where: 3D object recognition with accurate pose | |
CN109325978B (en) | Augmented reality display method, and attitude information determination method and apparatus | |
Castle et al. | Combining monoSLAM with object recognition for scene augmentation using a wearable camera | |
CN109791608A (en) | Mapping abstract and localization | |
CN110133582A (en) | Distortion in compensation electromagnetic tracking system | |
US20210110576A1 (en) | 3-dimensional reconstruction method, 3-dimensional reconstruction device, and storage medium | |
US10573050B1 (en) | Marker-based pose estimation | |
JP2012128661A (en) | Information processor, information processing method and program | |
CN112258567A (en) | Visual positioning method and device for object grabbing point, storage medium and electronic equipment | |
WO2021051526A1 (en) | Multi-view 3d human pose estimation method and related apparatus | |
CN112184757A (en) | Method and device for determining motion trail, storage medium and electronic device | |
CN111612852A (en) | Method and apparatus for verifying camera parameters | |
CN115131437A (en) | Pose estimation method, and training method, device, equipment and medium of relevant model | |
CN106709957B (en) | Method and system, the intelligent electronic device of polyphaser observed object | |
CN108734735A (en) | Object shapes tracks of device and method and image processing system | |
US11758100B2 (en) | Portable projection mapping device and projection mapping system | |
Cerveri et al. | Combined evolution strategies for dynamic calibration of video-based measurement systems | |
Kim et al. | Implementation of an omnidirectional human motion capture system using multiple kinect sensors | |
Hedborg et al. | Robust three-view triangulation done fast | |
KR102300500B1 (en) | Method, device and system for processing three-dimensional cut image of product | |
Holtz et al. | Automatic extrinsic calibration of depth sensors with ambiguous environments and restricted motion | |
Jiang et al. | Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |