CN105976366A - Method and device for target loop positioning - Google Patents
Method and device for target loop positioning Download PDFInfo
- Publication number
- CN105976366A CN105976366A CN201610283414.9A CN201610283414A CN105976366A CN 105976366 A CN105976366 A CN 105976366A CN 201610283414 A CN201610283414 A CN 201610283414A CN 105976366 A CN105976366 A CN 105976366A
- Authority
- CN
- China
- Prior art keywords
- ring line
- scoring ring
- moment
- image
- target surface
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for target loop positioning. The method comprises steps: a (TN)th precise target loop image at the TN time is determined, wherein the (TN)th precise target loop image comprises target center coordinates at the TN time, and N is a natural number larger than 0; a (TN)th coarse positioning target loop image at the TN time is acquired, wherein the (TN)th coarse positioning target loop image comprises target loops with the target center coordinates at the TN time as a circle center and with radiuses in a proportional relationship; when a (TN+1)th precise target loop image needs to be determined, a (TN+1)th target surface image at the TN+1 time is acquired; on the (TN+1)th target surface image, searching according to each target loop of the (TN)th coarse positioning target loop image is carried out; and according to pixel points of each searched target loop of the (TN+1)th target surface image, a (TN+1)th precise target loop image at the TN+1 time is obtained through fitting. By adopting the scheme of the invention, the real-time performance and the robustness during a target loop positioning process can be improved.
Description
Technical field
The present invention relates to technical field of image processing, particularly to the method and device of a kind of scoring ring line location.
Background technology
Indication of shots is the important step of gunnery training, and traditional artificial indication of shots cost is high, efficiency is low and poor stability.
Along with the development of information technology, use and realize automatic target-indicating based on image processing techniques, both can improve
Efficiency effectively reduces again the degree of danger of direct surveillance's indication of shots.At present, the target surface ring in automatic scoring round target system
The methods such as line localization method relates generally to that frame is poor, morphologic filtering and distortion correction.
Fig. 1 is scoring ring line positioning flow figure, as it can be seen, mainly include image segmentation, target position slightly extract,
Morphologic filtering, zone marker, target surface distortion correction, scoring ring line location.It is specifically described as follows:
Image is split according to front background difference, uses some simple and quick method such as Da-Jin algorithm.Target position slightly carries
Take the Pixel Information mainly according to target figure, such as the area of target surface, the feature (chequered with black and white) of target surface loop wire
Carry out coarse sizing etc. the result divided the image into, obtain complete target surface region, but there is also a large amount of simultaneously
Ambient interferences.Morphologic filtering and zone marker are used for filtering these ambient interferences, including not phase on target surface
The information such as the numeral closed, are accurately positioned target surface center ring position, ring radius for follow-up.It addition, at image
During sampling, can be with image fault, during target practice, the target surface that shell hole causes when entering target surface rocks also can
With certain distortion, need these distortion are corrected the precise positioning realizing target surface.
Distortion correction method currently mainly is, it is considered to some key points of benchmark image and real image (as
Angle point) corresponding relation, find out the mapped mode of the two, by actual fault image by reflecting of calculating
Emission mode carries out distortion correction.
After target surface fine positioning, the positional information of target center can be obtained, pass at double with radius further according to each scoring ring line
This feature of concentric circular increased, coarse positioning scoring ring line.Accurate target line position is typically in coarse positioning scoring ring line position
Near putting, use and carry out binaryzation in the rectangular neighborhood of the scoring ring line pixel of each coarse positioning,
Obtain accurate target line position, it is achieved the precise positioning of scoring ring line.
The deficiency of prior art is: owing to using point-to-point distortion correction when distortion correction, with
And employing substantial amounts of Binarization methods during fine positioning scoring ring line, algorithm is the highest, thus is difficult to meet in real time
Property requirement.And to the target surface vibrations during long-time target practice, illumination variation bad adaptability, robustness is not
Good.
Summary of the invention
The invention provides the method and device of a kind of scoring ring line location, in order to improve scoring ring line position fixing process
Real-time and robustness.
The embodiment of the present invention provides a kind of method that scoring ring line positions, including:
Determine TNThe T in momentNAccurate scoring ring line image, described TNAccurate scoring ring line image bag
Include TNThe target center coordinate in moment, described N is the natural number more than 0；
Obtain TNThe T in momentNThe scoring ring line image of coarse positioning, described TNThe scoring ring line chart of coarse positioning
As including with TNThe target center coordinate in moment is each scoring ring line of the center of circle, the proportional relation of radius；
It needs to be determined that TN+1The T in momentN+1During accurate scoring ring line image, obtain TN+1The of moment
TN+1Target surface image；
At described TN+1The T in momentN+1By described T on target surface imageNThe scoring ring line image of coarse positioning
Each scoring ring line scans for；
According to the described T searchedN+1The T in momentN+1Each scoring ring line pixel matching of target surface image obtains
To TN+1The T in momentN+1Accurate scoring ring line image.
It is preferred that it is described at described TN+1The T in momentN+1By described T on target surface imageNCoarse positioning
Each scoring ring line of scoring ring line image scans for, and is by described TNEach target of the scoring ring line image of coarse positioning
The rectangle frame position at loop wire pixel place is at described TN+1The T in momentN+1Relevant position on target surface image
Rectangle frame scan for.
Round matching based on method of least square is fitted to described in it is preferred that.
It is preferred that determine T1The T in moment1Accurate scoring ring line image, specifically includes:
Obtain T1The T in moment1Target surface image；
By described T1Carry out connected component analysis after target surface image binaryzation and obtain mask；Wherein, described
Connected component analysis is for rejecting the numeral on target surface and the hole within stuffing digit, and this mask does not include target
Heart region；
According to described mask to described T1The gray-scale map of target surface image carries out Da-Jin algorithm process, obtains T1
Accurate scoring ring line image.
It is preferred that to described T1Before target surface image binaryzation, farther include:
To described T1Target surface image carries out noise reduction process.
It is preferred that described noise reduction process includes that medium filtering processes.
The embodiment of the present invention provides the device that a kind of scoring ring line positions, including:
Determine module, be used for determining TNThe T in momentNAccurate scoring ring line image, described TNAccurately
Scoring ring line image include TNThe target center coordinate in moment, described N is the natural number more than 0；
First acquisition module, is used for obtaining TNThe T in momentNThe scoring ring line image of coarse positioning, described
TNThe scoring ring line image of coarse positioning includes with TNThe target center coordinate in moment is the center of circle, the proportional relation of radius
Each scoring ring line；
Second acquisition module, for it needs to be determined that TN+1The T in momentN+1During accurate scoring ring line image,
Obtain TN+1The T in momentN+1Target surface image；
Search module, at described TN+1The T in momentN+1By described T on target surface imageNCoarse positioning
Each scoring ring line of scoring ring line image scan for；
Fitting module, for according to the described T searchedN+1The T in momentN+1Each scoring ring of target surface image
Line pixel matching obtains TN+1The T in momentN+1Accurate scoring ring line image.
It is preferred that search module is further used for by described TNEach scoring ring of the scoring ring line image of coarse positioning
The rectangle frame position at line pixel place is at described TN+1The T in momentN+1Relevant position on target surface image
Rectangle frame scans for.
It is preferred that fitting module is further used for according to the described T searchedN+1The T in momentN+1Target surface
Each scoring ring line pixel of image carries out round matching based on method of least square and obtains TN+1The T in momentN+1
Accurate scoring ring line image.
It is preferred that determine that module is further used for:
Obtain T1The T in moment1Target surface image；
By described T1Carry out connected component analysis after target surface image binaryzation and obtain mask；Wherein, described
Connected component analysis is for rejecting the numeral on target surface and the hole within stuffing digit, and this mask does not include target
Heart region；
According to described mask to described T1The gray-scale map of target surface image carries out Da-Jin algorithm process, obtains T1
Accurate scoring ring line image.
It is preferred that determine that module is further used for described T1Before target surface image binaryzation, to described
T1Target surface image carries out noise reduction process.
Medium filtering is used to process it is preferred that determine module to be further used for when noise reduction process.
The present invention has the beneficial effect that:
In the technical scheme that the embodiment of the present invention provides, determining a certain accurate scoring ring line image (TN
Moment) after, when it needs to be determined that next accurate scoring ring line image (TN+1Moment) time, with this accurate target
The target center coordinate of loop wire image is the center of circle, then forms each scoring ring line of the proportional relation of radius, obtains corresponding
The scoring ring line image (T of coarse positioningNMoment), then by each scoring ring line of the scoring ring line image of this coarse positioning
Scan for, by described TNWhen each scoring ring line of the scoring ring line image of coarse positioning scans for, permissible
Quickly navigate to accurate each scoring ring line pixel, then just can get T by direct matchingN+1The of moment
TN+1Accurate scoring ring line image.Decrease the distortion correction step to target surface image, and not accurately
Use substantial amounts of Binarization methods during location, quickly update the coordinate of the pixel of each scoring ring line, the shortest.
Simultaneously as use the embodiment of the present invention provide technical scheme time, can by being constantly updated,
That is, after obtaining the accurate scoring ring line image in a certain moment, just can the most newly obtained subsequent time
Accurate scoring ring line image, the target surface occurred during therefore can overcoming long-time target practice rocks, illumination
Change etc. so that illumination variation is adapted to strong during long-term target practice by this programme, and robustness is high.
To sum up, this programme is used can to improve real-time and the robustness of scoring ring line position fixing process.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes of the present invention
Point, the schematic description and description of the present invention is used for explaining the present invention, is not intended that to the present invention not
Work as restriction.In the accompanying drawings:
Fig. 1 is that background of invention hits loop wire positioning flow figure；
Fig. 2 be the embodiment of the present invention hit loop wire location method implementing procedure schematic diagram；
Fig. 3 be the embodiment of the present invention hit loop wire search schematic diagram；
Fig. 4 is T in the embodiment of the present invention1Accurate scoring ring line image；
Fig. 5 be the embodiment of the present invention hit loop wire location be embodied as schematic flow sheet；
Fig. 6 is that the hit method of link position information updating of the embodiment of the present invention is embodied as schematic flow sheet；
Fig. 7 be the embodiment of the present invention hit loop wire location apparatus structure schematic diagram.
Detailed description of the invention
Below in conjunction with the accompanying drawings the detailed description of the invention of the present invention is illustrated.
The embodiment of the present invention carries out scoring ring line coarse positioning according to the front scoring ring line image once detected, and quickly
Detection scoring ring line position information, below when the explanation relating to example, by the resolution with image be
1024*768, target sheet occupy the example of more than the 70% of entire image and are specifically described.The description below relates to
And threshold value at the inferior proportional zoom of different resolution pattern.
Fig. 2 is the method implementing procedure schematic diagram of scoring ring line location, as it can be seen, may include steps of:
Step 201, determine TNThe T in momentNAccurate scoring ring line image, described TNAccurate scoring ring
Line image includes TNThe target center coordinate in moment, described N is the natural number more than 0；
Step 202, acquisition TNThe T in momentNThe scoring ring line image of coarse positioning, described TNCoarse positioning
Scoring ring line image includes with TNThe target center coordinate in moment is each scoring ring line of the center of circle, the proportional relation of radius；
Step 203, it needs to be determined that TN+1The T in momentN+1During accurate scoring ring line image, obtain TN+1
The T in momentN+1Target surface image；
Step 204, at described TN+1The T in momentN+1By described T on target surface imageNThe target of coarse positioning
Each scoring ring line of loop wire image scans for；
The described T that step 205, basis searchN+1The T in momentN+1Each scoring ring line pixel of target surface image
Point matching obtains TN+1The T in momentN+1Accurate scoring ring line image.
In being embodied as, determine T by the enforcement of step 201NThe target center coordinate in moment.Ideal situation
Under, scoring ring line is multiple centered by target center, and radius becomes the concentric circular that multiple proportion is incremented by, then step 202
Middle utilize the T obtained in step 201NThe target center coordinate in moment and the ideally proportional relation of radius
Each scoring ring line constitutes TNThe T in momentNThe scoring ring line image of coarse positioning.
For the enforcement of step 203, it needs to be determined that TN+1The T in momentN+1Accurate scoring ring line image
Time, during that is, need to update scoring ring line position information, obtain TN+1The T in momentN+1Target surface image.
For the enforcement of step 204, according to TNThe T in momentNThe scoring ring line image of coarse positioning is to scoring ring line
Carry out coarse positioning, then according to the scoring ring line of coarse positioning at TN+1The T in momentN+1Search on target surface image
TN+1The scoring ring line pixel of accurate scoring ring line image.
In enforcement, described at described TN+1The T in momentN+1By described T on target surface imageNCoarse positioning
Each scoring ring line of scoring ring line image scans for, and is by described TNEach target of the scoring ring line image of coarse positioning
The rectangle frame position at loop wire pixel place is at described TN+1The T in momentN+1Relevant position on target surface image
Rectangle frame scan for.
Concrete, at the rectangle frame of scoring ring line pixel of coarse positioning at TN+1The T in momentN+1Target surface figure
As searching for accurate scoring ring line pixel in the rectangle frame of upper relevant position, if searched, then by accurate target
Loop wire pixel stores, for the follow-up matching center of circle and radius.The size of rectangle frame should be suitable,
The excessive target line that other rings may be detected, too small then search time is long, reduces algorithm performance, here
Rectangle frame size is 20 × 20, and Fig. 3 is scoring ring line search schematic diagram, as it can be seen, the fine rule of white is thick
The scoring ring line of location, the thick line of white is the scoring ring line of fine positioning.
In enforcement, described in fit to round matching based on method of least square.
The accurate scoring ring line pixel obtained is come the matching center of circle by round matching based on method of least square
With each scoring ring line.Method of least square can be used for curve matching, uses least square fitting circle here.
Least square fitting circular curve: R2=(x-A)2+(y-B)2；
Above formula expands into: R2=x2-2Ax+A2+y2-2By+B2；
Make a=-2A, b=-2B, c=A2+B2-R2, can obtain another form of circular curve equation:
x2+y2+ ax+by+c=0, as long as obtaining parameter a, b, c just can be in the hope of the parameters of center of circle radius:
Scoring ring line pixel sample set (Xi,Yi) i ∈ (1,2,3...N) midpoint is d to the distance in the center of circlei, then
di 2=(Xi-A)2+(Yi-B)2, point (Xi,Yi) to the center of circle distance square with the difference of radius squared be:
δi=di 2-R2=(Xi-A)2+(Yi-B)2-R2=Xi 2+Yi 2+aXi+bYi+c。
(a, b c) are δ to make QiQuadratic sum, then Q (a, b, c)=∑ δi 2=∑ (Xi 2+Yi 2+aXi+bYi+c)2, by
In Q, (a, b, c) more than 0, there is the minimum more than or equal to 0 in function, and maximum is infinitely great.Now to a, b, c
Seek local derviation respectively, make local derviation be equal to 0, obtain extreme point, relatively the functional value of all extreme points,
To functional minimum value.Namely obtain parameter a, b, c, and then try to achieve the parameter of center of circle radius:
The algorithm improved on the basis of least square fitting circle is also in scope.
Owing to there will be target surface during long-time target practice and rocking, illumination variation, scoring ring line position needs to carry out
It is continuously updated, is obtaining T1The T in moment1After accurate scoring ring line image, just can be according to above-mentioned reality
Execute example and update T successively2The T in moment2Accurate scoring ring line image, TNThe T in momentNAccurate target
Loop wire image, TN+1The T in momentN+1Accurate scoring ring line image etc..
Below to how to obtain T1The T in moment1Accurate scoring ring line image is specifically described.
In enforcement, determine T1The T in moment1Accurate scoring ring line image, specifically includes:
Obtain T1The T in moment1Target surface image；
By described T1Carry out connected component analysis after target surface image binaryzation and obtain mask；Wherein, described
Connected component analysis is for rejecting the numeral on target surface and the hole within stuffing digit, and this mask does not include target
Heart region；
According to described mask to described T1The gray-scale map of target surface image carries out Da-Jin algorithm process, obtains T1
Accurate scoring ring line image.
Concrete, first obtain T1The T in moment1Target surface image, then obtains T1The ash of target surface image
Degree figure i (x), in enforcement, to described T1Before target surface image binaryzation, farther include:
To described T1Target surface image carries out noise reduction process.
In enforcement, described noise reduction process includes that medium filtering processes.
Concrete, in image transmitting process, medium filtering can be used here to T with noise1Target
Gray-scale map i (x) of face image carries out smooth operation, obtains filtering image f (x).Take into account noise reduction with in real time
Property, filter radius is set as 7.
Use Da-Jin algorithm to carry out binary conversion treatment filtering image f (x), obtain initial target surface region b (x), meter
Calculation formula is as follows:
Next initial target surface region b (x) is carried out morphologic filtering, b (x) not only includes target surface region,
Also include some tiny empty targets.Operate used here as morphological erosion, filter these empty targets, obtain
Inceptive filtering image m (x), the filtering core of use is the rectangle core of 5 × 5.
Then image m (x) is carried out connected domain analysis, by connected domain less for area (usually on target surface
Numeral) to reject, the area threshold set here is as 5000.The target center of standard target sheet is white, target center
Numeral be Lycoperdon polymorphum Vitt, the non-target center of standard target sheet is Lycoperdon polymorphum Vitt, the numeral of non-target center be white.Through above-mentioned step
After rapid process, the numeral at target center can be removed, and the hole of the digital internal at non-target center can be filled, but
Will not remove completely.So, in addition it is also necessary to the image after filtering connected domain carries out an inverse operation, to instead
Color image carries out a connected domain analysis again, removes the region of little area, and the area threshold set here is
30000.After above-mentioned process, having obtained accurate binaryzation mask mask (x) of target surface, this mask does not wraps
Include target center region.
Accurate binaryzation mask mask (x) of target surface has been obtained, below to how to apply target surface according to above-mentioned steps
Accurate binaryzation mask mask (x) obtains T1Accurate scoring ring line image illustrates.
For being accurately positioned, prior art is as follows:
Generally, do not distort in target center region, can be according to target surface accurate binaryzation mask
Mask (x) obtains the picture element position information in target center region, and then simulates accurate target center coordinate.Ideal situation
Under, scoring ring line is multiple centered by target center, and radius becomes the concentric circular that multiple proportion is incremented by.Actual image
In there are distortion, need to correct.Existing fine positioning algorithm is usually and considers the scoring ring line at coarse positioning
In the rectangular area of pixel, use the scoring ring line pixel that Da-Jin algorithm search is actual, the scoring ring line of coarse positioning is rectified
Just arrive actual scoring ring line position.
The deficiencies in the prior art are to need to calculate through substantial amounts of binaryzation, the highest.
For being accurately positioned, the present embodiment provides a kind of Binarization methods based on mask, according to the target obtained
Accurate binaryzation mask mask (x) in face is to T1Target surface image i (x) uses Da-Jin algorithm, disposably obtains such as figure
T shown in 41Accurate scoring ring line image res (x), computing formula is as follows:
In order to more clearly understand the present invention, illustrate with specific embodiment below.
Fig. 5 be scoring ring line location be embodied as schematic flow sheet, as it can be seen, may include steps of:
Step 501, acquisition T1The T in moment1Target surface image；
Step 502, to described T1Target surface image carries out noise reduction process；Here medium filtering is used to drop
Make an uproar；
Step 503, the image after noise reduction process is carried out binary conversion treatment；
Step 504, carry out connected component analysis according to the image after binaryzation and obtain mask；
Step 505, according to described mask to described T1The gray-scale map of target surface image carries out Da-Jin algorithm process,
Obtain T1Accurate scoring ring line image；
Step 506, according to the time set and/or the condition of setting, scoring ring line position information is updated.
Illustrate how step 506 updates scoring ring line position information below.N cited below is big
In the natural number of 0.
Fig. 6 is that the method that scoring ring line position information updates is embodied as schematic flow sheet, as it can be seen, permissible
Comprise the steps:
Step 601, determine TNThe T in momentNAccurate scoring ring line image；This scoring ring line image includes TN
The target center coordinate in moment, and each scoring ring line；
Step 602, acquisition TNThe T in momentNThe scoring ring line image of coarse positioning；This scoring ring line image includes
With TNThe target center coordinate in moment is each scoring ring line of the center of circle, the proportional relation of radius；
Step 603, by TNThe rectangle frame at each scoring ring line pixel place of the scoring ring line image of coarse positioning exists
TN+1The T in momentN+1Search pixel point on scoring ring line image；
The pixel matching that step 604, basis search obtains TN+1The T in momentN+1Accurate scoring ring line
Image.
Enforcement for the method for above-mentioned scoring ring line position information renewal can be rocked with target surface and/or illumination becomes
Change situation is condition or with time of setting as condition.
For step 604, fitting algorithm is the algorithm of least square fitting circle.
Based on same inventive concept, the embodiment of the present invention additionally provides the device of a kind of scoring ring line location, by
The principle solving problem in these equipment is similar to a kind of method that scoring ring line positions, the therefore reality of these equipment
Execute the enforcement of the method for may refer to, repeat no more in place of repetition.
Fig. 7 is the apparatus structure schematic diagram of scoring ring line location, as it can be seen, may include steps of:
Determine module 701, be used for determining TNThe T in momentNAccurate scoring ring line image, described TN
Accurate scoring ring line image includes TNThe target center coordinate in moment, and each scoring ring line, described N is more than 0
Natural number；
First acquisition module 702, is used for obtaining TNThe T in momentNThe scoring ring line image of coarse positioning, described
TNThe scoring ring line image of coarse positioning includes with TNThe target center coordinate in moment is the center of circle, the proportional relation of radius
Each scoring ring line；
Second acquisition module 703, for it needs to be determined that TN+1The T in momentN+1Accurate scoring ring line image
Time, obtain TN+1The T in momentN+1Target surface image；
Search module 704, at described TN+1The T in momentN+1By described T on target surface imageNSlightly
Each scoring ring line of the scoring ring line image of location scans for；
Fitting module 705, for according to the described T searchedN+1The T in momentN+1Each target of target surface image
Loop wire pixel matching obtains TN+1The T in momentN+1Accurate scoring ring line image.
In enforcement, search module is further used for by described TNEach scoring ring of the scoring ring line image of coarse positioning
The rectangle frame position at line pixel place is at described TN+1The T in momentN+1Relevant position on target surface image
Rectangle frame scans for.
In enforcement, fitting module is further used for according to the described T searchedN+1The T in momentN+1Target surface
Each scoring ring line pixel of image carries out round matching based on method of least square and obtains TN+1The T in momentN+1
Accurate scoring ring line image.
In enforcement, determine that module is further used for:
Obtain T1The T in moment1Target surface image；
By described T1Carry out connected component analysis after target surface image binaryzation and obtain mask；Wherein, described
Connected component analysis is for rejecting the numeral on target surface and the hole within stuffing digit, and this mask does not include target
Heart region；
According to described mask to described T1The gray-scale map of target surface image carries out Da-Jin algorithm process, obtains T1
Accurate scoring ring line image.
In enforcement, determine that module is further used for described T1Before target surface image binaryzation, to described
T1Target surface image carries out noise reduction process.
In enforcement, determine module to be further used for when noise reduction process and use medium filtering to process.
In sum, in the technical scheme that the embodiment of the present invention provides, a certain accurate scoring ring line is being determined
Image (TNMoment) after, when it needs to be determined that next accurate scoring ring line image (TN+1Moment) time, with this
The target center coordinate of accurate scoring ring line image is the center of circle, then forms each scoring ring line of the proportional relation of radius,
Scoring ring line image (T to corresponding coarse positioningNMoment), then by the scoring ring line image of this coarse positioning
Each scoring ring line scans for, by described TNEach scoring ring line of the scoring ring line image of coarse positioning scans for
Time, can quickly navigate to accurate each scoring ring line pixel, then just can get T by direct matchingN+1
The T in momentN+1Accurate scoring ring line image.Decrease the distortion correction step to target surface image, and do not have
Have when being accurately positioned and use substantial amounts of Binarization methods, quickly update the coordinate of the pixel of each scoring ring line,
The shortest.
Simultaneously as use the embodiment of the present invention provide technical scheme time, can by being constantly updated,
That is, after obtaining the accurate scoring ring line image in a certain moment, just can the most newly obtained subsequent time
Accurate scoring ring line image, the target surface occurred during therefore can overcoming long-time target practice rocks, illumination
Change etc. so that illumination variation is adapted to strong during long-term target practice by this programme, and robustness is high.
To sum up, this programme is used can to improve real-time and the robustness of scoring ring line position fixing process.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or meter
Calculation machine program product.Therefore, the present invention can use complete hardware embodiment, complete software implementation or knot
The form of the embodiment in terms of conjunction software and hardware.And, the present invention can use and wherein wrap one or more
Computer-usable storage medium containing computer usable program code (include but not limited to disk memory and
Optical memory etc.) form of the upper computer program implemented.
The present invention is with reference to method, equipment (system) and computer program product according to embodiments of the present invention
The flow chart of product and/or block diagram describe.It should be understood that can by computer program instructions flowchart and
/ or block diagram in each flow process and/or flow process in square frame and flow chart and/or block diagram and/
Or the combination of square frame.These computer program instructions can be provided to general purpose computer, special-purpose computer, embedding
The processor of formula datatron or other programmable data processing device is to produce a machine so that by calculating
The instruction that the processor of machine or other programmable data processing device performs produces for realizing at flow chart one
The device of the function specified in individual flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and computer or the process of other programmable datas can be guided to set
In the standby computer-readable memory worked in a specific way so that be stored in this computer-readable memory
Instruction produce and include the manufacture of command device, this command device realizes in one flow process or multiple of flow chart
The function specified in flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, makes
Sequence of operations step must be performed to produce computer implemented place on computer or other programmable devices
Reason, thus the instruction performed on computer or other programmable devices provides for realizing flow chart one
The step of the function specified in flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
Obviously, those skilled in the art can carry out various change and modification without deviating from this to the present invention
Bright spirit and scope.So, if the present invention these amendment and modification belong to the claims in the present invention and
Within the scope of its equivalent technologies, then the present invention is also intended to comprise these change and modification.
Claims (12)
1. the method for a scoring ring line location, it is characterised in that including:
Determine TNThe T in momentNAccurate scoring ring line image, described TNAccurate scoring ring line image bag
Include TNThe target center coordinate in moment, described N is the natural number more than 0；
Obtain TNThe T in momentNThe scoring ring line image of coarse positioning, described TNThe scoring ring line chart of coarse positioning
As including with TNThe target center coordinate in moment is each scoring ring line of the center of circle, the proportional relation of radius；
It needs to be determined that TN+1The T in momentN+1During accurate scoring ring line image, obtain TN+1The of moment
TN+1Target surface image；
At described TN+1The T in momentN+1By described T on target surface imageNThe scoring ring line image of coarse positioning
Each scoring ring line scans for；
According to the described T searchedN+1The T in momentN+1Each scoring ring line pixel matching of target surface image obtains
To TN+1The T in momentN+1Accurate scoring ring line image.
Method the most according to claim 1, it is characterised in that described at described TN+1The of moment
TN+1By described T on target surface imageNEach scoring ring line of the scoring ring line image of coarse positioning scans for, be by
Described TNThe rectangle frame position at each scoring ring line pixel place of the scoring ring line image of coarse positioning is described
TN+1The T in momentN+1On target surface image, the rectangle frame of relevant position scans for.
Method the most according to claim 1, it is characterised in that described in fit to based on least square
The round matching of method.
4. according to the arbitrary described method of claims 1 to 3, it is characterised in that determine T1The of moment
T1Accurate scoring ring line image, specifically includes:
Obtain T1The T in moment1Target surface image；
By described T1Carry out connected component analysis after target surface image binaryzation and obtain mask；Wherein, described
Connected component analysis is for rejecting the numeral on target surface and the hole within stuffing digit, and this mask does not include target
Heart region；
According to described mask to described T1The gray-scale map of target surface image carries out Da-Jin algorithm process, obtains T1
Accurate scoring ring line image.
Method the most according to claim 4, it is characterised in that to described T1Target surface image two
Before value, farther include:
To described T1Target surface image carries out noise reduction process.
Method the most according to claim 5, it is characterised in that described noise reduction process includes that intermediate value is filtered
Ripple processes.
7. the device of a scoring ring line location, it is characterised in that including:
Determine module, be used for determining TNThe T in momentNAccurate scoring ring line image, described TNAccurately
Scoring ring line image include TNThe target center coordinate in moment, described N is the natural number more than 0；
First acquisition module, is used for obtaining TNThe T in momentNThe scoring ring line image of coarse positioning, described
TNThe scoring ring line image of coarse positioning includes with TNThe target center coordinate in moment is the center of circle, the proportional relation of radius
Each scoring ring line；
Second acquisition module, for it needs to be determined that TN+1The T in momentN+1During accurate scoring ring line image,
Obtain TN+1The T in momentN+1Target surface image；
Search module, at described TN+1The T in momentN+1By described T on target surface imageNCoarse positioning
Each scoring ring line of scoring ring line image scan for；
Fitting module, for according to the described T searchedN+1The T in momentN+1Each scoring ring of target surface image
Line pixel matching obtains TN+1The T in momentN+1Accurate scoring ring line image.
Device the most according to claim 7, it is characterised in that search module is further used for by institute
State TNThe rectangle frame position at each scoring ring line pixel place of the scoring ring line image of coarse positioning is at described TN+1
The T in momentN+1On target surface image, the rectangle frame of relevant position scans for.
Device the most according to claim 7, it is characterised in that fitting module is further used for basis
The described T searchedN+1The T in momentN+1Each scoring ring line pixel of target surface image is carried out based on a young waiter in a wineshop or an inn
The round matching of multiplication obtains TN+1The T in momentN+1Accurate scoring ring line image.
10. according to the arbitrary described device of claim 7 to 9, it is characterised in that determine that module is further
For:
Obtain T1The T in moment1Target surface image；
By described T1Carry out connected component analysis after target surface image binaryzation and obtain mask；Wherein, described
Connected component analysis is for rejecting the numeral on target surface and the hole within stuffing digit, and this mask does not include target
Heart region；
According to described mask to described T1The gray-scale map of target surface image carries out Da-Jin algorithm process, obtains T1
Accurate scoring ring line image.
11. devices according to claim 10, it is characterised in that determine that module is further used for
To described T1Before target surface image binaryzation, to described T1Target surface image carries out noise reduction process.
12. devices according to claim 11, it is characterised in that determine that module is further used for
Medium filtering is used to process during noise reduction process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610283414.9A CN105976366B (en) | 2016-04-29 | 2016-04-29 | A kind of method and device of scoring ring line positioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610283414.9A CN105976366B (en) | 2016-04-29 | 2016-04-29 | A kind of method and device of scoring ring line positioning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105976366A true CN105976366A (en) | 2016-09-28 |
| CN105976366B CN105976366B (en) | 2019-03-26 |
Family
ID=56994111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610283414.9A Active CN105976366B (en) | 2016-04-29 | 2016-04-29 | A kind of method and device of scoring ring line positioning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105976366B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845506A (en) * | 2016-12-22 | 2017-06-13 | 中国人民武装警察部队工程大学 | A kind of target surface location of pixels coding method |
| CN109635679A (en) * | 2018-11-26 | 2019-04-16 | 深圳深知未来智能有限公司 | A kind of real-time target sheet positioning and loop wire recognition methods |
| CN110008864A (en) * | 2019-03-22 | 2019-07-12 | 清华大学深圳研究生院 | A kind of miniature manpower identification equipment and recognition methods |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000505548A (en) * | 1996-02-20 | 2000-05-09 | イメトリック ソシエテ アノニム | Automated 3D image measurement system |
| CN101694363A (en) * | 2009-09-30 | 2010-04-14 | 魏力中 | Target scoring method based on camera and system thereof |
| CN101937509A (en) * | 2010-08-17 | 2011-01-05 | 西安理工大学 | Automatic target identifying method based on image processing technology |
| CN103353259A (en) * | 2013-06-22 | 2013-10-16 | 太仓博天网络科技有限公司 | Automatic shoot target-scoring system based on image identification |
| CN204630485U (en) * | 2015-05-20 | 2015-09-09 | 广州南北电子科技有限公司 | A kind of intelligent newspapers target system |
-
2016
- 2016-04-29 CN CN201610283414.9A patent/CN105976366B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000505548A (en) * | 1996-02-20 | 2000-05-09 | イメトリック ソシエテ アノニム | Automated 3D image measurement system |
| CN101694363A (en) * | 2009-09-30 | 2010-04-14 | 魏力中 | Target scoring method based on camera and system thereof |
| CN101937509A (en) * | 2010-08-17 | 2011-01-05 | 西安理工大学 | Automatic target identifying method based on image processing technology |
| CN103353259A (en) * | 2013-06-22 | 2013-10-16 | 太仓博天网络科技有限公司 | Automatic shoot target-scoring system based on image identification |
| CN204630485U (en) * | 2015-05-20 | 2015-09-09 | 广州南北电子科技有限公司 | A kind of intelligent newspapers target system |
Non-Patent Citations (1)
| Title |
|---|
| 张丽霞: "基于图像技术的智能报靶系统设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845506A (en) * | 2016-12-22 | 2017-06-13 | 中国人民武装警察部队工程大学 | A kind of target surface location of pixels coding method |
| CN106845506B (en) * | 2016-12-22 | 2019-09-20 | 中国人民武装警察部队工程大学 | A kind of target surface location of pixels coding method |
| CN109635679A (en) * | 2018-11-26 | 2019-04-16 | 深圳深知未来智能有限公司 | A kind of real-time target sheet positioning and loop wire recognition methods |
| CN109635679B (en) * | 2018-11-26 | 2023-01-24 | 深圳深知未来智能有限公司 | Real-time target paper positioning and loop line identification method |
| CN110008864A (en) * | 2019-03-22 | 2019-07-12 | 清华大学深圳研究生院 | A kind of miniature manpower identification equipment and recognition methods |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105976366B (en) | 2019-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106875444B (en) | A kind of object localization method and device | |
| CN108717531B (en) | Human body posture estimation method based on Faster R-CNN | |
| CN107330917A (en) | The track up method and tracking equipment of mobile target | |
| CN106250938A (en) | Method for tracking target, augmented reality method and device thereof | |
| TW202011733A (en) | Method and device for performing target sampling on pictures | |
| CN105931269A (en) | Tracking method for target in video and tracking device thereof | |
| CN107633526A (en) | A kind of image trace point acquisition methods and equipment, storage medium | |
| CN103413120A (en) | Tracking method based on integral and partial recognition of object | |
| CN110189322A (en) | Measurement method of planeness, device, equipment, storage medium and system | |
| CN105930874A (en) | Bullet hole identification method and apparatus | |
| CN110111248A (en) | A kind of image split-joint method based on characteristic point, virtual reality system, camera | |
| CN109472193A (en) | Method for detecting human face and device | |
| CN105976366A (en) | Method and device for target loop positioning | |
| CN104517101A (en) | Game poker card recognition method based on pixel square difference matching | |
| CN104408704A (en) | Automatic zoom lens calibration device and calibration method | |
| CN106780504B (en) | It is a kind of based on distance keep level set beef image in carry on the back long flesh automatic division method | |
| CN109711242A (en) | Modification method, device and the storage medium of lane line | |
| CN110261069B (en) | Detection method for optical lens | |
| CN112435252B (en) | Warhead fragment perforation and pit detection method | |
| CN108986134A (en) | A kind of semi-automatic mask method of video object based on correlation filtering tracking | |
| CN110458940A (en) | The processing method and processing unit of motion capture | |
| CN110779395A (en) | Target shooting correction system and method | |
| CN105869164A (en) | Method and system for detecting on/off state of switch | |
| CN111191535A (en) | Pedestrian detection model construction method based on deep learning and pedestrian detection method | |
| CN110084743A (en) | Image mosaic and localization method based on more air strips starting track constraint |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |