CN105976366B - A kind of method and device of scoring ring line positioning - Google Patents
A kind of method and device of scoring ring line positioning Download PDFInfo
- Publication number
- CN105976366B CN105976366B CN201610283414.9A CN201610283414A CN105976366B CN 105976366 B CN105976366 B CN 105976366B CN 201610283414 A CN201610283414 A CN 201610283414A CN 105976366 B CN105976366 B CN 105976366B
- 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.)
- Active
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 kind of method and devices of scoring ring line positioning, comprising: determines TNThe T at momentNAccurate scoring ring line image, TNAccurate scoring ring line image includes TNThe target center coordinate at moment, N are the natural number greater than 0;Obtain TNThe T at momentNThe scoring ring line image of coarse positioning, TNThe scoring ring line image of coarse positioning includes with TNThe target center coordinate at moment is each scoring ring line in the center of circle, the proportional relationship of radius;It needs to be determined that TN+1When accurate scoring ring line image, T is obtainedN+1The T at momentN+1Target surface image;In TN+1T is pressed on target surface imageNEach scoring ring line of the scoring ring line image of coarse positioning scans for;According to the T searchedN+1Each scoring ring line pixel of target surface image is fitted to obtain TN+1The T at momentN+1Accurate scoring ring line image.The real-time and robustness of scoring ring line position fixing process can be improved using this programme.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of method and device of scoring ring line positioning.
Background technique
Indication of shots is the important link of gunnery training, and traditional artificial indication of shots is at high cost, low efficiency and safety are poor.With letter
The continuous development of breath technology realizes automatic target-indicating using based on image processing techniques, efficiency not only can be improved but also effectively reduced
The degree of danger of direct surveillance's indication of shots.Currently, the target surface loop wire localization method in automatic scoring round target system relates generally to, frame is poor, form
Learn the methods of filtering and distortion correction.
Fig. 1 is scoring ring line positioning flow figure, as shown, mainly including image segmentation, target position coarse extraction, Mathematical morphology filter
Wave, zone marker, target surface distortion correction, the positioning of scoring ring line.It is specifically described as follows:
Image segmentation is according to preceding background difference, using some simple and quick method such as Da-Jin algorithms.Target position coarse extraction is main
It is the result that is divided the image into such as the area of target surface, the feature (chequered with black and white) of target surface loop wire etc. according to the Pixel Information of target figure
Coarse sizing is carried out, obtains complete target surface region, but there is also have a large amount of background interference simultaneously.Morphologic filtering and region mark
Note is used for subsequent accurate positioning target surface center for filtering out the information such as incoherent number in these background interferences, including target surface
Ring position, ring radius.In addition, in image sampling image fault can be had, during target practice, shell hole causes when entering target surface
Target surface shake also can have certain distortion, need to these distortion carry out correction realize target surface precise positioning.
Current main distortion correction method is, some key points (such as angle point) for considering benchmark image and real image
Corresponding relationship finds out the mapped mode of the two, and actual fault image is passed through calculated mapped mode and carries out distortion correction.
After target surface fine positioning, the location information of available target center is incremental same at double with radius further according to each scoring ring line
The heart justifies this feature, coarse positioning scoring ring line.Accurate target line position is generally near coarse positioning scoring ring line position, using each
Binaryzation is carried out in the rectangular neighborhood of the scoring ring line pixel of a coarse positioning, accurate target line position can be obtained, and realizes scoring ring line
Precise positioning.
The deficiency of prior art is: due to using point-to-point distortion correction, and essence to determine in distortion correction
A large amount of Binarization methods are used when the scoring ring line of position, algorithm is time-consuming high, thus is difficult to meet requirement of real-time.And to it is long when
Between practice shooting during target surface vibration, illumination variation bad adaptability, robustness is bad.
Summary of the invention
The present invention provides a kind of method and devices of scoring ring line positioning, to improve the real-time of scoring ring line position fixing process
And robustness.
A kind of method of scoring ring line positioning is provided in the embodiment of the present invention, comprising:
Determine TNThe T at momentNAccurate scoring ring line image, the TNAccurate scoring ring line image includes TNMoment
Target center coordinate, the N are the natural number greater than 0;
Obtain TNThe T at momentNThe scoring ring line image of coarse positioning, the TNThe scoring ring line image of coarse positioning includes with TN
The target center coordinate at moment is each scoring ring line in the center of circle, the proportional relationship of radius;
It needs to be determined that TN+1The T at momentN+1When accurate scoring ring line image, T is obtainedN+1The T at momentN+1Target surface figure
Picture;
In the TN+1The T at momentN+1The T is pressed on target surface imageNEach scoring ring line of the scoring ring line image of coarse positioning
It scans for;
According to the T searchedN+1The T at momentN+1Each scoring ring line pixel of target surface image is fitted to obtain TN+1Moment
TN+1Accurate scoring ring line image.
Preferably, described in the TN+1The T at momentN+1The T is pressed on target surface imageNThe scoring ring line image of coarse positioning
Each scoring ring line scan for, be by the TNRectangle frame where each scoring ring line pixel of the scoring ring line image of coarse positioning
Position is in the TN+1The T at momentN+1The rectangle frame of corresponding position scans on target surface image.
Preferably, the circle fitting being fitted to based on least square method.
Preferably, determining T1The T at moment1Accurate scoring ring line image, specifically includes:
Obtain T1The T at moment1Target surface image;
By the T1Connected component analysis is carried out after target surface image binaryzation obtains exposure mask;Wherein, the connected region
It analyzes for rejecting the number on target surface and the hole inside stuffing digit, which does not include target center region;
According to the exposure mask to the T1The grayscale image of target surface image carries out Da-Jin algorithm processing, obtains T1Accurate target
Loop wire image.
Preferably, to the T1Before target surface image binaryzation, further comprise:
To the T1Target surface image carries out noise reduction process.
Preferably, the noise reduction process includes median filter process.
A kind of device of scoring ring line positioning is provided in the embodiment of the present invention, comprising:
Determining module, for determining TNThe T at momentNAccurate scoring ring line image, the TNAccurate scoring ring line image
Including TNThe target center coordinate at moment, the N are the natural number greater than 0;
First obtains module, for obtaining TNThe T at momentNThe scoring ring line image of coarse positioning, the TNThe target of coarse positioning
Loop wire image includes with TNThe target center coordinate at moment is each scoring ring line in the center of circle, the proportional relationship of radius;
Second obtains module, for it needs to be determined that TN+1The T at momentN+1When accurate scoring ring line image, T is obtainedN+1When
The T carvedN+1Target surface image;
Search module, in the TN+1The T at momentN+1The T is pressed on target surface imageNThe scoring ring line chart of coarse positioning
Each scoring ring line of picture scans for;
Fitting module, for according to the T searchedN+1The T at momentN+1Each scoring ring line pixel of target surface image is quasi-
Conjunction obtains TN+1The T at momentN+1Accurate scoring ring line image.
Preferably, search module is further used for by the TNEach scoring ring line pixel of the scoring ring line image of coarse positioning
The rectangle frame position at place is in the TN+1The T at momentN+1The rectangle frame of corresponding position scans on target surface image.
Preferably, fitting module is further used for according to the T searchedN+1The T at momentN+1Each target of target surface image
Loop wire pixel carries out the circle fitting based on least square method and obtains TN+1The T at momentN+1Accurate scoring ring line image.
Preferably, determining module is further used for:
Obtain T1The T at moment1Target surface image;
By the T1Connected component analysis is carried out after target surface image binaryzation obtains exposure mask;Wherein, the connected region
It analyzes for rejecting the number on target surface and the hole inside stuffing digit, which does not include target center region;
According to the exposure mask to the T1The grayscale image of target surface image carries out Da-Jin algorithm processing, obtains T1Accurate target
Loop wire image.
Preferably, determining module is further used for the T1Before target surface image binaryzation, to the T1Target surface figure
As carrying out noise reduction process.
Preferably, determining module is further used in noise reduction process using median filter process.
The present invention has the beneficial effect that:
In technical solution provided in an embodiment of the present invention, a certain accurate scoring ring line image (T is being determinedNMoment) after,
When it needs to be determined that next accurate scoring ring line image (TN+1Moment) when, it is circle with the target center coordinate of the accurate scoring ring line image
The heart re-forms each scoring ring line of the proportional relationship of radius, obtains the scoring ring line image (T of corresponding coarse positioningNMoment), then
It is scanned for by each scoring ring line of the scoring ring line image of the coarse positioning, is pressing the TNEach target of the scoring ring line image of coarse positioning
When loop wire scans for, accurate each scoring ring line pixel can be quickly navigated to, T then can be obtained by directly fittingN+1
The T at momentN+1Accurate scoring ring line image.Reduce the distortion correction step to target surface image, and be not accurately positioned
When use a large amount of Binarization methods, quickly update the coordinate of the pixel of each scoring ring line, it is time-consuming short.
Simultaneously as when using technical solution provided in an embodiment of the present invention, can by being updated constantly, that is,
After obtaining the accurate scoring ring line image at a certain moment, the accurate scoring ring line chart for obtaining subsequent time can be successively updated
Picture, therefore practice shooting for a long time the target surface shaking occurred in the process, illumination variation etc. can be overcome, so that this programme is practiced shooting for a long time
Strong, robustness height is adapted to illumination variation in the process.
To sum up, the real-time and robustness of scoring ring line position fixing process can be improved using this programme.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is scoring ring line positioning flow figure in background of invention;
Fig. 2 is the method implementation process diagram of scoring ring line positioning in the embodiment of the present invention;
Fig. 3 is scoring ring line search schematic diagram in the embodiment of the present invention;
Fig. 4 is T in the embodiment of the present invention1Accurate scoring ring line image;
Fig. 5 is the specific implementation flow diagram of scoring ring line positioning in the embodiment of the present invention;
Fig. 6 is that flow diagram is embodied in the method that scoring ring line position information updates in the embodiment of the present invention;
Fig. 7 is the apparatus structure schematic diagram of scoring ring line positioning in the embodiment of the present invention.
Specific embodiment
Description of specific embodiments of the present invention with reference to the accompanying drawing.
The embodiment of the present invention carries out scoring ring line coarse positioning according to the preceding scoring ring line image once detected, and quickly detects target
Link position information, below in the explanation for being related to example, will be 1024*768 with the resolution ratio of image, target sheet occupy it is whole
70% or more example of width image is specifically described.Threshold value involved in following the description is in the inferior ratio of different resolution mode
Example scaling.
Fig. 2 is the method implementation process diagram of scoring ring line positioning, as shown, may include steps of:
Step 201 determines TNThe T at momentNAccurate scoring ring line image, the TNAccurately scoring ring line image includes
TNThe target center coordinate at moment, the N are the natural number greater than 0;
Step 202 obtains TNThe T at momentNThe scoring ring line image of coarse positioning, the TNThe scoring ring line image of coarse positioning
Including with TNThe target center coordinate at moment is each scoring ring line in the center of circle, the proportional relationship of radius;
Step 203, it needs to be determined that TN+1The T at momentN+1When accurate scoring ring line image, T is obtainedN+1The T at momentN+1
Target surface image;
Step 204, in the TN+1The T at momentN+1The T is pressed on target surface imageNThe scoring ring line image of coarse positioning
Each scoring ring line scans for;
The T that step 205, basis searchN+1The T at momentN+1Each scoring ring line pixel of target surface image is fitted
To TN+1The T at momentN+1Accurate scoring ring line image.
In specific implementation, T has been determined by the implementation of step 201NThe target center coordinate at moment.Ideally, scoring ring line
It is multiple centered on target center, then the concentric circles that radius is incremented by multiple proportion obtains in step 202 using in step 201
TNEach scoring ring line of the target center coordinate at moment and the ideally proportional relationship of radius constitutes TNThe T at momentNCoarse positioning
Scoring ring line image.
Implementation for step 203, it needs to be determined that TN+1The T at momentN+1When accurate scoring ring line image, that is, needing
When updating scoring ring line position information, T is obtainedN+1The T at momentN+1Target surface image.
Implementation for step 204, according to TNThe T at momentNIt is slightly fixed that the scoring ring line image of coarse positioning carries out scoring ring line
Position, then according to the scoring ring line of coarse positioning in TN+1The T at momentN+1T is searched on target surface imageN+1Accurate scoring ring line image
Scoring ring line pixel.
It is described in the T in implementationN+1The T at momentN+1The T is pressed on target surface imageNThe scoring ring line image of coarse positioning
Each scoring ring line scan for, be by the TNRectangle frame where each scoring ring line pixel of the scoring ring line image of coarse positioning
Position is in the TN+1The T at momentN+1The rectangle frame of corresponding position scans on target surface image.
Specifically, coarse positioning scoring ring line pixel rectangle frame in TN+1The T at momentN+1Corresponding positions on target surface image
The accurate scoring ring line pixel of search stores accurate scoring ring line pixel if searched in the rectangle frame set, and uses
In the subsequent fitting center of circle and radius.The size of rectangle frame should be suitable, and the excessive target line that may detect other rings is too small
Then search time is too long, reduces algorithm performance, and it is scoring ring line search schematic diagram that rectangle frame size, which is 20 × 20, Fig. 3, here, such as schemes
Shown, white filament is the scoring ring line of coarse positioning, and white thick line is the scoring ring line of fine positioning.
In implementation, the circle fitting being fitted to based on least square method.
By obtained accurate scoring ring line pixel by being fitted the center of circle and each target based on the circle fitting of least square method
Loop wire.Least square method can be used for curve matching, use least square method fitting circle here.
Least square method is fitted circular curve: R2=(x-A)2+(y-B)2;
Above formula expansion are as follows: R2=x2-2Ax+A2+y2-2By+B2;
Enable a=-2A, b=-2B, c=A2+B2-R2, another form of circular curve equation: x can be obtained2+y2+ ax+by+c=
0, as long as finding out parameter a, b, c can be in the hope of the parameters of center of circle radius:
Scoring ring line pixel sample set (Xi,Yi) midpoint (1,2,3...N) i ∈ to the center of circle distance be di, then di 2=(Xi-
A)2+(Yi-B)2, point (Xi,Yi) to the center of circle distance the difference square with radius squared are as follows: δi=di 2-R2=(Xi-A)2+(Yi-
B)2-R2=Xi 2+Yi 2+aXi+bYi+c。
Enabling Q (a, b, c) is δiQuadratic sum, then Q (a, b, c)=∑ δi 2=∑ (Xi 2+Yi 2+aXi+bYi+c)2, due to Q
(a, b, c) is greater than 0, and function has the minimum more than or equal to 0, and maximum is infinity.Local derviation is now asked respectively to a, b, c,
It enables local derviation be equal to 0, obtains extreme point, functional minimum value can be obtained in the functional value of more all extreme points.Namely joined
Number a, b, c, and then acquire the parameter of center of circle radius:
The algorithm improved on the basis of least square method fitting circle is also in the scope of the present invention.
It will appear target surface shaking, illumination variation during practicing shooting due to long-time, scoring ring line position needs to carry out constantly
It updates, is obtaining T1The T at moment1After accurate scoring ring line image, T can be successively updated according to above-described embodiment2Moment
T2Accurate scoring ring line image, TNThe T at momentNAccurate scoring ring line image, TN+1The T at momentN+1Accurate target
Loop wire image etc..
Below to how obtaining T1The T at moment1Accurate scoring ring line image is specifically described.
In implementation, T is determined1The T at moment1Accurate scoring ring line image, specifically includes:
Obtain T1The T at moment1Target surface image;
By the T1Connected component analysis is carried out after target surface image binaryzation obtains exposure mask;Wherein, the connected region
It analyzes for rejecting the number on target surface and the hole inside stuffing digit, which does not include target center region;
According to the exposure mask to the T1The grayscale image of target surface image carries out Da-Jin algorithm processing, obtains T1Accurate target
Loop wire image.
Specifically, obtaining T first1The T at moment1Target surface image, then obtains T1The grayscale image i (x) of target surface image,
In implementation, to the T1Before target surface image binaryzation, further comprise:
To the T1Target surface image carries out noise reduction process.
In implementation, the noise reduction process includes median filter process.
Specifically, in image transmitting process noise can be had, here using median filtering to T1The ash of target surface image
Degree figure i (x) carries out smooth operation, obtains filtering image f (x).Noise reduction effect and real-time are taken into account, filter radius is set as 7.
Binary conversion treatment is carried out using Da-Jin algorithm to filtering image f (x), obtains initial target surface region b (x), calculation formula
It is as follows:
Next morphologic filtering is carried out to initial target surface region b (x), includes not only target surface region in b (x), further includes
Some tiny empty targets.It is operated used here as morphological erosion, filters out these empty targets, obtain inceptive filtering image m (x),
The filtering core used is 5 × 5 rectangle core.
Then to image m (x) carry out connected domain analysis, by the lesser connected domain of area (number usually on target surface) into
Row is rejected, and the area threshold set here is 5000.The target center of standard target sheet is white, and the number of target center is grey, standard target
The non-target center of paper is grey, and the number of non-target center is white.After above-mentioned steps are handled, the number at target center can be removed,
The hole of digital internal at non-target center can be filled, but not be completely removed.So, it is also necessary to the filtered figure of connected domain
As carrying out an inverse operation, carries out a connected domain analysis again to inverse image, remove the region of small area, set here
Area threshold is 30000.After above-mentioned processing, the accurate binaryzation exposure mask mask (x) of target surface is obtained, which does not include
Target center region.
The accurate binaryzation exposure mask mask (x) of target surface is obtained according to above-mentioned steps, below to how accurate using target surface
Binaryzation exposure mask mask (x) obtain T1Accurate scoring ring line image is illustrated.
For being accurately positioned, prior art is as follows:
Under normal circumstances, target center region is not distorted, and can be obtained according to the accurate binaryzation exposure mask mask (x) of target surface
To the picture element position information in target center region, and then fit accurate target center coordinate.Ideally, scoring ring line is multiple with target
Centered on the heart, the radius concentric circles incremental at multiple proportion.There are distortion in actual image, are corrected.It is existing
Fine positioning algorithm is usually to consider in the rectangular area of the scoring ring line pixel of coarse positioning, searches for actual scoring ring using Da-Jin algorithm
The scoring ring line of coarse positioning is remedied to practical scoring ring line position by line pixel.
The deficiencies in the prior art are to need to calculate by a large amount of binaryzation, time-consuming high.
It is accurate according to obtained target surface the present embodiment provides a kind of Binarization methods based on exposure mask for being accurately positioned
Binaryzation exposure mask mask (x) to T1Target surface image i (x) uses Da-Jin algorithm, disposably obtains T as shown in Figure 41Accurately
Scoring ring line image res (x), calculation formula is as follows:
In order to more clearly understand the present invention, it is illustrated below with specific embodiment.
Fig. 5 is the specific implementation flow diagram of scoring ring line positioning, as shown, may include steps of:
Step 501 obtains T1The T at moment1Target surface image;
Step 502, to the T1Target surface image carries out noise reduction process;Here noise reduction is carried out using median filtering;
Step 503 carries out binary conversion treatment to the image after noise reduction process;
Step 504 obtains exposure mask according to the image progress connected component analysis after binaryzation;
Step 505, according to the exposure mask to the T1The grayscale image of target surface image carries out Da-Jin algorithm processing, obtains T1
Accurate scoring ring line image;
Step 506 is updated scoring ring line position information according to the time of setting and/or the condition of setting.
It is illustrated below to how updating scoring ring line position information in step 506.N cited below is oneself greater than 0
So number.
Fig. 6 is that flow diagram is embodied in the method that scoring ring line position information updates, as shown, may include as follows
Step:
Step 601 determines TNThe T at momentNAccurate scoring ring line image;The scoring ring line image includes TNThe target center at moment
Coordinate and each scoring ring line;
Step 602 obtains TNThe T at momentNThe scoring ring line image of coarse positioning;The scoring ring line image includes with TNMoment
Target center coordinate is each scoring ring line in the center of circle, the proportional relationship of radius;
Step 603 presses TNRectangle frame where each scoring ring line pixel of the scoring ring line image of coarse positioning is in TN+1Moment
TN+1Search pixel point on scoring ring line image;
Step 604 is fitted to obtain T according to the pixel searchedN+1The T at momentN+1Accurate scoring ring line image.
It can be with target surface shaking and/or illumination variation situation for the implementation of the method for above-mentioned scoring ring line position information update
It is condition or the time to set as condition.
For step 604, fitting algorithm is the algorithm of least square method fitting circle.
Based on the same inventive concept, a kind of device of scoring ring line positioning is additionally provided in the embodiment of the present invention, due to these
The principle that equipment solves the problems, such as is similar to a kind of method that scoring ring line positions, therefore the implementation of these equipment may refer to method
Implement, overlaps will not be repeated.
Fig. 7 is the apparatus structure schematic diagram of scoring ring line positioning, as shown, may include steps of:
Determining module 701, for determining TNThe T at momentNAccurate scoring ring line image, the TNAccurate scoring ring line
Image includes TNThe target center coordinate at moment and each scoring ring line, the N are the natural number greater than 0;
First obtains module 702, for obtaining TNThe T at momentNThe scoring ring line image of coarse positioning, the TNCoarse positioning
Scoring ring line image include with TNThe target center coordinate at moment is each scoring ring line in the center of circle, the proportional relationship of radius;
Second obtains module 703, for it needs to be determined that TN+1The T at momentN+1When accurate scoring ring line image, obtain
TN+1The T at momentN+1Target surface image;
Search module 704, in the TN+1The T at momentN+1The T is pressed on target surface imageNThe scoring ring of coarse positioning
Each scoring ring line of line image scans for;
Fitting module 705, for according to the T searchedN+1The T at momentN+1Each scoring ring line pixel of target surface image
Point fitting obtains TN+1The T at momentN+1Accurate scoring ring line image.
In implementation, search module is further used for by the TNEach scoring ring line pixel of the scoring ring line image of coarse positioning
The rectangle frame position at place is in the TN+1The T at momentN+1The rectangle frame of corresponding position scans on target surface image.
In implementation, fitting module is further used for according to the T searchedN+1The T at momentN+1Each target of target surface image
Loop wire pixel carries out the circle fitting based on least square method and obtains TN+1The T at momentN+1Accurate scoring ring line image.
In implementation, determining module is further used for:
Obtain T1The T at moment1Target surface image;
By the T1Connected component analysis is carried out after target surface image binaryzation obtains exposure mask;Wherein, the connected region
It analyzes for rejecting the number on target surface and the hole inside stuffing digit, which does not include target center region;
According to the exposure mask to the T1The grayscale image of target surface image carries out Da-Jin algorithm processing, obtains T1Accurate target
Loop wire image.
In implementation, determining module is further used for the T1Before target surface image binaryzation, to the T1Target surface figure
As carrying out noise reduction process.
In implementation, determining module is further used in noise reduction process using median filter process.
In conclusion determining a certain accurate scoring ring line image (T in technical solution provided in an embodiment of the present inventionN
Moment) after, when it needs to be determined that next accurate scoring ring line image (TN+1Moment) when, with the target center of the accurate scoring ring line image
Coordinate is the center of circle, re-forms each scoring ring line of the proportional relationship of radius, obtains the scoring ring line image (T of corresponding coarse positioningNWhen
Carve), it is then scanned for by each scoring ring line of the scoring ring line image of the coarse positioning, is pressing the TNThe scoring ring line chart of coarse positioning
When each scoring ring line of picture scans for, accurate each scoring ring line pixel can be quickly navigated to, then by being directly fitted just
T can be obtainedN+1The T at momentN+1Accurate scoring ring line image.Reduce the distortion correction step to target surface image, and does not have
A large amount of Binarization methods are used when being accurately positioned, and quickly update the coordinate of the pixel of each scoring ring line, it is time-consuming short.
Simultaneously as when using technical solution provided in an embodiment of the present invention, can by being updated constantly, that is,
After obtaining the accurate scoring ring line image at a certain moment, the accurate scoring ring line chart for obtaining subsequent time can be successively updated
Picture, therefore practice shooting for a long time the target surface shaking occurred in the process, illumination variation etc. can be overcome, so that this programme is practiced shooting for a long time
Strong, robustness height is adapted to illumination variation in the process.
To sum up, the real-time and robustness of scoring ring line position fixing process can be improved using this programme.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (12)
1. a kind of method of scoring ring line positioning characterized by comprising
Determine TNThe T at momentNAccurate scoring ring line image, the TNAccurate scoring ring line image includes TNThe target center at moment is sat
Mark, the N are the natural number greater than 0;
Obtain TNThe T at momentNThe scoring ring line image of coarse positioning, the TNThe scoring ring line image of coarse positioning includes with TNMoment
Target center coordinate is each scoring ring line in the center of circle, the proportional relationship of radius;
It needs to be determined that TN+1The T at momentN+1When accurate scoring ring line image, T is obtainedN+1The T at momentN+1Target surface image;
In the TN+1The T at momentN+1The T is pressed on target surface imageNEach scoring ring line of the scoring ring line image of coarse positioning is searched
Rope;
According to the T searchedN+1The T at momentN+1Each scoring ring line pixel of target surface image is fitted to obtain TN+1The of moment
TN+1Accurate scoring ring line image.
2. the method according to claim 1, wherein described in the TN+1The T at momentN+1It is pressed on target surface image
The TNEach scoring ring line of the scoring ring line image of coarse positioning scans for, and is by the TNThe scoring ring line image of coarse positioning
Rectangle frame position where each scoring ring line pixel is in the TN+1The T at momentN+1The rectangle frame of corresponding position on target surface image
It scans for.
3. the method according to claim 1, wherein the circle fitting being fitted to based on least square method.
4. method according to any one of claims 1 to 3, which is characterized in that determine T1The T at moment1Accurate scoring ring line chart
Picture specifically includes:
Obtain T1The T at moment1Target surface image;
By the T1Connected component analysis is carried out after target surface image binaryzation obtains exposure mask;Wherein, the connected component analysis is used
In rejecting the number on target surface and the hole inside stuffing digit, which does not include target center region;
According to the exposure mask to the T1The grayscale image of target surface image carries out Da-Jin algorithm processing, obtains T1Accurate scoring ring line
Image.
5. according to the method described in claim 4, it is characterized in that, to the T1Before target surface image binaryzation, further wrap
It includes:
To the T1Target surface image carries out noise reduction process.
6. according to the method described in claim 5, it is characterized in that, the noise reduction process includes median filter process.
7. a kind of device of scoring ring line positioning characterized by comprising
Determining module, for determining TNThe T at momentNAccurate scoring ring line image, the TNAccurately scoring ring line image includes
TNThe target center coordinate at moment, the N are the natural number greater than 0;
First obtains module, for obtaining TNThe T at momentNThe scoring ring line image of coarse positioning, the TNThe scoring ring line of coarse positioning
Image includes with TNThe target center coordinate at moment is each scoring ring line in the center of circle, the proportional relationship of radius;
Second obtains module, for it needs to be determined that TN+1The T at momentN+1When accurate scoring ring line image, T is obtainedN+1Moment
TN+1Target surface image;
Search module, in the TN+1The T at momentN+1The T is pressed on target surface imageNThe scoring ring line image of coarse positioning
Each scoring ring line scans for;
Fitting module, for according to the T searchedN+1The T at momentN+1Each scoring ring line pixel of target surface image is fitted
To TN+1The T at momentN+1Accurate scoring ring line image.
8. device according to claim 7, which is characterized in that search module is further used for by the TNCoarse positioning
Rectangle frame position where each scoring ring line pixel of scoring ring line image is in the TN+1The T at momentN+1It is corresponding on target surface image
The rectangle frame of position scans for.
9. device according to claim 7, which is characterized in that fitting module is further used for according to searching
TN+1The T at momentN+1Each scoring ring line pixel of target surface image carries out the circle fitting based on least square method and obtains TN+1Moment
TN+1Accurate scoring ring line image.
10. according to any device of claim 7 to 9, which is characterized in that determining module is further used for:
Obtain T1The T at moment1Target surface image;
By the T1Connected component analysis is carried out after target surface image binaryzation obtains exposure mask;Wherein, the connected component analysis is used
In rejecting the number on target surface and the hole inside stuffing digit, which does not include target center region;
According to the exposure mask to the T1The grayscale image of target surface image carries out Da-Jin algorithm processing, obtains T1Accurate scoring ring line
Image.
11. device according to claim 10, which is characterized in that determining module is further used for the T1Target surface
Before image binaryzation, to the T1Target surface image carries out noise reduction process.
12. device according to claim 11, which is characterized in that determining module is further used for using in noise reduction process
Median filter 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 CN105976366A (en) | 2016-09-28 |
CN105976366B true 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) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
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 |
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 |
---|
基于图像技术的智能报靶系统设计;张丽霞;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120715(第7期);第3章第3.1-3.4节 |
Also Published As
Publication number | Publication date |
---|---|
CN105976366A (en) | 2016-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106875444B (en) | A kind of object localization method and device | |
CN110147721B (en) | Three-dimensional face recognition method, model training method and device | |
CN106960427A (en) | The method and apparatus of image in 2 D code processing | |
CN102646193B (en) | Segmentation method of character images distributed in ring shape | |
CN108985137A (en) | A kind of licence plate recognition method, apparatus and system | |
CN108701234A (en) | Licence plate recognition method and cloud system | |
CN111145163B (en) | Paper wrinkle defect detection method and device | |
CN105488791B (en) | The localization method and device of image border in natural background | |
CN105976366B (en) | A kind of method and device of scoring ring line positioning | |
CN107146200B (en) | Unmanned aerial vehicle remote sensing image splicing method based on image splicing quality evaluation | |
CN108537787B (en) | Quality judgment method for face image | |
CN104268853A (en) | Infrared image and visible image registering method | |
CN110189322A (en) | Measurement method of planeness, device, equipment, storage medium and system | |
CN105513046A (en) | Method and system for identifying electronic component poles, method and system for marking electronic component poles | |
CN104517101A (en) | Game poker card recognition method based on pixel square difference matching | |
CN110458940A (en) | The processing method and processing unit of motion capture | |
CN108846385A (en) | Based on convolution-deconvolution neural network image recognition, bearing calibration and device | |
CN116052222A (en) | Cattle face recognition method for naturally collecting cattle face image | |
JP2018120445A (en) | Car number recognition apparatus | |
CN111191535A (en) | Pedestrian detection model construction method based on deep learning and pedestrian detection method | |
CN106651962A (en) | Adaptive light compensation method based on projector-camera system | |
CN108805144A (en) | Shell hole recognition methods based on morphology correction and system, indication of shots equipment | |
CN109993090B (en) | Iris center positioning method based on cascade regression forest and image gray scale features | |
TWI383690B (en) | Method for image processing | |
CN107194310A (en) | The rigid-object tracking matched based on scene change classifications and online local feature |
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 |