CN108805144A - Shell hole recognition methods based on morphology correction and system, indication of shots equipment - Google Patents
Shell hole recognition methods based on morphology correction and system, indication of shots equipment Download PDFInfo
- Publication number
- CN108805144A CN108805144A CN201810555766.4A CN201810555766A CN108805144A CN 108805144 A CN108805144 A CN 108805144A CN 201810555766 A CN201810555766 A CN 201810555766A CN 108805144 A CN108805144 A CN 108805144A
- Authority
- CN
- China
- Prior art keywords
- image
- target surface
- shell hole
- target
- morphology
- 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.)
- Pending
Links
- 238000012937 correction Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000000877 morphologic effect Effects 0.000 claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 13
- 230000003044 adaptive effect Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 7
- 238000007619 statistical method Methods 0.000 claims description 6
- 238000011835 investigation Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims 1
- 238000003702 image correction Methods 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000017105 transposition Effects 0.000 description 2
- 239000000729 antidote Substances 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of shell hole recognition methods based on morphology correction and system, indication of shots equipment, wherein method to include：Morphological scale-space is carried out to the target surface original image after the target practice of acquisition, target surface original image is remedied on the target image of arbitrary linear distortion, obtains target surface correcting image；Front and back two frames target surface correcting image is corrected to morphology and carries out the frame difference processing based on different threshold values, obtains the profile in target surface correcting image；Based on the outline identification shell hole in target surface correcting image.Shell hole recognition methods and system provided by the invention based on morphology correction, and the indication of shots equipment including the shell hole identifying system, it is remedied on the target image of arbitrary linear distortion by the target surface original image after the target practice by acquisition, shell hole identification is carried out using the image after correction, so as to avoid using in the presence of the identification error caused by the original image Direct Recognition shell hole to distort, accuracy of identification and environmental suitability are substantially increased.
Description
Technical field
The present invention relates to image pattern recognition field more particularly to a kind of shell hole identification sides based on morphology correction
Method and system, indication of shots equipment.
Background technology
Currently, automatic scoring round target system is more used in target practice scene.In hit telling system based on image recognition
Shell hole identification general flow be：System inputs a width and is hit by a bullet front and back image as sample to be identified, is based on image procossing skill
Art (such as frame difference method) identifies shell hole.
Existing shell hole recognition methods has the following defects：During practical target practice, often it will appear because target is fixed loosely
Or the violent shaking of middle target moment target surface caused by the factors such as environment (such as strong wind), it is collected front and back so as to cause hit telling system
There is distortion in image.Use the picture Direct Recognition shell hole obtained in these cases, it will greatly increase the difficulty of shell hole identification
Degree, to make indication of shots result larger error occur.
Invention content
Based on this, the present invention provides it is a kind of based on morphology correction shell hole recognition methods and system, indication of shots equipment,
Using being handled original picture based on morphologic antidote before identification shell hole, to substantially increase accuracy of identification with
Environmental suitability.
Shell hole recognition methods provided by the invention based on morphology correction, including：
Morphology rectification step：Morphological scale-space is carried out to the target surface original image after the target practice of acquisition, by the target
Face original image is remedied on the target image of arbitrary linear distortion, obtains target surface correcting image；
Subregion frame difference step：Front and back two frames target surface correcting image is corrected to the morphology to carry out based on difference
The frame difference of threshold value is handled, and obtains the profile in the target surface correcting image；
Shell hole identification step：Based on the outline identification shell hole in the target surface correcting image.
As a kind of embodiment, the morphology rectification step includes the following steps：
Four are obtained on the coordinate and the target image on four vertex for waiting for corrected zone in the target surface original image
The coordinate on vertex；
Four on coordinate and the target image based on four vertex for waiting for corrected zone in the target surface original image
The coordinate on vertex calculates correction matrix using Morphological scale-space technology；
The target surface original image is mapped to according to the correction matrix on the target image, target mapping graph is obtained
Picture；
Target mapping image is smoothed, the target surface correcting image is obtained.
As a kind of embodiment, the subregion frame difference step includes the following steps：
In the morphology is corrected to obtain front and back two frames target surface correcting image, screened respectively using gray-scale statistical method
Go out the tonal range of green area and white area；
According to the current corresponding frame difference threshold value of tonal range adaptive generation；
The frame calculated between front and back two frame target surface correcting images is poor, if frame difference result of calculation is less than the investigation threshold of corresponding region
Value, then be set as 255, conversely, being set as 0 by the pixel value.
As a kind of embodiment, the shell hole identification step includes the following steps：
Pass through canny (Computational theory of edge detection, edge detection) operator extraction wheel
Wide edge；
Calculate the confidence level parameter of profile；
Profile by confidence level parameter higher than given threshold is determined as shell hole.
It is provided by the invention based on morphology correction shell hole recognition methods, after the frame difference step of subregion, further include with
Lower step：
The number of effective shell hole is identified according to the confidence level parameter of the profile in the target surface correcting image.
Correspondingly, the present invention also provides a kind of shell hole identifying systems based on morphology correction, including morphology to correct mould
Block, subregion frame difference module and shell hole identification module；
The morphology rectification module, for carrying out Morphological scale-space to the target surface original image after the target practice of acquisition, with
The target surface original image is remedied on the target image of arbitrary linear distortion, target surface correcting image is obtained；
The subregion frame difference module is carried out for correcting front and back two frames target surface correcting image to the morphology
Frame difference processing based on different threshold values, obtains the profile in the target surface correcting image；
The shell hole identification module, for based on the outline identification shell hole in the target surface correcting image.
As a kind of embodiment, the morphology rectification module includes coordinate acquiring unit, correction matrix calculating list
Member, map unit and smoothing processing unit；
The coordinate acquiring unit, the coordinate for obtaining four vertex for waiting for corrected zone in the target surface original image
With the coordinate on four vertex on the target image；
The correction matrix calculation unit, for based on four vertex for waiting for corrected zone in the target surface original image
The coordinate on four vertex on coordinate and the target image calculates correction matrix using Morphological scale-space technology；
The map unit, for the target surface original image to be mapped to the target image according to the correction matrix
On, obtain target mapping image；
The smoothing processing unit obtains the target surface correction for being smoothed to target mapping image
Image.
As a kind of embodiment, the subregion frame difference module include gray-scale statistical unit, adaptive unit and
Frame difference computing unit；
The gray-scale statistical unit, used in correcting to obtain front and back two frames target surface correcting image in the morphology, profit
Filter out the tonal range of green area and white area respectively with gray-scale statistical method；
The adaptive unit, for according to the current corresponding frame difference threshold value of tonal range adaptive generation；
The frame difference computing unit, it is poor for calculating the frame between front and back two frames target surface correcting image, if frame difference calculates knot
Fruit is less than the investigation threshold value of corresponding region, then the pixel value is set as 255, conversely, being set as 0.
As a kind of embodiment, the shell hole identification module includes contour edge extraction unit, confidence level parameter meter
Calculate unit and recognition unit；
The contour edge extraction unit, for passing through canny operator extraction contour edges；
The confidence level parameter calculation unit, the confidence level parameter for calculating profile；
The recognition unit is determined as shell hole for the profile by confidence level parameter higher than given threshold.
Shell hole identifying system provided by the invention based on morphology correction, further includes shell hole quantity identification module；
The shell hole quantity identification module is used for after the processing of subregion frame difference, according in the target surface correcting image
The confidence level parameter of profile identifies the number of effective shell hole.
Correspondingly, the present invention also provides a kind of indication of shots equipment, including input unit, processing unit and output device；
The input unit, inside sets camera, for obtaining the target surface original image after practicing shooting by the camera；
The processing unit is separately connected the input unit and the output device, and built-in claim 6 to 10 times
The shell hole identifying system based on morphology correction described in one；
The processing unit obtains target surface original image from the input unit, and is known based on the shell hole identifying system
Other shell hole exports indication of shots through the output device.
Compared with prior art, the technical program has the following advantages：
Shell hole recognition methods and system provided by the invention based on morphology correction, and including the shell hole identifying system
Indication of shots equipment the target surface original image after the target practice of acquisition is remedied to arbitrary linear first with morphology correcting technology
On the target image of distortion, it is ensured that do not lose artwork information；Then subregion frame difference technology is utilized, morphology is corrected
It is poor that front and back image carries out the frame based on different threshold values, obtains profile；Finally, in subregion, frame difference obtains identifying shell hole in profile.
The present invention is remedied to by the target surface original image after the target practice by acquisition on the target image of arbitrary linear distortion, and correction is utilized
Image afterwards carries out shell hole identification, so as to avoid using in the presence of the identification caused by the original image Direct Recognition shell hole to distort
Error substantially increases accuracy of identification and environmental suitability.
Description of the drawings
Fig. 1 is the flow diagram for the shell hole recognition methods corrected based on morphology that the embodiment of the present invention one provides；
Fig. 2 is the morphology correcting process for the shell hole recognition methods corrected based on morphology that the embodiment of the present invention one provides
Schematic diagram；
Fig. 3 a are A [8] [8] matrix schematic diagram；
Fig. 3 b are B [8] matrix schematic diagram
Fig. 4 is smoothing processing exemplary plot；
Fig. 5 is the structural schematic diagram of the shell hole identifying system provided by Embodiment 2 of the present invention based on morphology correction；
Fig. 6 is the structural schematic diagram for the indication of shots equipment that the embodiment of the present invention three provides.
Specific implementation mode
Below in conjunction with attached drawing, the technical characteristic and advantage above-mentioned and other to the present invention are clearly and completely described,
Obviously, described embodiment is only the section Example of the present invention, rather than whole embodiments.
Referring to Fig. 1, the shell hole recognition methods corrected based on morphology that the embodiment of the present invention one provides, including morphology
Rectification step, subregion frame difference step and shell hole identification step, specific method are as shown in Figure 1：
S100, Morphological scale-space is carried out to the target surface original image after the target practice of acquisition, target surface original image is corrected
Onto the target image of arbitrary linear distortion, target surface correcting image is obtained；
S200, front and back two frames target surface correcting image is corrected to morphology carry out at the frame difference based on different threshold values
Reason, obtains the profile in target surface correcting image；
S300, based on the outline identification shell hole in target surface correcting image.
Before above-mentioned steps S100, need first to obtain the target surface original image after practicing shooting using image acquiring device, so
Morphological images correcting technology is utilized afterwards, target surface original image is remedied on the target image of arbitrary linear distortion, and ensure
Artwork information is not lost.
The case where being directed to multiple target practice can also include the following steps after the frame difference step of subregion：It is rectified according to target surface
The confidence level parameter of profile in positive image identifies the number of effective shell hole.
Target surface original image after the target practice of acquisition is remedied to arbitrarily by the present embodiment first with morphology correcting technology
On the target image of linear distortion, it is ensured that do not lose artwork information；Then subregion frame difference technology is utilized, morphology is corrected
To front and back image to carry out the frame based on different threshold values poor, obtain profile；Finally, in subregion, frame difference obtains identifying bullet in profile
Hole.It is remedied to by the target surface original image after the target practice by acquisition on the target image of arbitrary linear distortion, and correction is utilized
Image afterwards carries out shell hole identification, so as to avoid using in the presence of the identification caused by the original image Direct Recognition shell hole to distort
Error substantially increases shell hole accuracy of identification and its environmental suitability.
Further, the morphology correction in S100 can specifically be realized by following steps：
S110, four vertex on the coordinate and target image on four vertex for waiting for corrected zone in target surface original image are obtained
Coordinate；
Four vertex on S120, coordinate and target image based on four vertex for waiting for corrected zone in target surface original image
Coordinate, utilize Morphological scale-space technology, calculate correction matrix；
S130, target surface original image is mapped to according to correction matrix on target image, obtains target mapping image；
S140, target mapping image is smoothed, obtains target surface correcting image.
As shown in Fig. 2, with by some irregular 4 side shape in target surface original image S, it is adjusted to regular shown in target image D
Rectangle morphology correcting process for：Specifically, the original image S that hit telling system shooting is obtained is as sample to be identified
This, will be waited in original image S four vertex of corrected zone coordinate be respectively (s [i] .x, s [i] .y), (i=0,1,2,3.),
Four vertex in corresponding target image D are (d [i] .x, d [i] .y), and (i=0,1,2,3.) is obtained respectively according to apex coordinate
To matrix A [8] [8], B [8], as shown in Figure 3a and Figure 3b shows.To matrix A [8] [8] carry out singular value decomposition obtain three matrix Us,
W, V so that they meet A=UWVT, wherein VTThe transposition of representing matrix V, then correcting matrix X [9] can ask according to following formula
?：X=V (W*)TB, wherein (W*) T indicate W adjoint matrix transposition, the value of last X [8] of X [9] is set as 1, then
3 × 3 form is translated into get correction matrix X [3] [3].
Further, when original image S being mapped to correction target image D, i.e., image is mapped to target from original image S
When image D, for any point (dx, dy) in target image D, corresponding point (sx, sy) is in original image S：
According to above-mentioned formula obtained (sx, sy) and non-integer, if rounding up to coordinate (sx, sy), and take corresponding
The value of point carries out assignment to (dx, dy), and the image after correcting will produce more sawtooth, particularly tight at the edge contour of object
Weight.Therefore also need to be smoothed, as shown in Figure 4：
Image is smoothed, is to find out weighted average by the value of 4 points around required (sx, sy), with gray scale
For figure, the coordinate of four points is respectively around point (sx, sy) (note：Indicate to carry out downward rounding to sx), gray value is respectively V11、V12、V21、V22, then
Weighted averageComputational methods be：
X in formulas、ys
The fractional part for indicating sx, sy respectively acquires weighted average as stated above to each of correction target figure D pointsAnd it will
Its as point (dx, dy) value to get to complete correcting image.For coloured image, including tri- kinds of colors of RGB, by above-mentioned
The weighted average that method finds out three channels respectively is respectivelyIt can be obtained complete correcting image.
Further, the subregions S200 frame is poor, can be realized by following steps：
S210, in morphology is corrected to obtain front and back two frames target surface correcting image, sieved respectively using gray-scale statistical method
Select the tonal range of green area and white area；
S220, according to the current corresponding frame difference threshold value of tonal range adaptive generation；
Frame before and after S230, calculating between two frame target surface correcting images is poor, if frame difference result of calculation is less than corresponding region
Threshold value is investigated, then the pixel value is set as 255, conversely, being set as 0.
Further, S300 shell holes identify, can be realized by following steps：
S310, pass through canny operator extraction contour edges；
S320, the confidence level parameter for calculating profile；
S330, the profile by confidence level parameter higher than given threshold are determined as shell hole.
Based on same inventive concept, as shown in figure 5, the embodiment of the present invention two also provides a kind of bullet corrected based on morphology
Hole identifying system, including morphology rectification module 100, subregion frame difference module 200 and shell hole identification module 300.Morphology
Rectification module 100 is used to carry out Morphological scale-space to the target surface original image after the target practice of acquisition, and target surface original image is rectified
Just on the target image of arbitrary linear distortion, target surface correcting image is obtained；Subregion frame difference module 200 is used to rectify morphology
The front and back two frames target surface correcting image just obtained carries out the processing of the frame difference based on different threshold values, obtains the wheel in target surface correcting image
It is wide；Shell hole identification module 300 is used for based on the outline identification shell hole in target surface correcting image.
Morphology rectification module 100 includes coordinate acquiring unit 110, correction matrix calculation unit 120, map unit 130
And smoothing processing unit 140.
Coordinate acquiring unit 110 is used to obtain the coordinate and target on four vertex that corrected zone is waited in target surface original image
The coordinate on four vertex on image；Correction matrix calculation unit 120 is used for based on waiting for the four of corrected zone in target surface original image
The coordinate on four vertex on the coordinate and target image on a vertex calculates correction matrix using Morphological scale-space technology；Mapping is single
Member 130 obtains target mapping image for target surface original image to be mapped to target image according to correction matrix；Smoothing processing
Unit 140 is used to be smoothed target mapping image, obtains target surface correcting image.
Subregion frame difference module 200 includes gray-scale statistical unit 210, adaptive unit 220 and frame difference computing unit
230。
Gray-scale statistical unit 210 is used in morphology is corrected to obtain front and back two frames target surface correcting image, utilizes gray scale
Statistical method filters out the tonal range of two kinds of regions of different colours respectively；Adaptive unit 220 is used for according to current gray scale
The corresponding frame difference threshold value of range adaptive generation；Frame difference computing unit 230 is used to calculate between front and back two frames target surface correcting image
Frame it is poor, if frame difference result of calculation be less than corresponding region investigation threshold value, which is set as 255, conversely, setting
It is 0.
Shell hole identification module 300 includes contour edge extraction unit 310, confidence level parameter calculation unit 320 and identification
Unit 330.
Contour edge extraction unit 310 is used to pass through canny operator extraction contour edges；Confidence level parameter calculation unit
The 320 confidence level parameter for calculating profile；The profile that recognition unit 330 is used for by confidence level parameter higher than given threshold judges
For shell hole.
Further, the shell hole identifying system provided by Embodiment 2 of the present invention based on morphology correction, further includes shell hole
Quantity identification module 400；Shell hole quantity identification module 400 is used for after the processing of subregion frame difference, according in target surface correcting image
The confidence level parameter of profile identify the number of effective shell hole.
Based on same inventive concept, as shown in fig. 6, the embodiment of the present invention three also provides a kind of indication of shots equipment, including input
Device 10, processing unit 20 and output device 30；
Camera is set in input unit 10, for obtaining the target surface original image after practicing shooting by camera；
Processing unit 20 is separately connected input unit 10 and output device 30, and built-in embodiment two is strong based on morphology
Positive shell hole identifying system；Processing unit 20 obtains target surface original image from input unit 10, and is based on shell hole identifying system
It identifies shell hole, indication of shots is exported through output device 30.
Although the invention has been described by way of example and in terms of the preferred embodiments, but it is not for limiting the present invention, any this field
Technical staff without departing from the spirit and scope of the present invention, may be by the methods and technical content of the disclosure above to this hair
Bright technical solution makes possible variation and modification, therefore, every content without departing from technical solution of the present invention, and according to the present invention
Technical spirit to any simple modifications, equivalents, and modifications made by above example, belong to technical solution of the present invention
Protection domain.
Claims (11)
1. a kind of shell hole recognition methods based on morphology correction, which is characterized in that including：
Morphology rectification step：Morphological scale-space is carried out to the target surface original image after the target practice of acquisition, by target surface original
On beginning image flame detection to the target image of arbitrary linear distortion, target surface correcting image is obtained；
Subregion frame difference step：Front and back two frames target surface correcting image is corrected to the morphology to carry out being based on different threshold values
Frame difference processing, obtain the profile in the target surface correcting image；
Shell hole identification step：Based on the outline identification shell hole in the target surface correcting image.
2. the shell hole recognition methods according to claim 1 based on morphology correction, which is characterized in that the morphology is rectified
Positive step, includes the following steps：
Obtain four vertex on the coordinate and the target image on four vertex for waiting for corrected zone in the target surface original image
Coordinate；
Four vertex on coordinate and the target image based on four vertex for waiting for corrected zone in the target surface original image
Coordinate, utilize Morphological scale-space technology, calculate correction matrix；
The target surface original image is mapped to according to the correction matrix on the target image, target mapping image is obtained；
Target mapping image is smoothed, the target surface correcting image is obtained.
3. the shell hole recognition methods according to claim 1 based on morphology correction, which is characterized in that the subregion frame
Poor step, includes the following steps：
In the morphology is corrected to obtain front and back two frames target surface correcting image, filtered out respectively using gray-scale statistical method green
The tonal range in color region and white area；
According to the current corresponding frame difference threshold value of tonal range adaptive generation；
The frame calculated between front and back two frame target surface correcting images is poor, if frame difference result of calculation is less than the investigation threshold value of corresponding region,
The pixel value is then set as 255, conversely, being set as 0.
4. the shell hole recognition methods according to claim 1 based on morphology correction, which is characterized in that the shell hole identification
Step includes the following steps：
Pass through canny operator extraction contour edges；
Calculate the confidence level parameter of profile；
Profile by confidence level parameter higher than given threshold is determined as shell hole.
5. the shell hole recognition methods according to any one of claims 1 to 4 based on morphology correction, which is characterized in that
It is further comprising the steps of after the frame difference step of subregion：
The number of effective shell hole is identified according to the confidence level parameter of the profile in the target surface correcting image.
6. a kind of shell hole identifying system based on morphology correction, which is characterized in that including morphology rectification module, subregion frame
Difference module and shell hole identification module；
The morphology rectification module, for carrying out Morphological scale-space to the target surface original image after the target practice of acquisition, by institute
It states target surface original image to be remedied on the target image of arbitrary linear distortion, obtains target surface correcting image；
The subregion frame difference module is based on for correcting front and back two frames target surface correcting image to the morphology
The frame difference of different threshold values is handled, and obtains the profile in the target surface correcting image；
The shell hole identification module, for based on the outline identification shell hole in the target surface correcting image.
7. the shell hole identifying system according to claim 6 based on morphology correction, which is characterized in that the morphology is rectified
Positive module includes coordinate acquiring unit, correction matrix calculation unit, map unit and smoothing processing unit；
The coordinate acquiring unit, the coordinate for obtaining four vertex for waiting for corrected zone in the target surface original image and institute
State the coordinate on four vertex on target image；
The correction matrix calculation unit, for the coordinate based on four vertex for waiting for corrected zone in the target surface original image
With the coordinate on four vertex on the target image correction matrix is calculated using Morphological scale-space technology；
The map unit, for the target surface original image to be mapped to the target image according to the correction matrix,
Obtain target mapping image；
The smoothing processing unit obtains the target surface correcting image for being smoothed to target mapping image.
8. the shell hole identifying system according to claim 6 based on morphology correction, which is characterized in that the subregion frame
Difference module includes gray-scale statistical unit, adaptive unit and frame difference computing unit；
The gray-scale statistical unit utilizes ash used in correcting to obtain front and back two frames target surface correcting image in the morphology
Degree statistical method filters out the tonal range of green area and white area respectively；
The adaptive unit, for according to the current corresponding frame difference threshold value of tonal range adaptive generation；
The frame difference computing unit, it is poor for calculating the frame between front and back two frames target surface correcting image, if frame difference result of calculation is small
Investigation threshold value in corresponding region, then be set as 255 by the pixel value, conversely, being set as 0.
9. the shell hole identifying system according to claim 6 based on morphology correction, which is characterized in that the shell hole identification
Module includes contour edge extraction unit, confidence level parameter calculation unit and recognition unit；
The contour edge extraction unit, for passing through canny operator extraction contour edges；
The confidence level parameter calculation unit, the confidence level parameter for calculating profile；
The recognition unit is determined as shell hole for the profile by confidence level parameter higher than given threshold.
10. the shell hole identifying system corrected based on morphology according to claim 6 to 9 any one of them, which is characterized in that also
Including shell hole quantity identification module；
The shell hole quantity identification module is used for after the processing of subregion frame difference, according to the profile in the target surface correcting image
Confidence level parameter identify the number of effective shell hole.
11. a kind of indication of shots equipment, which is characterized in that including input unit, processing unit and output device；
The input unit, inside sets camera, for obtaining the target surface original image after practicing shooting by the camera；
The processing unit is separately connected any one of the input unit and the output device, and built-in claim 6 to 10
The shell hole identifying system based on morphology correction；
The processing unit obtains target surface original image from the input unit, and identifies bullet based on the shell hole identifying system
Hole exports indication of shots through the output device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810555766.4A CN108805144A (en) | 2018-06-01 | 2018-06-01 | Shell hole recognition methods based on morphology correction and system, indication of shots equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810555766.4A CN108805144A (en) | 2018-06-01 | 2018-06-01 | Shell hole recognition methods based on morphology correction and system, indication of shots equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108805144A true CN108805144A (en) | 2018-11-13 |
Family
ID=64090948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810555766.4A Pending CN108805144A (en) | 2018-06-01 | 2018-06-01 | Shell hole recognition methods based on morphology correction and system, indication of shots equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108805144A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948630A (en) * | 2019-03-19 | 2019-06-28 | 深圳初影科技有限公司 | Recognition methods, device, system and the storage medium of target sheet image |
| CN111222504A (en) * | 2019-11-18 | 2020-06-02 | 杭州晨鹰军泰科技有限公司 | Bullet hole target scoring method, device, equipment and medium |
| CN112507827A (en) * | 2020-11-30 | 2021-03-16 | 之江实验室 | Intelligent video target shooting real-time detection method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654085A (en) * | 2015-12-31 | 2016-06-08 | 杭州晨鹰军泰科技有限公司 | Image technology-based bullet hole recognition method |
| CN106802113A (en) * | 2016-12-23 | 2017-06-06 | 西安交通大学 | Intelligent hit telling system and method based on many shell hole algorithm for pattern recognitions |
| CN206247950U (en) * | 2016-12-01 | 2017-06-13 | 齐煦林 | A kind of automatic scoring round target system based on image procossing mechanism |
| CN107123145A (en) * | 2017-05-04 | 2017-09-01 | 济南大学 | Elevator button positioning and recognition methods based on artificial target and geometric transformation |
| CN107341793A (en) * | 2017-06-23 | 2017-11-10 | 浙江华睿科技有限公司 | A kind of target surface image processing method and device |
-
2018
- 2018-06-01 CN CN201810555766.4A patent/CN108805144A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654085A (en) * | 2015-12-31 | 2016-06-08 | 杭州晨鹰军泰科技有限公司 | Image technology-based bullet hole recognition method |
| CN206247950U (en) * | 2016-12-01 | 2017-06-13 | 齐煦林 | A kind of automatic scoring round target system based on image procossing mechanism |
| CN106802113A (en) * | 2016-12-23 | 2017-06-06 | 西安交通大学 | Intelligent hit telling system and method based on many shell hole algorithm for pattern recognitions |
| CN107123145A (en) * | 2017-05-04 | 2017-09-01 | 济南大学 | Elevator button positioning and recognition methods based on artificial target and geometric transformation |
| CN107341793A (en) * | 2017-06-23 | 2017-11-10 | 浙江华睿科技有限公司 | A kind of target surface image processing method and device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948630A (en) * | 2019-03-19 | 2019-06-28 | 深圳初影科技有限公司 | Recognition methods, device, system and the storage medium of target sheet image |
| CN109948630B (en) * | 2019-03-19 | 2020-03-31 | 深圳初影科技有限公司 | Target paper image identification method, device and system and storage medium |
| CN111222504A (en) * | 2019-11-18 | 2020-06-02 | 杭州晨鹰军泰科技有限公司 | Bullet hole target scoring method, device, equipment and medium |
| CN112507827A (en) * | 2020-11-30 | 2021-03-16 | 之江实验室 | Intelligent video target shooting real-time detection method |
| CN112507827B (en) * | 2020-11-30 | 2022-05-13 | 之江实验室 | Intelligent video target shooting real-time detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389135B (en) | Image screening method and device | |
| CN108197546B (en) | Illumination processing method and device in face recognition, computer equipment and storage medium | |
| US20090027521A1 (en) | Image processing apparatus, image-taking system, image processing method and image processing program | |
| CN105894458A (en) | Processing method and device of image with human face | |
| JPWO2006036027A1 (en) | Image processing apparatus and method, and image processing program | |
| CN110008968B (en) | Automatic triggering method for robot settlement based on image vision | |
| CN108805144A (en) | Shell hole recognition methods based on morphology correction and system, indication of shots equipment | |
| TW201419853A (en) | Image processor and image dead pixel detection method thereof | |
| CN112785534A (en) | Ghost-removing multi-exposure image fusion method in dynamic scene | |
| CN109064418A (en) | A kind of Images Corrupted by Non-uniform Noise denoising method based on non-local mean | |
| WO2019210707A1 (en) | Image sharpness evaluation method, device and electronic device | |
| CN111008563B (en) | Dim light scene seed germination detection method and device and readable storage medium | |
| CN112396016B (en) | Face recognition system based on big data technology | |
| CN107564041A (en) | A kind of detection method of visible images moving air target | |
| CN101510306B (en) | Estimation method for video image illumination distribution | |
| JP2015092643A (en) | Image processing device, image processing method thereof, computer program and image processing system | |
| CN110674737B (en) | Iris recognition enhancement method | |
| CN117351472A (en) | Tobacco leaf information detection method and device and electronic equipment | |
| CN112188190A (en) | Stain detection method, cooking appliance, server, and storage medium | |
| CN103226690B (en) | Detect blood-shot eye illness method and device, removal blood-shot eye illness method and device | |
| CN107424134A (en) | Image processing method, device, computer-readable recording medium and computer equipment | |
| JP5080416B2 (en) | Image processing apparatus for detecting an image of a detection object from an input image | |
| CN108848363A (en) | A kind of auto white balance method suitable for large scene | |
| CN108734703B (en) | Polished tile printing pattern detection method, system and device based on machine vision | |
| CN112907454B (en) | Method, device, computer equipment and storage medium for acquiring image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |