CN113028912B - Bullet primer priming charge filling amount detection method based on 3D vision - Google Patents
Bullet primer priming charge filling amount detection method based on 3D vision Download PDFInfo
- Publication number
- CN113028912B CN113028912B CN202110427803.5A CN202110427803A CN113028912B CN 113028912 B CN113028912 B CN 113028912B CN 202110427803 A CN202110427803 A CN 202110427803A CN 113028912 B CN113028912 B CN 113028912B
- Authority
- CN
- China
- Prior art keywords
- primer
- image
- bullet
- ellipse
- laser
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 230000037452 priming Effects 0.000 title claims description 16
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000005260 corrosion Methods 0.000 claims abstract description 6
- 230000007797 corrosion Effects 0.000 claims abstract description 6
- 238000013507 mapping Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims abstract description 5
- NIXOWILDQLNWCW-UHFFFAOYSA-N acrylic acid group Chemical group C(C=C)(=O)O NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 claims description 8
- 239000011521 glass Substances 0.000 claims description 3
- 230000003760 hair shine Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000000149 penetrating effect Effects 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 1
- 101150087909 cog3 gene Proteins 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000011031 large-scale manufacturing process Methods 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- YLJREFDVOIBQDA-UHFFFAOYSA-N tacrine Chemical compound C1=CC=C2C(N)=C(CCCC3)C3=NC2=C1 YLJREFDVOIBQDA-UHFFFAOYSA-N 0.000 description 1
- 229960001685 tacrine Drugs 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F42—AMMUNITION; BLASTING
- F42B—EXPLOSIVE CHARGES, e.g. FOR BLASTING, FIREWORKS, AMMUNITION
- F42B35/00—Testing or checking of ammunition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
Abstract
The invention provides a bullet primer filling amount detection method based on 3D vision. Firstly, preprocessing the acquired primer depth image by histogram equalization, binaryzation, expansion, hole removal and corrosion to obtain a high-quality image. Then, performing circle domain detection on the preprocessed primer depth image by adopting a rapid ellipse detection method based on an arc adjacency matrix, and fitting to obtain the circle center C of each circle domain i . Thirdly, calculating the center C of each ellipse i Euclidean distance rho between the ellipse centroid and the ellipse centroid i And determining the target circular domain. And finally, respectively reducing the target circular area by two times and four times, mapping the target circular area to the primer depth image, and acquiring height information of a corresponding area so as to judge the filling amount of the primer of the bullet. The method has the advantages of high real-time property, strong robustness and high accuracy in detecting the filling quantity of the primer of the bullet.
Description
Technical Field
The invention relates to the field of non-contact detection of the quality of industrial products, in particular to a method for detecting the filling amount of primer priming charge of a bullet.
Background
The bullet is the indispensable partly in the weaponry, optimizes the production technology of weaponry, promotes the yields, is favorable to promoting the input-output ratio, ensures the needs of fighting immediately. The primer has the characteristics of long storage time, high ignition stability, safe use and the like, and is widely applied to ignition devices at the bottoms of various bullets and guns. The primer shell is filled with the primer, and plays a role in igniting when the bullet is fired. In the production process, the phenomenon of unqualified primer priming charge filling inevitably exists due to a plurality of production links. Primer is used as the key for igniting the bullet, the success rate of bullet firing is influenced when the primer is filled too little, and unnecessary waste is caused when the primer is filled too much.
The traditional primer production line generally adopts 2D visual detection to detect the primer priming charge filling amount. The detection mode cannot sense the height information of the primer surface, so that the accuracy of primer priming filling quantity detection is low. With the new requirements of the large-scale production of the primer on the detection speed and the detection precision, the existing detection mode is difficult to meet the detection of the primer priming charge filling amount. Therefore, a product which is unqualified in primer priming filling is detected and removed by full-automatic detection equipment with high speed, high precision and strong stability is urgently needed in the primer priming filling amount detection process.
Disclosure of Invention
Aiming at the problems, the invention provides a bullet primer priming charge filling amount detection method based on 3D vision, which can accurately, quickly and efficiently extract a target circular domain in a bullet primer image and obtain height information of the target circular domain so as to judge the bullet primer priming charge filling amount. The invention comprises the following contents:
s100, horizontally placing the top of a bullet primer upwards on a transparent acrylic conveying plate, moving the transparent acrylic conveying plate forwards at a fixed speed v, triggering a photoelectric sensor after the bullet primer reaches an imaging area, starting line laser to project laser to the top of the bullet primer at a time interval of t, starting a camera to acquire images of laser lines projected to the top of the primer at the time interval of t, and continuously acquiring n images containing the laser lines; the line laser projects laser lines vertically 90 degrees downwards, the camera obliquely photographs the ground fire at an angle alpha with the horizontal direction, and the annular light shines the bottom of the ground fire in a mode of penetrating through the glass conveying plate;
s200, continuously collecting n primer images containing laser lines with the size of (k, j), respectively extracting laser center lines in the images, obtaining depth information of each point on each laser line according to the formula (1), obtaining the depth information of (n multiplied by k) points through the n laser center lines, and synthesizing a depth image Bin 10;
in the formula, P is the point that laser throws on the detection object surface, O is the point that line laser center virtual projects on transparent ya keli conveying plate, M is the focus of camera, A is the point that O point appears on the camera, B is the point that P point appears on the camera, OA and PB all pass through focus M, A is theta with the laser line contained angle, OA is with camera mirror surface contained angle for
S300, preprocessing the depth image Bin10 by histogram equalization, binarization, expansion, hole removal and corrosion to obtain a high-quality image Bin 20;
s400, performing circle domain detection on the image Bin20 by adopting a rapid ellipse detection method based on an arc adjacency matrix, and fitting to obtain the circle center C of each ellipse i Combining with the Euclidean distance method to obtain the centroid E of the image Bin20 and the center C of each fitted ellipse i Euclidean distance ρ between them i According to rho i Judging a true circle in the image, and accurately extracting a target circle domain;
s500, reducing the target circular area by two times and four times respectively, mapping the target circular area to the primer depth image to obtain a primer large circular area and a primer small circular area, and extracting height information in the large circular area and the small circular area respectively to judge the filling amount of the primer priming agent of the bullet.
The invention has the following advantages:
1. the method for extracting the primer powder surface height based on the 3D vision has high precision and high speed, can meet the requirement on precision in primer industrial vision detection, and can well fit the beat of the primer in industrial production;
2. the bullet primer priming filling detection method based on 3D vision has good robustness and strong anti-interference capability.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a schematic view of a bullet primer detection station;
FIG. 3 is a schematic illustration of bullet primer image preprocessing;
FIG. 4 is a schematic diagram of the distance between the center of the fitted ellipse and the center of mass of the image;
fig. 5 is a schematic diagram of an image height information extraction area.
The specific implementation mode is as follows:
in the implementation of the invention, a Basler acA640-90gc camera is selected, the resolution is 658x 492, and the theoretical frame rate is 90 fps; a M5018-MP2 lens from computer was used, which had a focal length of 50 mm. The camera is combined with the lens to obtain images, and forms a 3D vision system together with the line laser to measure distance.
The flow chart of the technical scheme of the invention is shown in figure 1, and the specific implementation steps are as follows:
s100, horizontally placing the top of a bullet primer upwards on a transparent acrylic conveying plate, moving the transparent acrylic conveying plate forwards at a fixed speed v, triggering a photoelectric sensor after the bullet primer reaches an imaging area, starting line laser to project laser to the top of the bullet primer at a time interval of t, starting a camera to acquire images of laser lines projected to the top of the primer at the time interval of t, and continuously acquiring n images containing the laser lines; the line laser projects laser lines vertically at 90 degrees downwards, the camera photographs obliquely at an angle alpha with the horizontal direction, and the annular light shines the bottom of the primer in a mode of penetrating through the glass conveying plate;
s200, continuously collecting n primer images containing laser lines with the size of (k, j), respectively extracting laser center lines in the images, obtaining depth information of each point on each laser line according to the formula (1), obtaining the depth information of (n multiplied by k) points through the n laser center lines, and synthesizing a depth image Bin 10;
in the formula, P is a point projected by laser on the surface of a detected object, O is a point virtually projected by the center of line laser on the transparent acrylic transmission plate, M is the focus of a camera, A is a point presented by the point O on the camera, B is a point presented by the point P on the camera, OA and PB both pass through the focus M, the included angle between A and the laser line is theta, and the included angle between OA and the mirror surface of the camera is thetaThe bullet primer detection station is shown in figure 2;
s300, preprocessing the depth image Bin10 by histogram equalization, binarization, expansion, hole removal and corrosion to obtain a high-quality image Bin 20; image pre-processing and pre-processing are shown in FIG. 3;
s310, obtaining a gray level histogram of the depth image, normalizing the gray level histogram, then enhancing the contrast of the image through histogram equalization transformation, and highlighting a clear image edge to obtain an image Bin 11;
s320, calculating the inter-class variance of the image Bin11, using the maximum inter-class variance G as a threshold value, binarizing the image Bin11, eliminating a side circular ring area in the image, and reserving a circular area; after binarization, extracting a connected domain from the image by adopting a run-length method, and eliminating a noise region with a smaller area to obtain an image Bin 12;
s330, setting an expansion operator, and eliminating a noise area contained in the foreground image by using expansion operation to completely distinguish the background from the foreground to obtain an image Bin 13;
s340, eliminating internal noise points in the image through a hole elimination algorithm to obtain an image Bin 14;
s350, restoring the edge area which is mistakenly eliminated by the expansion operation by adopting corrosion operation, and finally obtaining a high-quality image Bin 20;
s400, performing circle domain detection on the image Bin20 by adopting a rapid ellipse detection method based on an arc adjacency matrix, and fitting to obtain the circle center C of each ellipse i Combining with the Euclidean distance method to obtain the centroid E of the image Bin20 and the center C of each fitted ellipse i Euclidean distance ρ between them i According to rho i Judging the true circle in the image accuratelyExtracting a target circle domain; the distance between the center of the fitted ellipse and the image centroid is shown in fig. 4;
s410, fitting the ellipse in the image by adopting a rapid ellipse detection method based on an arc adjacency matrix, and detecting the center C of the ith ellipse i Has the coordinates of
S420, calculating the center C of the ith ellipse i Euclidean distance rho between the elliptic image centroid E and the preprocessed elliptic image centroid E i :
Where point E is the actual centroid of the ellipse with pixel coordinates of (x) E ,y E );
S430, in Euclidean distance rho i Judging the corresponding ellipse when the minimum value is taken as true, judging the other ellipses as false, and taking the true circle as the target circle domain;
s500, respectively reducing the target circular area by two times and four times, mapping the target circular area to the primer depth image to obtain a primer large circular area and a primer small circular area, and respectively extracting height information in the large circular area and the small circular area to judge the filling amount of the primer priming charge of the bullet; the image height information extraction area is shown in fig. 5;
s510, respectively reducing the target circular domain by two times and four times, and mapping the target circular domain to the primer depth image to obtain a primer large circular domain and a primer small circular domain;
s520, extracting height information in the large circle region and the small circle region respectively through Cog3 DRangeImageHeightCalculatorltol in a Cognex algorithm library, wherein the height information comprises an average height value H of the small circle S_Mean Mean height value H of great circle L_Mean Small maximum height value H S_Max Maximum height value H of great circle L_Max Small circle minimum height value H S_Min And maximum circle minimum height value H L_Min ;
S530, judging the filling amount of the primer of the bullet according to the extracted height information of the large and small circular areas.
Claims (4)
1. A bullet primer filling amount detection method based on 3D vision is characterized by at least comprising the following steps:
s100, horizontally placing the top of a bullet primer upwards on a transparent acrylic conveying plate, moving the transparent acrylic conveying plate forwards at a fixed speed v, triggering a photoelectric sensor after the bullet primer reaches an imaging area, starting line laser to project laser to the top of the bullet primer at a time interval of t, starting a camera to acquire images of laser lines projected to the top of the primer at the time interval of t, and continuously acquiring n images containing the laser lines; the line laser projects laser lines vertically 90 degrees downwards, the camera obliquely photographs the ground fire at an angle alpha with the horizontal direction, and the annular light shines the bottom of the ground fire in a mode of penetrating through the glass conveying plate;
s200, continuously collecting n primer images with the size of (k, j) and containing laser lines, respectively extracting laser center lines in the images, obtaining depth information of each point on the laser lines according to the formula (1), obtaining depth information of (n multiplied by k) points through the n laser center lines, and synthesizing a depth image Bin 10;
in the formula, P is the point projected by the laser on the surface of the detected object, O is the point virtually projected by the center of the line laser on the transparent acrylic transmission plate, M is the focus of the camera, A is the point presented by the point O on the camera, B is the point presented by the point P on the camera, OA and PB pass through the focus M, the included angle between O A and the laser line is theta, and the included angle between OA and the mirror surface of the camera is theta
S300, preprocessing the depth image Bin10 by histogram equalization, binarization, expansion, hole removal and corrosion to obtain a high-quality image Bin 20;
s400, performing circular domain detection on the image Bin20 by adopting a rapid ellipse detection method based on arc adjacency matrixMeasuring and fitting to obtain the center C of each ellipse i Combining with the Euclidean distance method to obtain the centroid E of the image Bin20 and the center C of each fitted ellipse i Euclidean distance ρ between them i According to rho i Judging a true circle in the image, and accurately extracting a target circle domain;
s500, reducing the target circular area by two times and four times respectively, mapping the target circular area to the primer depth image to obtain a primer large circular area and a primer small circular area, and extracting height information in the large circular area and the small circular area respectively to judge the filling amount of the primer priming agent of the bullet.
2. The method of claim 1, wherein the depth image is preprocessed to obtain a high-quality image Bin20, and the step S300 further comprises:
s310, obtaining a gray level histogram of the depth image, normalizing the gray level histogram, then enhancing the contrast of the image through histogram equalization transformation, and highlighting a clear image edge to obtain an image Bin 11;
s320, calculating the inter-class variance of the image Bin11, using the maximum inter-class variance G as a threshold value, binarizing the image Bin11, eliminating a side circular ring area in the image, and reserving a circular area; after binarization, extracting a connected domain from the image by adopting a run-length method, and eliminating a noise region with a smaller area to obtain an image Bin 12;
s330, setting an expansion operator, and eliminating a noise area contained in the foreground image by using expansion operation to completely distinguish the background from the foreground to obtain an image Bin 13;
s340, eliminating internal noise points in the image through a hole elimination algorithm to obtain an image Bin 14;
and S350, restoring the edge area which is mistakenly eliminated by the expansion operation by adopting the corrosion operation, and finally obtaining the high-quality image Bin 20.
3. The method of detecting the priming charge of a bullet primer according to claim 1, wherein the target circle region is accurately extracted from the high-quality image Bin20, and said step S400 further comprises at least the following steps:
s410, fitting the ellipse in the image by adopting a rapid ellipse detection method based on an arc adjacency matrix, and fitting the center C of the ith ellipse i Has the coordinates of
S420, calculating the center C of the ith ellipse i Euclidean distance rho between the elliptic image centroid E and the preprocessed elliptic image centroid E i :
Where point E is the actual centroid of the ellipse with pixel coordinates of (x) E ,y E );
S430, in Euclidean distance rho i And judging the corresponding ellipse when the minimum value is taken as true, judging the other ellipses as false, and taking the true circle as the target circle domain.
4. The method of claim 1, wherein the method of detecting the amount of primer applied to the bullet primer comprises extracting the height information of the primer curved surface and determining the amount of primer applied to the bullet primer, and the step S500 further comprises the steps of:
s510, respectively reducing the target circular domain by two times and four times, and mapping the target circular domain to the primer depth image to obtain a primer large circular domain and a primer small circular domain;
s520, extracting height information in the large circle region and the small circle region respectively, wherein the height information comprises an average height value H of the small circle S_Mean Mean height value H of great circle L_Mean Small maximum height value H S_Max Maximum height value H of great circle L_Max Small circle minimum height value H S_Min And minimum height value H of great circle L_Min ;
S530, judging the filling amount of the primer of the bullet according to the extracted height information of the large and small circular areas.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110427803.5A CN113028912B (en) | 2021-04-21 | 2021-04-21 | Bullet primer priming charge filling amount detection method based on 3D vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110427803.5A CN113028912B (en) | 2021-04-21 | 2021-04-21 | Bullet primer priming charge filling amount detection method based on 3D vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113028912A CN113028912A (en) | 2021-06-25 |
CN113028912B true CN113028912B (en) | 2022-09-20 |
Family
ID=76457082
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110427803.5A Active CN113028912B (en) | 2021-04-21 | 2021-04-21 | Bullet primer priming charge filling amount detection method based on 3D vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113028912B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0814851A (en) * | 1994-06-30 | 1996-01-19 | Aisin Seiki Co Ltd | Non-contact volume measurement method and device |
CN202134079U (en) * | 2011-06-16 | 2012-02-01 | 长安大学 | Unmanned vehicle lane marker line identification and alarm device |
CN102915535A (en) * | 2012-08-23 | 2013-02-06 | 深圳大学 | Method and system for correcting circle center deviation of round mark points during camera projection transformation |
CN103353261A (en) * | 2013-07-30 | 2013-10-16 | 重庆长江电工工业集团有限公司 | Device for detecting powder amount of campaign bomb |
CN107764205A (en) * | 2017-11-06 | 2018-03-06 | 长安大学 | High-frequency resistance welding (HFRW) seam center three-dimensional detection device and detection method are scanned based on line-structured light |
CN108020549A (en) * | 2018-01-10 | 2018-05-11 | 中煤科工集团淮北爆破技术研究院有限公司 | A kind of detonator dose on-line measuring device |
CN108120353A (en) * | 2017-12-06 | 2018-06-05 | 中国兵器装备集团自动化研究所 | A kind of flash hole detection device and its method based on smart camera |
CN111156900A (en) * | 2018-11-08 | 2020-05-15 | 中国科学院沈阳自动化研究所 | Line-of-depth linear light measurement method for bullet primer assembly |
CN211205211U (en) * | 2020-01-13 | 2020-08-07 | 黑龙江省科学院智能制造研究所 | Hunting bullet outline defect detection device based on laser triangulation method |
CN112161574A (en) * | 2020-10-12 | 2021-01-01 | 昆明理工大学 | Three-dimensional measurement system and measurement method based on divergent multi-line laser projection |
CN112614139A (en) * | 2020-12-17 | 2021-04-06 | 武汉工程大学 | Conveyor belt ore agglomerate screening method based on depth map |
-
2021
- 2021-04-21 CN CN202110427803.5A patent/CN113028912B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0814851A (en) * | 1994-06-30 | 1996-01-19 | Aisin Seiki Co Ltd | Non-contact volume measurement method and device |
CN202134079U (en) * | 2011-06-16 | 2012-02-01 | 长安大学 | Unmanned vehicle lane marker line identification and alarm device |
CN102915535A (en) * | 2012-08-23 | 2013-02-06 | 深圳大学 | Method and system for correcting circle center deviation of round mark points during camera projection transformation |
CN103353261A (en) * | 2013-07-30 | 2013-10-16 | 重庆长江电工工业集团有限公司 | Device for detecting powder amount of campaign bomb |
CN107764205A (en) * | 2017-11-06 | 2018-03-06 | 长安大学 | High-frequency resistance welding (HFRW) seam center three-dimensional detection device and detection method are scanned based on line-structured light |
CN108120353A (en) * | 2017-12-06 | 2018-06-05 | 中国兵器装备集团自动化研究所 | A kind of flash hole detection device and its method based on smart camera |
CN108020549A (en) * | 2018-01-10 | 2018-05-11 | 中煤科工集团淮北爆破技术研究院有限公司 | A kind of detonator dose on-line measuring device |
CN111156900A (en) * | 2018-11-08 | 2020-05-15 | 中国科学院沈阳自动化研究所 | Line-of-depth linear light measurement method for bullet primer assembly |
CN211205211U (en) * | 2020-01-13 | 2020-08-07 | 黑龙江省科学院智能制造研究所 | Hunting bullet outline defect detection device based on laser triangulation method |
CN112161574A (en) * | 2020-10-12 | 2021-01-01 | 昆明理工大学 | Three-dimensional measurement system and measurement method based on divergent multi-line laser projection |
CN112614139A (en) * | 2020-12-17 | 2021-04-06 | 武汉工程大学 | Conveyor belt ore agglomerate screening method based on depth map |
Also Published As
Publication number | Publication date |
---|---|
CN113028912A (en) | 2021-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111488683B (en) | Fragment flying parameter determination method based on image processing technology | |
CN108247179A (en) | I shape grooves CO based on crater image2Weld deviation detecting method and device | |
CN107787496B (en) | Vanishing point correcting device and method | |
CN109839035B (en) | Accurate positioning method of target scoring system and target scoring system | |
CN109341427A (en) | A kind of laser gun target system | |
CN106524995B (en) | Detect the localization method of target object space length in real time based on visible images | |
CN115388706B (en) | Laser target drone with automatic calibration function | |
CN113028912B (en) | Bullet primer priming charge filling amount detection method based on 3D vision | |
CN113513991A (en) | Battery pole piece burr height detection method and device | |
CN115007470A (en) | Visual detection system and method for tobacco tar detection of electronic cigarette cartridge | |
CN114964007A (en) | Visual measurement and surface defect detection method for weld size | |
CN113514182B (en) | Shock wave overpressure field measuring method based on high-speed photographic system | |
KR101696089B1 (en) | Method and apparatus of finding object with imaging sonar | |
CN111127542A (en) | Image-based non-cooperative target docking ring extraction method | |
CN116105813A (en) | Slag volume flow measuring device and measuring method | |
CN112781452B (en) | Bullet primer top appearance defect detection method | |
CN112950511B (en) | Method for detecting invisible laser spot position near 850nm | |
CN111091086B (en) | Method for improving identification rate of single characteristic information of logistics surface by utilizing machine vision technology | |
CN114913323A (en) | Method for detecting open fire at night in charging pile area | |
CN111402283B (en) | Mars image edge characteristic self-adaptive extraction method based on gray variance derivative | |
KR102084858B1 (en) | A method of recognizing only golf ball objects in photograph using cameras in a golf simulator | |
CN114018946A (en) | OpenCV-based high-reflectivity bottle cap defect detection method | |
CN112861764A (en) | Face recognition living body judgment method | |
CN111738082A (en) | Identification method and device for automatically tracking and positioning fire source point based on machine vision | |
CN110634136A (en) | Pipeline wall damage detection method, device and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |