CN110853059B - Image identification method for target ring number - Google Patents
Image identification method for target ring number Download PDFInfo
- Publication number
- CN110853059B CN110853059B CN201911100835.3A CN201911100835A CN110853059B CN 110853059 B CN110853059 B CN 110853059B CN 201911100835 A CN201911100835 A CN 201911100835A CN 110853059 B CN110853059 B CN 110853059B
- Authority
- CN
- China
- Prior art keywords
- area
- center
- target
- coordinates
- mass
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image identification method of target ring number, which comprises the following steps: acquiring corner points which are farthest from the center of mass and closest to the circle center; calculating the area of a circle where the corner point farthest from the center of mass and closest to the center of the circle, recording the area as the area of the corner point, calculating the area of the circle where the center of mass of the bullet hole is located, and recording the area as the area of the center of mass; when the area of the angular point and the area of the particle are in the area range of the number of the ring, determining the number of the target rings as the area of the angular point and the number of the rings to which the area of the particle belongs; and when the area of the angular point and the area of the particle are not in the area range of the number of the ring, determining that the number of the target ring is the number of the ring to which the area of the mass center belongs plus 1. The invention accurately identifies the number of the target rings by calculating the area range of the corner point which is farthest from the center of mass and closest to the center of circle and the area range of the center of mass of the bullet hole, and can calculate the area of the ring number to which the center of mass coordinate of the bullet hole specifically deviates when the bullet hole is on the boundary line of the two ring numbers, and finally accurately identifies the ring number of the bullet hole.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to an image recognition method for target ring number.
Background
The traditional target ring number identification is mainly realized manually, and the problems of low accuracy, large potential safety hazard and insufficient human resource distribution exist. At present, products on the market for identifying the number of target rings have the defects of high cost, complex system, occupied space and the like. Meanwhile, when the bullet hole is on the boundary line of two ring numbers, human eyes can have the condition of wrong recognition.
The current research of a target scoring system based on an image processing technology is mainly divided into two aspects, one is the research of an automatic target scoring device, the automatic target scoring device is mainly formed by combining image processing with image acquisition, image transmission, an embedded technology and the like, and the automatic target scoring device mainly depends on mechanical measuring systems such as a double-layer electrode short circuit sampling system, an acoustoelectric positioning automatic target scoring system, a photoelectric electronic target system and the like, and the systems have complex hardware structures, require to make a special target and cannot be recycled, are high in cost and are poor in adaptability; secondly, the research of an image processing method, such as Liu Qiuyan, etc., adopts Hough transform to detect the target center in 'research of an automatic target-scoring method based on video image analysis', and analyzes a differential image to determine the position of a bullet hole; liu Ruixiang et al in paper chest ring target oriented automatic identification target-scoring system research adopts gray bidirectional xiaobo projection to determine the position of the target center; liu Xiangcui, et al, in "an automatic target scoring program based on image processing technology", use contour tracing to identify the contour. Although automatic target scoring systems based on image processing technology have achieved certain results, most of the current methods only perform identification and judgment according to the brightness of a loop and a bullet hole. Zheng Xiaoshi and the like in Chinese patent publication No. CN2831033Y automatic identification target-reporting device, consider that the front and back images are completely overlapped in the shooting process, and only adopt a simple threshold value method to judge the impact point; in the current case, coordinate measurement of the target in the projectile generally uses the projectile to leave a bullet mark through a solid target, and the shooter estimates the target coordinates of each projectile using a telescope or by means of a closed-loop television system, but it cannot accurately identify the number of rings in which the projectile hole is located.
Disclosure of Invention
The embodiment of the invention provides an image identification method for the number of target rings, which is used for solving the problem of inaccurate identification of the number of rings where a bullet hole is located in the background technology.
The embodiment of the invention provides an image identification method of target ring number, which comprises the following steps:
acquiring the area range of each ring area of the target disc and the circle center coordinate of the target disc;
acquiring the coordinates of the corner points of the bullet holes on the target disc, and acquiring the coordinates of the mass center of the bullet holes on the target disc through a Kmeans clustering algorithm;
calculating the distance between the angular point coordinates of the bullet hole and the particle coordinates, calculating the distance between the angular point coordinates of the bullet hole and the center coordinates of the target, and acquiring the angular points which are farthest from the center of mass and closest to the center of the target;
calculating the area of a circle where the corner point farthest from the center of mass and closest to the center of the circle, recording the area as the area of the corner point, calculating the area of the circle where the center of mass of the bullet hole is located, and recording the area as the area of the center of mass; when the angular point area and the mass point area are in the area range of the number of the rings, determining the number of the target rings as the angular point area and the number of the rings to which the mass point area belongs; and when the area of the angular point and the area of the particle are not in the area range of the number of the ring, determining that the number of the target ring is the number of the ring to which the area of the mass center belongs plus 1.
Further, an embodiment of the present invention provides an image identification method for target ring number, further including: carrying out threshold segmentation on the acquired image, and segmenting the number of rings of the target disc; the image threshold segmentation is performed on the acquired image, and specifically includes:
converting the collected image into a gray image;
and (4) performing threshold segmentation on the gray level image by adopting the Otsu method.
Further, the acquiring the area range of each ring region of the target disc and the circle center coordinate of the target disc specifically includes:
extracting and drawing each ring area of the target disc by adopting functions findContours and drawContours in an Opencv image processing library; and obtaining the circle center coordinate of the target disc by adopting a function minEnclosed circle () in the Opencv image processing library.
Further, the acquiring the coordinates of the corner points of the bullet holes on the target disc and the acquiring the coordinates of the mass center of the bullet holes on the target disc through a Kmeans clustering algorithm specifically include:
making a minimum circumscribed circle or a minimum circumscribed rectangle for each bullet hole, and determining a plurality of angular point coordinates of the regional edge of each bullet hole through Harris angular point detection, normalization processing and image enhancement processing;
determining the centroid coordinate of each bullet hole by performing a Kmeans clustering algorithm according to the coordinates of the plurality of corner points of each bullet hole; and the K value in the Kmeans clustering algorithm is the number of the minimum circumscribed circles or the minimum circumscribed rectangles of the corresponding bullet holes.
Further, the Harris corner detection specifically includes:
and carrying out threshold processing on the corner response function R, and extracting the local maximum value of R when R is greater than threshold.
Further, the acquiring the coordinates of the corner points of the bullet holes on the target disc and the acquiring the coordinates of the mass center of the bullet holes on the target disc through a Kmeans clustering algorithm specifically include:
making a minimum circumscribed circle or a minimum circumscribed rectangle for each bullet hole, and determining a convex hull point set of each bullet hole through convex hull detection;
determining the centroid coordinate of each bullet hole by performing a Kmeans clustering algorithm according to the convex hull point set of each bullet hole; and the K value in the Kmeans clustering algorithm is the number of the minimum circumscribed circles or the minimum circumscribed rectangles of the corresponding bullet holes.
The embodiment of the invention provides an image identification method of target ring number, which has the following beneficial effects compared with the prior art:
in the embodiment of the invention, firstly, the image is preprocessed to eliminate the noise, threshold segmentation is carried out by the Otsu method, contour extraction and contour area calculation are carried out to obtain the center coordinates of the target disc, the bullet holes are subjected to minimum circumcircles and the number of the minimum circumcircles is calculated, harris angular point detection is carried out on the bullet hole areas, image normalization and image enhancement are carried out, the angular point coordinates of each bullet hole are obtained, a Kmeans algorithm is carried out (the value of K is equal to the number of the minimum circumcircles), the centroid coordinates of each bullet hole are calculated, the area range of the centroid is determined, the number of rings of the target is accurately identified by calculating the area range of the angular point farthest from the centroid and closest to the center of the circle, and when the bullet hole is on the boundary line of two ring numbers, the centroid coordinates of the bullet hole can be calculated to be specifically deviated to which ring number area, and finally, the number of the ring of the bullet hole is accurately identified, so that automatic target reporting is realized.
Drawings
Fig. 1 is a schematic flow chart of an image recognition method for target ring number according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of Otsu image threshold segmentation according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the target disk ring number division according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating the division of the target disk into ring regions according to an embodiment of the present invention;
FIG. 5.1 is a schematic diagram of coordinates of a center of a circle of a target disk according to an embodiment of the present invention;
fig. 5.2 is a schematic diagram of coordinates of a bullet hole corner point provided in the embodiment of the present invention;
fig. 5.3 is a schematic diagram of a ring line bullet hole according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides an image identification method for target ring number, where the method includes:
step 1: and acquiring the area range of each ring area of the target disc and the circle center coordinate of the target disc.
Step 2: and acquiring the coordinates of the corner points of the bullet holes on the target disc, and acquiring the coordinates of the mass center of the bullet holes on the target disc through a Kmeans clustering algorithm.
And 3, step 3: and calculating the distance between the coordinates of the corner points of the bullet holes and the coordinates of the mass points, calculating the distance between the coordinates of the corner points of the bullet holes and the coordinates of the circle center of the target, and acquiring the corner points which are farthest from the mass center and closest to the circle center.
And 4, step 4: calculating the area of a circle where the corner point farthest from the center of mass and closest to the center of the circle, recording the area as the area of the corner point, calculating the area of the circle where the center of mass of the bullet hole is located, and recording the area as the area of the center of mass; when the area of the angular point and the area of the particle are in the area range of the number of the ring, determining the number of the target rings as the area of the angular point and the number of the rings to which the area of the particle belongs; and when the area of the angular point and the area of the particle are not in the area range of the number of the ring, determining that the number of the target ring is the number of the ring to which the area of the mass center belongs plus 1.
Above-mentioned technical scheme, through calculating the angular point place area scope farthest away from the barycenter and nearest apart from the centre of a circle and bullet hole barycenter place area scope, accurately discerned the target ring number to when the bullet hole was on the boundary line of two ring numbers, can calculate which ring number region specifically is partial to the barycenter coordinate in bullet hole, finally accurately discerned bullet hole place ring number, realize automatic target-reporting, it has low cost, long-life, and the practicality is strong, development prospect characteristics such as big.
Before the step 1, there is a step: namely, the picture content collected by the camera is preprocessed, and the ring number of the target disc is segmented. Wherein all pre-treatments include: a. to a grayscale image. b. Otsu method image threshold segmentation. Referring to fig. 2 to 3, this section includes performing image threshold segmentation on the graying and the Otsu method of the acquired picture content, and accurately segmenting the number of target discs.
For step 1, referring to fig. 3 to 4, extracting and drawing each ring region of the target disk (implemented by using functions findContours and drawContours in the Opencv image processing library); calculating the circular area range of each ring area of the target disc (realized by using the constants [ i ]); and paving the subsequent ring number identification according to the obtained circular area range of each ring area of the target disc. Referring to fig. 5.1, the coordinates of the center of the target disk are obtained by circumscribing a minimum circle minEnclosingCircle (), and the number of circumscribed circles is the value of K in the subsequent Kmeans clustering algorithm.
For step 2, performing minimum circumcircle or minimum circumrectangle on each bullet hole, and then performing Harris corner detection, namely performing threshold processing on a corner response function R: r > threshold, namely extracting the local maximum of R; then, normalizing the image, and limiting the data to be processed in (0,1) after processing; and then, carrying out image enhancement, traversing the whole image, referring to fig. 5.2 that the edge of each bullet hole region has a plurality of angular points, obtaining a plurality of angular point coordinates of each bullet hole, and carrying out a Kmeans clustering algorithm to obtain the centroid coordinate of each bullet hole.
It should be noted that, in the embodiment of the present invention, when the value of the Kmeans clustering algorithm K is taken, the value is obtained by using the number of circumscribed circles, and the value of K can also be obtained by calculating the number of minimum circumscribed rectangles using the minimum circumscribed rectangle. In the embodiment of the invention, when the center of mass of the bullet hole is positioned, convex hull detection can be used for replacing angular point detection, a convex hull point set of each bullet hole is obtained after the convex hull detection is finished, and then the center of mass of the bullet hole is positioned by using a Kmeans clustering algorithm.
For example, referring to fig. 5.2, taking the bullet hole 1 as an example, the coordinates a, b, c, and d of the 4 angular points of the bullet hole 1 are obtained, and the centroid coordinates of the bullet hole are obtained by performing a Kmeans clustering algorithm.
For steps 3 and 4, ring number identification is performed by multi-branch selection if statement:
according to the mass center coordinate of each bullet hole, calculating the distance between the corner point coordinate of the bullet hole and the particle coordinate, calculating the distance between the corner point coordinate of the bullet hole and the center coordinate of the target, and solving the corner points meeting the conditions, namely searching the corner point which is farthest from the mass center and closest to the center on the bullet hole.
And solving the areas of the circles where the corner points farthest from the center of mass and closest to the center of the circle, solving the area of the circle where the center of mass of the bullet hole is located, and comparing the areas of the two circles in the area range of which number of rings is determined, namely judging whether the numbers of the rings are the same.
If the area ranges of the number of the rings of the two circle areas are the same, the number of the rings is directly output if the bullet holes are between the ring lines and not on the ring lines (such as the bullet holes 1 in fig. 5.2).
If the area ranges of the number of the rings of the two areas are different, the bullet hole is on the loop line (such as the bullet hole 3 in fig. 5.3), and the number of the rings of the centroid area is +1.
It should be noted that the bullet hole is on the circular line, and assuming that the distance from the corner point a to the centroid is the same as the distance from the corner point d to the centroid, both are the corner points farthest from the centroid. And if the angular point a with the farthest distance is arranged on the inner side and the angular point d with the farthest distance is arranged on the outer side, the angular point a on the inner side needs to be taken to judge the number of rings. Therefore, in addition to the "corner point farthest from the centroid", the "corner point closest to the center of the circle" is also determined.
For example, referring to fig. 5.3, the bullet hole 3 is on an 8-ring outer ring, the angular point a and the angular point d are farthest from the centroid of the bullet hole 1 (the angular point at the outermost edge), and the angular point a is closest to the center of the target (the shooting rule takes the point closest to the center of the circle, i.e. the maximum number of rings), then the number of rings at the point a should be taken, which is 8 rings.
The above disclosure is only a few specific embodiments of the present invention, and those skilled in the art can make various modifications and variations of the present invention without departing from the spirit and scope of the present invention, and it is intended that the present invention encompass these modifications and variations as well as others within the scope of the appended claims and their equivalents.
Claims (4)
1. An image recognition method for the number of target rings, comprising:
acquiring the area range of each ring area of the target disc and the circle center coordinate of the target disc;
acquiring the coordinates of the corner points of the bullet holes on the target disc, and acquiring the coordinates of the mass center of the bullet holes on the target disc through a Kmeans clustering algorithm;
calculating the distance between the corner coordinates of the bullet hole and the particle coordinates, calculating the distance between the corner coordinates of the bullet hole and the center coordinates of the target, and acquiring the corner points which are farthest from the center of mass and closest to the center of the target;
calculating the area of a circle where the corner point farthest from the center of mass and closest to the center of the circle, recording the area as the area of the corner point, calculating the area of the circle where the center of mass of the bullet hole is located, and recording the area as the area of the center of mass; when the angular point area and the mass point area are in the area range of the number of the rings, determining the number of the target rings as the angular point area and the number of the rings to which the mass point area belongs; when the area of the angular point and the area of the particle are not in the area range of the number of the ring, determining the number of the target ring as the number of the ring to which the area of the mass center belongs plus 1;
the method for acquiring the corner coordinates of the bullet holes in the target disc and acquiring the centroid coordinates of the bullet holes in the target disc through a Kmeans clustering algorithm specifically comprises the following steps:
making a minimum circumscribed circle or a minimum circumscribed rectangle for each bullet hole, and determining a plurality of angular point coordinates of the regional edge of each bullet hole through Harris angular point detection, normalization processing and image enhancement processing;
determining the barycenter coordinates of each bullet hole by performing a Kmeans clustering algorithm according to the multiple corner point coordinates of each bullet hole; the K value in the Kmeans clustering algorithm is the number of the minimum circumscribed circles or the minimum circumscribed rectangles of the corresponding bullet holes;
the method for acquiring the coordinates of the corner points of the bullet holes in the target disc and acquiring the coordinates of the mass center of the bullet holes in the target disc through a Kmeans clustering algorithm specifically comprises the following steps:
making a minimum circumscribed circle or a minimum circumscribed rectangle for each bullet hole, and determining a convex hull point set of each bullet hole through convex hull detection;
determining the centroid coordinate of each bullet hole by performing a Kmeans clustering algorithm according to the convex hull point set of each bullet hole; and the K value in the Kmeans clustering algorithm is the number of the minimum circumscribed circles or the minimum circumscribed rectangles of the corresponding bullet holes.
2. The image recognition method of the number of target rings of claim 1, further comprising: carrying out threshold segmentation on the acquired image, and segmenting the number of rings of the target disc; the image threshold segmentation of the acquired image specifically includes:
converting the collected image into a gray image;
and (4) performing threshold segmentation on the gray level image by adopting the Otsu method.
3. The image recognition method of the number of target rings according to claim 1, wherein the obtaining of the area range of each ring region of the target disc and the coordinates of the center of the circle of the target disc specifically comprises:
extracting and drawing each ring area of the target disc by using functions findContours and drawContours in an Opencv image processing library; and obtaining the circle center coordinate of the target disc by adopting a function minEnclosed circle () in the Opencv image processing library.
4. The image recognition method of target ring number according to claim 1, wherein the Harris corner detection specifically comprises:
and performing threshold processing on the corner response function R, and extracting the local maximum value of R when R > threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911100835.3A CN110853059B (en) | 2019-11-12 | 2019-11-12 | Image identification method for target ring number |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911100835.3A CN110853059B (en) | 2019-11-12 | 2019-11-12 | Image identification method for target ring number |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110853059A CN110853059A (en) | 2020-02-28 |
| CN110853059B true CN110853059B (en) | 2023-04-07 |
Family
ID=69600519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911100835.3A Active CN110853059B (en) | 2019-11-12 | 2019-11-12 | Image identification method for target ring number |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110853059B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159124B (en) * | 2020-04-30 | 2024-03-22 | 珠海强源体育用品有限公司 | Image target ring recognition and calculation device and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101937509A (en) * | 2010-08-17 | 2011-01-05 | 西安理工大学 | Automatic target identifying method based on image processing technology |
| CN102175100A (en) * | 2011-03-22 | 2011-09-07 | 东南大学 | Embedded wireless automatic scoring system and scoring method thereof |
| WO2013189006A1 (en) * | 2012-06-18 | 2013-12-27 | 北京方格世纪科技有限公司 | Archery scoring system |
| CN106408527A (en) * | 2016-08-25 | 2017-02-15 | 安徽水滴科技有限责任公司 | Automatic target scoring method based on video analysis |
| 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 |
| CN109034156A (en) * | 2018-08-15 | 2018-12-18 | 洛阳中科协同科技有限公司 | A kind of pop-off localization method based on image recognition |
| CN109827474A (en) * | 2019-03-04 | 2019-05-31 | 中国人民武装警察部队工程大学 | A kind of more target position automatic target-indicating method and system in training place based on high-definition camera |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977952A (en) * | 2016-10-21 | 2018-05-01 | 冯原 | Medical image cutting method and device |
-
2019
- 2019-11-12 CN CN201911100835.3A patent/CN110853059B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101937509A (en) * | 2010-08-17 | 2011-01-05 | 西安理工大学 | Automatic target identifying method based on image processing technology |
| CN102175100A (en) * | 2011-03-22 | 2011-09-07 | 东南大学 | Embedded wireless automatic scoring system and scoring method thereof |
| WO2013189006A1 (en) * | 2012-06-18 | 2013-12-27 | 北京方格世纪科技有限公司 | Archery scoring system |
| CN106408527A (en) * | 2016-08-25 | 2017-02-15 | 安徽水滴科技有限责任公司 | Automatic target scoring method based on video analysis |
| 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 |
| CN109034156A (en) * | 2018-08-15 | 2018-12-18 | 洛阳中科协同科技有限公司 | A kind of pop-off localization method based on image recognition |
| CN109827474A (en) * | 2019-03-04 | 2019-05-31 | 中国人民武装警察部队工程大学 | A kind of more target position automatic target-indicating method and system in training place based on high-definition camera |
Non-Patent Citations (2)
| Title |
|---|
| 一种弹孔自动识别算法的研究;张旭光等;《光学精密工程》(第06期);全文 * |
| 基于MATLAB的靶纸图像识别研究;王蔚扬等;《计算机时代》(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110853059A (en) | 2020-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816644B (en) | Bearing defect automatic detection system based on multi-angle light source image | |
| CN101609504B (en) | Method for detecting, distinguishing and locating infrared imagery sea-surface target | |
| CN115018850B (en) | Method for detecting burrs of punched hole of precise electronic part based on image processing | |
| CN115691026A (en) | Intelligent early warning monitoring management method for forest fire prevention | |
| CN109145708A (en) | A kind of people flow rate statistical method based on the fusion of RGB and D information | |
| CN103295013A (en) | Pared area based single-image shadow detection method | |
| CN110245626B (en) | Method for accurately detecting eyelash image in iris image | |
| CN110675447A (en) | People counting method based on combination of visible light camera and thermal imager | |
| CN111476804B (en) | Efficient carrier roller image segmentation method, device, equipment and storage medium | |
| CN112149667A (en) | Method for automatically reading pointer type instrument based on deep learning | |
| CN112885108B (en) | Vehicle change detection method and system on parking space based on deep learning algorithm | |
| CN111047624A (en) | Image dim target detection method, device, equipment and storage medium | |
| CN115841488A (en) | Hole checking method of PCB (printed Circuit Board) based on computer vision | |
| CN110853059B (en) | Image identification method for target ring number | |
| CN107239743B (en) | automatic detection method for scale mark reading based on projection method | |
| CN117475353A (en) | Video-based abnormal smoke identification method and system | |
| CN110322508B (en) | Auxiliary positioning method based on computer vision | |
| CN109784229B (en) | Composite identification method for ground building data fusion | |
| US10621466B2 (en) | Method for extracting features of a thermal image | |
| CN113221603A (en) | Method and device for detecting shielding of monitoring equipment by foreign matters | |
| Si-ming et al. | Moving shadow detection based on Susan algorithm | |
| CN114677428A (en) | Power transmission line icing thickness detection method based on unmanned aerial vehicle image processing | |
| CN112990064A (en) | Dial pointer identification method based on color segmentation and probability model | |
| Fu et al. | Recognition of bridge over water in high-resolution remote sensing images | |
| CN109151451B (en) | Binocular night vision device resolution detection method |
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 |