CN112132807B - Weld joint region extraction method and device based on color similarity segmentation - Google Patents
Weld joint region extraction method and device based on color similarity segmentation Download PDFInfo
- Publication number
- CN112132807B CN112132807B CN202011008216.4A CN202011008216A CN112132807B CN 112132807 B CN112132807 B CN 112132807B CN 202011008216 A CN202011008216 A CN 202011008216A CN 112132807 B CN112132807 B CN 112132807B
- Authority
- CN
- China
- Prior art keywords
- image
- welding
- channel
- color similarity
- weld
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 63
- 230000011218 segmentation Effects 0.000 title claims abstract description 12
- 238000003466 welding Methods 0.000 claims abstract description 107
- 238000001914 filtration Methods 0.000 claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000005260 corrosion Methods 0.000 claims abstract description 9
- 230000007797 corrosion Effects 0.000 claims abstract description 9
- 238000009499 grossing Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 29
- 238000003706 image smoothing Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000750 progressive effect Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- 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
- G06T7/0004—Industrial image inspection
-
- 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 by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
-
- 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
Abstract
The invention discloses a weld joint region extraction method based on color similarity segmentation, which comprises the following steps: step 10, obtaining welding images frame by frame from a welding video stream; step 20, carrying out narrow-band filtering treatment on the obtained welding image to obtain a filtering image; step 30, extracting a designated color area of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line to obtain a laser image; step 40, performing smoothing and expansion corrosion operation on the laser image to obtain a smooth image; and 50, extracting the outline of the smooth image according to the weld characteristics to obtain a weld region. According to the weld joint region extraction method and device based on color similarity segmentation, interference is removed rapidly through real-time narrow-band filtering processing and color similarity detection on the welding video stream, and finally the weld joint region is extracted according to the weld joint characteristics, so that accurate extraction of the weld joint region is achieved rapidly and simply.
Description
Technical Field
The invention relates to the field of industrial automatic detection, in particular to a weld joint region extraction method and device based on color similarity segmentation.
Background
In modern manufacturing production, welding is one of the most important technological methods, and is widely used in the fields of mechanical manufacturing, nuclear industry, petrochemical industry, aerospace and the like. Because of the rapid development of information technology, a new revolution is brought to the traditional welding process, and the welding technology is dissolved into a plurality of front-edge industrial technologies such as computers, robots, microelectronics, lasers and the like, and is developed towards the direction of task planning, process control, quality monitoring intellectualization and automation. In particular, in recent years, the robot welding technology has been widely used in the field of mechanical manufacturing, and the automation level of welding has been greatly promoted. According to incomplete statistics, in practical industrial robots, the proportion of welding robots exceeds 50%, and the adoption of robot welding has become the main development direction of welding automation.
The intelligent welding technology research of the robot is started from the middle 90 th century in China, and the intelligent welding mainly comprises the aspects of autonomous planning of welding parameters, automatic identification of welding positions, autonomous planning of welding paths, optimal control of a welding process, automatic monitoring of welding quality and the like, such as guiding of the initial welding positions of the welding robot, automatic identification of joint forms, automatic identification of welding seams, tracking control of the welding seams and the like. In these intelligent welding technologies, the accurate extraction of the welding seam is the first step of realizing intelligent welding, and the success or failure of the extraction of the welding seam determines whether the automatic welding can be completed or not and the quality of the completion, so that the automatic welding seam is one of the main bottlenecks of the development of intelligent welding of a robot.
Existing patents on weld zone extraction have focused mainly on ray extraction, and vision-based methods have been gradually introduced as computer vision progresses. The main disadvantages of radiation-based detection are that the equipment is expensive and not easy to carry, and the radiation detection can only detect the inside, and the surface is basically indistinguishable. The vision-based method is only in recent years, and has some problems that strong exposure interference cannot be effectively shielded against the side welding side scanning condition, a large amount of external interference in the detection process needs to be removed by a large amount of algorithms, and the algorithm complexity is high.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a weld joint region extraction method and device based on color similarity segmentation, which are used for rapidly removing interference by carrying out real-time narrow-band filtering treatment and color similarity detection on a welding video stream, and finally extracting a weld joint region according to weld joint characteristics so as to rapidly and simply realize accurate extraction of the weld joint region.
In a first aspect, the present invention provides a method for extracting a weld region based on color similarity segmentation, including:
step 10, obtaining welding images frame by frame from a welding video stream;
step 20, carrying out narrow-band filtering treatment on the obtained welding image to obtain a filtering image;
step 30, extracting a designated color area of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line to obtain a laser image;
step 40, performing smoothing and expansion corrosion operation on the laser image to obtain a smooth image;
and 50, extracting the outline of the smooth image according to the weld characteristics to obtain a weld region.
Further, in the step 20, the obtained welding image is subjected to a narrow-band filtering process, which further specifically includes: and filtering the obtained welding image by adopting a 650nm narrow-band filter.
Further, in the step 30, the color similarity detection function formula is further specifically:
wherein I is 1 Representing the laser image after color similarity extraction, p is the pixel of the filtered image, dt is H channel [0,25]]S channel [43,255]]V channel [46,255]]Red region of (A) and H channel [156,180]]S channel [43,255]]V channel [46,255]]Purple regions of (c).
Further, contour extraction is performed on the smooth image according to the weld feature to obtain a weld region, which specifically includes:
extracting all circumscribed rectangles from the smoothed image by using a findContours function in opencv;
among all the parallel circumscribed rectangles, three adjacent rectangles are found, which satisfy: the side length of the middle rectangular long side is smaller than half of the side length of the rectangular long sides at the two ends, and the highest point of the middle rectangular and the highest point of the rectangular at the two ends are not on the same line; the rectangular surrounding areas at the two ends are the welding seam areas.
In a second aspect, the present invention provides a weld region extraction apparatus based on color similarity segmentation, including: the device comprises an image acquisition module, a narrow-band filtering module, a color similarity extraction module, an image smoothing module and a contour extraction module;
the image acquisition module is used for acquiring welding images frame by frame from the welding video stream;
the narrow-band filtering module is used for carrying out narrow-band filtering treatment on the obtained welding image to obtain a filtering image;
the color similarity extraction module is used for extracting a designated color area of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line to obtain a laser image;
the image smoothing module is used for carrying out smoothing and expansion corrosion operation on the laser image to obtain a smooth image;
and the contour extraction module is used for carrying out contour extraction on the smooth image according to the weld characteristics to obtain a weld region.
Further, in the narrowband filtering module, narrowband filtering processing is performed on the obtained welding image, which further specifically includes: and filtering the obtained welding image by adopting a 650nm narrow-band filter.
Further, in the color similarity extraction module, the color similarity detection function is further specifically:
wherein I is 1 Representing the laser image after color similarity extraction, p is the pixel of the filtered image, dt is H channel [0,25]]S channel [43,255]]V channel [46,255]]Red region of (A) and H channel [156,180]]S channel [43,255]]V channel [46,255]]Purple regions of (c).
Further, the contour extraction module further specifically includes: a rectangular extraction module and a welding line area acquisition module;
the rectangle extraction module is used for extracting all circumscribed rectangles from the smooth image by utilizing a findContours function in opencv;
the weld joint region acquisition module is used for finding three adjacent rectangles in all parallel circumscribed rectangles, and the three rectangles satisfy the following conditions: the side length of the middle rectangular long side is smaller than half of the side length of the rectangular long sides at the two ends, and the highest point of the middle rectangular and the highest point of the rectangular at the two ends are not on the same line; the rectangular surrounding areas at the two ends are the welding seam areas.
The embodiment of the invention has the following advantages:
carrying out real-time narrow-band filtering treatment and color similarity detection on the welding video stream, and carrying out filtering treatment by means of a narrow-band filter according to the wavelength of the laser line to basically filter out the reflection of the welding surface; then extracting a designated color region of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line, rapidly removing interference, and finally extracting a welding line region according to the welding line characteristics; the method provided by the invention is similar to a progressive scanning mode, and realizes efficient and high-speed extraction of the weld joint area, so that the extraction of the weld joint points is completed rapidly.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
The invention will be further described with reference to examples of embodiments with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method according to a first embodiment of the invention;
FIG. 2 is a schematic diagram of a welding and video acquisition device according to an embodiment of the present invention;
FIG. 3 is a schematic view of a filtered image according to a first embodiment of the present invention;
FIG. 4 is a diagram of a binarized image according to a first embodiment of the present invention;
FIG. 5 is a schematic view of a laser image according to a first embodiment of the present invention;
FIG. 6 is a schematic view of an extracted weld area in accordance with a first embodiment of the present invention;
fig. 7 is a schematic structural diagram of a device in a second embodiment of the present invention.
Detailed Description
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of this specification without the exercise of inventive faculty, shall fall within the scope of protection of this application.
Before describing the specific embodiments, the structure of the welding and video capturing device to which the method of the embodiments of the present application is specifically applied is described, as shown in fig. 2:
in the welding process, a laser emits light, a binocular camera erected at the tail end of the robot acquires welding video information in real time, a narrow-band filter is utilized for filtering light, and then a computer code is used for calling to carry out subsequent processing on an image.
The general idea of the invention is as follows:
the invention adopts an image-based method. Because the extraction of the welding area occurs before welding, the method plays a role in supporting the extraction of the welding point, and the detection of welding quality is not involved, so that an image-based welding area extraction method is designed. The method is different from other methods such as a ray-based method, but is similar to a progressive scanning mode in the welding process by a laser vision method, the welding seam area is efficiently and high-speed extracted, redundant external interference and overexposed light interference are filtered by a light filter, laser rays are extracted by color similarity, then the welding seam area is extracted according to the characteristics of the welding seam, the algorithm complexity is effectively reduced, the accuracy of extracting the welding seam is improved, and therefore the efficient extraction of the welding seam area is realized under the condition of low cost.
Example 1
The embodiment provides a weld joint region extraction method based on color similarity segmentation, as shown in fig. 1, comprising the following steps of;
step 10, obtaining welding images frame by frame from a welding video stream;
step 20, performing narrow-band filtering processing on the obtained welding image to obtain a filtered image, wherein in a specific embodiment, the obtained filtered image is shown in fig. 3;
because a certain overexposure problem occurs in the welding process, the filtering treatment is firstly carried out by means of a narrow-band filter. In this embodiment, the actual measurement shows that the wavelength of light emitted by the laser is about 650nm, so that the obtained welding image is filtered by using a 650nm narrow-band filter, and the problems of reflection and the like of some welding surfaces are basically filtered by the filtering. If other light sources are adopted, a narrow-band filter with corresponding frequency can be selected according to the requirement.
Step 30, extracting a designated color area of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line to obtain a laser image;
in this embodiment, the color similarity detection function formula is specifically:
wherein I is 1 Representing the laser image after color similarity extraction, p is the pixel of the filtered image, dt is H channel [0,25]]S channel [43,255]]V channel [46,255]]Red region of (A) and H channel [156,180]]S channel [43,255]]V channel [46,255]]Purple regions of (c).
In this embodiment, by extracting the color features of the laser line, it is found that two colors mainly exist: red and purple. The acquired image is converted to HSV color space, with the red centered primarily on H-channel [0,25], S-channel [43,255] and V-channel [46,255], and the red and violet portions centered primarily on H-channel [156,180], S-channel [43,255] and V-channel [46,255] by observation. On the basis of the rule, the color similarity detection function is used for judging pixel by pixel, the extracted binarized image is shown in fig. 4, and then the binarized image is mapped on the filtered image to obtain a laser image, as shown in fig. 5.
Step 40, performing smoothing and expansion corrosion operation on the laser image to obtain a smooth image; processing the laser image by formula (2):
I 2 ＝f s (I 1 ) (2)
wherein f s (g) Representing L0 gradient minimization filtering method and expansion corrosion operation, I 1 Representing laser images, I 2 Representing a smoothed image.
Because the obtained laser image has certain noise and edge protrusion problems, in order to better extract the weld joint area, the obtained image is subjected to smoothing treatment and expansion corrosion operation to remove discrete small area targets, so that the subsequent operation is convenient.
And 50, extracting the outline of the smooth image according to the weld characteristics to obtain a weld region, as shown in fig. 6.
Because some parts in the laser image are not welded devices, in order to obtain the laser line of the welding surface more accurately, the region where the welding line position is located is judged by a contour extraction method, so that the extraction of the welding line region is completed.
In this embodiment, the contour extraction of the smoothed image according to the weld feature (a smaller contour is located between two long contour curves, and the smaller contour curve and the two long contour curves are not in a line) specifically includes:
extracting all circumscribed rectangles from the smoothed image by using a findContours function in opencv;
among all the parallel circumscribed rectangles, three adjacent rectangles are found, which satisfy: the side length of the long side of the middle rectangle is smaller than half of the side length of the long sides of the two rectangles (the condition of the rectangle is only used as an example, and the outline area meeting the welding seam characteristics can be found by other algorithms), and the highest point of the middle rectangle and the highest point of the rectangles at the two ends are not in the same line; the rectangular surrounding areas at the two ends are the welding seam areas.
According to the invention, through carrying out real-time narrow-band filtering treatment and color similarity detection on the welding video stream, the interference is rapidly removed, and finally, the welding seam region is extracted according to the welding seam characteristics, so that the accurate extraction of the welding seam region is rapidly and simply realized. According to the embodiment, the obtained welding image is subjected to filtering treatment by adopting a 650nm narrow-band filter according to the laser characteristics, redundant external interference and overexposed light interference are effectively filtered, laser lines of a designated color area are extracted through color similarity, then a welding seam area is extracted according to the characteristics of the welding seam, algorithm complexity is effectively reduced, and accuracy of extracting the welding seam is improved.
Based on the same inventive concept, the present application also provides a device corresponding to the method in the first embodiment, and details of the second embodiment are described in the following.
Example two
In this embodiment, a weld region extraction device based on color similarity segmentation is provided, as shown in fig. 7, including: the device comprises an image acquisition module, a narrow-band filtering module, a color similarity extraction module, an image smoothing module and a contour extraction module;
the image acquisition module is used for acquiring welding images frame by frame from the welding video stream;
the narrow-band filtering module is used for carrying out narrow-band filtering treatment on the obtained welding image to obtain a filtering image;
the color similarity extraction module is used for extracting a designated color area of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line to obtain a laser image;
the image smoothing module is used for carrying out smoothing and expansion corrosion operation on the laser image to obtain a smooth image;
and the contour extraction module is used for carrying out contour extraction on the smooth image according to the weld characteristics to obtain a weld region.
In one possible implementation manner, in the narrowband filtering module, narrowband filtering processing is performed on the acquired welding image, and further specifically: and filtering the obtained welding image by adopting a 650nm narrow-band filter.
In one possible implementation manner, in the color similarity extraction module, the color similarity detection function is further specifically:
wherein I is 1 Representing the laser image after color similarity extraction, p is the pixel of the filtered image, dt is H channel [0,25]]S channel [43,255]]V channel [46,255]]Red region of (A) and H channel [156,180]]S channel [43,255]]V channel [46,255]]Purple regions of (c).
In one possible implementation manner, the contour extraction module further specifically includes: a rectangular extraction module and a welding line area acquisition module;
the rectangle extraction module is used for extracting all circumscribed rectangles from the smooth image by utilizing a findContours function in opencv;
the weld joint region acquisition module is used for finding three adjacent rectangles in all parallel circumscribed rectangles, and the three rectangles satisfy the following conditions: the side length of the middle rectangular long side is smaller than half of the side length of the rectangular long sides at the two ends, and the highest point of the middle rectangular and the highest point of the rectangular at the two ends are not on the same line; the rectangular surrounding areas at the two ends are the welding seam areas.
Since the device described in the second embodiment of the present invention is a device for implementing the method described in the first embodiment of the present invention, based on the method described in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and the deformation of the device, and thus the detailed description thereof is omitted herein. All devices used in the method according to the first embodiment of the present invention are within the scope of the present invention.
The invention carries out real-time narrow-band filtering treatment and color similarity detection on the welding video stream, and carries out filtering treatment by means of a narrow-band filter according to the wavelength of the laser line, so as to basically filter out the reflection of the welding surface; then extracting a designated color region of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line, rapidly removing interference, and finally extracting a welding line region according to the welding line characteristics; the method provided by the invention is similar to a progressive scanning mode, and realizes efficient and high-speed extraction of the weld joint area, so that the extraction of the weld joint points is completed rapidly.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that the specific embodiments described are illustrative only and not intended to limit the scope of the invention, and that equivalent modifications and variations of the invention in light of the spirit of the invention will be covered by the claims of the present invention.
Claims (8)
1. The color similarity segmentation-based weld joint region extraction method is characterized by comprising the following steps of:
step 10, obtaining welding images frame by frame from a welding video stream;
step 20, carrying out narrow-band filtering treatment on the obtained welding image to obtain a filtering image;
step 30, extracting a designated color area of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line to obtain a laser image;
step 40, performing smoothing and expansion corrosion operation on the laser image to obtain a smooth image;
and 50, extracting the outline of the smooth image according to the weld characteristics to obtain a weld region.
2. The method according to claim 1, characterized in that: in the step 20, the obtained welding image is subjected to narrow-band filtering treatment, which further specifically includes: and filtering the obtained welding image by adopting a 650nm narrow-band filter.
3. The method according to claim 1, characterized in that: in the step 30, the color similarity detection function formula is further specifically:
wherein I is 1 Representing the laser image after color similarity extraction, p is the pixel of the filtered image, dt is H channel [0,25]]S channel [43,255]]V channel [46,255]]Red region of (A) and H channel [156,180]]S channel [43,255]]V channel [46,255]]Purple regions of (c).
4. The method according to claim 1, characterized in that: extracting the outline of the smooth image according to the weld characteristics to obtain a weld region, which specifically comprises the following steps:
extracting all circumscribed rectangles from the smoothed image by using a findContours function in opencv;
among all the parallel circumscribed rectangles, three adjacent rectangles are found, which satisfy: the side length of the middle rectangular long side is smaller than half of the side length of the rectangular long sides at the two ends, and the highest point of the middle rectangular and the highest point of the rectangular at the two ends are not on the same line; the rectangular surrounding areas at the two ends are the welding seam areas.
5. The utility model provides a weld area extraction element based on colour similarity segmentation which characterized in that includes: the device comprises an image acquisition module, a narrow-band filtering module, a color similarity extraction module, an image smoothing module and a contour extraction module;
the image acquisition module is used for acquiring welding images frame by frame from the welding video stream;
the narrow-band filtering module is used for carrying out narrow-band filtering treatment on the obtained welding image to obtain a filtering image;
the color similarity extraction module is used for extracting a designated color area of the filter image by utilizing a color similarity detection function according to the color characteristics of the laser line to obtain a laser image;
the image smoothing module is used for carrying out smoothing and expansion corrosion operation on the laser image to obtain a smooth image;
and the contour extraction module is used for carrying out contour extraction on the smooth image according to the weld characteristics to obtain a weld region.
6. The apparatus according to claim 5, wherein: in the narrow-band filtering module, narrow-band filtering processing is performed on the obtained welding image, and the method further specifically comprises the following steps: and filtering the obtained welding image by adopting a 650nm narrow-band filter.
7. The apparatus according to claim 5, wherein: in the color similarity extraction module, the color similarity detection function is further specifically:
wherein I is 1 Representing the laser image after color similarity extraction, p is the pixel of the filtered image, dt is H channel [0,25]]S channel [43,255]]V channel [46,255]]Red region of (A) and H channel [156,180]]S channel [43,255]]V channel [46,255]]Purple regions of (c).
8. The apparatus according to claim 5, wherein: the contour extraction module further specifically includes: a rectangular extraction module and a welding line area acquisition module;
the rectangle extraction module is used for extracting all circumscribed rectangles from the smooth image by utilizing a findContours function in opencv;
the weld joint region acquisition module is used for finding three adjacent rectangles in all parallel circumscribed rectangles, and the three rectangles satisfy the following conditions: the side length of the middle rectangular long side is smaller than half of the side length of the rectangular long sides at the two ends, and the highest point of the middle rectangular and the highest point of the rectangular at the two ends are not on the same line; the rectangular surrounding areas at the two ends are the welding seam areas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011008216.4A CN112132807B (en) | 2020-09-23 | 2020-09-23 | Weld joint region extraction method and device based on color similarity segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011008216.4A CN112132807B (en) | 2020-09-23 | 2020-09-23 | Weld joint region extraction method and device based on color similarity segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112132807A CN112132807A (en) | 2020-12-25 |
| CN112132807B true CN112132807B (en) | 2024-02-23 |
Family
ID=73842777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011008216.4A Active CN112132807B (en) | 2020-09-23 | 2020-09-23 | Weld joint region extraction method and device based on color similarity segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112132807B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2923606A1 (en) * | 2007-11-09 | 2009-05-15 | Controle Des Points De Soudure | Non-destructively controlling welding point, by examining welding point surface using camera, quantifying distribution of chromatic density/halo formed around crucible junction, and comparing value determined at interval of reference value |
| CN101486124A (en) * | 2009-02-13 | 2009-07-22 | 南京工程学院 | Multi-structured light binocular composite vision weld joint tracking method and device |
| CN106442543A (en) * | 2016-10-14 | 2017-02-22 | 龚新林 | Detection method for identifying surface quality of continuous laser seam of metal workpiece online |
| CN106469312A (en) * | 2016-09-29 | 2017-03-01 | 江苏省特种设备安全监督检验研究院 | Weld seam visual identity method based on region growing label |
| CN107914067A (en) * | 2017-10-31 | 2018-04-17 | 南昌大学 | A kind of welding gun deviation three-dimensional extracting method of the plate sheet welding based on passive vision sensing |
| KR20180115645A (en) * | 2017-04-13 | 2018-10-23 | 재단법인 경북아이티융합 산업기술원 | Apparatus for weld bead recognition of 2d image-based and soot removal method using the same |
| CN109434251A (en) * | 2018-10-22 | 2019-03-08 | 湖北文理学院 | A kind of weld image tracking based on particle filter |
| CN109949346A (en) * | 2019-03-04 | 2019-06-28 | 天津科技大学 | Welding seam tracking method based on histograms of oriented gradients particle filter |
| JP2019141900A (en) * | 2018-02-23 | 2019-08-29 | 日本製鉄株式会社 | Welding operation monitoring system and welding operation monitoring method |
| CN110717872A (en) * | 2019-10-08 | 2020-01-21 | 江西洪都航空工业集团有限责任公司 | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning |
| CN110852173A (en) * | 2019-10-15 | 2020-02-28 | 山东大学 | Visual positioning method and system for fuzzy weld joint |
| CN110930368A (en) * | 2019-10-31 | 2020-03-27 | 中船重工鹏力（南京）智能装备系统有限公司 | Method for extracting characteristics of real-time welding image of sheet lap weld |
| WO2020107866A1 (en) * | 2018-11-30 | 2020-06-04 | 平安科技（深圳）有限公司 | Text region obtaining method and apparatus, storage medium and terminal device |
| CN111666889A (en) * | 2020-06-08 | 2020-09-15 | 南京聚特机器人技术有限公司 | Welding seam identification method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| MY137246A (en) * | 2002-04-30 | 2009-01-30 | Jfe Steel Corp | Method and instrument for measuring bead cutting shape of electric welded tube |
-
2020
- 2020-09-23 CN CN202011008216.4A patent/CN112132807B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2923606A1 (en) * | 2007-11-09 | 2009-05-15 | Controle Des Points De Soudure | Non-destructively controlling welding point, by examining welding point surface using camera, quantifying distribution of chromatic density/halo formed around crucible junction, and comparing value determined at interval of reference value |
| CN101486124A (en) * | 2009-02-13 | 2009-07-22 | 南京工程学院 | Multi-structured light binocular composite vision weld joint tracking method and device |
| CN106469312A (en) * | 2016-09-29 | 2017-03-01 | 江苏省特种设备安全监督检验研究院 | Weld seam visual identity method based on region growing label |
| CN106442543A (en) * | 2016-10-14 | 2017-02-22 | 龚新林 | Detection method for identifying surface quality of continuous laser seam of metal workpiece online |
| KR20180115645A (en) * | 2017-04-13 | 2018-10-23 | 재단법인 경북아이티융합 산업기술원 | Apparatus for weld bead recognition of 2d image-based and soot removal method using the same |
| CN107914067A (en) * | 2017-10-31 | 2018-04-17 | 南昌大学 | A kind of welding gun deviation three-dimensional extracting method of the plate sheet welding based on passive vision sensing |
| JP2019141900A (en) * | 2018-02-23 | 2019-08-29 | 日本製鉄株式会社 | Welding operation monitoring system and welding operation monitoring method |
| CN109434251A (en) * | 2018-10-22 | 2019-03-08 | 湖北文理学院 | A kind of weld image tracking based on particle filter |
| WO2020107866A1 (en) * | 2018-11-30 | 2020-06-04 | 平安科技（深圳）有限公司 | Text region obtaining method and apparatus, storage medium and terminal device |
| CN109949346A (en) * | 2019-03-04 | 2019-06-28 | 天津科技大学 | Welding seam tracking method based on histograms of oriented gradients particle filter |
| CN110717872A (en) * | 2019-10-08 | 2020-01-21 | 江西洪都航空工业集团有限责任公司 | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning |
| CN110852173A (en) * | 2019-10-15 | 2020-02-28 | 山东大学 | Visual positioning method and system for fuzzy weld joint |
| CN110930368A (en) * | 2019-10-31 | 2020-03-27 | 中船重工鹏力（南京）智能装备系统有限公司 | Method for extracting characteristics of real-time welding image of sheet lap weld |
| CN111666889A (en) * | 2020-06-08 | 2020-09-15 | 南京聚特机器人技术有限公司 | Welding seam identification method and device |
Non-Patent Citations (2)
| Title |
|---|
| "管道无损检测系统中基于色彩信息的焊缝识别";毛万冲;《中国优秀硕士学位论文全文数据库 信息科技辑》;全文 * |
| 基于HSI空间和引导滤波的焊缝图像伪彩色增强;阙禄松;王明泉;张俊生;李汉;;中国科技论文(03);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112132807A (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021169335A1 (en) | Visual online detection method for laser welding point of lithium battery tab | |
| Shah et al. | Butt welding joints recognition and location identification by using local thresholding | |
| US7162073B1 (en) | Methods and apparatuses for detecting classifying and measuring spot defects in an image of an object | |
| CN110717872B (en) | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning | |
| CN111369516B (en) | Transformer bushing heating defect detection method based on infrared image recognition | |
| CN114821114A (en) | Groove cutting robot image processing method based on visual system | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
| CN111932490A (en) | Method for extracting grabbing information of visual system of industrial robot | |
| CN113588663B (en) | Pipeline defect identification and information extraction method | |
| CN109001213B (en) | Reel-to-reel ultrathin flexible IC substrate appearance detection method | |
| CN112132807B (en) | Weld joint region extraction method and device based on color similarity segmentation | |
| CN113971681A (en) | Edge detection method for belt conveyor in complex environment | |
| CN111833350A (en) | Machine vision detection method and system | |
| CN116883498A (en) | Visual cooperation target feature point positioning method based on gray centroid extraction algorithm | |
| CN115587993A (en) | Mask welding spot defect detection method based on AI and machine vision algorithm | |
| CN113705487B (en) | Precision workpiece identification and technological parameter association system and identification method | |
| CN115753791A (en) | Defect detection method, device and system based on machine vision | |
| CN112734916B (en) | Color confocal parallel measurement three-dimensional morphology reduction method based on image processing | |
| CN114037682A (en) | Two-dimensional automatic detection method for optical element surface defects | |
| CN115866502A (en) | Microphone part surface defect online detection process | |
| CN114155236A (en) | Laser stripe center line extraction method suitable for dynamic measurement environment | |
| AU2021368390A1 (en) | Multi-target recognition system and method for follow-up robot based on coded thermal infrared mark | |
| Zhong et al. | A fast template matching method for LED chip Localization | |
| Lim et al. | Optical inspection method of lead frame using mathematical morphology |
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 |