CN109685758B - Weld visual positioning method based on multi-template matching - Google Patents
Weld visual positioning method based on multi-template matching Download PDFInfo
- Publication number
- CN109685758B CN109685758B CN201811271176.5A CN201811271176A CN109685758B CN 109685758 B CN109685758 B CN 109685758B CN 201811271176 A CN201811271176 A CN 201811271176A CN 109685758 B CN109685758 B CN 109685758B
- Authority
- CN
- China
- Prior art keywords
- block
- template
- welding
- camera
- seat
- 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
-
- 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
- G06T2207/30244—Camera pose
Abstract
The invention discloses a weld visual positioning method based on multi-template matching, which comprises the following steps: s1, fixing a welding gun and a vision system to enable the relative positions of the welding gun and the vision system to be unchanged; s2, positioning the center of the welding seam: s21, selecting a clear welding line image with obvious target characteristics as a reference image; s22, creating two rectangular regions containing weld corners in the reference image, namely ROI regions, extracting laser stripes of the ROI regions through threshold segmentation, and generating a template region image; s23, selecting parameters in the template area image to sequentially create multiple templates; s24, acquiring images in real time in the welding process, determining the positions of the left corner and the right corner of the groove in the images, and determining the position of the center of the welding line according to the positions and the centers of the two corners. The invention reduces the interference of irregular signals between two inflection points and greatly improves the matching accuracy.
Description
Technical Field
The invention relates to the field of visual positioning. More particularly, the invention relates to a visual positioning method of a welding seam based on multi-template matching.
Background
As an important production mode closely related to the manufacturing industry, pipeline welding is developed with the modernization of industrial production, and faces unprecedented challenges in many aspects, new requirements are provided for the welding technology level and the welding production mode, and the improvement of the intellectualization and automation level in welding is urgently needed. The automatic tracking system for the pipeline welding seam plays an increasingly important role as an important aspect for embodying the technical level of welding automation. At present, most of automatic welding robots used in China adopt a guide rail type welding design, and the robots move along guide rails, so that a certain effect is achieved. However, the guide rail must be accurately installed and debugged in advance during use, and the guide rails made of certain special materials are expensive, so that the popularization and the application of the guide rail are limited to a certain extent.
With the rapid development of artificial intelligence technologies such as machine vision and image processing in recent years, the welding seam positioning technology based on machine vision gets more and more attention of domestic and foreign students, so that automatic welding is possible by applying visual sensing guidance. The invention designs a visual system based on a machine vision principle, provides a visual positioning method based on multi-template matching for positioning the welding seam center and the welding gun swing center, and the deviation value of the positions of the welding seam center and the welding gun swing center can be used as an important reference index for guiding the welding gun to automatically weld. Template matching algorithms have been introduced and applied in the prior art, but usually a single template is selected, and when visual positioning is performed under the condition that the pipelines are not aligned regularly or completely, matching is not successful.
Disclosure of Invention
The invention aims to provide a multi-template matching-based visual positioning method for a welding line, which reduces the interference of irregular signals between two inflection points, greatly improves the matching accuracy and can ensure that an automatic pipeline welding system can operate more stably.
To achieve these objects and other advantages in accordance with the purpose of the invention, there is provided a visual weld positioning method based on multi-template matching, comprising the steps of:
s1, fixing a welding gun and a vision system to enable the relative positions of the welding gun and the vision system to be unchanged;
s2, positioning the center of the welding seam:
s21, selecting a clear welding line image with obvious target characteristics as a reference image;
s22, creating two rectangular regions containing weld corners in the reference image, namely ROI regions, extracting laser stripes of the ROI regions through threshold segmentation, and generating a template region image;
s23, selecting parameters in the template area image to sequentially create multiple templates;
s24, acquiring images in real time in the welding process, determining the positions of the left corner and the right corner of the groove in the images, and determining the position of the center of the welding line according to the positions and the centers of the two corners.
Preferably, the reference image in S21 is subjected to preprocessing for removing arc interference.
Preferably, the S23 performs parameter selection in the template region image to sequentially create multiple templates, specifically including:
creating a first region template containing a left inflection point;
creating a second region template containing a right turning point region;
and performing parameter setting on the first area template and the second area template, wherein the parameter setting determines parameters by observing the influence of two parameters, namely the pyramid layer number of the first area template or the second area template and the minimum contrast value of an object point contained in the first area template or the second area template, on the created first area template and the created second area template.
Preferably, the parameters include: the first area template and the second area template may be rotated through an angular range and a step size within the rotational angle range.
Preferably, in S24, specifically, the following are:
the method comprises the steps of collecting images in real time in the welding process, firstly defining a rectangular ROI (region of interest) containing positions of left and right inflection points, determining a search range of a template, then calling created template information to search for the position of the template in the images, and determining the positions of left and right corners of a slope in the images so as to determine the position of the center of a welding seam.
Preferably, the camera in the vision system is fixed with the reflector into a whole through a connecting device;
the connecting device includes:
the reflecting mirror comprises a first fixing plate, a second fixing plate and a reflecting mirror, wherein the first fixing plate is cylindrical and fixes the reflecting mirror, and the top surface of the first fixing plate is connected with a disk-shaped shading plate;
the two upright columns are respectively and vertically arranged on the bottom surface of the first fixing plate, and the connecting line of the two upright columns passes through the circle center of the bottom surface of the first fixing plate;
the camera inner seat is used for fixing a camera, the outer part of the camera inner seat is of a cube structure, horizontal shaft rods are symmetrically arranged on opposite first side faces of the camera inner seat, and gears of the same type are symmetrically connected to a pair of shaft rods;
the camera outer seat is provided with a square cavity with an open top surface, a pair of racks is vertically arranged in the cavity, the racks can be meshed with the gear, and the racks extend to the middle of the cavity from the top of the cavity along the vertical direction; a socket is arranged outside the camera outer seat and is fixed with the upright post;
four group's focus guiding mechanism set up in the cavity bottom respectively, and four group's focus guiding mechanism are located the camera on the central line of seat bottom surface four sides respectively, focus guiding mechanism includes:
the top surface of the moving block is horizontal and is provided with a clamping groove, the bottom surface of the camera inner base extends to the center line along the center lines of the four sides to form a convex block, the convex block is clamped in the clamping groove, the bottom surface of the moving block is an inclined surface, and the bottom surface of the moving block is provided with an inclined block with the same inclination as the bottom surface;
the fixed block is fixed in the camera outer seat, the top surface of the fixed block is an inclined surface, the top surface of the fixed block is provided with an inclined groove matched with the inclined block, and the bottom surface of the moving block is attached to the top surface of the fixed block;
the telescopic end of the electric push rod is fixed on the side face of the moving block and drives the moving block to slide on the fixed block, the base of the electric push rod is arranged on the sleeve seat in a sliding mode, and the camera outer seat is provided with a first opening for enabling the electric push rod to move up and down;
the four groups of infrared ranging sensors are fixed on the outer camera seat and respectively correspond to four corners of the bottom surface of the inner camera seat;
and the controller receives signals sent by the infrared distance measuring sensor and drives the electric push rods to stretch according to the received signals.
Preferably, the fixed block is composed of a top block, a middle block and a bottom block, the top surface of the top block is an inclined plane, the bottom surface of the top block is a plane, and the middle block and the bottom block are both in a cuboid structure;
the bottom block is provided with a first member, the lower part of the first member is positioned below the top surface of the bottom block, the first member is rotatably connected with a first rod body, the other end of the first rod body is rotatably connected with a second member, the upper part of the second member is positioned above the bottom surface of the top block, the top block is provided with a first groove body matched with the upper part of the first member, the bottom block is provided with a second groove body matched with the lower part of the second member, and the top surface of the bottom block is provided with a third groove body for accommodating the first rod body; one side of the middle block is provided with a second opening so as not to be interfered by the first rod body when moving.
Preferably, the upright post is made of transparent materials.
The invention at least comprises the following beneficial effects: the method for positioning the welding line by multi-template matching has stronger applicability and higher robustness. The matching accuracy can be kept above 90% basically, the interference of irregular signals between two inflection points is reduced, on the other hand, the matching accuracy is greatly improved, and the automatic pipeline welding system can be ensured to run more stably. Even if arc light interference exists, the template matching positioning can also play a good role in the condition of not shielding the inflection point.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
FIG. 1 is a flow chart diagram of a visual weld positioning method based on multi-template matching;
FIG. 2 is a schematic view of the groove surface of the weld of the first embodiment;
FIG. 3 left template area image;
FIG. 4 right template area image;
FIG. 5 is a schematic view showing the result of the center positioning of the weld;
FIG. 6 is a diagram of the effect of automatic welding;
FIG. 7 is a schematic view of the structure of the connecting device;
FIG. 8 is a schematic structural diagram of a fixing block;
fig. 9 is a schematic view of the connection of the top block and the bottom block in the fixed block.
1 shading plate, 2 first fixed plate, 3 reflector, 4 upright post, 5 camera, 6 camera inner seat, 7 socket, 8 rack, 9 shaft rod, 10 gear, 11 moving block, 12 electric push rod, 13 sleeve seat, 14 fixed block, 15 slide rail, 16 convex block, 17 camera outer seat, 141 top block, 142 middle block, 143 bottom block, 144 first rod body, 145 first groove body, 146 second component, 147 first component, 148 second groove body, 149 baffle plate,
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
In the description of the present invention, the terms "lateral", "longitudinal", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
As shown in FIGS. 1 to 6, the present invention provides a first embodiment.
A welding line visual positioning method based on multi-template matching comprises the following steps:
s1, fixing a welding gun and a vision system to enable the relative positions of the welding gun and the vision system to be unchanged;
s2, positioning the center of the welding seam:
s21, selecting a clear welding line image with obvious target characteristics as a reference image;
and S22, at the starting moment, creating two rectangular regions containing weld corners in the reference image, namely ROI regions, extracting laser stripes of the ROI regions through threshold segmentation, and generating a template region image, wherein the two rectangular regions are shown in figures 3 and 4.
S23, selecting parameters in the template area image to sequentially create multiple templates;
s24, acquiring images in real time in the welding process, determining the positions of the left corner and the right corner of the groove in the images, and determining the position of the center of the welding line according to the positions and the centers of the two corners.
In this embodiment, templates respectively having left and right inflection point position regions are created, and compared with a single template, although the setting is performed once more, irregular signal interference in a groove inflection point center region is avoided, the matching difficulty is reduced, and the positioning accuracy is increased. And the noise interference can be reduced by selecting multiple templates, and the positioning precision is improved.
Secondly, compared with other welding seam tracking image processing methods, the interference degree of arc light is reduced by adopting a multi-template matching method, as shown in fig. 5, it can be obviously seen that in the welding process, even if arc light interference exists, template matching positioning can also play a good role.
Further, in order to avoid the situation that the inflection point is possibly submerged by the arc, the reference image in S21 is preprocessed to remove the arc interference, so as to ensure the location of the inflection point.
Further, the S23 performs parameter selection in the template region image to sequentially create multiple templates, specifically including:
a first region template is created that includes a left inflection point.
And simultaneously creating a second region template containing a right turning point region in the image, wherein the two templates are created by the same method except for different parameters.
The method comprises the steps of setting parameters of a first area template and a second area template, and determining appropriate parameters by observing the influence of two parameters, namely the pyramid layer number of the first area template or the second area template and the minimum contrast value of an object point contained in the first area template or the second area template, on the created first area template and the created second area template in order to check whether the template contains related information describing a target object.
Further, the algorithm defines the angular range over which the first and second region templates can be rotated and the step size within the rotational angle range to define the template (first and second region templates) object.
The algorithm sets the method of template optimization and template creation.
The algorithm sets the matching template conditions in the image.
Finally, an appropriate template is successfully created, the template handle is returned, and the created template is saved in the specified file.
Further, in S24, specifically, the method includes:
firstly, defining a rectangular ROI (region of interest) containing positions of left and right inflection points, determining a search range of a template, and then calling created template information to find the position of the template in an image, wherein an algorithm is designed as follows:
first, the algorithm sets the starting angle and the angle range of the search, and the set value must intersect with the created template.
Further, the algorithm sets a minimum match value that defines the quality score of finding the template in the image when the template matches.
Further, the algorithm sets the number of layers of the pyramid in the search.
Further, the algorithm sets the search greediness to avoid finding the same matching region with the target at different locations in the image.
And finally, outputting the row and column coordinates, the angle and the fraction of the matched position.
The positions of the left corner and the right corner of the notch in the image are determined according to the output row coordinates and the output column coordinates, the position of the center of the welding line is determined according to the average value of the output row coordinates, the deviation direction of the trolley can be judged according to the obtained angle information, the matching degree can be judged according to the obtained matching score, the matching degree is high when the score is high, and otherwise, the matching fails.
In the first embodiment, as shown in fig. 5, a large rectangular frame is the ROI selected at the start time, and the determination of the search region of the image template can reduce the matching time, a small rectangular frame represents the center position of the weld determined by the target search during the welding process, and a vertical line on the small frame represents the reference position (i.e., the center position of the weld when the welding gun is aligned with the center of the weld before the start of welding). The deviation value of the two central positions (the left deviation of the vertical line is assumed to be negative, and the opposite direction is positive) reflects the deviation of the welding path of the trolley, if the deviation value is 0, the trolley is normal, the deviation of the trolley is not corrected, and the travelling direction is not changed; if the deviation value is positive (or negative), namely the swing center of the welding gun is deviated to the left (or right) than the center of the welding seam, the control system drives the welding trolley to automatically finish the deviation rectifying process to the right (or left) after receiving the deviation value.
Meanwhile, under the condition that all other conditions are consistent, visual positioning is carried out by respectively using a multi-template matching method and a single-template matching algorithm provided by the text, and the automatic welding of a whole circle of pipeline is completed. Under the condition that the calculated amount of the two algorithms is equivalent (namely, the calculated amount can both meet the real-time requirement of automatic tracking of the welding seam), the matching accuracy of single-template matching (the single-template refers to the creation of a template containing two inflection point regions at the same time) is only about 70%, the matching accuracy of the multi-template matching algorithm can be basically and stably kept above 90%, compared with the former, the method has great improvement, on one hand, the interference of irregular signals between two inflection points is reduced, on the other hand, the matching accuracy is greatly improved, and the more stable operation of an automatic pipeline welding system can be ensured.
Fig. 6 shows the practical effect of using the method of the first embodiment for automatic welding of pipes. Under the effect of the deviation rectification of the vision system, the method has good effect even under the condition that the welding trolley slightly deviates (the trolley deviates due to the fact that a pipeline is out of round or welding slag is adsorbed on the magnetic wheels in the welding process), and further verifies the effectiveness and stability of the method.
In another technical scheme, a camera 5 in the vision system is fixed with a reflector 3 into a whole through a connecting device;
as shown in fig. 7 to 9, the connecting device includes:
a first fixing plate 2 having a cylindrical shape and fixing a reflecting mirror 3, wherein a disk-shaped light shielding plate 1 is connected to a top surface of the first fixing plate 2;
the two upright columns 4 are respectively and vertically arranged on the bottom surface of the first fixing plate 2, and a connecting line of the two upright columns 4 penetrates through the circle center of the bottom surface of the first fixing plate 2;
the camera inner seat 6 is used for fixing the camera 5, the outer part of the camera inner seat 6 is of a square structure, horizontal shaft levers 9 are symmetrically arranged on the opposite first side faces of the camera inner seat, and gears 10 with the same type are symmetrically connected to the pair of shaft levers 9;
the camera outer seat 17 is provided with a square cavity with an open top surface, a pair of racks 8 are vertically arranged in the cavity, the racks 8 can be meshed with the gear 10, and the racks 8 extend from the top of the cavity to the middle of the cavity along the vertical direction; a socket 7 is arranged outside the camera outer seat 17, and the socket 7 is fixed with the upright post 4;
four group's focus guiding mechanism set up in the cavity bottom respectively, and four group's focus guiding mechanism are located the camera on 6 bottom surface four sides's of inner tower central line respectively, focus guiding mechanism includes:
the top surface of the moving block 11 is horizontal and is provided with a clamping groove, the bottom surface of the camera inner base 6 extends to the center line along the center lines of four sides to form a convex block 16, the convex block 16 is clamped in the clamping groove, the bottom surface of the moving block 11 is an inclined surface, and the bottom surface of the moving block is provided with an inclined block with the same inclination as the bottom surface;
the fixed block 14 is fixed in the camera outer seat 17, the top surface of the fixed block 14 is an inclined surface, the top surface of the fixed block is provided with an inclined groove matched with the inclined block, and the bottom surface of the moving block 11 is attached to the top surface of the fixed block 14;
the telescopic end of the electric push rod 12 is fixed on the side surface of the moving block 11 to drive the moving block 11 to slide on the fixed block 14, the base of the electric push rod 12 is arranged on the sleeve seat 13 in a sliding manner (the sleeve seat 13 is arranged outside the camera outer seat 17 in a surrounding manner and used for fixing the electric push rod 12, four groups of sliding rails 15 are arranged on the sleeve seat 13, the bases of the four electric push rods 12 are respectively connected with the sliding rails 15 in a sliding manner), and the camera outer seat 17 is provided with a first opening for the electric push rod 12 to move up and down; four groups of infrared distance measuring sensors which are fixed on the camera outer seat 17 and are respectively opposite to four corners of the bottom surface of the camera inner seat 6;
and a controller for receiving the signal from the infrared distance measuring sensor and driving the electric push rods 12 to extend and retract according to the received signal.
In above-mentioned technical scheme, need guarantee camera 5 and speculum 3 on same axis, the position is accurate when at first will guaranteeing fixed camera 5, can improve the precision, still need adjust camera 5's focal length simultaneously, consequently, will adjust the relative camera outer base 17's of camera inner base 6 distance, the uniformity when camera inner base 6 moves relative camera outer base 17 is guaranteed in setting up of rack 8 and gear 10, when four distances of 6 bottom surface four corners departments of camera inner base that infrared distance measuring sensor detected are different, controller control finely tunes the flexible distance of each electric putter 12, it is the same to the distance that detects, thereby guarantee the sag of the relative camera outer base 17 of whole camera inner base 6.
In another technical scheme, the fixed block 14 is composed of a top block 141, a middle block 142 and a bottom block 143, the top surface of the top block 141 is an inclined surface, the bottom surface is a plane, and the middle block 142 and the bottom block 143 are both rectangular structures;
a first member 147 is arranged on the bottom block 143, the lower part of the first member 147 is positioned below the top surface of the bottom block 143, the first member 147 is rotatably connected with a first rod 144, the other end of the first rod 144 is rotatably connected with a second member 146, the upper part of the second member 146 is positioned above the bottom surface of the top block 141, a first groove 145 matched with the upper part of the first member 147 is arranged on the top block 141, a second groove 148 matched with the lower part of the second member 146 is arranged on the bottom block 143, and a third groove for accommodating the first rod 144 is arranged on the top surface of the bottom block 143; the middle block 142 has a second opening at one side thereof so as not to be interfered by the first lever 144 when moving.
In the above technical scheme, the height of the whole fixed block 14 is adjusted by setting or extracting the middle block 142 to adapt to different cameras 5, the middle block 142 is taken out when not needed, the first rod body 144 is rotated to be collected into the third groove body, the top block 141 and the bottom block 143 are clamped together, in addition, when the middle block 142 is needed, the middle block 142 is clamped into the middle block, the baffle 149 is arranged on one side of the bottom block 143, the baffle 149 is fixed with the top block 141, and therefore the middle block 142 is prevented from moving in the direction away from the first rod body 144, and a limiting function is achieved.
In another technical scheme, the upright post 4 is made of transparent material.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (6)
1. The welding line visual positioning method based on multi-template matching is characterized by comprising the following steps:
s1, fixing a welding gun and a vision system to enable the relative positions of the welding gun and the vision system to be unchanged;
s2, positioning the center of the welding seam:
s21, selecting a clear welding line image with obvious target characteristics as a reference image;
s22, creating two rectangular regions containing weld corners in the reference image, namely ROI regions, extracting laser stripes of the ROI regions through threshold segmentation, and generating a template region image;
s23, selecting parameters in the template area image to sequentially create multiple templates;
s24, acquiring images in real time in the welding process, determining the positions of the left corner and the right corner of the groove in the images, and determining the position of the center of a welding line by the centers of the positions of the two corners;
a camera in the vision system is fixed with the reflector into a whole through a connecting device;
the connecting device includes:
the reflecting mirror comprises a first fixing plate, a second fixing plate and a reflecting mirror, wherein the first fixing plate is cylindrical and fixes the reflecting mirror, and the top surface of the first fixing plate is connected with a disk-shaped shading plate;
the two upright columns are respectively and vertically arranged on the bottom surface of the first fixing plate, and the connecting line of the two upright columns passes through the circle center of the bottom surface of the first fixing plate;
the camera inner seat is used for fixing a camera, the outer part of the camera inner seat is of a cube structure, horizontal shaft rods are symmetrically arranged on opposite first side faces of the camera inner seat, and gears of the same type are symmetrically connected to a pair of shaft rods;
the camera outer seat is provided with a square cavity with an open top surface, a pair of racks is vertically arranged in the cavity, the racks can be meshed with the gear, and the racks extend to the middle of the cavity from the top of the cavity along the vertical direction; a socket is arranged outside the camera outer seat and is fixed with the upright post;
four group's focus guiding mechanism set up in the cavity bottom respectively, and four group's focus guiding mechanism are located the camera on the central line of seat bottom surface four sides respectively, focus guiding mechanism includes:
the top surface of the moving block is horizontal and is provided with a clamping groove, the bottom surface of the camera inner base extends to the center line along the center lines of the four sides to form a convex block, the convex block is clamped in the clamping groove, the bottom surface of the moving block is an inclined surface, and the bottom surface of the moving block is provided with an inclined block with the same inclination as the bottom surface;
the fixed block is fixed in the camera outer seat, the top surface of the fixed block is an inclined surface, the top surface of the fixed block is provided with an inclined groove matched with the inclined block, and the bottom surface of the moving block is attached to the top surface of the fixed block;
the telescopic end of the electric push rod is fixed on the side face of the moving block and drives the moving block to slide on the fixed block, the base of the electric push rod is arranged on the sleeve seat in a sliding mode, and the camera outer seat is provided with a first opening for enabling the electric push rod to move up and down;
the four groups of infrared ranging sensors are fixed on the outer camera seat and respectively correspond to four corners of the bottom surface of the inner camera seat;
the controller receives signals sent by the infrared distance measuring sensor and drives the electric push rods to stretch according to the received signals;
the fixed block consists of a top block, a middle block and a bottom block, the top surface of the top block is an inclined surface, the bottom surface of the top block is a plane, and the middle block and the bottom block are both in cuboid structures;
the bottom block is provided with a first member, the lower part of the first member is positioned below the top surface of the bottom block, the first member is rotatably connected with a first rod body, the other end of the first rod body is rotatably connected with a second member, the upper part of the second member is positioned above the bottom surface of the top block, the top block is provided with a first groove body matched with the upper part of the first member, the bottom block is provided with a second groove body matched with the lower part of the second member, and the top surface of the bottom block is provided with a third groove body for accommodating the first rod body; one side of the middle block is provided with a second opening so as not to be interfered by the first rod body when moving.
2. The visual seam welding positioning method based on the multi-template matching as claimed in claim 1, wherein the reference image in S21 is preprocessed for removing arc interference.
3. The visual weld positioning method based on multi-template matching as claimed in claim 1, wherein the S23 performs parameter selection in the template region image to sequentially create the multi-templates, specifically including:
creating a first region template containing a left inflection point;
creating a second region template containing a right turning point region;
and performing parameter setting on the first area template and the second area template, wherein the parameter setting determines parameters by observing the influence of two parameters, namely the pyramid layer number of the first area template or the second area template and the minimum contrast value of an object point contained in the first area template or the second area template, on the created first area template and the created second area template.
4. The visual weld positioning method based on multi-template matching as claimed in claim 3, wherein the parameters comprise: the first area template and the second area template may be rotated through an angular range and a step size within the rotational angle range.
5. The visual weld positioning method based on multi-template matching as claimed in claim 4, wherein the step S24 specifically comprises:
the method comprises the steps of collecting images in real time in the welding process, firstly defining a rectangular ROI (region of interest) containing positions of left and right inflection points, determining a search range of a template, then calling created template information to search for the position of the template in the images, and determining the positions of left and right corners of a slope in the images so as to determine the position of the center of a welding seam.
6. The visual weld positioning method based on multi-template matching as claimed in claim 1, wherein the upright is made of transparent material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811271176.5A CN109685758B (en) | 2018-10-29 | 2018-10-29 | Weld visual positioning method based on multi-template matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811271176.5A CN109685758B (en) | 2018-10-29 | 2018-10-29 | Weld visual positioning method based on multi-template matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109685758A CN109685758A (en) | 2019-04-26 |
| CN109685758B true CN109685758B (en) | 2020-10-16 |
Family
ID=66185743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811271176.5A Active CN109685758B (en) | 2018-10-29 | 2018-10-29 | Weld visual positioning method based on multi-template matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109685758B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113639630A (en) * | 2021-04-01 | 2021-11-12 | 浙江大学台州研究院 | Dimension measuring instrument system based on multi-template matching and automatic focusing functions |
| CN112785648B (en) * | 2021-04-12 | 2021-07-06 | 成都新西旺自动化科技有限公司 | Visual alignment method, device and equipment based on to-be-imaged area and storage medium |
| CN113838137A (en) * | 2021-11-24 | 2021-12-24 | 中导光电设备股份有限公司 | Method and system for acquiring correction mark position based on TFT-LCD |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9149658B2 (en) * | 2010-08-02 | 2015-10-06 | Guided Therapy Systems, Llc | Systems and methods for ultrasound treatment |
| CN103203760B (en) * | 2012-01-17 | 2015-06-17 | 上海未来伙伴机器人有限公司 | Camera fixing device and panoramic vision system with same |
-
2018
- 2018-10-29 CN CN201811271176.5A patent/CN109685758B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109685758A (en) | 2019-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109685758B (en) | Weld visual positioning method based on multi-template matching | |
| CN109604777A (en) | Welding seam traking system and method based on laser structure light | |
| CN107824940A (en) | Welding seam traking system and method based on laser structure light | |
| EP3749475B1 (en) | Method for seam tracking in pipe welding | |
| CN106181162B (en) | A kind of real-time weld joint tracking detection method based on machine vision | |
| Fan et al. | A precise initial weld point guiding method of micro-gap weld based on structured light vision sensor | |
| CN109676243A (en) | Weld distinguishing and tracking system and method based on dual laser structure light | |
| WO2019033712A1 (en) | Map creation method for mobile robot and path planning method based on map | |
| CN102073148B (en) | High-accuracy visual coaxial optical alignment assembly system for miniature structural member | |
| CN109658456A (en) | Tank body inside fillet laser visual vision positioning method | |
| CN110773840B (en) | Welding deviation measuring method and device and automatic welding system | |
| CN111570975B (en) | Welding deviation measuring method and device based on synchronous drawing and automatic welding system | |
| CN107020449A (en) | Weld seam tracking sensor and its welding seam tracking method | |
| CN108858191A (en) | Visual guide method suitable for the automatic loading process of automobile top cover | |
| CN114474041A (en) | Welding automation intelligent guiding method and system based on cooperative robot | |
| CN113134683A (en) | Laser marking method and device based on machine learning | |
| CN108127217A (en) | Spiral heat exchanger edge weld guides the welder and method of welding automatically | |
| JP2021193400A (en) | Method for measuring artefact | |
| CN102538707B (en) | Three dimensional localization device and method for workpiece | |
| CN111570974B (en) | Welding deviation measuring method and device based on synchronous drawing and automatic welding system | |
| JP2004239791A (en) | Position measuring method by zooming | |
| JPH10300633A (en) | Image processing head light tester | |
| Fan et al. | An initial point alignment method of narrow weld using laser vision sensor | |
| CN116160458B (en) | Multi-sensor fusion rapid positioning method, equipment and system for mobile robot | |
| CN110726402B (en) | Laser point vision guiding method of non-orthogonal shafting laser total station |
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 |