Laser path planning visual algorithm

A path planning and vision technology, applied in computing, image data processing, instruments, etc., can solve problems such as insufficient vacancy alignment, low position, incomplete punching, etc., and achieve the effect of rapid positioning and recognition

Inactive Publication Date: 2021-04-30
HARGLO APPLIED LASER TECH INST CO LTD +2
2 Cites 2 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0002] In the process of traditional iron tower operation, the screw holes of the tower material are sometimes incompletely drilled or the gaps are not aligned properly due...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Abstract

The invention relates to a laser path planning visual algorithm, which comprises the following steps of: firstly, moving a lens to ensure that a to-be-cut hole position is in an area; performing photographing to obtain an original image; performing Laplace transformation on the original image to enhance the edge difference of the image; carrying out expansion operation, and enlarging the edge area; carrying out threshold segmentation, and highlighting edges; finding out a prototype with the maximum area; carrying out threshold segmentation on the found hole position on the basis of the Laplace transform image; finding ou the contours, combining the similar contours, and finally extracting the maximum contour; and obtaining a fitting circle through the the contour, wherein the fitted arc is an arc with a cutting function and is also a cutting path. The industrial camera is additionally arranged on the laser cutting head and used for hole recognition and searching and positioning calculation of cutting points, and circle supplementing and cutting path planning can be rapidly carried out. Through a visual algorithm, path planning can be completed within 0.5 second, and positioning and recognition of a to-be-cut point can be rapidly achieved.

Application Domain

Technology Topic

Image

  • Laser path planning visual algorithm
  • Laser path planning visual algorithm
  • Laser path planning visual algorithm

Examples

  • Experimental program(2)

Example Embodiment

[0038] Example 1
[0039] A laser path planning vision algorithm is characterized in that it comprises the following steps:
[0040] Step ①, first move the lens to ensure that the hole to be cut is within the area; take a photo to obtain the original image;
[0041] In step ②, Laplace transform is performed on the original image to enhance the edge difference of the image;
[0042] Step ③, perform expansion operation to enlarge the edge area;
[0043] Step ④, threshold segmentation, highlight the edge;
[0044] Step ⑤, find the prototype with the largest area, that is, the hole position of the upper steel plate in reality, and the prototype obtained here is marked as circle R01;
[0045] Step ⑥, based on the hole position found in step ⑤, threshold segmentation is performed on the basis of the Laplace transformed image;
[0046] Step ⑦, find out the contour, and merge similar contours, and finally extract the largest contour;
[0047] In step ⑧, the fitted circle is obtained through the contour, and the fitted arc is the arc with cutting, which is also the cutting path.
[0048] In particular, the lens in step ① is a 200W pixel industrial camera lens equipped with a custom light source.
[0049] In particular, step ④ threshold segmentation to form a binarized image.
[0050] In particular, the mask range is obtained from the binarized image.
[0051] In particular, in step ⑦, the contour is found through the connected domain, and it is judged whether the contour satisfies the set area and circularity thresholds, and if the requirements are met, go to step 8, otherwise go to step ①.
[0052] In particular, in step ⑧, the upper circle is obtained by contour fitting, and then the dynamic threshold segmentation is performed, and the back circle is connected to the domain, and then the front circle and the back circle contour are obtained. The intersection points of the front circle contour and the back circle contour are A and B. After the geometric solution The center of the circle is the arc center C.
[0053] The image is taken by a 200W pixel industrial camera, equipped with a customized light source, and the algorithm is limited. Image processing methods such as image grayscale, expansion corrosion, and threshold segmentation are used; the identified information is used to perform layered processing on the photographed tower materials to determine the upper layer to be cut The position of the screw hole of the tower material, and finally use the knowledge of geometry to fit the circular path, and verify the rationality of the planned path to ensure that the result is obtained within 0.5s and timeliness. Using the machine vision method to plan the cutting path, and controlling the execution system for movement and laser light output, the purpose of automatic cutting can be achieved and the accuracy is improved.
[0054] In the actual experiment, the actual measured value of the diameter of the lower circle is 21.02mm. The diameter of the lower circle recognized by the vision system, namely the dotted circle, is 20.96mm. After the cutting is completed, the actual diameter is 21.04mm. It can be seen that the processing error is small, and the angle steel can be locked after the bolt passes through. It can be seen that the implementation of the present invention can quickly and accurately plan the cutting path and assist the laser cutting operation. Compared with manually finding the cutting point, the visual method is faster and more accurate, and it can realize unmanned operation, which is safer .
[0055] An industrial camera is installed on the laser cutting head for hole identification and cutting point search and positioning calculation, which can quickly perform circular filling and cutting path planning. Through the visual algorithm, the path planning can be completed within 0.5 seconds, and the positioning and identification of the intended cutting point can be quickly realized.

Example Embodiment

[0056] Example 2
[0057] A laser path planning vision algorithm is characterized in that it comprises the following steps:
[0058] Step ①, first move the lens to ensure that the hole to be cut is within the area; take a photo to obtain the original image;
[0059] In step ②, Laplace transform is performed on the original image to enhance the edge difference of the image;
[0060] Step ③, perform expansion operation to enlarge the edge area;
[0061] Step ④, threshold segmentation, highlight the edge;
[0062] Step ⑤, find the prototype with the largest area, that is, the hole position of the upper steel plate in reality, and the prototype obtained here is marked as circle R01;
[0063] Step ⑥, based on the hole position found in step ⑤, threshold segmentation is performed on the basis of the Laplace transformed image;
[0064] Step ⑦, find out the contour, and merge similar contours, and finally extract the largest contour;
[0065] In step ⑧, the fitted circle is obtained through the contour, and the fitted arc is the arc with cutting, which is also the cutting path.
[0066] In particular, step ④ threshold segmentation to form a binarized image.
[0067] In particular, the mask range is obtained from the binarized image.
[0068] In particular, in step ⑦, the contour is found through the connected domain, and it is judged whether the contour satisfies the set area and circularity thresholds, and if the requirements are met, go to step 8, otherwise go to step ①.
[0069]In particular, in step ⑧, the upper circle is obtained by contour fitting, and then the dynamic threshold segmentation is performed, and the back circle is connected to the domain, and then the front circle and the back circle contour are obtained. The intersection points of the front circle contour and the back circle contour are A and B. After the geometric solution The center of the circle is the arc center C.
[0070] The image is taken by a 200W pixel industrial camera, equipped with a customized light source, and the algorithm is limited. Image processing methods such as image grayscale, expansion corrosion, and threshold segmentation are used; the identified information is used to perform layered processing on the photographed tower materials to determine the upper layer to be cut The position of the screw hole of the tower material, and finally use the knowledge of geometry to fit the circular path, and verify the rationality of the planned path to ensure that the result is obtained within 0.5s and timeliness. Using the machine vision method to plan the cutting path, and controlling the execution system for movement and laser light output, the purpose of automatic cutting can be achieved and the accuracy is improved.
[0071] An industrial camera is installed on the laser cutting head for hole identification and cutting point search and positioning calculation, which can quickly perform circular filling and cutting path planning. Through the visual algorithm, the path planning can be completed within 0.5 seconds, and the positioning and identification of the intended cutting point can be quickly realized.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

PropertyMeasurementUnit
Diameter21.02mm
Diameter20.96 ~ 21.04mm
tensileMPa
Particle sizePa
strength10

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Similar technology patents

Insect disease monitoring system based on unmanned plane multispectral remote sensing

InactiveCN105739518AHigh computing powerQuickly identify and locatePhotogrammetry/videogrammetryPosition/course control in three dimensionsSpecies identificationSensing system
Owner:中孚航空科技(天津)有限公司

Damage imaging system based on Lamb waves

InactiveCN108267509AQuickly identify and locateMaterial analysis using acoustic emission techniquesProcessing detected response signalPhysicsSignal processing algorithms
Owner:海宁盛台材料科技有限公司

Steel pipeline defect magnetic three-component combined detection and identification method

PendingCN113030247AQuickly identify and locateImprove application effectMaterial magnetic variablesComputational physicsMagnetic field magnitude
Owner:中海石油技术检测有限公司

Classification and recommendation of technical efficacy words

  • Quickly identify and locate

Insect disease monitoring system based on unmanned plane multispectral remote sensing

InactiveCN105739518AHigh computing powerQuickly identify and locatePhotogrammetry/videogrammetryPosition/course control in three dimensionsSpecies identificationSensing system
Owner:中孚航空科技(天津)有限公司

Damage imaging system based on Lamb waves

InactiveCN108267509AQuickly identify and locateMaterial analysis using acoustic emission techniquesProcessing detected response signalPhysicsSignal processing algorithms
Owner:海宁盛台材料科技有限公司

Steel pipeline defect magnetic three-component combined detection and identification method

PendingCN113030247AQuickly identify and locateImprove application effectMaterial magnetic variablesComputational physicsMagnetic field magnitude
Owner:中海石油技术检测有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products