Top Banner
Vision-Based System for Welding Groove Measurements for Robotic Welding Applications BQ Leonardo, CR Steffens, SC Silva Fil., JL Mór, V Hüttner, EA Leivas, VS Rosa and SSC Botelho [email protected] Center of Computer Science, Federal University of Rio Grande, Brazil
9

Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Feb 19, 2017

Download

Science

Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Vision-Based System for Welding Groove Measurements for Robotic Welding ApplicationsBQ Leonardo, CR Steffens, SC Silva Fil., JL Mór, V Hüttner, EA Leivas, VS

Rosa and SSC Botelho

[email protected]

Center of Computer Science, Federal University of Rio Grande, Brazil

Page 2: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Source: worldoceanreview.com

Page 3: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Welding is easy! Isn’t it?

• Manual process affects the quality of the weld• Rework

• Material waste

• Weak and breakable final product

• Reproducibility and regularity

• The human side• Welding is unhealthy – ergonomy, heat and fumes

• Laborious and repetitive task

Page 4: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Typical Setup of a Linear Welding System

Page 5: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Typical Setup of a Linear Welding System

Page 6: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Typical Setup of a Linear Welding System

Page 7: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Proposed Solution

• Contrast Enhancement

• Noise reduction (Gaussian, Mean, Median filters)

• Edge and line detection(Canny + Hough, PPHT, LSWMS, EDLines, Fast LSD)

• Heuristics and Non-MaximaSuppression

• Pixel to metric unitconversion

Page 8: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Embedded Visual Welding System

Page 9: Vision-Based System for Welding Groove Measurements for Robotic Welding Applications - ICRA 2016

Conclusion

• Modular Vision-Based Measurement for linear welding robots

• Machine Vision can be used on reflective metallic surfaces

• Avoided complicated hardware setup

• State of the art algorithms offer better cost-benefit ratio

• Developed a complete solution, featuring illumination, image acquisition and processing, robot operation and welding equipment setup