Abstract
An improved line detection method, the fast GPI method, is presented in this paper. This method improves the GPI method, reduces computational time and memory storage. After the image is filtered by Sobel operator, the feature points are stored and a sequence of projection angles is calculated by these points. A preliminary GPI matrix is calculated by these angles and then the preliminary projection angle is obtained; more detailed calculation in the vicinity of the preliminary projection angle is performed. So the final GPI matrix can be calculated, and search the extreme of the final matrix, the straight line can be located in the image. This method can detect the position of the line more quickly than the GPI method and avoid massive calculations, and is useful in image understanding, especially for robot seam tracking in robotic welding.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Jain, R., Kasturi, R., Schunck, B.G.: Machine Vision. McGraw-Hill Inc., New York (1995)
Zhang, Y.: Image Engineering—Image Processing and Analysis. Tsinghua University Press, Beijing (1999) (in Chinese)
Bums, J.B., Hanson, A.R., Reseman, E.M.: Extracting Straight Lines. IEEE Transaction on Pattern Analysis and Machine Intelligence 8(7), 425–455 (1986)
Zhang, W., Chen, Q., Du, D., Sun, Z.: Gray Projection Integral Method for Line Detection. Journal of Tsinghua University (Science and Technology) 45(11), 1446–1449 (2005)
Zheng, Z., Zhang, W., Chen, Q., Du, D.: Multi-step GPI Method by Circular Sub-window for Weld Detection in Image. Transactions of the China Welding Institution 28(8), 77–80 (2007)
Gonzalez, R.C., Woods, R.E., Eddins, S.L.: Digital Image Processing Using MATLAB. Pub. House of Electronics Industry; Pearson Prentice Hall, Beijing (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, B., Tan, S., Zhang, W. (2011). A Fast GPI Line Detection Method for Robot Seam Tracking. In: Tarn, TJ., Chen, SB., Fang, G. (eds) Robotic Welding, Intelligence and Automation. Lecture Notes in Electrical Engineering, vol 88. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19959-2_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-19959-2_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19958-5
Online ISBN: 978-3-642-19959-2
eBook Packages: EngineeringEngineering (R0)