Abstract
We present a complete, working system for analyzing coaxially viewed robotic weld scenes. The analysis is cast in the form of a consistent labeling problem in which the objects are small image regions from a regular tesselation and the possible labels are base metal, electrode, gas cup, filler wire, weld bead, and weld pool. Local domain knowledge and measurements on the image function are used to produce an initial set of labeling probabilities. These are then adjusted by probabilistic relaxation using global domain knowledge to arrive at a final consistent labeling, which constitutes the image analysis. The primary goal of this analysis is a sufficiently accurate description of the size and shape of the weld pool to allow quality monitoring of the welding process. This represents a significant departure from the primary objectives of prior work in this area, most of which has focused on the seam tracking problem. Discussions with welding engineers indicate that they are anxious to acquire whatever information may be available. Thus, this system serves the secondary goal of providing some idea of what might be possible, given both relatively modest, and therefore affordable, resources and a real time performance requirement. In constructing and demonstrating a complete system, we provide useful insight into the engineering of such systems for practical applications, addressing attribute extraction, feature selection, and statistical region classification. A novel, efficient near-optimal feature selection algorithm which we callratchet search is also presented. Finally, we discuss how such a system, which is quite robust, could be embedded into robotic welding systems to provide important weld quality analysis for process control.
Similar content being viewed by others
References
Nayak N, Ray A (1990) An integrated system for intelligent seam tracking in robotic welding, part I: Conceptual and analytical development, in Proceedings IEEE International Conference on Robotics and Automation, pp. 1892–1897
Clocksin WF, Bromley JSE, Davey PG, Vidler AR, Morgan CGM (1985) An implementation of modelbased visual feedback for robot arc welding of thin sheet steel, International Journal of Robotics Research 4(1): 13–26
Richardson RD, Richardson RW (1983) The measurement of two-dimensional arc weld pool geometry by image analysis, in Control of Manufacturing and Robotic Systems (DE Hardt and WJ Book, eds.), The American Society of Mechanical Engineers, pp. 137–148
Richardson RW, Gutow D, Anderson R, Farson D (1984) Coaxial arc weld pool viewing for process monitoring and control, Welding Journal 63(3):43–50
Richardson RW (1986) Robotic weld joint tracking systems-theory and implementation methods, Welding Journal 65(11):43–51
Nitzan D (1988) Three-dimensional vision structure for robot applications, IEEE Transactions on Pattern Analysis and Machine Intelligence 10:291–309
Nayak N, Ray A (1990) An integrated system for intelligent seam tracking in robotic welding, part II: design and implementation, in Proceedings IEEE International Conference on Robotics and Automation, pp. 1898–1903
Nan H, Abbott MG, Beattie RJ (1988) Approaches to low level image processing for vision guided seam tracking systems, in International Conference on Pattern Recognition, pp. 601–603
Antoshchenko EM, Vorob'ev YA, Fateev AN, Kovika ND(1984) A television system for automatic guiding of welding heads of mills for internal welding large diameter pipes, Welding Production 31:39–41
Sato T (1990) Development of an intelligent robot for welding pressure vessels, Welding International 4(3):228–233
Mazurov VM, Karpov VS, Panarin VM, Malyutin AA, Shestakov VN, Chinaev PI (1984) System for automatic tracking of the joint using the arc as the sensing element, Welding Production 31:42–43
Maqueira B, Umeagukwu CI, Jarzynski J (1989) Application of ultrasonic sensors to robotic seam tracking, IEEE Transactions on Robotics and Automation 5:337–344
Masaki I, Gorman RR, Shulman BH, Dunne MJ, Toda H (1981) Arc welding robot with vision, in Proceedings 11th International Symposium on Industrial Robots, pp. 813–817
Agapakis JE, Masubuchi K, Wittels N (1985) General visual sensing techniques for automated welding fabrication, in Proceedings 15th International Symposium on Industrial Robots, pp. 103–114
Morgan CG, Bromley JSE, Davey PG, Vidler AR (1983) Visual guidance techniques for robot arc welding, in Proceedings SPIE 449:390–399
Rosenfeld A, Kak AC (1982) Digital Picture Processing, vol. 2. New York: Academic Press
Haralick RM, Shapiro LG (1979) The consistent labeling problem: Part i, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-1, pp. 173–184
Haralick RM, Shapiro LG (1980) The consistent labeling problem: Part ii, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-2, pp. 193–203
Haralick RM (1979) Statistical and structural approaches to texture, Proceedings of the IEEE, pp. 786–804
Haralick RM, Shanmugam K, Dinstein I (1973) Texture features for image classification, IEEE Transactions on Systems, Man, and Cybernetics SMC-3(6):610–621
Davis LA, Johns SA, Aggarwal JK (1979) Texture analysis using generalized co-occurrence matrice, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-1, pp. 251–259
Conners R (1979) Towards a set of statistical features which measure visually perceivable qualities of textures, in Proceedings of the Conference on Pattern Recognition and Image Processing, pp. 382–390
Dyer C, Hong T, Rosenfeld A (1980) Texture classification using grey level co-occurrence based on edge maxima, IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-10, pp. 158–163
Pavlidis T (1982) Algorithms for Computer Graphics and Image Processing. Rockville, Maryland: Computer Science Press
Weszka JS, Rosenfeld A (1976) An application of texture analysis to materials inspection, Pattern Recognition 8:195–199
Levine MD (1985) Vision in Man and Machine. New York: McGraw-Hill
Galloway MM (1975) Texture analysis using gray level run lengths, Computer Graphics and Image Processing 4:172–179
Stearns SD (1976) On selecting features for pattern classifiers, in Proceedings of International Joint Conference on Pattern Recognition, pp. 71–75
Mucciardi A, Gose E (1971) A comparison of seven techniques for choosing subsets of pattern recognition properties, IEEE Transactions on Computers, vol. C-20, pp. 1023–1031
Witney A (1971) A direct method of nonparametric measurement selection, IEEE Transactions on Computers, vol. C-20, pp. 1100–1103
Marill T, Green D (1963) On the effectiveness of receptors in recognition systems, IEEE Transactions on Information Theory, vol. IT-9, pp. 11–17
Chang C-Y (1973) Dynamic programming as applied to feature subset selection in a pattern recognition system, IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, pp. 166–171
Michael M, Lin W (1973) Experimental study of information measure and inter-intra class distance ratios on feature selection and orderings, IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, pp. 172–181
Kubichek R, Quincy E (1985) Statistical modeling and feature selection for seismic pattern recognition, Pattern Recognition 18(6): 441–448
Chen CH (1975) On a class of computationally efficient feature selection criteria, Pattern Recognition 7:87–94
Van Trees HL (1968) Detection, Estimation, and Modulation Theory, Part I. New York: John Wiley & Sons
Lafrance P (1990) Fundamental Concepts in Communication. Englewood Cliffs, New Jersey: Prentice-Hall
Rosenfeld A, Hummel RA, Zucker SW (1976) Scene labeling by relaxation operations, IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-6, pp. 420–433
Ballard DH, Brown CM (1982) Computer Vision. Englewood Cliffs, New Jersey: Prentice-Hall
Press W, Flannery B, Teukolsky S, Vetterling W (1986) Numeric Recipes: The art of Scientific Computing. Cambridge University Press
Yamamoto H (1979) A method of deriving compatibility coefficients for relaxation operators, Computer Graphics and Image Processing 10:256–271
Fekete G, Eklundh J, Rosenfeld A (1981) Relaxation: evaluation and applications, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-3, pp. 459–469
Author information
Authors and Affiliations
Additional information
This research supported by the departments of Welding Engineering and Electrical Engineering at The Ohio State University.
Rights and permissions
About this article
Cite this article
Boyer, K.L., Penix, W.A. An image analysis system for coaxially viewed weld scenes. Machine Vis. Apps. 5, 277–293 (1992). https://doi.org/10.1007/BF01212716
Issue Date:
DOI: https://doi.org/10.1007/BF01212716