ORIGINAL ARTICLE Welding seam profiling techniques based on active vision sensing for intelligent robotic welding Jawad Muhammad 1 & Halis Altun 2 & Essam Abo-Serie 1 Received: 29 November 2015 /Accepted: 31 March 2016 # Springer-Verlag London 2016 Abstract Intelligent robotic welding involves replicating the role of a manual professional welder to adaptively control the welding process. This is necessary to achieve accurate, fast and high-quality welding process in addition to the challeng- ing factors for humans to operate in the welding environment. Therefore, robotic welding exists since the early days of ro- botics and it is still an active research area. This is why there have been numerous researches in this area for a very long time. Among various techniques proposed by researchers for the adaptive control of the robotic welding process, vision- based control is the most popular due to its non-invasiveness. Therefore, in this paper, we review, analyse and categorise the proposed vision-based techniques with the aim of covering the different image processing and feature extraction aspect of the techniques. The focus is mainly on the active vision system where various image processing techniques have been utilised in extracting the welding seam features. The challenges and difficulties to extract seam features in active vision system have been highlighted. The trends and new approaches have been indicated in order to provide a comprehensive source for researchers who are planning to carry out research related to the intelligent robot vision techniques for welding automation. Keywords Survey on active vision . Survey on seam finding . Survey on intelligent robotic welding . Survey on seam tracking . Robotic arc welding . Robotic laser welding . Welding automation . Laser vision sensor . Machine vision . Feature extraction 1 Introduction Robotic welding is one of the oldest and most rapidly growing areas for robotics applications. However, fully automated ro- botic welding system is yet to be effectively achieved. This is due to the harsh environmental conditions created by the welding process and various factors such as welding spatter and arc lights disturbance, vigorous welding structure types, distortions due to welding heat generation and varying struc- ture of the welding seams [1]. These factors collectively affect the realisation of a fully automated robotic welding system. Intelligent robotic welding system comprises three basic com- ponents as shown in Fig. 1: (1) tracking and profiling of welding seam and pool, (2) robot trajectory planning and con- trol [2–8] and (3) welding process parameter control [9–12]. Tracking and profiling of welding seam provide information for robot trajectory planning and control. It is also a crucial step in controlling welding parameters to match the require- ments set for achieving high-quality welding. As there are plenty of different research directions on the tracking and pro- filing of welding seam and pool, in this review, we will focus on describing and categorizing the proposed approaches in this field. The aim is to give a comprehensive insight by ex- ploring the available techniques proposed in the literature and by indicating the cons and pros of the techniques. The review will only be limited to the first component of welding system (tracking and profiling of welding seam); the second and third components will not be covered in this review. Methods in tracking and profiling welding pool and seam can be categorised into (i) vision-based sensing and (ii) non- vision-based sensing methods. The most common non-vision- based sensing method is the through-arc sensing method. The method uses the electrical parameters from the welding arc and the knowledge about the motion of the weld torch which is controlled by the welding robot [1, 9, 13]. The through-arc * Jawad Muhammad jmuhammad@mevlana.edu.tr 1 Mevlana Universitesi, Konya, Konya, Turkey 2 Karatay University, Konya, Konya, Turkey Int J Adv Manuf Technol DOI 10.1007/s00170-016-8707-0