caa a22 4500 469051582 CHVBK 20180323132832.0 cr unu---uuuuu 170328e19920901xx s 000 0 eng 10.1007/BF01212714 doi (NATIONALLICENCE)springer-10.1007/BF01212714 Kierkegaard Pär Department of Mechanical Engineering, Division of Assembly Technology, University of Linköping, Linköping, Sweden aut A method for detection of circular arcs based on the Hough transform [Elektronische Daten] [Pär Kierkegaard] The circular arc is a very useful feature for object detection and recognition in industrial environments. In this paper, a method for detection of circular arcs is described that is based on the Hough transform. The method estimates all five arc parameters and is robust in the presence of a moderate amount of noise. It has a computational and memory complexity ofO(n·m·R) andO(n·m) respectively, wheren andm are the sizes in thex andy directions andR is the maximum expected arc radius in pixels. Arcs as small as 45 degrees and radii down to 4 pixels can be detected. The computing time is almost independent of the number of circular arcs in the image. Springer-Verlag New York Inc, 1992 Hough transform nationallicence feature extraction nationallicence circular arcs nationallicence Machine Vision and Applications Springer-Verlag 5/4(1992-09-01), 249-263 0932-8092 5:4<249 1992 5 138 https://doi.org/10.1007/BF01212714 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF01212714 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Kierkegaard Pär Department of Mechanical Engineering, Division of Assembly Technology, University of Linköping, Linköping, Sweden aut NATIONALLICENCE 773 0- Machine Vision and Applications Springer-Verlag 5/4(1992-09-01), 249-263 0932-8092 5:4<249 1992 5 138 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer