J. M. González-Linares, N. Guil, P. Pérez, M. Ehrenmann, R. Dillmann
{"title":"An efficient image processing algorithm for high-level skill acquisition","authors":"J. M. González-Linares, N. Guil, P. Pérez, M. Ehrenmann, R. Dillmann","doi":"10.1109/ISATP.1999.782969","DOIUrl":null,"url":null,"abstract":"This paper describes the set-up of the image processing system installed at the IPR in Karlsruhe. It will serve for sensor device in the programming by demonstration field. As a first application example, it is used as source for images in the demonstration of a bag packaging task. A detection algorithm that finds positions of infusion bags is presented. It was developed at the Department of Computer Architecture of the University of Malaga, and uses a straight line Hough transform after the application of a Canny filter. Then, the position of the rubber caps of the bags are located by a binarization technique to predicate the orientation of the bag. However, since the computing power is quite limited, the algorithms must have as low complexity as possible.","PeriodicalId":326575,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Assembly and Task Planning (ISATP'99) (Cat. No.99TH8470)","volume":"407 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 1999 IEEE International Symposium on Assembly and Task Planning (ISATP'99) (Cat. No.99TH8470)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISATP.1999.782969","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10
Abstract
This paper describes the set-up of the image processing system installed at the IPR in Karlsruhe. It will serve for sensor device in the programming by demonstration field. As a first application example, it is used as source for images in the demonstration of a bag packaging task. A detection algorithm that finds positions of infusion bags is presented. It was developed at the Department of Computer Architecture of the University of Malaga, and uses a straight line Hough transform after the application of a Canny filter. Then, the position of the rubber caps of the bags are located by a binarization technique to predicate the orientation of the bag. However, since the computing power is quite limited, the algorithms must have as low complexity as possible.