{"title":"A 2D-mapping strategy based on line segment extraction","authors":"Claudia Patricia Ochoa Diaz, A. Alvares","doi":"10.1109/ANDESCON.2010.5633272","DOIUrl":null,"url":null,"abstract":"This paper presents a strategy for a 2D-map building process for indoor environments. The strategy is conformed by two main processes: a line extraction phase based on a modified version of the Incremental algorithm, followed by a merging phase that grouped the extracted lines which represents the same real structure. This strategy is oriented for a sensory system configuration conformed by a set of range sensors. No a priori knowledge about the shape, or the number of the structures of the environment is necessary. The resulting map is a line-based representation in a global reference, without being necessary a previous construction of a local representation of the environment. The implemented algorithm is tested in both, simulated and real environments, with a robot platform equipped with a sensory system composed by 24 ultrasonic sensors in a ring configuration. Results show the viability of the proposed strategy.","PeriodicalId":359559,"journal":{"name":"2010 IEEE ANDESCON","volume":"149 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE ANDESCON","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ANDESCON.2010.5633272","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
This paper presents a strategy for a 2D-map building process for indoor environments. The strategy is conformed by two main processes: a line extraction phase based on a modified version of the Incremental algorithm, followed by a merging phase that grouped the extracted lines which represents the same real structure. This strategy is oriented for a sensory system configuration conformed by a set of range sensors. No a priori knowledge about the shape, or the number of the structures of the environment is necessary. The resulting map is a line-based representation in a global reference, without being necessary a previous construction of a local representation of the environment. The implemented algorithm is tested in both, simulated and real environments, with a robot platform equipped with a sensory system composed by 24 ultrasonic sensors in a ring configuration. Results show the viability of the proposed strategy.