Miguel Saavedra Ruiz, A. Vargas, Victor Romero Cano
{"title":"Detection and tracking of a landing platform for aerial robotics applications","authors":"Miguel Saavedra Ruiz, A. Vargas, Victor Romero Cano","doi":"10.1109/CCRA.2018.8588112","DOIUrl":null,"url":null,"abstract":"It is expected that autonomous aerial vehicles or drones will be integral part of transportation and surveying robotic systems in the near future. For ensuring its strong adoption, such aerial vehicles should not only be fast and reliable, they should also be energy efficient. Energy efficiency can be obtained by exploiting the efficiency of another means of transportation such as ground vehicles. In order to take advantage of the intrinsic energy efficiency of ground vehicles, drones have to be endowed with the capability of accurately localizing a landing platform. This paper presents the development and evaluation of an embedded vision-based landing platform detection a tracking system. The system extends the capabilities of a popular SURF-based feature detector, descriptor and matcher so observations about template detections can be obtained. These detections are then feed into a Kalman filter-based estimation module tailored especially for the task at hand. The experimental evaluation shows that the approach is capable of robustly localizing a landing platform on the ground.","PeriodicalId":359172,"journal":{"name":"2018 IEEE 2nd Colombian Conference on Robotics and Automation (CCRA)","volume":"95 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE 2nd Colombian Conference on Robotics and Automation (CCRA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCRA.2018.8588112","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
It is expected that autonomous aerial vehicles or drones will be integral part of transportation and surveying robotic systems in the near future. For ensuring its strong adoption, such aerial vehicles should not only be fast and reliable, they should also be energy efficient. Energy efficiency can be obtained by exploiting the efficiency of another means of transportation such as ground vehicles. In order to take advantage of the intrinsic energy efficiency of ground vehicles, drones have to be endowed with the capability of accurately localizing a landing platform. This paper presents the development and evaluation of an embedded vision-based landing platform detection a tracking system. The system extends the capabilities of a popular SURF-based feature detector, descriptor and matcher so observations about template detections can be obtained. These detections are then feed into a Kalman filter-based estimation module tailored especially for the task at hand. The experimental evaluation shows that the approach is capable of robustly localizing a landing platform on the ground.