Weichert, F.F.WeichertFiedler, D.D.FiedlerHegenberg, J.J.HegenbergMüller, H.H.MüllerPrasse, C.C.PrasseRoidl, M.M.RoidlTen Hompel, M.M.Ten Hompel2022-03-042022-03-042010https://publica.fraunhofer.de/handle/publica/22186110.1007/s12159-010-0025-6In this study, we present a novel approach for continuous detection, localization, and identification of parcels and bins in automated facility logistics systems. It presents a distinct departure from the traditional system design: light barriers and barcode readers are substituted by low-cost cameras and few RFID readers. By combining vision-based systems and RFID systems, this approach can compensate for the drawbacks of each respective system. For example, only the vision system is used for localization. The main part of our paper describes computer-graphics methods specific to the given problem to both track and read visual markers attached to parcels or bins. In addition, we use information from the RFID system to narrow the decision space for detection and identification. From an economic point of view, this approach can lower the costs of changing a material flow system.enRFIDcomputer visiontracking2D Markersensor fusionpiece goodconveyor658338journal article