Auflistung nach Autor:in "Suppa, Michael"
1 - 2 von 2
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelReal-time Image-based Localization for Hand-held 3D-modeling(KI - Künstliche Intelligenz: Vol. 24, No. 3, 2010) Mair, Elmar; Strobl, Klaus H.; Bodenmüller, Tim; Suppa, Michael; Burschka, DariusWe present a self-referencing hand-held scanning device for vision-based close-range 3D-modeling. Our approach replaces external global tracking devices with ego-motion estimation directly from the camera used for reconstruction. The system is capable of online estimation of the 6DoF pose on hand-held devices with high motion dynamics especially in rotational components. Inertial information supports directly the tracking process to allow for robust tracking and feature management in highly dynamic environments. We introduce a weighting function for landmarks that contribute to the pose estimation increasing the accuracy of the localization and filtering outliers in the tracking process. We validate our approach with experimental results showing the robustness and accuracy of the algorithm. We compare the results to external global referencing solutions used in current modeling systems.
- ZeitschriftenartikelVision-Based Solutions for Robotic Manipulation and Navigation Applied to Object Picking and Distribution(KI - Künstliche Intelligenz: Vol. 33, No. 2, 2019) Roa-Garzón, Máximo A.; Gambaro, Elena F.; Florek-Jasinska, Monika; Endres, Felix; Ruess, Felix; Schaller, Raphael; Emmerich, Christian; Muenster, Korbinian; Suppa, MichaelThis paper presents a robotic demonstrator for manipulation and distribution of objects. The demonstrator relies on robust 3D vision-based solutions for navigation, object detection and detection of graspable surfaces using the rc _ visard , a self-registering stereo vision sensor. Suitable software modules were developed for SLAM and for model-free suction gripping. The modules run onboard the sensor, which enables creating the presented demonstrator as a standalone application that does not require an additional host PC. The modules are interfaced with ROS, which allows a quick implementation of a fully functional robotic application.