Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/600426A9-2418-400E-B5A1-6FD8EBA07836 | - |
| Identifier | https://doi.org/10.26233/heallink.tuc.90473 | - |
| Language | en | - |
| Extent | 27.2 megabytes | en |
| Title | Acceleration of simultaneous localization and mapping (SLAM) algorithms on graphics processing units (GPUs) for unmanned air drones | en |
| Title | Επιτάχυνση με χρήση κάρτας γραφικών του αλγορίθμου SLAM για χαρτογράφηση και εντοπισμό θέσης σε μη επανδρωμένα εεροχήματα | el |
| Creator | Felekis Panagiotis | en |
| Creator | Φελεκης Παναγιωτης | el |
| Contributor [Thesis Supervisor] | Dollas Apostolos | en |
| Contributor [Thesis Supervisor] | Δολλας Αποστολος | el |
| Contributor [Committee Member] | Lagoudakis Michail | en |
| Contributor [Committee Member] | Λαγουδακης Μιχαηλ | el |
| Contributor [Committee Member] | Partsinevelos Panagiotis | en |
| Contributor [Committee Member] | Παρτσινεβελος Παναγιωτης | el |
| Publisher | Πολυτεχνείο Κρήτης | el |
| Publisher | Technical University of Crete | en |
| Academic Unit | Technical University of Crete::School of Electrical and Computer Engineering | en |
| Academic Unit | Πολυτεχνείο Κρήτης::Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών | el |
| Description | An object, turn a screw, or weld two pieces of metal together. Mobile robots must solve two basic problems: create a map of the environment and position themselves into this map. Simultaneous localization and mapping (SLAM) approaches can incrementally construct a map of the robot's surrounding environment, while estimating the robot's position in the map. Visual SLAM (vSLAM) uses the camera to obtain corresponding two dimensional digital images from the real three-dimensional world. These camera provides images with high resolution, rich colours and textures, which we can exploit to create a very rich map. Due to high computational demands of vSLAM, scaled-down versions are used with smaller resolution and less key features, resulting in poor estimations. In this thesis, we propose an accelerated version of ORB vSLAM that uses a GPU. In our version, we use high resolution images which results in more accurate and rich results. Our system operates in NVIDIA Jetson Tx2 embedded module which is suitable for autonomous robots due to low power consumption. In terms of performance results, our system performs almost identically to a fully-powered desktop CPU, while consuming 5$\times$ less power. We also prove that our system is as much accurate as the non-accelerated vSLAM system, by using a well-established accuracy dataset. | en |
| Content Summary | In order to achieve fully autonomous work in an unknown environment, many robots rely on cameras and vision algorithms to figure out where to place an object, turn a screw, or weld two pieces of metal together. Mobile robots must solve two basic problems: create a map of the environment and position themselves into this map. Simultaneous localization and mapping (SLAM) algorithm can incrementally construct a map of the robot's surrounding environment while estimating the robot's position in the map. Visual SLAM (vSLAM) uses the camera to obtain corresponding two dimensional digital images from the real three-dimensional world. These camera provides images with high resolution, rich colours and textures where we can exploit to create a very rich map. Due to high computational demands of vSLAM, scaled-down versions are used with smaller resolution and less key features, resulting in poor estimations. In this thesis, we propose an accelerated version of vSLAM that uses a GPU. In our version, we use high resolution images which results in more accurate and rich results. Our system operates in NVIDIA Jetson Tx2 embedded module which is suitable for autonomous robots due to low power consumption. In terms of performance results, our system performs almost identical to a full-powered desktop CPU, while consuming 5x less power. We also prove that our system is as much accurate as other SLAM systems, by using a well-established accuracy dataset. | en |
| Content Summary | Σε αυτή την ερευνά προτείνουμε ένα SLAM σύστημα που χρησιμοποιεί κάρτα γραφικών για την επιτάχυνση του. Με αυτό τον τρόπο μπορούμε να χρησιμοποιήσουμε βίντεο υψηλής ευκρίνειας, για την καλύτερη χαρτογράφηση του περιβάλλοντος, σε λιγότερο χρόνο. Το σύστημα μας λειτουργεί σε ενσωματωμένη συσκευή NVIDIA Jetson Tx2 η οποία είναι κατάλληλη για αυτόνομα ρομπότ λόγο των υψηλών ενεργειακών αποδόσεων και μικρού μεγέθους. Συγκρίνουμε την ακρίβεια, την υπολογιστική και ενεργειακή απόδοση του συστήματος μας, με έναν προσωπικό υπολογιστή. | el |
| Type of Item | Διπλωματική Εργασία | el |
| Type of Item | Diploma Work | en |
| License | http://creativecommons.org/licenses/by/4.0/ | en |
| Date of Item | 2021-10-12 | - |
| Date of Publication | 2021 | - |
| Subject | Image processing | en |
| Subject | Computer vision | en |
| Bibliographic Citation | Panagiotis Felekis, "Acceleration of simultaneous localization and mapping (SLAM) algorithms on graphics processing units (GPUs) for unmanned air drones", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2021 | en |
| Bibliographic Citation | Παναγιώτης Φελέκης, "Επιτάχυνση με χρήση κάρτας γραφικών του αλγορίθμου SLAM για χαρτογράφηση και εντοπισμό θέσης σε μη επανδρωμένα εεροχήματα ", Διπλωματική Εργασία, Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών, Πολυτεχνείο Κρήτης, Χανιά, Ελλάς, 2021 | el |
Copyright © DIAS 2013
