Towards Dense Visual SLAM
| Autor: | Pietzsch, Tobias |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2011 |
| Předmět: |
info:eu-repo/classification/ddc/004
ddc:004 SLAM-Verfahren Erweiterte Realität Bildfolgenverarbeitung Bildverarbeitung Lokalisierung Dreidimensionales maschinelles Sehen Simultane Lokalisierung und Kartierung SLAM Visuelles SLAM Erweiterte Realität Inverse-Tiefe-Parametrisierung Bildverarbeitung Dreidimensionales Maschinelles Sehen Stereo-Sehen Flächen-Modelle Simultaneous Localization And Mapping Visual SLAM Stereo Vision Augmented Reality Extended Kalman Filter Inverse Depth Higher-Level Features Planar Features Dense Mapping Dense Maps Direct Measurement Method Visual SLAM Evaluation |
| Druh dokumentu: | Text<br />Doctoral Thesis |
| Popis: | Visual Simultaneous Localisation and Mapping (SLAM) is concerned with simultaneously estimating the pose of a camera and a map of the environment from a sequence of images. Traditionally, sparse maps comprising isolated point features have been employed, which facilitate robust localisation but are not well suited to advanced applications. In this thesis, we present map representations that allow a more dense description of the environment. In one approach, planar features are used to represent textured planar surfaces in the scene. This model is applied within a visual SLAM framework based on the Extended Kalman Filter. We presents solutions to several challenges which arise from this approach. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|