Yüksek LisansAçık Erişim

Uydu görüntülerini kullanarak pozisyon tahmini bulmak

Bu tez size mi ait?

Bu kayıt toplu arşivden geldi. Sizinse profilinize bağlayın.

2014
0 görüntülenme
0 i̇ndirme

Özet (EN)

This thesis deals with estimating position and orientation in real time, using visual measurements. A system has been developed with which to solve this problem for unprepared environments, assuming that a map or scene model is available. Compared to 'camera-only' examples, the developed system is accurate and robust, and can handle periods of uninformative or no visual data, reducing the need for high frequency visual updates. The system achieves real-time pose estimation via the use of a framework of nonlinear state estimation for which state space models have been developed. System performance was evaluated using an augmented reality application in which the system output was used to superimpose virtual graphics on the live video stream. Furthermore, experiments were performed in which an industrial robot providing ground truth data was used to move the sensor unit. In both cases the system performed well. Calibration of the relative position and orientation of the camera was found to be essential for proper system operation. A new and easy-to-use algorithm with which to estimate these data was developed using a stereo visual approach. Experimental results revealed that the algorithm works well in practice.

Yazar

Omar Hazzaa

Bu Yayına Nasıl Atıf Yapılır

Omar Hazzaa (Master Thesis). Uydu görüntülerini kullanarak pozisyon tahmini bulmak, 2014, Çankaya University.

Anahtar Kelimeler

Lisans

Tüm Hakları Saklıdır

Bu eser belirtilen lisans koşulları altında paylaşılmaktadır.

Çankaya University tezlerinden daha fazlası