Visual Simultaneous Localization and Mapping Using Direct-Based Method for Unmanned Aerial Vehicle (UAV)
The Direct Sparse Odometry (DSO) technique is a new form of visual odometry that makes use of a direct and sparse structure to achieve precision. In this project, the objective is to apply the DSO algorithm on the Unmanned Aerial Vehicle (UAV) application. The main studies in this project are focusi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SIGMA BOT
2023
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/39638/1/Visual%20Simultaneous%20Localization%20and%20Mapping%20Using%20DirectBased%20Method%20for%20Unmanned%20Aerial%20Vehicle%20%28UAV%29.pdf http://umpir.ump.edu.my/id/eprint/39638/ http://www.red.pe.org.pl/abstract_pl.php?nid=13826&lang=1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The Direct Sparse Odometry (DSO) technique is a new form of visual odometry that makes use of a direct and sparse structure to achieve precision. In this project, the objective is to apply the DSO algorithm on the Unmanned Aerial Vehicle (UAV) application. The main studies in this project are focusing on the experimentation for DSO algorithm parameter setting. Another objective is to evaluate the parameter and performance of DSO algorithm. The data evaluation was based on three different environments in the university campus. In this project, the Realsense D435i camera was applied to the RDDRONE-FMUK66 with interface of the Raspberry Pi 3 B+ model to capture the data. This project managed to analyze suitable point values on the active points and gradient parameter setting. The same parameter configuration which concerns on point density and keyframe management have been experimented in the three environment. From this project it is concluded that DSO on UAV can be improved in order to gain a stable data processing to be applied in the algorithm. |
|---|