Efficient 2D SLAM for a Mobile Robot with a Downwards Facing Camera
(2018) In Master's Theses in Mathematical Sciences FMA820 20171Mathematics (Faculty of Engineering)
- Abstract
- As digital cameras become cheaper and better, computers more powerful,
and robots more abundant the merging of these three techniques also becomes
more common and capable. The combination of these techniques is
often inspired by the human visual system and often strives to give machines the same capabilities that humans already have, such as object identification, navigation, limb coordination, and event detection. One such field that is particularly popular is that of SLAM, or Simultaneous Localization and Mapping, which has high-profile applications in self-driving cars and delivery drones.
This thesis proposes and describes an online SLAM algorithm for a specific
scenario: that of a robot with a downwards facing camera exploring... (More) - As digital cameras become cheaper and better, computers more powerful,
and robots more abundant the merging of these three techniques also becomes
more common and capable. The combination of these techniques is
often inspired by the human visual system and often strives to give machines the same capabilities that humans already have, such as object identification, navigation, limb coordination, and event detection. One such field that is particularly popular is that of SLAM, or Simultaneous Localization and Mapping, which has high-profile applications in self-driving cars and delivery drones.
This thesis proposes and describes an online SLAM algorithm for a specific
scenario: that of a robot with a downwards facing camera exploring a flat
surface (e.g., a floor). The method is based on building homographies from
robot odometry data, which are then used to rectify the images so that the
tilt of the camera with regards to the floor is eliminated, thereby moving the problem from 3D to 2D. The 2D pose of the robot in the plane is estimated using registrations of SURF features, and then a bundle adjustment algorithm is used to consolidate the most recent measurements with the older ones in order to optimize the map.
The algorithm is implemented and tested with an AR.Drone 2.0 quadcopter.
The results are mixed, but hardware seems to be the limiting factor: the
algorithm performs well and runs at 5-20 Hz on a i5 desktop computer; but
the bad quality, high compression and low resolution of the drone’s bottom
camera makes the algorithm unstable and this cannot be overcome, even with
several tiers of outlier filtering. (Less) - Popular Abstract (Swedish)
- För att robotar skall vara praktiska behöver de ha en flexibel uppfattning om sin omgivning och deras egen position i den, men de metoder som finns för detta idag är ofta väldigt krävande. I det här projektet har en förenklad metod för kartläggning i realtid med en drönare utvecklats. Algoritmen behandlar ett enklare problem än de vanliga tredimensionella problemen - istället för att titta framåt i rummet tittar drönaren neråt och försöker bygga en karta genom att pussla ihop bilder av golvet. Metoden är effektiv, men kvalitén på drönarens kamera som användes är för dålig för att metoden skall ge pålitliga resultat.
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/8935244
- author
- Colliander, Christian LU
- supervisor
- organization
- course
- FMA820 20171
- year
- 2018
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- SLAM, 2D SLAM, Visual SLAM, Quadcopter, Drone, Camera, Downwards facing camera, Computer Vision, Image Analysis, ROS, Robotics
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3337-2018
- ISSN
- 1404-6342
- other publication id
- 2018:E2
- language
- English
- id
- 8935244
- date added to LUP
- 2018-02-26 15:47:21
- date last changed
- 2018-02-26 15:47:21
@misc{8935244,
abstract = {{As digital cameras become cheaper and better, computers more powerful,
and robots more abundant the merging of these three techniques also becomes
more common and capable. The combination of these techniques is
often inspired by the human visual system and often strives to give machines the same capabilities that humans already have, such as object identification, navigation, limb coordination, and event detection. One such field that is particularly popular is that of SLAM, or Simultaneous Localization and Mapping, which has high-profile applications in self-driving cars and delivery drones.
This thesis proposes and describes an online SLAM algorithm for a specific
scenario: that of a robot with a downwards facing camera exploring a flat
surface (e.g., a floor). The method is based on building homographies from
robot odometry data, which are then used to rectify the images so that the
tilt of the camera with regards to the floor is eliminated, thereby moving the problem from 3D to 2D. The 2D pose of the robot in the plane is estimated using registrations of SURF features, and then a bundle adjustment algorithm is used to consolidate the most recent measurements with the older ones in order to optimize the map.
The algorithm is implemented and tested with an AR.Drone 2.0 quadcopter.
The results are mixed, but hardware seems to be the limiting factor: the
algorithm performs well and runs at 5-20 Hz on a i5 desktop computer; but
the bad quality, high compression and low resolution of the drone’s bottom
camera makes the algorithm unstable and this cannot be overcome, even with
several tiers of outlier filtering.}},
author = {{Colliander, Christian}},
issn = {{1404-6342}},
language = {{eng}},
note = {{Student Paper}},
series = {{Master's Theses in Mathematical Sciences}},
title = {{Efficient 2D SLAM for a Mobile Robot with a Downwards Facing Camera}},
year = {{2018}},
}