Abstract
We examine monocular vision-based simultaneous localization and mapping (SLAM) of a mobile robot using an upward-looking camera. Although a monocular camera looking up toward the ceiling can provide a low-cost solution to indoor SLAM, this approach is often unable to achieve dependable navigation due to a lack of reliable visual features on the ceiling. We propose a novel approach to monocular SLAM using corner, lamp, and door features simultaneously to achieve stable navigation in various environments. We use the corner features and the circular-shaped brightest parts of the ceiling image for detection of lamp features. Furthermore, vertical and horizontal lines are combined to robustly detect line-based door features to reduce the problem that line features can be easily misidentified due to nearby edges. The use of these three types of features as landmarks increases our ability to observe the features in various environments and maintains the stability of the SLAM process. A series of experiments in indoor environments showed that the proposed scheme resulted in dependable navigation.
| Original language | English |
|---|---|
| Article number | 5704202 |
| Pages (from-to) | 4804-4812 |
| Number of pages | 9 |
| Journal | IEEE Transactions on Industrial Electronics |
| Volume | 58 |
| Issue number | 10 |
| DOIs | |
| Publication status | Published - 2011 Oct 1 |
Fingerprint
Keywords
- Ceiling
- mobile robot
- monocular camera
- simultaneous localization and mapping (SLAM)
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Control and Systems Engineering
- Computer Science Applications
Cite this
Monocular vision-based SLAM in indoor environment using corner, lamp, and door features from upward-looking camera. / Hwang, Seo Yeon; Song, Jae-Bok.
In: IEEE Transactions on Industrial Electronics, Vol. 58, No. 10, 5704202, 01.10.2011, p. 4804-4812.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Monocular vision-based SLAM in indoor environment using corner, lamp, and door features from upward-looking camera
AU - Hwang, Seo Yeon
AU - Song, Jae-Bok
PY - 2011/10/1
Y1 - 2011/10/1
N2 - We examine monocular vision-based simultaneous localization and mapping (SLAM) of a mobile robot using an upward-looking camera. Although a monocular camera looking up toward the ceiling can provide a low-cost solution to indoor SLAM, this approach is often unable to achieve dependable navigation due to a lack of reliable visual features on the ceiling. We propose a novel approach to monocular SLAM using corner, lamp, and door features simultaneously to achieve stable navigation in various environments. We use the corner features and the circular-shaped brightest parts of the ceiling image for detection of lamp features. Furthermore, vertical and horizontal lines are combined to robustly detect line-based door features to reduce the problem that line features can be easily misidentified due to nearby edges. The use of these three types of features as landmarks increases our ability to observe the features in various environments and maintains the stability of the SLAM process. A series of experiments in indoor environments showed that the proposed scheme resulted in dependable navigation.
AB - We examine monocular vision-based simultaneous localization and mapping (SLAM) of a mobile robot using an upward-looking camera. Although a monocular camera looking up toward the ceiling can provide a low-cost solution to indoor SLAM, this approach is often unable to achieve dependable navigation due to a lack of reliable visual features on the ceiling. We propose a novel approach to monocular SLAM using corner, lamp, and door features simultaneously to achieve stable navigation in various environments. We use the corner features and the circular-shaped brightest parts of the ceiling image for detection of lamp features. Furthermore, vertical and horizontal lines are combined to robustly detect line-based door features to reduce the problem that line features can be easily misidentified due to nearby edges. The use of these three types of features as landmarks increases our ability to observe the features in various environments and maintains the stability of the SLAM process. A series of experiments in indoor environments showed that the proposed scheme resulted in dependable navigation.
KW - Ceiling
KW - mobile robot
KW - monocular camera
KW - simultaneous localization and mapping (SLAM)
UR - http://www.scopus.com/inward/record.url?scp=80052378190&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052378190&partnerID=8YFLogxK
U2 - 10.1109/TIE.2011.2109333
DO - 10.1109/TIE.2011.2109333
M3 - Article
AN - SCOPUS:80052378190
VL - 58
SP - 4804
EP - 4812
JO - IEEE Transactions on Industrial Electronics
JF - IEEE Transactions on Industrial Electronics
SN - 0278-0046
IS - 10
M1 - 5704202
ER -