2017
DOI: 10.1016/j.robot.2016.12.001
|View full text |Cite
|
Sign up to set email alerts
|

Comparing holistic and feature-based visual methods for estimating the relative pose of mobile robots

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
38
0

Year Published

2017
2017
2024
2024

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 29 publications
(38 citation statements)
references
References 41 publications
0
38
0
Order By: Relevance
“…The OpenCV implementations of SIFT [21], ORB [45] and BRISK [27] were used to obtain the feature descriptors. These descriptors have also been used in a recent comparison of holistic and feature-based methods for relative pose estimation, also done in our research group [46]. SIFT is relatively slow, but generally achieves better results than the fast binary methods.…”
Section: Feature-based Method: Fabmapmentioning
confidence: 99%
See 4 more Smart Citations
“…The OpenCV implementations of SIFT [21], ORB [45] and BRISK [27] were used to obtain the feature descriptors. These descriptors have also been used in a recent comparison of holistic and feature-based methods for relative pose estimation, also done in our research group [46]. SIFT is relatively slow, but generally achieves better results than the fast binary methods.…”
Section: Feature-based Method: Fabmapmentioning
confidence: 99%
“…We use the binary LDB and BRISK descriptors. LDB has been identified as the best method in the original paper [37], while BRISK showed a good trade-off between speed and accuracy in one of our own studies about visual homing [46]. To compare two images, the Hamming distance for all pairs of descriptors is computed, and the minimum is stored as dissimilarity value.…”
Section: Ablementioning
confidence: 99%
See 3 more Smart Citations