Paper Info
Title
On The Performance Of Pose-Based Rgb-D Visual Navigation Systems
Abstract
This paper presents a thorough performance analysis of several variants of the feature-based visual navigation system that uses RGB-D data to estimate in real-time the trajectory of a freely moving sensor. The evaluation focuses on the advantages and problems that are associated with choosing a particular structure of the sensor-tracking front-end, employing particular feature detectors/descriptors, and optimizing the resulting trajectory treated as a graph of sensor poses. Moreover, a novel yet simple graph pruning algorithm is introduced, which enables to remove spurious edges from the pose-graph. The experimental evaluation is performed on two publicly available RGB-D data sets to ensure that our results are scientifically verifiable.
Year
DOI
Venue
2014
10.1007/978-3-319-16808-1_28
COMPUTER VISION - ACCV 2014, PT II
Field
DocType
Volume
Computer vision,Data set,Pattern recognition,Visual odometry,Computer science,Verifiable secret sharing,Artificial intelligence,RGB color model,Mobile robot navigation,Motion estimation,Spurious relationship,Trajectory
Conference
9004
ISSN
Citations 
PageRank 
0302-9743
7
0.48
References 
Authors
22
3
Name
Order
Citations
PageRank
Dominik Belter110016.31
Michal Nowicki2378.73
Piotr Skrzypczynski314825.07