Automatic image scaling for place recognition in changing environments
Data(s) |
27/05/2015
|
---|---|
Resumo |
Robustness to variations in environmental conditions and camera viewpoint is essential for long-term place recognition, navigation and SLAM. Existing systems typically solve either of these problems, but invariance to both remains a challenge. This paper presents a training-free approach to lateral viewpoint- and condition-invariant, vision-based place recognition. Our successive frame patch-tracking technique infers average scene depth along traverses and automatically rescales views of the same place at different depths to increase their similarity. We combine our system with the condition-invariant SMART algorithm and demonstrate place recognition between day and night, across entire 4-lane-plus-median-strip roads, where current algorithms fail. |
Formato |
application/pdf |
Identificador | |
Publicador |
IEEE |
Relação |
http://eprints.qut.edu.au/84553/1/ICRA2015_camera_ready.pdf DOI:10.1109/ICRA.2015.7139316 Pepperell, Edward, Corke, Peter, & Milford, Michael (2015) Automatic image scaling for place recognition in changing environments. In Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA 2015), IEEE, Washington State Convention Center, Seattle, WA, pp. 1118-1124. http://purl.org/au-research/grants/ARC/DE120100995 |
Direitos |
Copyright 2015 [Please consult the author] |
Fonte |
ARC Centre of Excellence for Robotic Vision; School of Electrical Engineering & Computer Science; Science & Engineering Faculty |
Palavras-Chave | #Place recognition #Localisation #Navigation |
Tipo |
Conference Paper |