Header

UZH-Logo

Maintenance Infos

Place recognition in semi-dense maps: Geometric and learning-based approaches


Ye, Yawei; Cieslewski, Titus; Loquercio, Antonio; Scaramuzza, Davide (2017). Place recognition in semi-dense maps: Geometric and learning-based approaches. In: British Machine Vision Conference, London, 4 September 2017 - 7 September 2017, 1-8.

Abstract

For robotics and augmented reality systems operating in large and dynamic environments,
place recognition and tracking using vision represent very challenging tasks. Additionally,
when these systems need to reliably operate for very long time periods, such
as months or years, further challenges are introduced by severe environmental changes,
that can significantly alter the visual appearance of a scene. Thus, to unlock long term,
large scale visual place recognition, it is necessary to develop new methodologies for
improving localization under difficult conditions. As shown in previous work, gains in
robustness can be achieved by exploiting the 3D structural information of a scene. The
latter, extracted from image sequences, carries in fact more discriminative clues than
individual images only. In this paper, we propose to represent a scene’s structure with
semi-dense point clouds, due to their highly informative power, and the simplicity of their
generation through mature visual odometry and SLAM systems. Then we cast place
recognition as an instance of pose retrieval and evaluate several techniques, including
recent learning based approaches, to produce discriminative descriptors of semi-dense
point clouds. Our proposed methodology, evaluated on the recently published and challenging
Oxford Robotcar Dataset, shows to outperform image-based place recognition,
with improvements up to 30% in precision across strong appearance changes. To the best
of our knowledge, we are the first to propose place recognition in semi-dense maps.

Abstract

For robotics and augmented reality systems operating in large and dynamic environments,
place recognition and tracking using vision represent very challenging tasks. Additionally,
when these systems need to reliably operate for very long time periods, such
as months or years, further challenges are introduced by severe environmental changes,
that can significantly alter the visual appearance of a scene. Thus, to unlock long term,
large scale visual place recognition, it is necessary to develop new methodologies for
improving localization under difficult conditions. As shown in previous work, gains in
robustness can be achieved by exploiting the 3D structural information of a scene. The
latter, extracted from image sequences, carries in fact more discriminative clues than
individual images only. In this paper, we propose to represent a scene’s structure with
semi-dense point clouds, due to their highly informative power, and the simplicity of their
generation through mature visual odometry and SLAM systems. Then we cast place
recognition as an instance of pose retrieval and evaluate several techniques, including
recent learning based approaches, to produce discriminative descriptors of semi-dense
point clouds. Our proposed methodology, evaluated on the recently published and challenging
Oxford Robotcar Dataset, shows to outperform image-based place recognition,
with improvements up to 30% in precision across strong appearance changes. To the best
of our knowledge, we are the first to propose place recognition in semi-dense maps.

Statistics

Downloads

29 downloads since deposited on 24 Aug 2017
29 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:7 September 2017
Deposited On:24 Aug 2017 13:03
Last Modified:29 Jul 2018 04:17
OA Status:Green
Free access at:Related URL. An embargo period may apply.
Related URLs:http://rpg.ifi.uzh.ch/docs/BMVC17_Ye.pdf
Other Identification Number:merlin-id:15108

Download

Download PDF  'Place recognition in semi-dense maps: Geometric and learning-based approaches'.
Preview
Content: Published Version
Filetype: PDF
Size: 3MB