Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization
Paper i proceeding, 2019

Long-term visual localization is the problem of estimating the camera pose of a given query image in a scene whose appearance changes over time. It is an important problem in practice, for example, encountered in autonomous driving. In order to gain robustness to such changes, long-term localization approaches often use segmantic segmentations as an invariant scene representation, as the semantic meaning of each scene part should not be affected by seasonal and other changes. However, these representations are typically not very discriminative due to the limited number of available classes. In this paper, we propose a new neural network, the Fine-Grained Segmentation Network (FGSN), that can be used to provide image segmentations with a larger number of labels and can be trained in a self-supervised fashion. In addition, we show how FGSNs can be trained to output consistent labels across seasonal changes. We demonstrate through extensive experiments that integrating the fine-grained segmentations produced by our FGSNs into existing localization algorithms leads to substantial improvements in localization performance.

Författare

Måns Larsson

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Erik Stenborg

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Carl Toft

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Lars Hammarstrand

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Torsten Sattler

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Fredrik Kahl

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Proceedings of the IEEE International Conference on Computer Vision

15505499 (ISSN)

Vol. 2019-October October 31-41

IEEE International Conference on Computer Vision
Seoul, South Korea,

Perceptron

VINNOVA (2017-01942), 2017-06-01 -- 2019-11-30.

Styrkeområden

Informations- och kommunikationsteknik

Ämneskategorier

Datorseende och robotik (autonoma system)

DOI

10.1109/ICCV.2019.00012

Mer information

Senast uppdaterat

2024-07-17