Improving constrained bundle adjustment through semantic scene labeling - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Improving constrained bundle adjustment through semantic scene labeling

(1) , (1) , (1) , (2)
1
2

Abstract

There is no doubt that SLAM and deep learning methods can benefit from each other. Most recent approaches to coupling those two subjects, however, either use SLAM to improve the learning process, or tend to ignore the geometric solutions that are currently used by SLAM systems. In this work, we focus on improving city-scale SLAM through the use of deep learning. More precisely, we propose to use CNNbased scene labeling to geometrically constrain bundle adjustment. Our experiments indicate a considerable increase in robustness and precision.

Dates and versions

cea-01813719 , version 1 (12-06-2018)

Identifiers

Cite

A. Salehi, V. Gay-Bellile, S. Bourgeois, F. Chausse. Improving constrained bundle adjustment through semantic scene labeling. ECCV 2016: Computer Vision – ECCV 2016 Workshops, Oct 2016, Amsterdam, Netherlands. pp.133-142, ⟨10.1007/978-3-319-49409-8_13⟩. ⟨cea-01813719⟩
90 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More