papers AI Learner
The Github is limit! Click to go to the new site.

OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios

2019-03-19
Lukas Schaupp, Mathias Bürki, Renaud Dubé, Roland Siegwart, Cesar Cadena

Abstract

We introduce a novel method for oriented place recognition with 3D LiDAR scans. A Convolutional Neural Network is trained to extract compact descriptors from single 3D LiDAR scans. These can be used both to retrieve near-by place candidates from a map, and to estimate the yaw discrepancy needed for bootstrapping local registration methods. We employ a triplet loss function for training and use a hard-negative mining strategy to further increase the performance of our descriptor extractor. In an evaluation on the NCLT and KITTI datasets, we demonstrate that our method outperforms related state-of-the-art approaches based on both data-driven and handcrafted data representation in challenging long-term outdoor conditions.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.07918

PDF

http://arxiv.org/pdf/1903.07918


Similar Posts

Comments