CurriculumLoc: 多段階精緻化によるクロスドメイン地理的位置推定の強化
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement
カリキュラム学習に着想を得て、意味的なシーン認識から幾何学的構造の検証へと段階的に精緻化する多段階パイプラインを提案し、クロスドメインの視覚的地理位置推定精度を向上させた。
著者: Boni Hu, Lin Chen, Runjian Chen, Shuhui Bu, Pengcheng Han, Haowei Li
分類: cs.CV, cs.RO
原文アブストラクト
Visual geolocalization is a cost-effective and scalable task that involves matching one or more query images, taken at some unknown location, to a set of geo-tagged reference images. Existing methods, devoted to semantic features representation, evolving towards robustness to a wide variety between query and reference, including illumination and viewpoint changes, as well as scale and seasonal variations. However, practical visual geolocalization approaches need to be robust in appearance changing and extreme viewpoint variation conditions, while providing accurate global location estimates. Therefore, inspired by curriculum design, human learn general knowledge first and then delve into professional expertise. We first recognize semantic scene and then measure geometric structure. Our approach, termed CurriculumLoc, involves a delicate design of multi-stage refinement pipeline and a novel keypoint detection and description with global semantic awareness and local geometric verification. We rerank candidates and solve a particular cross-domain perspective-n-point (PnP) problem based on these keypoints and corresponding descriptors, position refinement occurs incrementally. The extensive experimental results on our collected dataset, TerraTrack and a benchmark dataset, ALTO, demonstrate that our approach results in the aforementioned desirable characteristics of a practical visual geolocalization solution. Additionally, we achieve new high recall@1 scores of 62.6% and 94.5% on ALTO, with two different distances metrics, respectively. Dataset, code and trained models are publicly available on https://github.com/npupilab/CurriculumLoc.
