Saved in:
Bibliographic Details
Main Authors: Fu, Chencan, Li, Lin, Mei, Jianbiao, Ma, Yukai, Peng, Linpeng, Zhao, Xiangrui, Liu, Yong
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.06881
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914881878360064
author Fu, Chencan
Li, Lin
Mei, Jianbiao
Ma, Yukai
Peng, Linpeng
Zhao, Xiangrui
Liu, Yong
author_facet Fu, Chencan
Li, Lin
Mei, Jianbiao
Ma, Yukai
Peng, Linpeng
Zhao, Xiangrui
Liu, Yong
contents Place recognition is a challenging but crucial task in robotics. Current description-based methods may be limited by representation capabilities, while pairwise similarity-based methods require exhaustive searches, which is time-consuming. In this paper, we present a novel coarse-to-fine approach to address these problems, which combines BEV (Bird's Eye View) feature extraction, coarse-grained matching and fine-grained verification. In the coarse stage, our approach utilizes an attention-guided network to generate attention-guided descriptors. We then employ a fast affinity-based candidate selection process to identify the Top-K most similar candidates. In the fine stage, we estimate pairwise overlap among the narrowed-down place candidates to determine the final match. Experimental results on the KITTI and KITTI-360 datasets demonstrate that our approach outperforms state-of-the-art methods. The code will be released publicly soon.
format Preprint
id arxiv_https___arxiv_org_abs_2303_06881
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Coarse-to-Fine Place Recognition Approach using Attention-guided Descriptors and Overlap Estimation
Fu, Chencan
Li, Lin
Mei, Jianbiao
Ma, Yukai
Peng, Linpeng
Zhao, Xiangrui
Liu, Yong
Computer Vision and Pattern Recognition
Robotics
Place recognition is a challenging but crucial task in robotics. Current description-based methods may be limited by representation capabilities, while pairwise similarity-based methods require exhaustive searches, which is time-consuming. In this paper, we present a novel coarse-to-fine approach to address these problems, which combines BEV (Bird's Eye View) feature extraction, coarse-grained matching and fine-grained verification. In the coarse stage, our approach utilizes an attention-guided network to generate attention-guided descriptors. We then employ a fast affinity-based candidate selection process to identify the Top-K most similar candidates. In the fine stage, we estimate pairwise overlap among the narrowed-down place candidates to determine the final match. Experimental results on the KITTI and KITTI-360 datasets demonstrate that our approach outperforms state-of-the-art methods. The code will be released publicly soon.
title A Coarse-to-Fine Place Recognition Approach using Attention-guided Descriptors and Overlap Estimation
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2303.06881