SONIC: Sonar Image Correspondence using Pose Supervised Learning for Imaging Sonars

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gode, Samiran, Hinduja, Akshay, Kaess, Michael
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910445387907072
author Gode, Samiran
Hinduja, Akshay
Kaess, Michael
author_facet Gode, Samiran
Hinduja, Akshay
Kaess, Michael
contents In this paper, we address the challenging problem of data association for underwater SLAM through a novel method for sonar image correspondence using learned features. We introduce SONIC (SONar Image Correspondence), a pose-supervised network designed to yield robust feature correspondence capable of withstanding viewpoint variations. The inherent complexity of the underwater environment stems from the dynamic and frequently limited visibility conditions, restricting vision to a few meters of often featureless expanses. This makes camera-based systems suboptimal in most open water application scenarios. Consequently, multibeam imaging sonars emerge as the preferred choice for perception sensors. However, they too are not without their limitations. While imaging sonars offer superior long-range visibility compared to cameras, their measurements can appear different from varying viewpoints. This inherent variability presents formidable challenges in data association, particularly for feature-based methods. Our method demonstrates significantly better performance in generating correspondences for sonar images which will pave the way for more accurate loop closure constraints and sonar-based place recognition. Code as well as simulated and real-world datasets will be made public to facilitate further development in the field.
format Preprint
id arxiv_https___arxiv_org_abs_2310_15023
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SONIC: Sonar Image Correspondence using Pose Supervised Learning for Imaging Sonars
Gode, Samiran
Hinduja, Akshay
Kaess, Michael
Computer Vision and Pattern Recognition
Robotics
In this paper, we address the challenging problem of data association for underwater SLAM through a novel method for sonar image correspondence using learned features. We introduce SONIC (SONar Image Correspondence), a pose-supervised network designed to yield robust feature correspondence capable of withstanding viewpoint variations. The inherent complexity of the underwater environment stems from the dynamic and frequently limited visibility conditions, restricting vision to a few meters of often featureless expanses. This makes camera-based systems suboptimal in most open water application scenarios. Consequently, multibeam imaging sonars emerge as the preferred choice for perception sensors. However, they too are not without their limitations. While imaging sonars offer superior long-range visibility compared to cameras, their measurements can appear different from varying viewpoints. This inherent variability presents formidable challenges in data association, particularly for feature-based methods. Our method demonstrates significantly better performance in generating correspondences for sonar images which will pave the way for more accurate loop closure constraints and sonar-based place recognition. Code as well as simulated and real-world datasets will be made public to facilitate further development in the field.
title SONIC: Sonar Image Correspondence using Pose Supervised Learning for Imaging Sonars
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2310.15023