Learning-Based Distance Estimation for 360° Single-Sensor Setups

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Quan, Yitong, Kiefer, Benjamin, Messmer, Martin, Zell, Andreas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915358771773440
author Quan, Yitong
Kiefer, Benjamin
Messmer, Martin
Zell, Andreas
author_facet Quan, Yitong
Kiefer, Benjamin
Messmer, Martin
Zell, Andreas
contents Accurate distance estimation is a fundamental challenge in robotic perception, particularly in omnidirectional imaging, where traditional geometric methods struggle with lens distortions and environmental variability. In this work, we propose a neural network-based approach for monocular distance estimation using a single 360° fisheye lens camera. Unlike classical trigonometric techniques that rely on precise lens calibration, our method directly learns and infers the distance of objects from raw omnidirectional inputs, offering greater robustness and adaptability across diverse conditions. We evaluate our approach on three 360° datasets (LOAF, ULM360, and a newly captured dataset Boat360), each representing distinct environmental and sensor setups. Our experimental results demonstrate that the proposed learning-based model outperforms traditional geometry-based methods and other learning baselines in both accuracy and robustness. These findings highlight the potential of deep learning for real-time omnidirectional distance estimation, making our approach particularly well-suited for low-cost applications in robotics, autonomous navigation, and surveillance.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20586
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning-Based Distance Estimation for 360° Single-Sensor Setups
Quan, Yitong
Kiefer, Benjamin
Messmer, Martin
Zell, Andreas
Computer Vision and Pattern Recognition
Robotics
Accurate distance estimation is a fundamental challenge in robotic perception, particularly in omnidirectional imaging, where traditional geometric methods struggle with lens distortions and environmental variability. In this work, we propose a neural network-based approach for monocular distance estimation using a single 360° fisheye lens camera. Unlike classical trigonometric techniques that rely on precise lens calibration, our method directly learns and infers the distance of objects from raw omnidirectional inputs, offering greater robustness and adaptability across diverse conditions. We evaluate our approach on three 360° datasets (LOAF, ULM360, and a newly captured dataset Boat360), each representing distinct environmental and sensor setups. Our experimental results demonstrate that the proposed learning-based model outperforms traditional geometry-based methods and other learning baselines in both accuracy and robustness. These findings highlight the potential of deep learning for real-time omnidirectional distance estimation, making our approach particularly well-suited for low-cost applications in robotics, autonomous navigation, and surveillance.
title Learning-Based Distance Estimation for 360° Single-Sensor Setups
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2506.20586