Flying Co-Stereo: Enabling Long-Range Aerial Dense Mapping via Collaborative Stereo Vision of Dynamic-Baseline

Opens in a new window Opens an external website Opens an external website in a new window

This website utilizes technologies such as cookies to enable essential site functionality, as well as for analytics, personalization, and targeted advertising. Privacy Policy

Accept Deny Non-Essential

Storage Preferences

Flying Co-Stereo: Enabling Long-Range Aerial Dense Mapping via Collaborative Stereo Vision of Dynamic-Baseline | IEEE Journals & Magazine | IEEE Xplore

[](https://ieeexplore.ieee.org/document/)

[](https://ieeexplore.ieee.org/rest/api/hpdata)

Donate
[Cart](https://www.ieee.org/cart/public/myCart/page.html?refSite=https://ieeexplore.ieee.org&refSiteName=IEEE%20Xplore "View Cart")[](https://ieeexplore.ieee.org/document/)
[](javascript:void() "Create Account")
[](https://ieeexplore.ieee.org/document/ "Sign In")
[Create Account](javascript:void() "Create Account")
[Personal Sign In](javascript:void() "Sign In")

[](https://ieeexplore.ieee.org/document/)

[ Image 1: IEEE Xplore logo - Link to home ](https://ieeexplore.ieee.org/Xplore/home.jsp "Delivering full text access to the world's highest quality technical literature in engineering and technology")

Browse
My Settings
Help

[Institutional Sign In](javascript:void())

Image 2: IEEE logo - Link to IEEE main site homepage

Institutional Sign In

Search by Content Type

ADVANCED SEARCH

Search by Content Type

ADVANCED SEARCH

Journals & Magazines>IEEE Transactions on Robotics>Volume: 42[](https://ieeexplore.ieee.org/Xplorehelp/ieee-xplore-training/working-with-documents#interactive-html)

Flying Co-Stereo: Enabling Long-Range Aerial Dense Mapping via Collaborative Stereo Vision of Dynamic-Baseline

Publisher: IEEE

Cite This

[PDF](javascript:void() "You do not have access to this PDF")

Zhaoying Wang[](https://orcid.org/0000-0002-1312-6783); Xingxing Zuo[](https://orcid.org/0000-0003-4158-3153); Wei Dong[](https://orcid.org/0000-0003-2640-1585)

[All Authors](javascript:void())

[](https://ieeexplore.ieee.org/document/)

Cites in

Paper

669

Full

Text Views

[](javascript:void())
[](javascript:void())
[](javascript:void())
[](javascript:void())
[Alerts](javascript:void())# Alerts

Manage Content Alerts [Add to Citation Alerts](javascript:void())

Abstract

Document Sections

[I. Introduction](javascript:void())
[II. Related Work](javascript:void())
[III. System Overview](javascript:void())
[IV. Flying Co-Stereo Baseline Estimation](javascript:void())
[V. Cross-Camera Feature Association](javascript:void())

Show Full Outline

Abstract:

For unmanned aerial vehicle (UAV) swarms operating in large-scale unknown environments, lightweight long-range mapping is crucial for enhancing safe navigation. Tradition...Show More

Metadata

Abstract:

For unmanned aerial vehicle (UAV) swarms operating in large-scale unknown environments, lightweight long-range mapping is crucial for enhancing safe navigation. Traditional stereo cameras constrained by a short fixed baseline suffer from limited perception ranges. To overcome this limitation, we present flying collaborative stereo (flying co-stereo), a cross-agent collaborative stereo vision system that leverages the wide-baseline spatial configuration of two UAVs for long-range dense mapping. However, realizing this capability presents several challenges. First, the independent motion of each UAV leads to a dynamic and continuously changing stereo baseline, making accurate and robust estimation difficult. Second, efficiently establishing feature correspondences across independently moving viewpoints is constrained by the limited computational capacity of onboard edge devices. To tackle these challenges, we introduce the flying co-stereo system within a novel collaborative dynamic-baseline stereo mapping (CDBSM) framework. We first develop a dual-spectrum visual-inertial-ranging estimator to achieve robust and precise online estimation of the baseline between the two UAVs. In addition, we propose a hybrid feature association strategy that integrates cross-agent feature matching—based on a computationally intensive yet accurate deep neural network—with intra-agent, optical-flow-based lightweight feature tracking. Furthermore, benefiting from the wide baselines between the two UAVs, our system accurately recovers long-range covisible 3-D sparse points. We then employ a monocular depth network to predict up-to-scale dense depth maps, which are refined using accurate metric scales derived from the triangulated sparse points via exponential fitting. Extensive real-world experiments demonstrate that the proposed flying co-stereo system achieves robust and accurate dynamic baseline estimation in complex environments while maintaining efficient feature matching with resourc...

Published in:IEEE Transactions on Robotics ( Volume: 42)

Page(s): 951 - 970

Date of Publication: 26 January 2026 [](http://ieeexplore.ieee.org/Xplorehelp/Help_Pubdates.html)

ISSN Information:

DOI:10.1109/TRO.2026.3658293

Publisher: IEEE

Funding Agency:

Contents

I. Introduction

Onboard visual perception has become essential for autonomous unmanned aerial vehicles (UAVs) to safely navigate unknown environments [1], enabling applications from high-speed learning flight in the wild [2], swarm flight in bamboo [3], and forest rescue operations [4]. To ensure safe and fast navigation in large-scale environments, long-range perception capability is paramount [1]. Compared to LiDAR systems [5], [6], [7], [8], cost-effective and lightweight stereo cameras can provide 3-D depth perception through binocular disparity as well as richer visual information [9]. Conventional compact stereo cameras are typically limited to depth perception within 20 m [10], constrained by their short fixed baselines. Although wide-baseline systems using multiple cameras on large fixed-wing aircraft have shown long-range mapping capabilities [11], their platform size renders them unsuitable for small UAV swarms.

Authors

Figures

References

Citations

Keywords

Metrics

Footnotes

More Like This

Simultaneous Localization and Mapping for Mobile Robots Using Stereo Vision Camera

2019 IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM)

Published: 2019

Simultaneous localization and mapping of a mobile robot with surveillance and flying cameras

2018 SICE International Symposium on Control Systems (SICE ISCS)

Published: 2018

[Show More](javascript:void())

References

References is not available for this document.

IEEE Personal Account

Change username/password

Purchase Details

Profile Information

Need Help?

[US & Canada: +1 800 678 4333](tel:+1-800-678-4333)
[Worldwide: +1 732 981 0060](tel:+1-732-981-0060)
Contact & Support

Follow

[](https://www.facebook.com/IEEEXploreDigitalLibrary/ "Follow IEEE Xplore on Facebook, opens in a new tab")
[](https://www.instagram.com/ieeexplore_org "Follow IEEE Xplore on Instagram, opens in a new tab")
[](https://www.linkedin.com/showcase/ieee-xplore "Follow IEEE Xplore on LinkedIn, opens in a new tab")
[](https://www.youtube.com/ieeexplore "Follow IEEE Xplore on Youtube , opens in a new tab")
[](https://twitter.com/IEEEXplore?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor "Follow IEEE Xplore on Twitter, opens in a new tab")

A public charity, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.

IEEE Account

Purchase Details

Profile Information

Need Help?

US & Canada: +1 800 678 4333
Worldwide: +1 732 981 0060
Contact & Support

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2026 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.