A UAV Image Stitching Method for Complex Urban Environments

To address the issues of uneven feature point distribution, environmental interference, and insufficient real-time performance in UAV image stitching in complex urban environments, this paper proposes an improved ORB algorithm based on Gaussian scale-space optimization and dynamic grid division, com...

Full description

Saved in:
Bibliographic Details
Main Authors: W. Niu, D. Qiu, R. Wu, Z. Wang, Y. Shi
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1123/2025/isprs-archives-XLVIII-G-2025-1123-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849419935098339328
author W. Niu
D. Qiu
R. Wu
R. Wu
Z. Wang
Y. Shi
author_facet W. Niu
D. Qiu
R. Wu
R. Wu
Z. Wang
Y. Shi
author_sort W. Niu
collection DOAJ
description To address the issues of uneven feature point distribution, environmental interference, and insufficient real-time performance in UAV image stitching in complex urban environments, this paper proposes an improved ORB algorithm based on Gaussian scale-space optimization and dynamic grid division, combined with a global geometric consistency optimization strategy. First, local adaptive noise filtering and bilateral filtering are applied to enhance image quality. Then, multi-scale feature detection is achieved using a Gaussian scale-space pyramid, and dynamic grid division is employed to balance feature point distribution. Finally, a global energy function, including reprojection error and smoothness constraints, is constructed to iteratively optimize the homography matrix and suppress stitching distortions. Experimental results show that the proposed method achieves high processing speed on low-performance hardware platforms, improves feature point distribution uniformity to 0.89, and achieves stitching accuracy (RMSE) of 3.5 pixels, significantly outperforming ORB and SIFT algorithms, while remaining robust in dynamic occlusion and lighting variation scenarios. This method provides a lightweight and efficient solution for UAV image stitching in urban environments, supporting applications such as urban planning and disaster assessment. Future work will explore lightweight deep learning integration and edge computing acceleration to further improve dynamic scene adaptability.
format Article
id doaj-art-c8c07433e3104c1291313cd2f2eacd40
institution Kabale University
issn 1682-1750
2194-9034
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-c8c07433e3104c1291313cd2f2eacd402025-08-20T03:31:55ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-07-01XLVIII-G-20251123112910.5194/isprs-archives-XLVIII-G-2025-1123-2025A UAV Image Stitching Method for Complex Urban EnvironmentsW. Niu0D. Qiu1R. Wu2R. Wu3Z. Wang4Y. Shi5School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSurveying and Natural Resource Spatial Data Technology Wu Runze Studio, Beijing Institute of Surveying and Mapping Design and Research, Beijing, ChinaBeijing Skill Master Studio, Beijing, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing, ChinaTo address the issues of uneven feature point distribution, environmental interference, and insufficient real-time performance in UAV image stitching in complex urban environments, this paper proposes an improved ORB algorithm based on Gaussian scale-space optimization and dynamic grid division, combined with a global geometric consistency optimization strategy. First, local adaptive noise filtering and bilateral filtering are applied to enhance image quality. Then, multi-scale feature detection is achieved using a Gaussian scale-space pyramid, and dynamic grid division is employed to balance feature point distribution. Finally, a global energy function, including reprojection error and smoothness constraints, is constructed to iteratively optimize the homography matrix and suppress stitching distortions. Experimental results show that the proposed method achieves high processing speed on low-performance hardware platforms, improves feature point distribution uniformity to 0.89, and achieves stitching accuracy (RMSE) of 3.5 pixels, significantly outperforming ORB and SIFT algorithms, while remaining robust in dynamic occlusion and lighting variation scenarios. This method provides a lightweight and efficient solution for UAV image stitching in urban environments, supporting applications such as urban planning and disaster assessment. Future work will explore lightweight deep learning integration and edge computing acceleration to further improve dynamic scene adaptability.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1123/2025/isprs-archives-XLVIII-G-2025-1123-2025.pdf
spellingShingle W. Niu
D. Qiu
R. Wu
R. Wu
Z. Wang
Y. Shi
A UAV Image Stitching Method for Complex Urban Environments
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title A UAV Image Stitching Method for Complex Urban Environments
title_full A UAV Image Stitching Method for Complex Urban Environments
title_fullStr A UAV Image Stitching Method for Complex Urban Environments
title_full_unstemmed A UAV Image Stitching Method for Complex Urban Environments
title_short A UAV Image Stitching Method for Complex Urban Environments
title_sort uav image stitching method for complex urban environments
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1123/2025/isprs-archives-XLVIII-G-2025-1123-2025.pdf
work_keys_str_mv AT wniu auavimagestitchingmethodforcomplexurbanenvironments
AT dqiu auavimagestitchingmethodforcomplexurbanenvironments
AT rwu auavimagestitchingmethodforcomplexurbanenvironments
AT rwu auavimagestitchingmethodforcomplexurbanenvironments
AT zwang auavimagestitchingmethodforcomplexurbanenvironments
AT yshi auavimagestitchingmethodforcomplexurbanenvironments
AT wniu uavimagestitchingmethodforcomplexurbanenvironments
AT dqiu uavimagestitchingmethodforcomplexurbanenvironments
AT rwu uavimagestitchingmethodforcomplexurbanenvironments
AT rwu uavimagestitchingmethodforcomplexurbanenvironments
AT zwang uavimagestitchingmethodforcomplexurbanenvironments
AT yshi uavimagestitchingmethodforcomplexurbanenvironments