Parallel SfM for UAV Images via Anchor-Free Merging

JIANG San; MA Yichen; JIANG Wanshou; LI Qingquan

doi:10.13203/j.whugis20240347

您当前的位置：

首页 >

文章列表页 >

Parallel SfM for UAV Images via Anchor-Free Merging

Photogrammetry and Remote Sensing | 更新时间：2026-11-05

- Parallel SfM for UAV Images via Anchor-Free Merging
- Geomatics and Information Science of Wuhan University Vol. 51, Issue 6, Pages: 1194-1203(2026)
- 作者机构：
  
  1.深圳大学广东省城市空间信息工程重点实验室，广东深圳，518060
  2.深圳大学自然资源部大湾区地理环境监测重点实验室，广东深圳，518060
  3.自然资源信息管理与数字孪生工程软件教育部工程研究中心，湖北武汉，430074
  4.武汉大学测绘遥感信息工程全国重点实验室，湖北武汉，430079
- 作者简介：
- 基金信息：
- DOI：10.13203/j.whugis20240347
  CLC： P237
- Received：15 January 2025，
  
  Published：05 June 2026
- 稿件说明：
移动端阅览
姜三,马一尘,江万寿，等.不依赖固定锚点合并的无人机影像并行化SfM方法[J].武汉大学学报（信息科学版）,2026,51(6):1194-1203.

JIANG San,MA Yichen,JIANG Wanshou,et al.Parallel SfM for UAV Images via Anchor-Free Merging[J].Geomatics and Information Science of Wuhan University,2026,51(6):1194-1203.
姜三,马一尘,江万寿，等.不依赖固定锚点合并的无人机影像并行化SfM方法[J].武汉大学学报（信息科学版）,2026,51(6):1194-1203. DOI：10.13203/j.whugis20240347

JIANG San,MA Yichen,JIANG Wanshou,et al.Parallel SfM for UAV Images via Anchor-Free Merging[J].Geomatics and Information Science of Wuhan University,2026,51(6):1194-1203. DOI：10.13203/j.whugis20240347

摘要

增量式运动恢复结构（structure from motion

SfM）并行化方法中，存在场景图构建忽略影像局部连接强度、子场景（空间关联的影像集合）合并路径长和效率低等问题，使其难以满足大场景影像处理需求。提出了一种不依赖固定锚点（参考模型）合并的无人机影像并行化SfM方法。设计了顾及影像局部连接强度约束的场景图构建方法，有效提升了场景图分块的紧凑性，保证了分块内部影像SfM重建的高稳健性；提出了不依赖固定锚点的子场景并行化合并方法，实现合并路径自适应调整与多子场景并行化合并，有效提高了子场景合并的可靠性和效率。利用真实无人机影像进行实验，结果表明，所提方法能够实现9倍加速比的子场景合并，且相对定向和绝对定向性能与现有方法相当。所提方法已成功应用于覆盖范围约50 km

近9万张无人机影像的并行化SfM重建。

Abstract

Objectives

Incremental structure from motion (SfM) has become the widely used workflow for aerial triangulation of unmanned aerial vehicle (UAV) images. However

it suffers from significant issues of error accumulation and efficiency degradation. The existing parallelization methods for SfM suffer from issues such as the scene graph construction ignoring the local connection strength of images

long merging paths for sub-scenes (spatially related image collections)

and low efficiency

making it difficult to meet the requirements of large-scale scene image processing.

Methods

This paper proposes a parallelized SfM method for UAV images that does not rely on fixed anchor points (reference models). The proposed solution develops a scene graph construction algorithm that considers local connection strength constraints

effectively improving the compactness of scene graph partitioning and ensuring the high robustness of SfM reconstruction within partitions. Then

it proposes a parallelized sub-scene merging method that does not rely on fixed anchor points

enabling adaptive adjustment of merging paths and parallel merging of multiple sub-scenes

significantly enhancing the reliability and efficiency of sub-scene merging. To avoid the influence of outliers in corresponding geometric elements

this paper employs the random sample consensus hypothesis-verification framework for robust parameter estimation and designs a transformation model estimation based on a bidirectional mean square reprojection error metric.

Results

Experiments using real UAV images demonstrate that the proposed method achieves a 9 times speedup in sub-scene merging

with relative and absolute orientation performance comparable to the existing methods. And the proposed method has also been successfully applied to the parallel SfM reconstruction of nearly 90 000 UAV images covering an area of about 50 km

Conclusions

Considering the metric of efficiency and precision

the proposed method can be a validate solution for the efficient SfM reconstruction for large-scale UAV datasets.

关键词

Keywords

references

JIANG S ， SfMJIANG W S ， WANG L Z . Unmanned Aerial Vehicle-Based Photogrammetric 3D Mapping： A Survey of Techniques， Applications， and Challenges ［J］. IEEE Geoscience and Remote Sensing Magazine ， 2022 ， 10 （ 2 ）： 135 - 171 .

WANG X ， XIANG H Y ， NIU W Y ， et al . Oblique Photogrammetry Supporting Procedural Tree Modeling in Urban Areas ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 2023 ， 200 ： 120 - 137 .

MURTIYOSO A ， GRUSSENMEYER P . Documentation of Heritage Buildings Using Close-range UAV Images： Dense Matching Issues， Comparison and Case Studies ［J］. The Photogrammetric Record ， 2017 ， 32 （ 159 ）： 206 - 229 .

JIANG S ， JIANG W S ， HUANG W ， et al . UAV-Based Oblique Photogrammetry for Outdoor Data Acquisition and Offsite Visual Inspection of Transmission Line ［J］. Remote Sensing ， 2017 ， 9 （ 3 ）： 278 .

ZHANG Q ， TIAN Y Q ， DING Y F ， et al . CoopHance： Cooperative Enhancement for Robustness of Deep Learning Systems ［C］// ACM SIGSOFT International Symposium on Software Testing and Analysis ， Seattle， USA ， 2023 .

许志华，吴立新，刘军，等 . 顾及影像拓扑的SfM算法改进及其在灾场三维重建中的应用［J］. 武汉大学学报（信息科学版）， 2015 ， 40 （ 5 ）： 599 - 606 .

XU Zhihua ， WU Lixin ， LIU Jun ， et al . Modification of SfM Algorithm Referring to Image Topology and Its Application in 3-Dimension Reconstruction of Disaster Area ［J］. Geomatics and Information Science of Wuhan University ， 2015 ， 40 （ 5 ）： 599 - 606 .

陈武，姜三，李清泉，等 . 无人机影像增量式运动恢复结构研究进展［J］. 武汉大学学报（信息科学版）， 2022 ， 47 （ 10 ）： 1662 - 1674 .

CHEN Wu ， JIANG San ， LI Qingquan ， et al . Recent Research of Incremental Structure from Motion for Unmanned Aerial Vehicle Images ［J］. Geomatics and Information Science of Wuhan University ， 2022 ， 47 （ 10 ）： 1662 - 1674 .

WU C C ， AGARWAL S ， CURLESS B ， et al . Multicore Bundle Adjustment ［C］// EEE/CVF Conference on Computer Vision and Pattern Recognition ， Colorado Springs， USA ， 2011 .

SUN Y B ， SUN H B ， YAN L ， et al . RBA： Reduced Bundle Adjustment for Oblique Aerial Photogrammetry ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 2016 ， 121 ： 128 - 142 .

VERHOEVEN G . Taking Computer Vision Aloft-Archaeological Three-Dimensional Reconstructions from Aerial Photographs with Photoscan ［J］. Archaeological Prospection ， 2011 ， 18 （ 1 ）： 67 - 73 .

CHEN Y ， SHEN S H ， CHEN Y S ， et al . Graph-Based Parallel Large Scale Structure from Motion ［J］. Pattern Recognition ， 2020 ， 107 ： 107537 .

JU Y ， HUANG Y H ， ZHENG J T ， et al . Multi-thread Parallel Algorithm for Reconstructing 3D Large-Scale Porous Structures ［J］. Computers & Geosciences ， 2017 ， 101 ： 10 - 20 .

姜三，马一尘，李清泉，等 . 无序无人机影像的并行化SfM三维重建方法［J］. 测绘学报， 2024 ， 53 （ 5 ）： 946 - 958 .

JIANG San ， MA Yichen ， LI Qingquan ， et al . Parallel SfM-Based 3D Reconstruction for Unordered UAV Images ［J］. Acta Geodaetica et Cartographica Sinica ， 2024 ， 53 （ 5 ）： 946 - 958 .

LIU Z D ， QV W ， CAI H L ， et al . An Efficient and Robust Hybrid SfM Method for Large-scale Scenes ［J］. Remote Sensing ， 2023 ， 15 （ 3 ）： 769 .

CUI H N ， GAO X ， SHEN S H ， et al . HSfM： Hybrid Structure-from-Motion ［C］// IEEE Conference on Computer Vision and Pattern Recognition ， Honolulu， USA ， 2017 .

JIANG S ， LI Q Q ， JIANG W S ， et al . Parallel Structure from Motion for UAV Images via Weighted Connected Dominating Set ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2022 ， 60 ： 5413013 .

XU B ， ZHANG L ， LIU Y X ， et al . Robust Hierarchical Structure from Motion for Large-Scale Unstructured Image Sets ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 2021 ， 181 ： 367 - 384 .

ZHU S Y ， SHEN T W ， ZHOU L ， et al . Parallel Structure from Motion from Local Increment to Global Averaging ［PP/OL］. V3. arVix （ 2017-06-05 ）［ 2024-04-18 ］. https：//arxiv.org/abs/1702.08601 https://arxiv.org/abs/1702.08601 .

KLODT M ， VEDALDI A . Supervising the New with the Old： Learning SfM from SfM ［C］// European Conference on Computer Vision ， Munich， Germany ， 2018 .

LI Q Q ， HUANG H ， YU W S ， et al . Optimized Views Photogrammetry： Precision Analysis and a Large-Scale Case Study in Qingdao ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2023 ， 16 ： 1144 - 1159 .

SCHÖNBERGER J L ， FRAHM J M . Structure-from-motion Revisited ［C］// IEEE Conference on Computer Vision and Pattern Recognition ， Las Vegas， USA ， 2016 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fast Feature Matching of UAV Images via Indexing Constraints of Vocabulary Trees

High-Resolution L-Band InSAR Study of Intense Near-Field Deformation Associated with Shallow Moderate Earthquakes

Machine Learning-Based Remote Sensing Retrieval of Soil Moisture： Advances and Challenges

Spatiotemporal Evolution and Explainable Analysis of Grassland Vulnerability in the Hohhot-Baotou-Ordos-Yulin Urban Agglomeration

Research Progress in Eco-Geological Environmental Monitoring and Construction of an Intelligent Monitoring System in the Qinling Mountains

Related Author

JIANG Wanshou

GUO Bingxuan

JIANG San

Weiqi WANG

Xiong YOU

Jian YANG

Qin LI

Chunsen ZHANG

Related Institution

School of Computer Science, China University of Geosciences

Guangdong Laboratory of Artificial Intelligence and Digital Economy

State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University

Institute of Geospatial Information, Information Engineering University

College of Geomatics, Xi an University of Science and Technology

AI问答

⁰