EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UGV Swarm Multi-View Fusion Under Occlusion: A Graph-Based Calibration-Free Framework

Jiaqi Jing, Weilong Song, Hangcheng Zhang, Yong Liu, Fuyong Feng, Dezhi Zheng, Shangchun Fan

Drones · 18.03.2026 · 10 (3) · 214

DOI: 10.3390/drones10030214 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 18.03.2026. Verfasst von Jiaqi Jing und 6 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In unmanned ground vehicle (UGV) swarm systems, comprehensive environmental awareness is critical for coordinated operations. Yet they are frequently deployed in occlusion-rich, constrained environments where multi-agent visual fusion is essential. However, existing methods are critically limited by offline-calibrated extrinsic parameters, hindering flexible deployment, and by a strong co-visibility assumption, which fails under severe occlusion. To overcome these constraints, we introduce an end-to-end, calibration-free framework for the joint registration of cameras and subjects. Our approach begins with a single-view module that estimates subjects’ poses and appearance features. Subsequently, a novel graph-based pose propagation module (GPPM) treats UGVs’ cameras as nodes in a graph, connecting them with edges when they share co-visible subjects identified via appearance matching. Breadth-first search (BFS) then finds the shortest registration path from any camera to a designated root camera, enabling pose propagation via local co-visibility links and global alignment of all subjects into a unified bird’s-eye-view (BEV) space. This strategy relaxes the stringent requirement of full co-visibility with the root node. A multi-task loss function is proposed to jointly optimize pose estimation and feature matching. Trained and evaluated on a synthetic dataset with occlusions (CSRD-O) collected by a UGV swarm system, our framework achieves mean camera pose errors of 1.57 m/8.70° and mean subject pose errors of 1.40 m/9.14°. Furthermore, we demonstrate a scene monitoring task using a UGV swarm system. Experiments show that the proposed method generates robust BEV estimates even under severe occlusion and low inter-view overlap. This work presents a purely visual, self-calibrating multi-view fusion perception scheme, demonstrating its potential to support cooperative perception, task-oriented monitoring, and collective situational awareness in UGV swarm systems.

Zitieren

APA

Jing, J., Song, W., Zhang, H., Liu, Y., Feng, F., Zheng, D., & Fan, S. (2026). UGV Swarm Multi-View Fusion Under Occlusion: A Graph-Based Calibration-Free Framework. Drones, 10(3), 214. https://doi.org/10.3390/drones10030214

Vancouver

Jing J, Song W, Zhang H, Liu Y, Feng F, Zheng D, et al. UGV Swarm Multi-View Fusion Under Occlusion: A Graph-Based Calibration-Free Framework. Drones. 2026;10(3):214. doi:10.3390/drones10030214

BibTeX
@article{Jing2026,
  author = {Jing, Jiaqi and Song, Weilong and Zhang, Hangcheng and Liu, Yong and Feng, Fuyong and Zheng, Dezhi and Fan, Shangchun},
  title = {UGV Swarm Multi-View Fusion Under Occlusion: A Graph-Based Calibration-Free Framework},
  journal = {Drones},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {214},
  doi = {10.3390/drones10030214}
}
Kostenlos starten →