Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 21, 2026DronesOpen Access

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

View Full Paper
Ask AI
Bookmark
Share

Authors

JJJiaqi JingWSWeilong SongHZHailong Zhang

Discussion

Loading...

Member takes

Overview

End-to-end framework enhances environmental awareness in UGV swarms during occlusion-rich deployments, indicating improved performance.

Key Points

  • The aim is to develop a calibration-free framework for multi-view visual fusion in UGV swarm systems operating in occluded environments.
  • Developed a single-view module for pose and feature estimation.
  • Introduced a graph-based pose propagation module to link camera nodes.
  • Utilized breadth-first search to determine registration paths between cameras.
  • Optimized pose estimation and feature matching using a multi-task loss function.
  • Evaluated the framework on a synthetic dataset with occlusions.
  • Achieved mean camera pose errors of 1.57 m/8.70° and subject pose errors of 1.40 m/9.14°.
  • Generated robust bird’s-eye-view estimates despite severe occlusion and low overlap.
  • Demonstrated effective scene monitoring in UGV swarm systems.

Cite This Study

Jing et al. (2026) studied this question.

synapsesocial.com/papers/69be36666e48c4981c675507https://doi.org/10.3390/drones10030214
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Research on Multi-Source Heterogeneous Collaborative Perception System Based on Unmanned Aerial Vehicle and Unmanned Ground Vehicle2026
  2. 2Vision-Based Unmanned Aerial Vehicle Swarm Cooperation and Online Point-Cloud Registration for Global Localization in Global Navigation Satellite System-Intermittent Environments2026 · 2 citations
  3. 3Cost-effective Swarm Navigation System via Close Cooperation2024 · 9 citations
  4. 4Online Multi-Sensor Calibration Method for Unmanned Surface Vehicle Swarms in Complex and Contested Environments2026
  5. 5Weak Calibration Cross-Fusion Framework for Multi-Modal 3D Object Detection on Unmanned Surface Vehicles2026