Metraipolis › archive › dc_42e4fc7ad3aa
Understanding Temporal Semantic Stability in Open-Vocabulary UAV Perception through Metric 3D Fusion — arXiv:2608.28665
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28665
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:53:10.248Z
- SHA-256 of the archived text
ffaa391d6b197cbdcc480fb23fe7fc83e098787ba3e8aa2fc80025bdb16ed30c- Stable URL of this page
https://metraipolis.com/documento/dc_42e4fc7ad3aa
How to cite
Understanding Temporal Semantic Stability in Open-Vocabulary UAV Perception through Metric 3D Fusion — arXiv:2608.28665 — arXiv (en), https://arxiv.org/abs/2608.28665 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_42e4fc7ad3aa (Metraipolis archive dc_42e4fc7ad3aa, sha256 ffaa391d6b197cbdcc480fb23fe7fc83e098787ba3e8aa2fc80025bdb16ed30c)
BibTeX
@misc{dc42e4fc7ad3aa,
title = {Understanding Temporal Semantic Stability in Open-Vocabulary UAV Perception through Metric 3D Fusion — arXiv:2608.28665},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28665},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_42e4fc7ad3aa; sha256 ffaa391d6b197cbdcc480fb23fe7fc83e098787ba3e8aa2fc80025bdb16ed30c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28665. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent open-vocabulary segmentation models have advanced semantic perception for UAVs, but predictions from moving aerial platforms can remain temporally inconsistent across repeated observations of the same physical scene. We investigate temporal semantic stability by associating frame-wise predictions with persistent world-space locations through metric 3D fusion. We introduce a voxel-level evaluation framework that jointly characterises final semantic agreement, Semantic Belief Drift (SBD), Observation Persistence (OP), and semantic uncertainty. Experiments on UAVid-3D reveal substantial frame-wise semantic flicker and show that high aggregate world-space agreement can overstate temporal stability when locations have limited repeated-observation support. Persistence-stratified analysis shows that recurrent voxels expose greater semantic disagreement, while belief drift decreases as additional evidence accumulates. This behaviour is observed across two segmentation backbones and remains consistent under variations in voxel resolution, geometric association, and temporal sampling density. Conditions that reduce world-space recurrence can increase apparent aggregate stability, demonstrating that semantic consistency must be interpreted together with observation support. Our findings highlight observation persistence as an essential conditioning variable for evaluating long-horizon semantic reliability. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.28665 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:47.918Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).