Metraipolis › archive › dc_137eb7a6a76c
DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models — arXiv:2609.07780
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07780
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:11:59.053Z
- SHA-256 of the archived text
2cee7a0a891b9569fab77c7ec4e4b3ddcea77638c78514669740b3a54e44e9f9- Stable URL of this page
https://metraipolis.com/documento/dc_137eb7a6a76c
How to cite
DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models — arXiv:2609.07780 — arXiv (en), https://arxiv.org/abs/2609.07780 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_137eb7a6a76c (Metraipolis archive dc_137eb7a6a76c, sha256 2cee7a0a891b9569fab77c7ec4e4b3ddcea77638c78514669740b3a54e44e9f9)
BibTeX
@misc{dc137eb7a6a76c,
title = {DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models — arXiv:2609.07780},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07780},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_137eb7a6a76c; sha256 2cee7a0a891b9569fab77c7ec4e4b3ddcea77638c78514669740b3a54e44e9f9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07780. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automated drone surveillance has become increasingly important for public safety, critical infrastructure protection,and restricted airspace monitoring. While existing vision-based systems achieve strong performance for drone detection and tracking, reliable payload characterization remains highly challenging under long-range imaging conditions due to limited availability of annotated real-world datasets, and substantial distribution shifts encountered during deployment. Existing approaches formulate payload characterization as a closed-set object detection problem, limiting their ability to recognize previously unseen payloads and generalize beyond the training distribution. To address these challenges, we generate a photorealistic synthetic drone-payload dataset using Unreal Engine 5 and Cosys-AirSim and propose DroneGround: Grounded Vision-Language Payload Characterization, a two-stage framework for robust open-vocabulary payload analysis. DroneGround first employs a YOLO26s detector to localize drones and extract drone-centric image crops, followed by a LoRA-fine-tuned PaliGemma vision-language model that generates seman- tic descriptions of the detected drones and their attached payloads, enabling open-vocabulary payload characterization beyond predefined categories. An occlusion-based grounding module further provides interpretable payload localization by identifying image regions responsible for the generated descriptions. Extensive experiments on both synthetic and real-world drone imagery demonstrate that DroneGround substantially improves robustness under synthetic-to-real distribution shifts, outperforming a conventional closed-set payload detector by improving the F1-score from 82.5% to 96.3%, while achieving significantly better generalization to previously unseen payload categories (80.4%versus 42.7% F1). Dataset and code will be released upon request. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.07780 — 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 2026-10-16T14:49:57.253Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).