Metraipolis › archive › dc_5c232df48084
Frame-to-Panorama Localization and Context-Aware Sampling for Scene-Specific Ship Detection in a Smart Marina Testbed — arXiv:2609.29447
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29447
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:27:31.267Z
- SHA-256 of the archived text
3fbb657a1bf09a2d40b564008757ec2adbdbc7721eee2a0c146dcecb37405ec0- Stable URL of this page
https://metraipolis.com/documento/dc_5c232df48084
How to cite
Frame-to-Panorama Localization and Context-Aware Sampling for Scene-Specific Ship Detection in a Smart Marina Testbed — arXiv:2609.29447 — arXiv (en), https://arxiv.org/abs/2609.29447 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5c232df48084 (Metraipolis archive dc_5c232df48084, sha256 3fbb657a1bf09a2d40b564008757ec2adbdbc7721eee2a0c146dcecb37405ec0)
BibTeX
@misc{dc5c232df48084,
title = {Frame-to-Panorama Localization and Context-Aware Sampling for Scene-Specific Ship Detection in a Smart Marina Testbed — arXiv:2609.29447},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29447},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5c232df48084; sha256 3fbb657a1bf09a2d40b564008757ec2adbdbc7721eee2a0c146dcecb37405ec0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29447. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Smart maritime infrastructures provide continuous access to heterogeneous sensing streams, enabling repeated experimentation, digital-twin development, and AI-based maritime services. However, sensing hardware alone is not sufficient for scene-specific model development: historical video streams must also be spatially indexed, contextualized, and reduced to informative subsets for annotation. This paper presents a frame-to-panorama localization and context-aware sampling pipeline for ship detection in historical PTZ maritime video lacking reliable pan, tilt, and zoom metadata. The main contribution is an end-to-end data-curation approach that recovers camera-view information from historical PTZ video and combines it with environmental context and visual diversity to construct compact, scene-specific training sets. Specifically, frames are localized on a reference panorama using SuperPoint and LightGlue, enriched with weather and solar-state metadata, and selected through diversity sampling to preserve variation across camera view and environmental conditions. A second context-aware stage targets under-represented distant-vessel cases near the horizon using tile-level visual embeddings and Gaussian Mixture Model clustering. Applied within the CMMI MDigi-I Smart Marina testbed, the proposed pipeline reduces 40,718 candidate frames to 220 images for annotation, corresponding to a 99.5% reduction. A YOLO26-m detector fine-tuned on this subset achieves a mean AP50 of 94.78% $\pm$ 0.51% and a mean AP50-95 of 75.10% $\pm$ 1.73% under sequence-grouped five-fold cross-validation. These results demonstrate that highly redundant infrastructure video streams can be transformed into compact, spatially and contextually diverse training sets for scene-specific detector adaptation while substantially reducing annotation effort. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computational Geometry (cs.CG). Pagina del lavoro: https://arxiv.org/abs/2609.29447 — 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 2026-10-08T03:50:58.066Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).