Metraipolis › archive › dc_6df0db249aca

Identity-Consistent Analysis of Long-Shot Windsurfing Video: A Domain-Specific Offline Tracking System — arXiv:2609.24492

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24492
License (as archived)
CC0-1.0
Archived
2026-10-09T22:06:03.158Z
SHA-256 of the archived text
925d101c7d9041b732099dfbb7b90a640d86c5917db9fd86443879eb6d796c42
Stable URL of this page
https://metraipolis.com/documento/dc_6df0db249aca

How to cite

Identity-Consistent Analysis of Long-Shot Windsurfing Video: A Domain-Specific Offline Tracking System — arXiv:2609.24492 — arXiv (en), https://arxiv.org/abs/2609.24492 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6df0db249aca (Metraipolis archive dc_6df0db249aca, sha256 925d101c7d9041b732099dfbb7b90a640d86c5917db9fd86443879eb6d796c42)
BibTeX
@misc{dc6df0db249aca,
  title = {Identity-Consistent Analysis of Long-Shot Windsurfing Video: A Domain-Specific Offline Tracking System — arXiv:2609.24492},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24492},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6df0db249aca; sha256 925d101c7d9041b732099dfbb7b90a640d86c5917db9fd86443879eb6d796c42},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24492. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-shot windsurfing video combines small targets, large camera pans, prolonged overlaps, and rapidly changing backgrounds. The desired output is not a generic MOT trace but a separate, stable rider-relative video for each surfer; one false identity merge can invalidate an otherwise useful result. We present an offline analysis system that detects surfers, forms conservative local tracklets, links them globally with camera-compensated motion and a foreground-masked sail-color descriptor, and uses two pose keypoints on the rig to drive a rider-relative virtual camera. The tracking stage is evaluated on 21 manually reconstructed development videos containing 41,004 retained observations. On this fixed-observation protocol, the production system achieves 0.957 pairwise precision, 0.918 recall, and 0.937 F1, compared with 0.792 F1 for OC-SORT and 0.828 for BoT-SORT. Compared with OC-SORT, it reduces fragmentation excess from 845 to 42, but nine of its 95 output tracks mix rider identities and these errors affect seven of the 21 videos.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.24492 — 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 2026-10-09T21:45:21.049Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).