Metraipolis › archive › dc_be49e5969bb7

Online Multi-Camera 3D Tracking via ID Prediction over Recurrent Sparse Queries — arXiv:2609.18363

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.18363
License (as archived): CC0-1.0
Archived: 2026-10-15T16:16:28.056Z
SHA-256 of the archived text: 25eb92c1bfbb1ddc1b54d8ddfc1beed77624a3988fdd35def3d2c6cac1f892b6
Stable URL of this page: https://metraipolis.com/documento/dc_be49e5969bb7

How to cite

Online Multi-Camera 3D Tracking via ID Prediction over Recurrent Sparse Queries — arXiv:2609.18363 — arXiv (en), https://arxiv.org/abs/2609.18363 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be49e5969bb7 (Metraipolis archive dc_be49e5969bb7, sha256 25eb92c1bfbb1ddc1b54d8ddfc1beed77624a3988fdd35def3d2c6cac1f892b6)

BibTeX

@misc{dcbe49e5969bb7,
  title = {Online Multi-Camera 3D Tracking via ID Prediction over Recurrent Sparse Queries — arXiv:2609.18363},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18363},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be49e5969bb7; sha256 25eb92c1bfbb1ddc1b54d8ddfc1beed77624a3988fdd35def3d2c6cac1f892b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18363. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Online multi camera 3D tracking must maintain scene global identities across synchronized views, yet query-based trackers carry these identities only implicitly in the instance bank, where they fragment upon query interruption. We present an online architecture that recovers association accuracy by predicting IDs explicitly over recurrent sparse queries. An outside-in Sparse4D detector fuses calibrated views into world frame 3D detections while propagating a sparse query bank, and a causal MOTIP ID decoder associates detections against a finite trajectory memory. We adapt MOTIP's relative-ID prediction and recycled slot runtime to globally fused 3D observations, and introduce metric spatial gating and proximity based newborn recovery. On the official 2026 AI City Challenge Track 1 test set, our method raises HOTA from 29.63 with native instance bank identities to 38.01, primarily through an AssA increase from 20.83 to 31.10, and ranks third on the public leaderboard. Full-sequence validation over all 9,000 frames of each scene shows that decoupled ID training improves HOTA over native identities, whereas continuing detector training alongside the detached ID objective produces scene-dependent gains and losses.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.18363 — 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 2026-10-15T15:45:19.779Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).