Metraipolis › archive › dc_ccc00806e00f

Progressive Risk Estimation for Accident Anticipation — arXiv:2609.32811

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32811
License (as archived)
CC0-1.0
Archived
2026-10-07T23:51:05.894Z
SHA-256 of the archived text
b4d8c14e75429d18fefcf0f72f3427a516787ab858f9ef77656e78414cea90e1
Stable URL of this page
https://metraipolis.com/documento/dc_ccc00806e00f

How to cite

Progressive Risk Estimation for Accident Anticipation — arXiv:2609.32811 — arXiv (en), https://arxiv.org/abs/2609.32811 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccc00806e00f (Metraipolis archive dc_ccc00806e00f, sha256 b4d8c14e75429d18fefcf0f72f3427a516787ab858f9ef77656e78414cea90e1)
BibTeX
@misc{dcccc00806e00f,
  title = {Progressive Risk Estimation for Accident Anticipation — arXiv:2609.32811},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32811},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccc00806e00f; sha256 b4d8c14e75429d18fefcf0f72f3427a516787ab858f9ef77656e78414cea90e1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32811. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accident anticipation aims to recognize anomalous driving cues before a crash while avoiding false alarms during normal driving. Existing approaches typically formulate this task as binary classification, focusing on whether an accident will occur rather than when it will occur. We propose PRE-ACT, a framework that models accident risk as a continuously evolving signal that increases as the crash approaches. By explicitly enforcing temporal ordering and distance-to-accident awareness, our method progressively raises risk while suppressing premature alarms, leading to significant improvements on MM-AU subsets and Nexar. We further introduce a Separation Score to evaluate the global behavior of predicted risk curves beyond local temporal windows. Code and visualizations are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.32811 — 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 2026-10-07T23:29:27.103Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).