BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Goldshmidt, Roni, Scott, Hamish, Niccolini, Lorenzo, Zhu, Shizhan, Moura, Daniel, Zvitia, Orly
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909850527596544
author Goldshmidt, Roni
Scott, Hamish
Niccolini, Lorenzo
Zhu, Shizhan
Moura, Daniel
Zvitia, Orly
author_facet Goldshmidt, Roni
Scott, Hamish
Niccolini, Lorenzo
Zhu, Shizhan
Moura, Daniel
Zvitia, Orly
contents Existing collision prediction methods often fail to distinguish between ego-vehicle threats and random accidents not involving the ego vehicle, leading to excessive false alerts in real-world deployment. We present BADAS, a family of collision prediction models trained on Nexar's real-world dashcam collision dataset -- the first benchmark designed explicitly for ego-centric evaluation. We re-annotate major benchmarks to identify ego involvement, add consensus alert-time labels, and synthesize negatives where needed, enabling fair AP/AUC and temporal evaluation. BADAS uses a V-JEPA2 backbone trained end-to-end and comes in two variants: BADAS-Open (trained on our 1.5k public videos) and BADAS1.0 (trained on 40k proprietary videos). Across DAD, DADA-2000, DoTA, and Nexar, BADAS achieves state-of-the-art AP/AUC and outperforms a forward-collision ADAS baseline while producing more realistic time-to-accident estimates. We release our BADAS-Open model weights and code, along with re-annotations of all evaluation datasets to promote ego-centric collision prediction research.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data
Goldshmidt, Roni
Scott, Hamish
Niccolini, Lorenzo
Zhu, Shizhan
Moura, Daniel
Zvitia, Orly
Computer Vision and Pattern Recognition
Existing collision prediction methods often fail to distinguish between ego-vehicle threats and random accidents not involving the ego vehicle, leading to excessive false alerts in real-world deployment. We present BADAS, a family of collision prediction models trained on Nexar's real-world dashcam collision dataset -- the first benchmark designed explicitly for ego-centric evaluation. We re-annotate major benchmarks to identify ego involvement, add consensus alert-time labels, and synthesize negatives where needed, enabling fair AP/AUC and temporal evaluation. BADAS uses a V-JEPA2 backbone trained end-to-end and comes in two variants: BADAS-Open (trained on our 1.5k public videos) and BADAS1.0 (trained on 40k proprietary videos). Across DAD, DADA-2000, DoTA, and Nexar, BADAS achieves state-of-the-art AP/AUC and outperforms a forward-collision ADAS baseline while producing more realistic time-to-accident estimates. We release our BADAS-Open model weights and code, along with re-annotations of all evaluation datasets to promote ego-centric collision prediction research.
title BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.14876