用真实行车记录视频训练，精准区分自身车辆危险与无关事故。
BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data
- 基于真实驾驶数据构建端到端模型，聚焦自身车辆安全
- 在多个数据集上达到领先准确率，误报更少、预警更准
- 开源模型与标注数据，推动车辆碰撞预测研究
现有碰撞预测方法常无法区分自身车辆威胁与无关事故，导致真实场景部署中误报频发。本文提出BADAS，一套基于Nexar真实行车记录仪数据集（首个专为自身车辆评估设计的基准）训练的碰撞预测模型。我们重新标注主流数据集以识别自身车辆参与情况，添加共识预警时间标签，并合成负样本，实现公平的平均精度（AP）/AUC及时间维度评估。BADAS采用V-JEPA2主干网络端到端训练，包含两个版本：基于1500段公开视频的BADAS-Open，以及基于4万段私有视频的BADAS1.0。在DAD、DADA-2000、DoTA和Nexar数据集上，BADAS均达到当前最优的AP/AUC表现，优于前向碰撞预警的ADAS基线，并生成更真实的事故发生时间估计。我们开源了BADAS-Open模型权重与代码，以及所有评估数据集的重标注结果，以促进自身车辆视角的碰撞预测研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。