arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.07375cs.CVcs.LG
收藏

面向鲁棒视场估计的概率分割

Probabilistic Segmentation for Robust Field of View Estimation

Duke University(杜克大学)

R. Spencer Hallyburton, David Hunt, Yiwei He, Judy He, Miroslav Pajic

AI总结:

本文针对自动驾驶视场估计易受攻击的问题,提出一种结合蒙特卡洛dropout和异常检测的学习型概率分割模型,并构建首个自动驾驶FOV数据集,验证了其攻击鲁棒性和实时部署可行性。

摘要:

针对传感与感知的攻击威胁着自动驾驶车辆(AVs)的安全部署。具备安全意识的传感器融合有助于缓解威胁,但需要精确的视场(FOV)估计,而这一能力尚未在自动驾驶场景中得到评估。为填补这一空白,我们改编经典计算机图形学算法,开发了首个面向自动驾驶的FOV估计器,并创建了首批带有真实FOV标签的数据集。遗憾的是,我们发现这些方法本身极易受到针对传感的攻击。为提高FOV估计对攻击的鲁棒性,我们提出了一种基于学习的分割模型,该模型捕获FOV特征,集成蒙特卡洛dropout(MCD)进行不确定性量化,并在置信图上执行异常检测。我们通过全面评估展示了其攻击抵抗能力以及跨环境的强泛化性。架构权衡研究表明,该模型在多种应用中具备实时部署的可行性。

英文摘要:

Attacks on sensing and perception threaten the safe deployment of autonomous vehicles (AVs). Security-aware sensor fusion helps mitigate threats but requires accurate field of view (FOV) estimation which has not been evaluated autonomy. To address this gap, we adapt classical computer graphics algorithms to develop the first autonomy-relevant FOV estimators and create the first datasets with ground truth FOV labels. Unfortunately, we find that these approaches are themselves highly vulnerable to attacks on sensing. To improve robustness of FOV estimation against attacks, we propose a learning-based segmentation model that captures FOV features, integrates Monte Carlo dropout (MCD) for uncertainty quantification, and performs anomaly detection on confidence maps. We illustrate through comprehensive evaluations attack resistance and strong generalization across environments. Architecture trade studies demonstrate the model is feasible for real-time deployment in multiple applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑