面向安全关键行人检测的基于光流的可信度度量
A Flow-based Credibility Metric for Safety-critical Pedestrian Detection
AI总结：
本文针对自动驾驶中行人检测的安全评估问题，提出了一种基于光流信号的新颖可信度指标c-flow，无需额外标签即可增强对安全关键漏检的分析，帮助开发者识别此类漏检。
摘要：
对于自动驾驶（AD）中的感知而言，安全至关重要。然而，当前最先进的目标检测中一个主要的安全隐患是，标准评估方案使用与安全无关的指标来论证检测性能的充分性。因此，在评估任务中必须利用补充的领域知识来突出安全关键的漏检。为了解决这一欠规范问题，本文提出了一种新颖的可信度指标，称为c-flow，用于行人边界框。为此，c-flow依赖于来自图像序列的互补光流信号，并在无需额外标签的情况下增强了对安全关键漏检的分析。我们在一个大型AD数据集上，使用最先进的行人检测器实现并评估了c-flow。我们的分析表明，c-flow使开发者能够识别安全关键的漏检。
英文摘要：
Safety is of utmost importance for perception in automated driving (AD). However, a prime safety concern in state-of-the art object detection is that standard evaluation schemes utilize safety-agnostic metrics to argue sufficient detection performance. Hence, it is imperative to leverage supplementary domain knowledge to accentuate safety-critical misdetections during evaluation tasks. To tackle the underspecification, this paper introduces a novel credibility metric, called c-flow, for pedestrian bounding boxes. To this end, c-flow relies on a complementary optical flow signal from image sequences and enhances the analyses of safety-critical misdetections without requiring additional labels. We implement and evaluate c-flow with a state-of-the-art pedestrian detector on a large AD dataset. Our analysis demonstrates that c-flow allows developers to identify safety-critical misdetections.
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。
