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 2403.01172cs.CV
收藏

利用学习表征对自动驾驶系统中的二维目标检测进行运行时内省

Run-time Introspection of 2D Object Detection in Automated Driving Systems Using Learning Representations

University of Warwick(华威大学);Queen’s University of Belfast(贝尔法斯特女王大学);WMG at the University of Warwick(华威大学WMG学院)

Hakan Yekta Yatbaz, Mehrdad Dianati, Konstantinos Koufos, Roger Woodman

AI总结:

针对DNN二维目标检测器易出错的问题,提出基于骨干网络激活模式的帧级运行时内省方法,并在KITTI和BDD上验证其错误检测与抗偏移性能优于SOTA。

摘要:

可靠检测周围环境中的各类物体和道路使用者,对自动驾驶系统(ADS)的安全运行至关重要。尽管近期基于深度神经网络(DNN)开发的高精度目标检测器取得了进展,但它们仍容易出现检测错误,在ADS这类安全关键应用中可能导致致命后果。解决该问题的一种有效补救措施是为系统配备运行时监控,在自主系统语境下称为内省。受此启发,我们提出一种新颖的内省方案,它在帧级别针对基于DNN的二维目标检测运行,并利用神经网络激活模式。所提方法使用若干不同模式对目标检测器骨干网络的神经激活模式进行预处理。为提供广泛的比较分析和公平比较,我们还调整并实现了若干用于二维目标检测错误检测的最先进(SOTA)内省机制,使用在KITTI和BDD数据集上评估的一阶段和两阶段目标检测器。我们从错误检测、对数据集偏移的适应能力以及计算和内存资源需求方面比较了所提方案的性能。性能评估表明,所提内省方案优于SOTA方法,在BDD数据集上实现了9%至17%的漏检错误率绝对降低。

英文摘要:

Reliable detection of various objects and road users in the surrounding environment is crucial for the safe operation of automated driving systems (ADS). Despite recent progresses in developing highly accurate object detectors based on Deep Neural Networks (DNNs), they still remain prone to detection errors, which can lead to fatal consequences in safety-critical applications such as ADS. An effective remedy to this problem is to equip the system with run-time monitoring, named as introspection in the context of autonomous systems. Motivated by this, we introduce a novel introspection solution, which operates at the frame level for DNN-based 2D object detection and leverages neural network activation patterns. The proposed approach pre-processes the neural activation patterns of the object detector's backbone using several different modes. To provide extensive comparative analysis and fair comparison, we also adapt and implement several state-of-the-art (SOTA) introspection mechanisms for error detection in 2D object detection, using one-stage and two-stage object detectors evaluated on KITTI and BDD datasets. We compare the performance of the proposed solution in terms of error detection, adaptability to dataset shift, and, computational and memory resource requirements. Our performance evaluation shows that the proposed introspection solution outperforms SOTA methods, achieving an absolute reduction in the missed error ratio of 9% to 17% in the BDD dataset.

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。

↑