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 2210.09441cs.CVcs.HCcs.RO
收藏

通过模态和视图分析的实时驾驶员监控系统

Real-Time Driver Monitoring Systems through Modality and View Analysis

University of Warwick(华威大学);Ford Motor Company(福特汽车公司);University of Glasgow(格拉斯哥大学)

Yiming Ma, Victor Sanchez, Soodeh Nikan, Devesh Upadhyay, Bhushan Atote, Tanaya Guha

摘要:

众所周知,驾驶员分心是交通事故的主要原因。虽然监控系统可以检测与驾驶无关的活动,并有助于降低风险,但它们必须准确和有效才能适用。不幸的是,最先进的方法优先考虑准确性而忽略延迟,因为它们利用了连续帧高度相似的跨视图和多模式视频。因此,在本文中,我们追求的时间有效的检测模型,忽略视频帧之间的时间关系,并调查的重要性,每一个感测模态在检测驱动器的活动。实验结果表明:1)我们提出的算法是实时的【形】,与基于视频的模型相比,可以达到相似的性能(97.5\ % AUC-PR),但计算量明显减少; 2)具有红外通道的顶视图比任何其他单一模态都更有信息量。此外,我们通过手动注释其测试集来增强DAD数据集,以实现多分类。我们还深入分析了视觉传感器类型及其放置位置对每个类别预测的影响。代码和新标签将被发布。

英文摘要:

Driver distractions are known to be the dominant cause of road accidents. While monitoring systems can detect non-driving-related activities and facilitate reducing the risks, they must be accurate and efficient to be applicable. Unfortunately, state-of-the-art methods prioritize accuracy while ignoring latency because they leverage cross-view and multimodal videos in which consecutive frames are highly similar. Thus, in this paper, we pursue time-effective detection models by neglecting the temporal relation between video frames and investigate the importance of each sensing modality in detecting drives' activities. Experiments demonstrate that 1) our proposed algorithms are real-time and can achieve similar performances (97.5\% AUC-PR) with significantly reduced computation compared with video-based models; 2) the top view with the infrared channel is more informative than any other single modality. Furthermore, we enhance the DAD dataset by manually annotating its test set to enable multiclassification. We also thoroughly analyze the influence of visual sensor types and their placements on the prediction of each class. The code and the new labels will be released.

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。

↑