Real-Time Video Anonymization in Smart City Intersections
Real-Time Video Anonymization in Smart City Intersections
复制标题
DOI：
10.1109/mass56207.2022.00078
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Alex Angus;Zhuoxu Duan;G. Zussman;Z. Kostić
中科院分区：
文献类型：
--
作者：
Alex Angus;Zhuoxu Duan;G. Zussman;Z. Kostić
智慧城市中的摄像机可用于提供数据，以提升行人安全和交通管理水平。然而，视频录制本质上会侵犯隐私，因此需要找到技术解决方案来保护隐私。预计部署在纽约市COSMOS研究试验台上的智慧城市应用程序将对隐私较为友好。本文介绍了一种隐私保护方法——一种以模糊行人面部和车辆牌照的形式实现的视频匿名化流程。该流程利用基于YOLOv4定制的深度学习模型，在街景视频录制中检测隐私敏感对象。为实现实时推理，该流程通过NVIDIA TensorRT优化来提高速度。当将此方法应用于在纽约市COSMOS试验台内一个十字路口采集的视频数据集时，所提出的方法对可见的面部和牌照进行匿名化处理，召回率高达99%，推理速度超过每秒100帧。本文还给出了全面评估研究的结果。可通过COSMOS试验台门户网站访问部分匿名化视频。
Video cameras in smart cities can be used to provide data to improve pedestrian safety and traffic management. Video recordings inherently violate privacy, and technological solutions need to be found to preserve it. Smart city applications deployed on top of the COSMOS research testbed in New York City are envisioned to be privacy friendly. This contribution presents one approach to privacy preservation - a video anonymization pipeline implemented in the form of blurring of pedestrian faces and vehicle license plates. The pipeline utilizes customized deep-learning models based on YOLOv4 for detection of privacy-sensitive objects in street-level video recordings. To achieve real time inference, the pipeline includes speed improvements via NVIDIA TensorRT optimization. When applied to the video dataset acquired at an intersection within the COSMOS testbed in New York City, the proposed method anonymizes visible faces and license plates with recall of up to 99% and inference speed faster than 100 frames per second. The results of a comprehensive evaluation study are presented. A selection of anonymized videos can be accessed via the COSMOS testbed portal.