This article presents real-time edge video analytics for multicamera privacy-aware pedestrian tracking (REVAMP ² T), as an integrated end-to-end Internet of Things (IoT) system for privacy built-in decentralized situational awareness. REVAMP ² T presents novel algorithmic and system constructs to push deep learning and video analytics next to IoT devices (i.e., video cameras). On the algorithm side, REVAMP ² T proposes a unified integrated computer vision pipeline for detection, reidentification, and tracking across multiple cameras without the need for storing the streaming data. At the same time, it avoids facial recognition and tracks and reidentifies the pedestrians based on their key features at runtime. On the IoT system side, REVAMP ² T provides an infrastructure to maximize the hardware utilization on the edge, orchestrates global communications, and provides system-wide reidentification, without the use of personally identifiable information, for a distributed IoT network. For the results and evaluation, this article also proposes a new metric, accuracy ${\cdot}$ efficiency (Æ), for holistic evaluation of IoT systems for real-time video analytics based on accuracy, performance, and power efficiency. REVAMP ² T outperforms the current state of the art by as much as 13-fold Æ improvement.

中文翻译：

---

REVAMP ² T：用于多摄像机隐私意识的行人跟踪的实时边缘视频分析

本文介绍了用于多摄像机隐私感知行人跟踪（REVAMP ² T）的实时边缘视频分析 ，作为集成的端到端物联网（IoT）系统，用于内置隐私的分散式态势感知。REVAMP ² T提出了新颖的算法和系统构造，以将深度学习和视频分析推向物联网设备（即摄像机）之后。在算法方面，REVAMP ² T提出了一个统一的集成计算机视觉管道，用于跨多个摄像机的检测，重新识别和跟踪，而无需存储流数据。同时，它避免了面部识别，并在运行时根据行人的关键特征对其进行跟踪和重新识别。在物联网系统方面，REVAMP ² T为分布式IoT网络提供了一个基础架构，以最大程度地提高边缘上的硬件利用率，协调全球通信并提供系统范围内的重新标识，而无需使用个人身份信息。对于结果和评估，本文还提出了一种新的指标，即准确性 $ {\ cdot} $ 效率（Æ），用于基于准确性，性能和功率效率对IoT系统进行实时视频分析的整体评估。REVAMP ² T比现有技术高出13倍之多。