REVAMP^2T: Real-time Edge Video Analytics for Multi-camera
Privacy-aware Pedestrian Tracking
release_ozelzzwl5rc7vm3pzuva3upqxy
by
Christopher Neff, Matías Mendieta, Shrey Mohan, Mohammadreza
Baharani, Samuel Rogers, Hamed Tabkhi
2019
Abstract
This article presents REVAMP^2T, Real-time Edge Video Analytics for
Multi-camera Privacy-aware Pedestrian Tracking, as an integrated end-to-end IoT
system for privacy-built-in decentralized situational awareness. REVAMP^2T
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^2T proposes a unified integrated computer vision pipeline for
detection, re-identification, and tracking across multiple cameras without the
need for storing the streaming data. At the same time, it avoids facial
recognition, and tracks and re-identifies pedestrians based on their key
features at runtime. On the IoT system side, REVAMP^2T provides
infrastructure to maximize hardware utilization on the edge, orchestrates
global communications, and provides system-wide re-identification, 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·Efficiency (Æ), for holistic evaluation of IoT systems for
real-time video analytics based on accuracy, performance, and power efficiency.
REVAMP^2T outperforms current state-of-the-art by as much as thirteen-fold
Æ improvement.
In text/plain
format
Archived Files and Locations
application/pdf 1.2 MB
file_r6eqa66izvbuvin5i5oerpjjty
|
arxiv.org (repository) web.archive.org (webarchive) |
1911.09217v2
access all versions, variants, and formats of this works (eg, pre-prints)