Visible to the public A Scalable and Privacy-Aware IoT Service for Live Video Analytics

TitleA Scalable and Privacy-Aware IoT Service for Live Video Analytics
Publication TypeConference Paper
Year of Publication2017
AuthorsWang, Junjue, Amos, Brandon, Das, Anupam, Pillai, Padmanabhan, Sadeh, Norman, Satyanarayanan, Mahadev
Conference NameProceedings of the 8th ACM on Multimedia Systems Conference
PublisherACM
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-5002-0
KeywordsAI, artificial intelligence, cloud computing, cloudlet, edge computing, face recognition, Human Behavior, human factor, human factors, Metrics, privacy, Privacy Mediator, privacy protection, pubcrawl, resilience, Resiliency, Scalability, user behavior, user privacy in the cloud
Abstract

We present OpenFace, our new open-source face recognition system that approaches state-of-the-art accuracy. Integrating OpenFace with inter-frame tracking, we build RTFace, a mechanism for denaturing video streams that selectively blurs faces according to specified policies at full frame rates. This enables privacy management for live video analytics while providing a secure approach for handling retrospective policy exceptions. Finally, we present a scalable, privacy-aware architecture for large camera networks using RTFace.

URLhttp://doi.acm.org/10.1145/3083187.3083192
DOI10.1145/3083187.3083192
Citation Keywang_scalable_2017