Gabriel Platform v2

We have released Gabriel version 2.0. Clients can now send frames from multiple sources. Support for multiple cognitive engines, running on the same server or elsewhere.

Edge Idea Challenge

Seamster.io, new community leveraging the adoption of edge computing applications has launched a contest for the best ideas on the use cases of mobile edge computing. You can submit your concept here https://seamster.io/idea-challenge. Good luck!

Blog: Seeing Further Down the Visual Cloud Road

Written by Jim Blakley | December 4, 2019 (Note: This Blog is a republication of my final blog while at Intel.) Almost three years ago, Carnegie Mellon University Prof. Dave Andersen and I announced the Intel Science and Technology Center for Visual Cloud Systems (ISTC-VCS) at the 2016 NAB Show. Along

Shared Edge Experience

How can two customers, attached to two different networks, share the same edge application and experience? How can two cars, using two different carriers, communicate in low latency?

OpenRTiST 2.0

OpenRTiST 2.0 has been released, built on a new Gabriel platform using websockets/protobufs. New features include dynamic discovery of styles, local execution using pytorch-android, and a new web app for training new models.

Blog: Overcoming Visual Analysis Paralysis

Written by Jim Blakley| October 25, 2019 (Note: This is a repost of my blog on the Intel IT Peer Network. While the theme is not edge specific, the use case – smart city video analytics – is very much an edge case. And, the request that motivated the work was in

Edge Computing Hackathon (27-28th September, Cracow, Poland)

Probably the biggest European edge computing hackathon will be held in Cracow last weekend of September. The developers will get the opportunity to use Edge Cloud 1.0 APIs and local edge computing infrastructure with 4G and 5G access. For more details please visit https://www.krakowhack.mobiledgex.com/

Deep neural networks, computer vision, and edge-native applications

Very recently, triggered by a conversation about how to optimize a machine learning application in the context of 5G and network-based edge computing, one of my colleagues pointed me to a 2017 paper about collaborative intelligence between cloud and mobile edge, authored by Yiping Kang et al. That paper analyses