7/12/2023 0 Comments The bleeding edgeRushmi Malaviarachchi is the Group Program Manager for Windows IoT engineering, delivering Windows to power the intelligent edge in fixed-purpose and IoT devices. Rushmi Malaviarachchi, Partner Group Program Manager, Microsoft Keynote: Microsoft IoT & the Intelligent Edge In this talk, I highlight several opportunities to substantially improve the tradeoffs between bandwidth usage and inference accuracy by intelligently leveraging the computation at cameras, edge servers and the cloud. However, these streaming protocols do not optimize the analytics quality (accuracy) of vision analytics (deep neural networks). In the past decade, numerous efforts have optimized video streaming protocols to provide better quality-of-experience to users. Reinventing Video Streaming for Distributed Vision Analyticsĭriven by the ubiquity of camera-equipped devices and the prohibitive cost of modern vision techniques, we see a growing need for a custom video streaming protocol that streams videos from cameras to cloud servers to perform neural-network-based video analytics. Deployment results show that Cascade improves accuracy by 25X compared to competing solutions and is within 6% of optimum. Cascade introduces “dominant demand” to identify the best trade-off between multiple resources and accuracy, and narrows the search space by identifying a “Pareto band” of promising configurations. In this talk, I’ll describe a system Cascade that optimizes queries on live videos by carefully selecting their “query plan” – implementations (and their knobs) – and placing them across the hierarchy of clusters to maximize average query accuracy. We believe that cameras represent the most challenging of “things” in Internet-of-Things, and live video analytics may well represent the killer application for edge computing. Our position is that a hierarchical architecture of public clouds, private clusters and edges extending all the way down to compute at the cameras is the only viable approach that can meet the strict requirements of live and large-scale video analytics. Video cameras are pervasively deployed for security and smart city scenarios, with millions of them in large cities worldwide. Speaker: Ganesh Ananthanarayanan, Microsoft Research Live Video Analytics – the “killer app” for edge computing! This enables privacy management for live video analytics while providing a secure approach for handling retrospective policy exceptions. Using OpenFace, our new open-source face recognition system that approaches state-of-the-art accuracy, we are able to selectively obscure faces according to user-specified policies at full frame rate. In this talk, I will describe how Edge Computing can be used to denature live video thereby making it “safe” from a privacy point of view. Privacy is clearly a major concern with video in public spaces. He or she merely has to be visible to a camera. Its passive nature means that a participant does not have to wear a special device, install an app, or do anything special. It offers high resolution, wide coverage, and low cost relative to other sensing modalities. It is flexible and open-ended: new image and video processing algorithms can extract new information from existing video streams. Live video offers several advantages relative to other sensing modalities. Speaker: Mahadev Satyanarayanan, Carnegie Mellon University Using Edge Computing for Privacy in Real-Time Video Analytics She has a doctorate in Artificial Intelligence on Multi-Agent Reasoning Systems, from Exeter University, UK and an MBA from Warwick University, UK. She owns six international patents for intelligent optimization, automated network health and monetization of traffic on telecom networks. Rashmi previously led Motorola’s worldwide System Integration portfolio and was instrumental in deploying some of the first expert and AI systems in 2G, 3G and 4G networks. She has been at the forefront of telecoms and IP media for over 20 years, managing network applications, cloud, media, IoT and M2M businesses for HPE during the previous 6 years, where most recently she was the Head of AI Solutions for High Performance Compute solutions. ![]() Working closely with ecosystem partners, Rashmi is responsible for proving forefront solutions combining IoT, AI and Edge as well as other emergent technologies at Microsoft. Rashmi Misra, General Manager IOT & AI Solutions, Partner Device Solutions, Microsoftĭr Rashmi Misra is General Manager of IOT & AI Solutions, in the Partner Device Solutions division of Microsoft. ![]() Keynote: Realizing the intelligent edge, from lite and nimble to heavy and ultra fast Victor Bahl, Distinguished Scientist, Microsoft Research
0 Comments
Leave a Reply. |