Networked Cameras Are the New Big Data Clusters
- Junchen Jiang ,
- Yuhao Zhou ,
- Ganesh Ananthanarayanan ,
- Yuanchao Shu ,
- Andrew A. Chien
Workshop on Hot Topics in Video Analytics and Intelligent Edges (HotEdgeVideo) |
With plummeting camera prices and increasing accuracy of deep neural networks (DNNs), we see an explosive growth of video-analytics applications over large camera deployments in the thousands, creating a multibillion dollar markets. Meanwhile, the proliferation of on-camera resource has spurred the prospect of massive live video analytics at edge. To deliver these promises, however, we must address the fundamental systems challenge: How to use on-camera resource in a large fleet of cameras to run more video-analytics applications?
Microsoft Rocket: Hybrid Edge + Cloud Video Analytics Platform
Today, video cameras are being used at a large scale by public and private enterprises for a variety of reasons—from security surveillance and traffic planning to consumer support in retail and hospitality settings. Thanks to gains in computer vision, particularly object detection and classification, video analysis has become more accurate. Fast and affordable real-time analysis, however, is lagging. Project Rocket seeks to make easy, cost-effective video analysis of live camera streams a reality.
Project Rocket, an extensible software stack that leverages the edge and cloud, is designed with maximum functionality in mind, capable of meeting the needs of varying video analytic applications. In this webinar, Microsoft researchers Ganesh Ananthanarayanan and Yuanchao Shu explain how Rocket—now open source on GitHub—uses approximation to run scalable analytics across the edge and cloud and how efficient live video analysis advances the interactive querying of stored video. The researchers will also provide a tutorial on how to get started with the stack and how to construct and execute video analytics pipelines.
Together, you’ll explore:
- Exciting applications of video analytics
- Techniques that make continuous video analytics dramatically cheaper
- Key components of the Rocket video analytics software stack
- Building your own video analytics applications
Resource list:
- Microsoft Rocket (opens in new tab) (Project page)
- Microsoft Rocket (opens in new tab) (GitHub)
- Live video analytics and research as Test Cricket with Dr. Ganesh Ananthanarayanan (opens in new tab) (Podcast)
- Cracking open the DNN black-box (opens in new tab) (Publication)
- Networked Cameras Are the New Big Data Clusters (opens in new tab) (Publication)
- Demo: Video Analytics – Killer App for Edge Computing (opens in new tab) (Publication)
- Ganesh Ananthanarayanan (opens in new tab) (Researcher profile)
- Yuanchao Shu (opens in new tab) (Researcher profile)
*This on-demand webinar features a previously recorded Q&A session and open captioning.
This webinar originally aired on December 12, 2019
Explore more Microsoft Research webinars: https://aka.ms/msrwebinars (opens in new tab)