Live Video Analytics at Scale with Approximation and Delay-Tolerance

نویسندگان

  • Haoyu Zhang
  • Ganesh Ananthanarayanan
  • Peter Bodík
  • Matthai Philipose
  • Paramvir Bahl
  • Michael J. Freedman
چکیده

Video cameras are pervasively deployed for security and smart city scenarios, with millions of them in large cities worldwide. Achieving the potential of these cameras requires efficiently analyzing the live videos in realtime. We describe VideoStorm, a video analytics system that processes thousands of video analytics queries on live video streams over large clusters. Given the high costs of vision processing, resource management is crucial. We consider two key characteristics of video analytics: resource-quality tradeoff with multi-dimensional configurations, and variety in quality and lag goals. VideoStorm’s offline profiler generates query resourcequality profile, while its online scheduler allocates resources to queries to maximize performance on quality and lag, in contrast to the commonly used fair sharing of resources in clusters. Deployment on an Azure cluster of 101 machines shows improvement by as much as 80% in quality of real-world queries and 7× better lag, processing video from operational traffic cameras.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

On the Efficiency of Shaping Live Video Streams

In this work the efficiency of shaping live video streams is considered. We propose low complexity shaping algorithms adequate for real-time operation and supporting applications with a wide range of delay tolerance. The effect of shaping is investigated considering video streams multiplexed at an output link with a small buffer to absorb packet scale congestion. The advantage of using small bu...

متن کامل

Adaptive Live Video Streaming by Priority Drop

The reordering window in PPS introduces latency, however, and this latency might be problematic for video surveillance applications, which stream live video. In live video streaming, the latency characteristics of the streaming mechanisms partially determine the freshness of the video content. The freshness of the video content, which is measured by the end-to-end latency from a frame being cap...

متن کامل

Online Smoothing of Live, Variable-Bit-Rate Video

Bandwidth smoothing techniques are eeective at reducing the burstiness of a compressed, pre-recorded video stream by prefetching frames into the client playback buuer in advance of each burst. In contrast to stored video, live applications typically have limited knowledge of frame sizes and often require bounds on the delay between the source and the client(s). This paper addresses bandwidth sm...

متن کامل

A Novel Caching Strategy in Video-on-Demand (VoD) Peer-to-Peer (P2P) Networks Based on Complex Network Theory

The popularity of video-on-demand (VoD) streaming has grown dramatically over the World Wide Web. Most users in VoD P2P networks have to wait a long time in order to access their requesting videos. Therefore, reducing waiting time to access videos is the main challenge for VoD P2P networks. In this paper, we propose a novel algorithm for caching video based on peers' priority and video's popula...

متن کامل

A Scalable and Privacy-Aware IoT Service for Live Video Analytics

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 handli...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017