Abstract
The efficient processing of video streams is a key component in many emerging Internet of Things (IoT) and edge applications, such as Virtual and Augmented Reality (V/AR) and self-driving cars. These applications require real-time high-throughput video processing. This can be attained via a collaborative processing model between the edge and the cloud---called an Edge-Cloud model. To this end, many approaches were proposed to optimize the latency and bandwidth consumption of Edge-Cloud video processing, especially for Neural Networks (NN)-based methods. In this demonstration. We investigate the efficiency of these NN techniques, how they can be combined, and whether combining them leads to better performance. Our demonstration invites participants to experiment with the various NN techniques, combine them, and observe how the underlying NN changes with different techniques and how these changes affect accuracy, latency and bandwidth consumption.
- N. Fraser. Differential synchronization. In Proceedings of the 9th ACM symp. on Document eng., 2009. Google ScholarDigital Library
- P. Kaewtrakulpong and R. Bowden. An improved adaptive background mixture model for realtime tracking with shadow detection. 2001.Google Scholar
- D. Kang et al. Noscope: optimizing neural network queries over video at scale. PVLDB, 10(11):1586--1597, 2017. Google ScholarDigital Library
- Y. Kang et al. Neurosurgeon: Collaborative intelligence between the cloud and mobile edge. In ASPLOS, 2017. Google ScholarDigital Library
- P. Lindstrom. Fixed-rate compressed floating-point arrays. IEEE transactions on visualization and computer graphics, 20(12):2674--2683, 2014.Google Scholar
- J. Redmon and A. Farhadi. YOLO9000: better, faster, stronger. CoRR, abs/1612.08242, 2016.Google Scholar
- A. Vulimiri et al. Wanalytics: Geo-distributed analytics for a data intensive world. In SIGMOD, 2015. Google ScholarDigital Library
Recommendations
Collaborative Edge-Cloud and Edge-Edge Video Analytics
SoCC '19: Proceedings of the ACM Symposium on Cloud ComputingAccording to YouTube statistics [1], more than 400 hours of content is uploaded to its platform every minute. At this rate, it is estimated that it would take more than 70 years of continuous watch time in order to view all content on YouTube, assuming ...
Real time identification and control of dynamic systems using recurrent neural networks
Recently, several recurrent neural networks for solving constraint optimization problems were developed. In this paper, we propose a novel approach to the use of a projection neural network for solving real time identification and control of time ...
A comparison of neural networks for real-time emotionrecognition from speech signals A comparison of neural networks for real-time emotionrecognition from speech signals
Speech and emotion recognition improve the quality of human computer interaction and allow easier to use interfaces for every level of user in software applications. In this study, we have developed two different neural networks called emotion ...
Comments