ABSTRACT
Deep learning with Deep Neural Networks (DNNs) can achieve much higher accuracy on many computer vision tasks than classic machine learning algorithms. Because of the high demand for both computation and storage resources, DNNs are often deployed in the cloud. Unfortunately, executing deep learning inference in the cloud, especially for real-time video analysis, often incurs high bandwidth consumption, high latency, reliability issues, and privacy concerns. Moving the DNNs close to the data source with an edge computing paradigm is a good approach to address those problems. The lack of an open source framework with a high-level API also complicates the deployment of deep learning-enabled service at the Internet edge. This paper presents EdgeEye, an edge-computing framework for real-time intelligent video analytics applications. EdgeEye provides a high-level, task-specific API for developers so that they can focus solely on application logic. EdgeEye does so by enabling developers to transform models trained with popular deep learning frameworks to deployable components with minimal effort. It leverages the optimized inference engines from industry to achieve the optimized inference performance and efficiency.
- Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. TensorFlow: A System for Large-Scale Machine Learning.. In OSDI, Vol. 16. 265--283. Google ScholarDigital Library
- Amazon. 2018. The world's first deep learning enabled video camera for developers. Retrieved March 29, 2018 from https://aws.amazon.com/deeplens/Google Scholar
- Ganesh Ananthanarayanan, Paramvir Bahl, Peter Bodík, Krishna Chintalapudi, Matthai Philipose, Lenin Ravindranath, and Sudipta Sinha. 2017. Real-Time Video Analytics: The Killer App for Edge Computing. Computer 50, 10 (2017), 58--67.Google ScholarDigital Library
- Adam Bergkvist, Daniel C Burnett, Cullen Jennings, Anant Narayanan, and Bernard Aboba. 2012. Webrtc 1.0: Real-time communication between browsers. Working draft, W3C 91 (2012).Google Scholar
- Bocoup. 2018. Johnny-Five: The JavaScript Robotics and IoT Platform. Retrieved March 29, 2018 from http://johnny-five.io/Google Scholar
- BVLC. 2018. Caffe: a fast open framework for deep learning. Retrieved March 29, 2018 from https://github.com/BVLC/caffeGoogle Scholar
- Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. 2015. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 (2015).Google Scholar
- Ronan Collobert, Samy Bengio, and Johnny Mariéthoz. 2002. Torch: a modular machine learning software library. Technical Report. Idiap.Google Scholar
- Luis López Fernández, Miguel París Díaz, Raúl Benítez Mejías, Francisco Javier López, and José Antonio Santos. 2013. Kurento: a media server technology for convergent WWW/mobile real-time multimedia communications supporting WebRTC. In World of Wireless, Mobile and Multimedia Networks (WoWMoM), 2013 IEEE 14th International Symposium and Workshops on a. IEEE, 1--6.Google ScholarCross Ref
- Google. 2017. Google Clips. Retrieved March 29, 2018 from https://store.google.com/us/product/google_clips?hl=en-USGoogle Scholar
- GStreamer. 2018. GStreamer: open source multimedia framework. Retrieved March 26, 2018 from https://gstreamer.freedesktop.org/Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision. 1026--1034. Google ScholarDigital Library
- Intel. 2017. Intel's Deep Learning Inference Engine Developer Guide. Retrieved March 26, 2018 from https://software.intel.com/en-us/inference-engine-devguideGoogle Scholar
- Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia. ACM, 675--678. Google ScholarDigital Library
- Peng Liu, Dale Willis, and Suman Banerjee. 2016. Paradrop: Enabling lightweight multi-tenancy at the network's extreme edge. In Edge Computing (SEC), IEEE/ACM Symposium on. IEEE, 1--13.Google Scholar
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In European conference on computer vision. Springer, 21--37.Google ScholarCross Ref
- Nvidia. 2016. DetectNet: Deep Neural Network for Object Detection in DIGITS. Retrieved March 28, 2018 from https://devblogs.nvidia.com/detectnet-deep-neural-network-object-detection-digits/Google Scholar
- Nvidia. 2018. NVIDIA DeepStream SDK. Retrieved March 27, 2018 from https://developer.nvidia.com/deepstream-sdkGoogle Scholar
- Nvidia. 2018. NVIDIA DIGITS, Interactive Deep Learning GPU Training System. Retrieved March 28, 2018 from https://developer.nvidia.com/digitsGoogle Scholar
- NVIDIA. 2018. NVIDIA TensorRT - Programmable Inference Accelerator. Retrieved March 26, 2018 from https://developer.nvidia.com/tensorrtGoogle Scholar
- NVIDIA. 2018. TECHNICAL OVERVIEW: NVIDIA DEEP LEARNING PLATFORM. Retrieved March 29, 2018 from https://images.nvidia.com/content/pdf/inference-technical-overview.pdfGoogle Scholar
- Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 779--788.Google ScholarCross Ref
- resin.io. 2018. Resin.io homepage. Retrieved March 26, 2018 from https://resin.io/Google Scholar
- Samsung. 2018. IoT.js - A framework for Internet of Things. Retrieved March 29, 2018 from http://iotjs.net/Google Scholar
- Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).Google Scholar
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, et al. 2015. Going deeper with convolutions. Cvpr.Google Scholar
- Shan Tang. 2018. A list of ICs and IPs for AI, Machine Learning and Deep Learning. Retrieved March 29, 2018 from https://basicmi.github.io/Deep-Learning-Processor-List/Google Scholar
- Haoyu Zhang, Ganesh Ananthanarayanan, Peter Bodik, Matthai Philipose, Paramvir Bahl, and Michael J Freedman. 2017. Live Video Analytics at Scale with Approximation and Delay-Tolerance.. In NSDI, Vol. 9. 1. Google ScholarDigital Library
- Tan Zhang, Aakanksha Chowdhery, Paramvir Victor Bahl, Kyle Jamieson, and Suman Banerjee. 2015. The design and implementation of a wireless video surveillance system. In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking. ACM, 426--438. Google ScholarDigital Library
- Jianxin Zhao, Richard Mortier, Jon Crowcroft, and Liang Wang. 2017. User-centric Composable Services: A New Generation of Personal Data Analytics. arXiv preprint arXiv:1710.09027 (2017).Google Scholar
Index Terms
- EdgeEye: An Edge Service Framework for Real-time Intelligent Video Analytics
Recommendations
Deep learning architectures in emerging cloud computing architectures: Recent development, challenges and next research trend
AbstractThe challenges of the conventional cloud computing paradigms motivated the emergence of the next generation cloud computing architectures. The emerging cloud computing architectures generate voluminous amount of data that are beyond ...
Graphical abstractDisplay Omitted
Highlights- The article presents literature review on the application of deep learning in emerging cloud computing architectures.
Fruit category classification via an eight-layer convolutional neural network with parametric rectified linear unit and dropout technique
AbstractIn this paper, we apply an improved deep convolutional neural network (CNN) in fruit category classification, which is a hotspot in computer vision field. We created an 8-layer deep convolutional neural network, and utilized parametric rectified ...
Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy
MECOMM'18: Proceedings of the 2018 Workshop on Mobile Edge CommunicationsAs the backbone technology of machine learning, deep neural networks (DNNs) have have quickly ascended to the spotlight. Running DNNs on resource-constrained mobile devices is, however, by no means trivial, since it incurs high performance and energy ...
Comments