Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

EdgeVision: Towards Collaborative Video Analytics on Distributed Edges for Performance Maximization (2211.03102v3)

Published 6 Nov 2022 in cs.DC, cs.MA, and cs.MM

Abstract: Deep Neural Network (DNN)-based video analytics significantly improves recognition accuracy in computer vision applications. Deploying DNN models at edge nodes, closer to end users, reduces inference delay and minimizes bandwidth costs. However, these resource-constrained edge nodes may experience substantial delays under heavy workloads, leading to imbalanced workload distribution. While previous efforts focused on optimizing hierarchical device-edge-cloud architectures or centralized clusters for video analytics, we propose addressing these challenges through collaborative distributed and autonomous edge nodes. Despite the intricate control involved, we introduce EdgeVision, a Multiagent Reinforcement Learning (MARL)- based framework for collaborative video analytics on distributed edges. EdgeVision enables edge nodes to autonomously learn policies for video preprocessing, model selection, and request dispatching. Our approach utilizes an actor-critic-based MARL algorithm enhanced with an attention mechanism to learn optimal policies. To validate EdgeVision, we construct a multi-edge testbed and conduct experiments with real-world datasets. Results demonstrate a performance enhancement of 33.6% to 86.4% compared to baseline methods.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. W. Xing, Y. Yang, S. Zhang, Q. Yu, and L. Wang, “Noisyotnet: A robust real-time vehicle tracking model for traffic surveillance,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 4, pp. 2107–2119, 2021.
  2. Z. Xiao, Z. Xia, H. Zheng, B. Y. Zhao, and J. Jiang, “Towards performance clarity of edge video analytics,” in 2021 IEEE/ACM Symposium on Edge Computing (SEC).   IEEE, 2021, pp. 148–164.
  3. J. Jiang, Z. Luo, C. Hu, Z. He, Z. Wang, S. Xia, and C. Wu, “Joint model and data adaptation for cloud inference serving,” in 2021 IEEE Real-Time Systems Symposium (RTSS).   IEEE, 2021, pp. 279–289.
  4. S. Yi, Z. Hao, Q. Zhang, Q. Zhang, W. Shi, and Q. Li, “Lavea: Latency-aware video analytics on edge computing platform,” in Proceedings of the Second ACM/IEEE Symposium on Edge Computing, 2017, pp. 1–13.
  5. Y. Guan, X. Zhang, and Z. Guo, “Prefcache: Edge cache admission with user preference learning for video content distribution,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 4, pp. 1618–1631, 2020.
  6. Z. Yan, M. Zhao, C. Westphal, and C. W. Chen, “Toward guaranteed video experience: Service-aware downlink resource allocation in mobile edge networks,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 6, pp. 1819–1831, 2018.
  7. B. Qian, Z. Wen, J. Tang, Y. Yuan, A. Y. Zomaya, and R. Ranjan, “Osmoticgate: Adaptive edge-based real-time video analytics for the internet of things,” IEEE Transactions on Computers, 2022.
  8. X. Wang and G. Gao, “SmartEye: An open source framework for real-time video analytics with edge-cloud collaboration,” in Proceedings of ACM International Conference on Multimedia, 2021, pp. 3767–3770.
  9. X. Ran, H. Chen, X. Zhu, Z. Liu, and J. Chen, “Deepdecision: A mobile deep learning framework for edge video analytics,” in IEEE Conference on Computer Communications.   IEEE, 2018, pp. 1421–1429.
  10. T. Tan and G. Cao, “Deep learning video analytics through edge computing and neural processing units on mobile devices,” IEEE Transactions on Mobile Computing, 2021.
  11. K. Zhao, Z. Zhou, X. Chen, R. Zhou, X. Zhang, S. Yu, and D. Wu, “EdgeAdaptor: Online configuration adaption, model selection and resource provisioning for edge DNN inference serving at scale,” IEEE Transactions on Mobile Computing, 2022.
  12. Y. Li, A. Padmanabhan, P. Zhao, Y. Wang, G. H. Xu, and R. Netravali, “Reducto: On-camera filtering for resource-efficient real-time video analytics,” in Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication (SIGCOMM), 2020, pp. 359–376.
  13. M. Li, Y. Li, Y. Tian, L. Jiang, and Q. Xu, “Appealnet: An efficient and highly-accurate edge/cloud collaborative architecture for dnn inference,” in 2021 58th ACM/IEEE Design Automation Conference (DAC).   IEEE, 2021, pp. 409–414.
  14. Y. Wang, W. Wang, J. Zhang, J. Jiang, and K. Chen, “Bridging the Edge-Cloud barrier for real-time advanced vision analytics,” in 11th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 19), 2019.
  15. H. Zhang, L. Liu, H. Zhou, L. Si, H. Sun, and N. Zheng, “Fchp: Exploring the discriminative feature and feature correlation of feature maps for hierarchical dnn pruning and compression,” IEEE Transactions on Circuits and Systems for Video Technology, 2022.
  16. Y. Kim, J.-S. Choi, and M. Kim, “A real-time convolutional neural network for super-resolution on fpga with applications to 4k uhd 60 fps video services,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 8, pp. 2521–2534, 2018.
  17. X. Zhang, H. Sun, S. Chen, and N. Zheng, “Vlsi architecture exploration of guided image filtering for 1080p@ 60hz video processing,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 28, no. 1, pp. 230–241, 2016.
  18. G. Ma, Z. Wang, M. Zhang, J. Ye, M. Chen, and W. Zhu, “Understanding performance of edge content caching for mobile video streaming,” IEEE Journal on Selected Areas in Communications, vol. 35, no. 5, pp. 1076–1089, 2017.
  19. Y. Zhang, J.-H. Liu, C.-Y. Wang, and H.-Y. Wei, “Decomposable intelligence on cloud-edge IoT framework for live video analytics,” IEEE Internet of Things Journal, vol. 7, no. 9, pp. 8860–8873, 2020.
  20. A. H. Jiang, D. L.-K. Wong, C. Canel, L. Tang, I. Misra, M. Kaminsky, M. A. Kozuch, P. Pillai, D. G. Andersen, and G. R. Ganger, “Mainstream: Dynamic stem-sharing for multi-tenant video processing,” in 2018 USENIX Annual Technical Conference (USENIX ATC 18), 2018, pp. 29–42.
  21. M. Zhang, F. Wang, Y. Zhu, J. Liu, and Z. Wang, “Towards cloud-edge collaborative online video analytics with fine-grained serverless pipelines,” in Proceedings of the 12th ACM Multimedia Systems Conference, 2021, pp. 80–93.
  22. Y. Huang, F. Wang, F. Wang, and J. Liu, “DeePar: A hybrid device-edge-cloud execution framework for mobile deep learning applications,” in IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).   IEEE, 2019, pp. 892–897.
  23. C. Long, Y. Cao, T. Jiang, and Q. Zhang, “Edge computing framework for cooperative video processing in multimedia IoT systems,” IEEE Transactions on Multimedia, vol. 20, no. 5, pp. 1126–1139, 2017.
  24. Z. Fu, J. Ren, D. Zhang, Y. Zhou, and Y. Zhang, “Kalmia: A heterogeneous qos-aware scheduling framework for dnn tasks on edge servers,” in IEEE Conference on Computer Communications, 2022, pp. 780–789.
  25. K. Du, A. Pervaiz, X. Yuan, A. Chowdhery, Q. Zhang, H. Hoffmann, and J. Jiang, “Server-driven video streaming for deep learning inference,” in Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication (SIGCOMM), 2020, pp. 557–570.
  26. C. Pakha, A. Chowdhery, and J. Jiang, “Reinventing video streaming for distributed vision analytics,” in 10th USENIX workshop on hot topics in cloud computing (HotCloud 18), 2018.
  27. T. Elgamal, S. Shi, V. Gupta, R. Jana, and K. Nahrstedt, “Sieve: Semantically encoded video analytics on edge and cloud,” in 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS).   IEEE, 2020, pp. 1383–1388.
  28. C. Canel, T. Kim, G. Zhou, C. Li, H. Lim, D. G. Andersen, M. Kaminsky, and S. Dulloor, “Scaling video analytics on constrained edge nodes,” Proceedings of Machine Learning and Systems, pp. 406–417, 2019.
  29. J. Jiang, G. Ananthanarayanan, P. Bodik, S. Sen, and I. Stoica, “Chameleon: scalable adaptation of video analytics,” in Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, 2018, pp. 253–266.
  30. C. Wang, S. Zhang, Y. Chen, Z. Qian, J. Wu, and M. Xiao, “Joint configuration adaptation and bandwidth allocation for edge-based real-time video analytics,” in IEEE Conference on Computer Communications.   IEEE, 2020, pp. 257–266.
  31. H. Zhang, G. Ananthanarayanan, P. Bodik, M. Philipose, P. Bahl, and M. J. Freedman, “Live video analytics at scale with approximation and Delay-Tolerance,” in 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17), 2017, pp. 377–392.
  32. C.-C. Hung, G. Ananthanarayanan, P. Bodik, L. Golubchik, M. Yu, P. Bahl, and M. Philipose, “Videoedge: Processing camera streams using hierarchical clusters,” in 2018 IEEE/ACM Symposium on Edge Computing (SEC).   IEEE, 2018, pp. 115–131.
  33. X. Zeng, B. Fang, H. Shen, and M. Zhang, “Distream: scaling live video analytics with workload-adaptive distributed edge intelligence,” in Proceedings of the 18th Conference on Embedded Networked Sensor Systems, 2020, pp. 409–421.
  34. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  35. J. Utah, “Traffic camera videos and dash camera videos,” Mar 2018, https://www.youtube.com/channel/UCBcVQr-07MH-p9e2kRTdB3A/videos.
  36. Z. Akhtar, Y. S. Nam, R. Govindan, S. Rao, J. Chen, E. Katz-Bassett, B. Ribeiro, J. Zhan, and H. Zhang, “Oboe: Auto-tuning video abr algorithms to network conditions,” in Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, 2018, pp. 44–58.
  37. G. Urdaneta, G. Pierre, and M. Van Steen, “Wikipedia workload analysis for decentralized hosting,” Computer Networks, vol. 53, no. 11, pp. 1830–1845, 2009.
  38. S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems, vol. 28, 2015.
  39. T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988.
  40. K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2961–2969.
  41. D. Kang, J. Emmons, F. Abuzaid, P. Bailis, and M. Zaharia, “Noscope: optimizing neural network queries over video at scale,” arXiv preprint arXiv:1703.02529, 2017.
  42. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv preprint arXiv:1707.06347, 2017.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Guanyu Gao (13 papers)
  2. Yuqi Dong (1 paper)
  3. Ran Wang (172 papers)
  4. Xin Zhou (319 papers)
Citations (3)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets