Skip to main content

Advertisement

Springer Nature Link
Log in

Deep action: A mobile action recognition framework using edge offloading

  • Published:
Peer-to-Peer Networking and Applications Aims and scope Submit manuscript

Abstract

Recording users’ lives as short-form videos has been an emerging trend with the advance of mobile devices. The videos contain a wealth of information that requires a significant amount of computation to retrieve. In this paper, we propose Deep action, a framework that leverages edge offloading to enable human actions recognition on mobile devices. Deep action first samples frames from a video according to the accuracy requirement. The sampled frames are then compressed and fed into deep learning models to generate an action label. Considering the varying conditions of the wireless connection, we design an online scheduler to strategically offload compressed video snippets to the edge server. Furthermore, we use OpenCL to implement the video compression-related operations on mobile GPU, such that the model inference and video compression can operate in parallel on the mobile device. We implement Deep action on the Android OS and evaluate it on a commercial off-the-shelf mobile device and an edge server. The performance evaluation demonstrates that Deep action brings up to 19 × and 13 × execution speedup, compared to the local-only and remote-only strategies, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Investigation and Analysis Report on China’s Short Video Industry from 2018 to 2019.https://report.iimedia.cn/repo13-0/39194.html

  2. Seeing AI. https://www.microsoft.com/en-us/ai/seeing-ai

  3. TensorFlow Lite on GPU. https://tensorflow.google.cn/lite/performance/gpu_advanced

  4. Afsar P, Cortez P, Santos H Automatic human action recognition from video using hidden markov model. IEEE 18th International Conference on Computational Science and Engineering, pp. 105–109

  5. Afzal M, Shah N, Muhammad T (2019) Web video classification with visual and contextual semantics. Int J Commun Syst 32(13):1–15

    Article  Google Scholar 

  6. Chang MJ, Hsieh JT, Fang CY, Chen SW (2019) A vision-based human action recog- nition system for moving cameras through deep learning. In: Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning, pp. 85–91

  7. Chen TYH, Ravindranath L, Deng S, Bahl P, Balakrishnan H (2015) Glimpse: Con- tinuous, real-time object recognition on mobile devices. In: Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems, SenSys ’15, pp. 155–168. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/2809695.2809711

  8. Fangbemi AS, Liu B, Yu NH, Zhang Y (2018) Efficient human action recognition in- terface for augmented and virtual reality applications based on binary descriptor. International Conference on Augmented Reality, Virtual Reality and Computer Graph- ics (AVR), pp. 252–260. Springer

  9. Hossain MS, Muhammad G, Abdul W, Song B, Gupta BB (2018) Cloud-assisted secure video transmission and sharing framework for smart cities. Futur Gener Comput Syst 83:596–606

    Article  Google Scholar 

  10. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861

  11. Huynh LN, Lee Y, Balan RK (2017) DeepMon: Mobile GPU-based deep learning frame- work for continuous vision applications. In: Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services, pp. 82–95

  12. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size. arXiv preprint arXiv:1602.07360

  13. Ibrar M, Wang L, Muntean GM, Chen J, Shah N, Akbar A (2021) IHSF: An intelligent solution for improved performance of reliable and time-sensitive flows in hybrid SDN- based FC IoT systems. IEEE Internet Things J 8(5):3130–3142

    Article  Google Scholar 

  14. Jararweh Y, Alsmirat M, Al-Ayyoub M, Benkhelifa E, Darabseh A, Gupta B, Doulat A (2017) Software-defined system support for enabling ubiquitous mobile edge com- puting. Comput J 60(10):1443–1457

    Article  Google Scholar 

  15. Jegham I, Khalifa AB, Alouani I, Mahjoub MA (2020) Vision-based human action recognition: An overview and real world challenges. Forensic Science International: Digital Investigation 32:200901

  16. Kaushik S, Gandhi C (2019) Ensure hierarchal identity based data security in cloud envi- ronment. International Journal of Cloud Applications and Computing (IJCAC) 9(4):21–36

    Article  Google Scholar 

  17. Kumar A (2019) Design of secure image fusion technique using cloud for privacy-preserving and copyright protection. International Journal of Cloud Applications and Computing (IJCAC) 9(3):22–36

    Article  Google Scholar 

  18. Laptev I, Marszalek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE

  19. Li D, Deng L, Gupta BB, Wang H, Choi C (2019) A novel cnn based security guaran- teed image watermarking generation scenario for smart city applications. Inf Sci 479:432–447

    Article  Google Scholar 

  20. Liu L, Zhong R, Zhang W, Liu Y, Zhang J, Zhang L, Gruteser M (2018) Cutting the cord: Designing a high-quality untethered vr system with low latency remote render- ing. In: Proceedings of the 16th Annual International Conference on Mobile Systems, Applications, and Services, pp. 68–80

  21. Lu Z, Chan K, Pu S, Porta TL (2019) Crowdvision: A computing platform for video crowdprocessing using deep learning. IEEE Trans Mobile Comput 18(7):1513–1526

    Article  Google Scholar 

  22. Lv F, Nevatia R (2007) Single view human action recognition using key pose matching and viterbi path searching. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE

  23. Mach P, Becvar Z (2017) Mobile edge computing: A survey on architecture and computation offloading. IEEE Commun Surveys Tuts 19(3):1628–1656. https://doi.org/10.1109/COMST.2017.2682318

    Article  Google Scholar 

  24. Natarajan P, Nevatia R (2008) Online, real-time tracking and recognition of human actions. In: 2008 IEEE Workshop on Motion and video Computing, pp. 1–8. IEEE

  25. Tejero-de Pablos A, Nakashima Y, Yokoya N, D´ıaz-Pernas FJ, Mart´ınez-Zarzuela M (2016) Flexible human action recognition in depth video sequences using masked joint trajectories. EURASIP Journal on Image and Video Processing 2016(1), pp. 1–12

  26. Ran X, Chen H, Zhu X, Liu Z, Chen J (2018) DeepDecision: A mobile deep learning framework for edge video analytics. In: 2018 IEEE Conference on Computer Commu- nications (INFOCOM), pp. 1421–1429

  27. Richardson IE (2004) H.264 and MPEG-4 video compression: video coding for next- generation multimedia. John Wiley & Sons pp. 159–220

  28. Shechtman E, Irani M (2007) Space-time behavior-based correlation-or-how to tell if two underlying motion fields are similar without computing them? IEEE Trans Pattern Anal Mach Intell 29(11):2045–2056

    Article  Google Scholar 

  29. Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. arXiv preprint arXiv:1406.2199

  30. Su L, Lu Y, Wu F, Li S, Gao W (2009) Complexity-constrained H.264 video encoding. IEEE Trans Circuits Syst Video Technol 19(4):477–490

  31. Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp. 4489–4497

  32. Tran D, Ray J, Shou Z, Chang SF, Paluri M (2017) Convnet architecture search for spatiotemporal feature learning. arXiv preprint arXiv:1708.05038

  33. Valery O, Liu P, Wu J (2017) CPU/GPU collaboration techniques for transfer learning on mobile devices. In: 2017 IEEE 23rd International Conference on Parallel and Distributed Systems (ICPADS), pp. 477–484

  34. Wang F, Zhang C, Liu J, Zhu Y, Pang H, Sun L (2019) Intelligent edge-assisted crowdcast with deep reinforcement learning for personalized qoe. IEEE Conference on Computer Communications, pp. 910–918. IEEE

  35. Wu C, Zaheer M, Hu H, Manmatha R, Smola AJ, Kr¨ahenbu¨hl P (2018) Compressed video action recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6026–6035

  36. Xu M, Qian F, Zhu M, Huang F, Pushp S, Liu X (2019) Deepwear: Adaptive local offloading for on-wearable deep learning. IEEE Trans Mob Comput 19(2):314–330

    Article  Google Scholar 

  37. Xu M, Zhu M, Liu Y, Lin FX, Liu X (2018) DeepCache: Principled cache for mobile deep vision. In: Proceedings of the 24th Annual International Conference on Mobile Computing and Networking, pp. 129–144

  38. Zhang S, Wei Z, Nie J, Huang L, Zhen L (2017) A review on human activity recognition using vision-based method. Journal of Healthcare Engineering 2017(3):1–31

    Google Scholar 

  39. Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6848–6856

  40. Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J (2019) Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proc IEEE 107(8):1738–1762

    Article  Google Scholar 

  41. Zhu Y, Li X, Liu C, Zolfaghari M, Xiong Y, Wu C, Zhang Z, Tighe J, Man- matha R, Li M (2020) A comprehensive study of deep video action recognition. arXiv preprint arXiv:2012.06567

Download references

Author information

Authors and Affiliations

  1. Central South University, 932 Lushan S Rd, Changsha, Hunan, China

    Deyu Zhang, Sijing Duan, Yunzhen Luo & Fucheng Jia

  2. Hunan Provincial Education Examination Board Xiaoxiang Middle Rd, Changsha, Hunan, China

    Heguo Zhang

  3. Shandong Youth University of Political Science, 31699 Jingshi E Rd, Jinan, 250102, Shandong, China

    Feng Liu

Authors
  1. Deyu Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Heguo Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Sijing Duan
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yunzhen Luo
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Fucheng Jia
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Feng Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Feng Liu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, D., Zhang, H., Duan, S. et al. Deep action: A mobile action recognition framework using edge offloading. Peer-to-Peer Netw. Appl. 15, 324–339 (2022). https://doi.org/10.1007/s12083-021-01232-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12083-021-01232-0

Keywords