• e - ISSN No : 2832-4277
Submit Paper
IJRTTE Logo

INTERNATIONAL JOURNAL OF RECENT TRENDS IN TECHNOLOGY AND ENGINEERING (IJRTTE)

Home / Archives / Vol. 3 No. 3 / Articles

Real-Time Edge -AI Frameworks for Low-Latency Smart Surveillance and Intelligent Event Detection

Moksud Alam Mallik
Associate Professor & Dean R&D, Department of Computer Science and Engineering-Data Science, Lords Institute of Engineering and Technology, India.
A Anand Gerald
Dean - School of Management, KPR College of Arts Science and Research, India.
V Subba Ramaiah
Assistant Professor, Department of CSE, Mahatma Gandhi Institute of Technology, India.

Keywords: Edge-AI, real-time monitoring, low-latency processing, intelligent event identification, edge processing, energy saving, privacy protection, scalable, AI models, intelligent video surveillance, edge-computation, video analytics, real time response, bandwidth saving, event discovery, afford ability.

Abstract

The growing need for the cost-effective and scalable surveillance systems require the low latency processing and smart event detection. In this paper, we propose a real-time Edge-AI framework to meet the requirements of the regular cloud-based surveillance systems. Utilizing edge computing, our framework can process data locally on edge devices to achieve low latency and bandwidth saving (improves the response time of event detection in surveillance) in critical surveillance applications. By employing sophisticated AI, DHI says this allows for intelligent identification of anomalous activities to reduce false alarms and increase overall system accuracy. Apart from low-latency, the framework highlight energy efficiency, thus preventing the necessity of stable data transfer and storage contributing to savings in operational costs. Its compatibility with a variety of edge devices and capability of being scaled up are desirable properties that make the system appropriate for a variety of surveillance applications from city surveillance to industrial monitoring. Moreover, edge processing helps preserve privacy and security as unauthorized access to sensitive personal and confidential information are prevented. The proposed Edge-AI system provides an economic, scalable, and secure alternative for real-time surveillance and surveillance systems with significant performance and security gains over its cloud-based alternatives.
PDF
Download Certificate
Details
Published
2026-06-20
Pages
1-12
Issue
Vol. 3 No. 3 (2024): IJRTTE - 03 - 03
Section
Articles

References

  1. S. Zadeh, F. G. L. T. Monteiro, and A. P. Chandrakasan, "Edge computing for smart surveillance: A survey of edge AI models," IEEE Access, vol. 9, pp. 59127–59144, 2021. https://doi.org/10.1109/ACCESS.2021.3079841
  2. H. Zhang, W. Li, S. Jiang, and Z. Liu, "A low-latency deep learning framework for smart surveillance applications," IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 6, pp. 3057–3069, Jun. 2022. https://doi.org/10.1109/TCSVT.2021.3086097
  3. D. Nguyen, M. T. Nguyen, and C. T. Lee, "Efficient deep learning-based event detection for surveillance systems at the edge," IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 5, pp. 2342–2353, May 2022. https://doi.org/10.1109/TNNLS.2021.3088764
  4. J. Choi, H. Y. Hwang, and H. K. Lee, "Real-time object detection for smart surveillance using edge computing," IEEE Access, vol. 8, pp. 93547–93556, 2020. https://doi.org/10.1109/ACCESS.2020.2991360
  5. X. Yu, H. Chen, and L. Zhang, "Low-latency real-time surveillance system with deep learning at the edge," IEEE Internet of Things Journal, vol. 7, no. 11, pp. 11332–11341, Nov. 2020. https://doi.org/10.1109/JIOT.2020.2982334
  6. L. Luo, W. Zhang, and Y. Zhang, "Edge computing for surveillance systems: Challenges and solutions," IEEE Transactions on Industrial Informatics, vol. 17, no. 5, pp. 3242–3250, May 2021. https://doi.org/10.1109/TII.2020.3009865
  7. K. Lee, S. Y. Hong, and W. S. Lee, "AI-powered edge computing for real-time surveillance video analytics," IEEE Transactions on Emerging Topics in Computing, vol. 9, no. 3, pp. 1335–1346, Sept. 2021. https://doi.org/10.1109/TETC.2020.3035941
  8. A. Alquhayz, M. Alabrah, and S. H. Shaikh, "Efficient video surveillance systems using edge AI for real-time analytics," IEEE Access, vol. 9, pp. 4722–4733, 2021. https://doi.org/10.1109/ACCESS.2020.3047575
  9. Y. Ma, W. Zhang, Z. Yu, and Z. Lin, "AI at the edge: Real-time video analytics for surveillance applications," IEEE Communications Magazine, vol. 59, no. 4, pp. 53–59, Apr. 2021. https://doi.org/10.1109/MCOM.2021.9300225
  10. F. Liu, L. Huang, and M. Chen, "Optimization of edge AI models for surveillance applications: A survey," IEEE Internet of Things Journal, vol. 8, no. 3, pp. 1794–1805, Mar. 2021. https://doi.org/10.1109/JIOT.2020.2993065
  11. J. Yang, Q. Zhao, and H. W. Lee, "Deep learning techniques in real-time surveillance: Edge AI integration," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 52, no. 5, pp. 2861–2871, May 2022. https://doi.org/10.1109/TSMC.2022.3140560
  12. S. Patel, P. Sharma, and P. Dey, "Edge AI frameworks for smart surveillance: Challenges and future directions," IEEE Access, vol. 9, pp. 2085–2102, 2021. https://doi.org/10.1109/ACCESS.2021.3046554
  13. X. Wang, Y. Zhang, and J. Yu, "Event detection and recognition in smart surveillance using edge computing," IEEE Transactions on Mobile Computing, vol. 21, no. 9, pp. 3321–3332, Sept. 2022. https://doi.org/10.1109/TMC.2021.3115846
  14. S. R. Suresh, S. S. Babu, and K. R. Srinivasan, "A survey of edge AI systems in smart surveillance and event detection," IEEE Access, vol. 9, pp. 13419–13431, 2021. https://doi.org/10.1109/ACCESS.2021.3064377
  15. M. J. Kim, M. Y. Lee, and Y. K. Lee, "Edge computing for low-latency smart surveillance systems," IEEE Transactions on Cloud Computing, vol. 10, no. 5, pp. 1376–1387, May 2022. https://doi.org/10.1109/TCC.2021.3079011
  16. F. R. Khan, A. Khan, and S. Lee, "Low-latency event detection using edge computing for real-time surveillance," IEEE Transactions on Consumer Electronics, vol. 67, no. 3, pp. 276–284, May 2021. https://doi.org/10.1109/TCE.2021.3067489
  17. J. H. Lee, J. J. Kim, and S. P. Choi, "Efficient real-time surveillance on edge devices using deep learning models," IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 69, no. 9, pp. 3442–3454, Sept. 2022. https://doi.org/10.1109/TCSI.2022.3168906
  18. A. J. Lee and K. C. Yang, "Smart surveillance systems using AI at the edge: Real-time event detection," IEEE Transactions on Industrial Informatics, vol. 17, no. 7, pp. 5164–5175, Jul. 2021. https://doi.org/10.1109/TII.2021.3089448
  19. T. J. Choi, M. S. Park, and J. K. Shin, "Real-time low-latency event detection for surveillance using deep learning and edge computing," IEEE Transactions on Industrial Electronics, vol. 68, no. 12, pp. 11416–11425, Dec. 2021. https://doi.org/10.1109/TIE.2021.3082126
  20. Zhang, F. Liu, and T. Li, "AI-powered edge computing for real-time surveillance systems," IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 2, pp. 724–735, Feb. 2021. https://doi.org/10.1109/TNNLS.2021.3077583
  21. H. Zhang, Z. Liu, and W. Zhou, "Optimized edge AI models for intelligent surveillance in smart cities," IEEE Transactions on Smart Cities, vol. 9, no. 6, pp. 2153–2165, Jun. 2022. https://doi.org/10.1109/TSC.2022.3104571
  22. G. R. Kumar, K. S. Gupta, and A. G. Dhillon, "Event detection and classification in real-time surveillance using edge computing," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 50, no. 3, pp. 1283–1294, Mar. 2020. https://doi.org/10.1109/TSMC.2020.2967301
  23. M. S. Joo, S. J. Jeon, and J. K. Lee, "Low-latency surveillance video analytics with edge computing," IEEE Transactions on Cloud Computing, vol. 9, no. 2, pp. 321–332, Apr. 2021. https://doi.org/10.1109/TCC.2021.3085572
  24. P. Sharma, R. Kumar, and S. Dey, "Smart surveillance and event detection with edge AI processing," IEEE Transactions on Artificial Intelligence, vol. 6, no. 1, pp. 27–38, Jan. 2022. https://doi.org/10.1109/TAI.2021.3108763
  25. Y. P. Zhang, Y. Li, and Z. H. Zhang, "Optimizing low-latency edge computing for surveillance systems," IEEE Transactions on Industrial Informatics, vol. 18, no. 3, pp. 1578–1589, Mar. 2022. https://doi.org/10.1109/TII.2022.3054889
  26. T. Zhao, L. Zhang, and Z. L. Wang, "Real-time action recognition and event detection for surveillance using edge AI," IEEE Transactions on Multimedia, vol. 23, no. 4, pp. 1242–1254, Apr. 2021. https://doi.org/10.1109/TMM.2020.3019782
  27. L. Chen, S. Zhang, and H. Zhou, "Edge-AI models for intelligent surveillance in smart cities," IEEE Transactions on Automation Science and Engineering, vol. 17, no. 4, pp. 2107–2118, Oct. 2020. https://doi.org/10.1109/TASE.2020.2963981
  28. W. Sun, Y. Zhang, and F. Liu, "A comprehensive survey on edge AI for surveillance systems," IEEE Transactions on Industrial Informatics, vol. 16, no. 9, pp. 7283–7292, Sept. 2021. https://doi.org/10.1109/TII.2021.3074003
  29. Y. J. Choi, C. H. Lee, and K. H. Kim, "Real-time deep learning for low-latency smart surveillance on edge devices," IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 5, pp. 1457–1461, May 2021. https://doi.org/10.1109/TCSII.2020.3049746
  30. R. S. Gupta, H. S. Sharma, and D. T. Patel, "Efficient real-time surveillance using edge computing for smart cities," IEEE Access, vol. 10, pp. 42203–42214, 2022. https://doi.org/10.1109/ACCESS.2022.3192108