A Comparative Study of Computing Paradigms for Real-Time‎Image Processing: Cloud, Edge, And On-Device AI

  • Authors

    • Won-hyuk Choi Department of Avionics, Hanseo University
    • Woo-Jin Jung Department of Aeronautical System Engineering, Hanseo University
    https://doi.org/10.14419/cbjvn374

    Received date: June 16, 2025

    Accepted date: June 23, 2025

    Published date: July 27, 2025

  • Cloud Computing; Edge Computing; AI-Based On-Device Edge Computing; Real-Time Processing; Data Analysis

  • Abstract

    With the growing demand for real-time image and video processing, selecting an efficient computing architecture has become increasingly ‎important. This study conducts a comparative analysis of three paradigms—cloud computing (CC), edge computing (EC), and on-device ‎edge computing (ODEC)—to determine the most suitable method for real-time applications. By evaluating their performance across varying ‎data volumes and network conditions, we identify the trade-offs in latency, scalability, and responsiveness. The findings reveal that cloud ‎computing suffers from increased latency due to transmission bottlenecks, while edge and on-device computing significantly reduce latency ‎through decentralized processing. Among the three, ODEC demonstrates the most consistent performance, particularly in environments ‎requiring large-scale data handling and minimal network dependence. These results suggest that on-device AI offers a promising direction ‎for future real-time systems by addressing the limitations of traditional architectures.

  • References

    1. Fernandes, V.; Carvalho, G.; Pereira, V.; Bernardino, J. Analyzing Data Reduction Techniques: An Experimental Perspective. Appl. Sci. ‎‎2024, 14, 3436.‎ https://doi.org/10.3390/app14083436.
    2. ‎Siddiqui, S.T.; Khan, M.R.; Khan, Z.; Rana, N.; Khan, H.; Alam, M.I. Significance of Internet-of-Things Edge and Fog Computingin Edu-‎cation Sector. In Proceedings of the 2023 International Conference on Smart Computing and Application (ICSCA), Hail,Saudi Arabia, 5–6 ‎February 2023; IEEE: Piscataway, NJ, USA; pp. 1–6‎. https://doi.org/10.1109/ICSCA57840.2023.10087582.
    3. ‎Lee, H.; Kim, J.; Park, S. Edge AI vs. Cloud AI: A Comparative Study of Performance, Latency, and Scalability. Appl. Sci. 2025, 15, 1289.‎
    4. ‎Nasir Abbas at al “Mobile Edge Computing: A Survey” IEEE internet of Things Journal, Vol. 5, No. 1, pp. 450-465, Sep 2017.‎ https://doi.org/10.1109/JIOT.2017.2750180.
    5. ‎Y. Mao et al., “A Survey on Mobile Edge Computing: The Communication Perspective,” IEEE Commun. Surveys Tuts, Vol. 19, no. 4, pp. ‎‎2322–2358, Apr. 2017.‎ https://doi.org/10.1109/COMST.2017.2745201.
    6. J. Gubbi, R. Buyya, S. Marusic, and M. Palaniswami, “Internet of Things (IoT): A vision, architectural elements, and future directions,” ‎Future Generation Computer Systems, Vol. 29, No. 7, pp.1645-1660, Sept. 2013.‎ https://doi.org/10.1016/j.future.2013.01.010.
    7. ‎Chen, A.; Liu, F.H.; Wang, S.D.e. Data reduction for real-time bridge vibration data on edge. In Proceedings of the 2019 IEEE Internation-‎al Con-ference on Data Science and Advanced Analytics, DSAA, Washington, DC, USA, 5–8 October 2019; pp. 602–603. https://doi.org/10.1109/DSAA.2019.00077.
    8. ‎Kyung-rae. C ; Seok-min.H; Won-hyuk.C . Performance Comparison and Optimal Selection of Computing Techniques for Corridor Sur-‎veillance Journal of the Korean Society of Navigation, 2023, 27.6: 771-776.‎
    9. ‎IFTIKHAR, Sundas, et al. AI-based fog and edge computing: A systematic review, taxonomy and future directions. Internet of Things, ‎‎2023, 21: 100674.‎ https://doi.org/10.1016/j.iot.2022.100674.
    10. ‎HUA, Haochen, et al. Edge computing with artificial intelligence: A machine learning perspective. ACM Computing Surveys, 2023, 55.9: ‎‎1-35. https://doi.org/10.1145/3555802.
    11. JMERENDA, Massimo; PORCARO, Carlo; IERO, Demetrio. Edge machine learning for ai-enabled iot devices: A review. Sensors, 2020, ‎‎20.9: 2533.‎ https://doi.org/10.3390/s20092533.

  • Downloads

  • How to Cite

    Choi , W.- hyuk ., & Jung, W.-J. . . (2025). A Comparative Study of Computing Paradigms for Real-Time‎Image Processing: Cloud, Edge, And On-Device AI. International Journal of Basic and Applied Sciences, 14(3), 332-337. https://doi.org/10.14419/cbjvn374