Edge Computing for Computer Vision in IoT: Feasibility and Directions

Authors

DOI:

https://doi.org/10.4108/eetiot.9404

Keywords:

Artificial Intelligence, LoRaWAN, Edge AI, SatIoT, Precision Agriculture, Embedded Systems, Resource Management

Abstract

The convergence of decentralized architectures integrating Machine Learning, Computer Vision and Low Power Wide Area Networks is increasingly becoming an integral part of our daily existence. Internet of Things serves as a real-time data conduit enhancing decision making via embedded technology and continuous data exchange. This paper explores the feasibility of Edge Computing as a foundational pillar in this evolving landscape. We experiment under real world, dynamic conditions, evaluate the technological aspects, strategies, process flows and key observations under the broad Edge Computing domain. Research pathways include Multi-access Edge topologies in future 6G networks, model quantization, and satellite-enhanced communication platforms. Additionally, a discussion is added supporting the advanced AI functionalities, including zero-shot learning, multi modal perception, and decentralized generative AI, thereby broadening the scope of intelligent applications across various domains. The significance and research objective of this study are threefold: (1) evaluation of LoRaWAN and satellite IoT communication strategies, (2) analysis of CV workloads on edge hardware and (3) future research directions where Edge Computing can support low-latency, energy-efficient and socially impactful IoT applications. By explicitly addressing these aspects, we aim to establish a clear link between the technological feasibility, ultimately with a practical and socioeconomic relevance.

Downloads

Download data is not yet available.
<br data-mce-bogus="1"> <br data-mce-bogus="1">

Author Biographies

Panagiotis Savvidis, Democritus University of Thrace

Mr. P. Savvidis received a BSc: “Applied Informatics and Multimedia” from the Technological Educational Institute of Crete in 2006 and an Mphil: “Advanced Technologies in Informatics and Computers” from the
International Hellenic University in 2024. Early interests include industrial robotics and later in research for Computer Vision, Machine Learning and IoT with significance to Embedded Systems. Last his interests span to the practical implementation and fusion of the above interdisciplinary fields.

George A. Papakostas, Democritus University of Thrace

George A. Papakostas received the diploma in Electrical and Computer Engineering in 1999 and M.Sc. and Ph.D. in Electrical and Computer Engineering in 2002 and 2007, respectively, from the Democritus University of Thrace (DUTh), Greece. He is a Tenured Full Professor in the Department of Informatics DUTh, Greece. He is the Head of the Machine Learning and Vision (MLV) Research Group. Prof. Papakostas has (co)authored more than 240 publications, his publications have over 4500 citations with an h-index 37 (Google Scholar). His research interests include machine learning, computer/machine vision, pattern recognition, and computational intelligence. Prof. Papakostas has is included in the top 2% of researchers worldwide for the year 2022 in the field of “Artificial Intelligence &amp; Image Processing”.

References

[1] Huh JH, Seo YS. Understanding Edge Computing: Engineering Evolution With Artificial Intelligence. IEEE Access. 2019;7:164229–164245. doi:10.1109/ACCESS.2019.2945338

[2] Cao K, Liu Y, Meng G, Sun Q. An Overview on Edge Computing Research. IEEE Access. 2020;8:85714–85728. doi:10.1109/ACCESS.2020.2991734

[3] Iftikhar S, Gill SS, et al. AI-based fog and edge computing: A systematic review, taxonomy and future directions. Internet of Things. 2022;17:100674. doi:10.1016/j.iot.2022.100674

[4] Savvidis P, Papakostas GA. Remote Crop Sensing with IoT and AI on the Edge. In: 2021 IEEE International Conference on Artificial Intelligence of Things (AIIoT). 2021. p. 1–5. doi:10.1109/AIIoT52608.2021.9454237

[5] OASES. Harvesting and utilising the vast amounts of data produced by modern aircraft: Part 1 [Internet]. [cited 2025 May 19]. Available from: https://www.oases.aero/blog/harvesting-and-utilising-the-vast-amounts-of-data-produced-by-modern-aircraft-part-1/

[6] Shi W, Cao J, Zhang Q. Edge Computing: Vision and Challenges. IEEE Internet Things J. 2016;3(5):637–646. doi:10.1109/JIOT.2016.2579198

[7] Yan Q, Li W, Li J, et al. Real-Time Air-to-Ground Data Communication Technology of Aeroengine Health Management System with Adaptive Rate in the Whole Airspace. J Sensors. 2021;2021:9912574. doi:10.1155/2021/9912574

[8] Red Hat. What is multi-access edge computing? [Internet]. [cited 2025 May 19]. Available from: https://www.redhat.com/en/topics/edge-computing/what-is-multi-access-edge-computing

[9] Ke R, Zhuang Y. A Smart, Efficient, and Reliable Parking Surveillance System With Edge Artificial Intelligence on IoT Devices. IEEE Trans Intell Transp Syst. 2020;22(5):2639–2649. doi:10.1109/TITS.2020.2984197

[10] Wang Y, Xu L, Zhu L. LAMANCO: A Lightweight Anonymous Mutual Authentication Scheme for N -Times Computing Offloading in IoT. IEEE Internet Things J. 2018;6(2):3797–3806. doi:10.1109/JIOT.2018.2888636

[11] Koutitas G, Vyas S, Vyas C. Practical Methods for Efficient Resource Utilization in Augmented Reality Services. IEEE Access. 2020;8:216732–216746. doi:10.1109/ACCESS.2020.3042616

[12] Wang J, Feng Z, Chen Z. Bandwidth-Efficient Live Video Analytics for Drones Via Edge Computing. In: 2018 IEEE SecureComm. 2018. p. 1–6. doi:10.1109/SEC.2018.00019

[13] Fisher C. Cloud versus On-Premise Computing. Am J Ind Bus Manag. 2018;8(9):1987–1998. doi:10.4236/ajibm.2018.89133

[14] Floyer D. The vital role of edge computing in the internet of things [Internet]. Wikibon. [cited 2025 May 19]. Available from: https://wikibon.com/the-vital-role-of-edge-computing-in-the-internet-of-things/

[15] Yar H, Imran AS. Towards Smart Home Automation Using IoT-Enabled Edge-Computing Paradigm. Sensors. 2021;21(14):4932. doi:10.3390/s21144932

[16] Lyu T, Dou X, et al. A Novel Maritime Edge Computing System for Internet of Vessels. In: 2023 IEEE ICCT. 2023. p. 1–6. doi:10.1109/ICCT59356.2023.10419619

[17] Shi W, Dustdar S. The Promise of Edge Computing. Computer. 2016;49(5):78–81. doi:10.1109/MC.2016.145

[18] IEEE Innovation at Work. Real-life edge computing use cases [Internet]. [cited 2025 May 19]. Available from: https://innovationatwork.ieee.org/real-life-edge-computing-use-cases/

[19] Murshed MGS, Murphy C, Hou D. Machine Learning at the Network Edge: A Survey. ACM Comput Surv. 2021;54(8):1–37. doi:10.1145/3469029

[20] Mazzia V, Khaliq A, Salvetti F. Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application. IEEE Access. 2020;8:9102–9114. doi:10.1109/ACCESS.2020.2964608

[21] Chen X, Zhang J, Lin B. Energy-Efficient Offloading for DNN-Based Smart IoT Systems in Cloud-Edge Environments. IEEE Trans Parallel Distrib Syst. 2021;33(2):452–466. doi:10.1109/TPDS.2021.3100298

[22] Cao J, Xu L, Abdallah R. EdgeOS_H: A Home Operating System for Internet of Everything. In: 2017 IEEE ICDCS. 2017. p. 2361–2366. doi:10.1109/ICDCS.2017.325

[23] Puthal D, Mohanty SP, Wilson S. Collaborative Edge Computing for Smart Villages [Energy and Security]. IEEE Consum Electron Mag. 2021;10(2):91–97. doi:10.1109/MCE.2021.3051813

[24] IIC. Introduction to Edge Computing in IIoT [Internet]. 2018 [cited 2025 May 19]. Available from: https://www.iiconsortium.org/pdf/Introduction_to_Edge_Computing_in_IIoT_2018-06-18.pdf

[25] Adami D, Ojo MO, Giordano S. Design, development and evaluation of an intelligent animal repelling system for crop protection based on embedded edge-AI. IEEE Access. 2021;9:132125–39. doi:10.1109/ACCESS.2021.3114503

[26] Ali-Eldin A, Wang B, Shenoy P. The hidden cost of the edge: A performance comparison of edge and cloud latencies. arXiv preprint arXiv:2104.14050 doi: 10.48550/arXiv.2104.14050

[27] Arroba P, Buyya R, Cárdenas R, Risco-Martín JL, Moya JM. Sustainable edge computing: Challenges and future directions. Softw Pract Exp. 2024 Nov;54(11):2272–96. doi:10.1002/spe.3340

[28] Jebril AH, Jebril AH. Overcoming Limitations of LoRa Physical Layer in Image Transmission. Sensors. 2018;18(10):3257. doi:10.3390/s18103257

[29] Lalle Y, Fourati LC, et al. A Comparative Study of LoRaWAN, SigFox, and NB-IoT for Smart Water Grid. In: 2019 Global Information Infrastructure and Networking Symposium. 2019. p. 1–6. doi:10.1109/GIIS48668.2019.9044961

[30] Pocero Fraile L, Tsampas S, et al. A Comparative Study of LoRa and IEEE 802.15.4-Based IoT Deployments Inside School Buildings. IEEE Access. 2020;8:149198–149213. doi:10.1109/ACCESS.2020.3020685

[31] Griva AI, Boursianis AD, et al. LoRa-Based IoT Network Assessment in Rural and Urban Scenarios. Sensors. 2023;23(3):1695. doi:10.3390/s23031695

[32] Farhad A, Kim DH, et al. Scalability of LoRaWAN in an Urban Environment: A Simulation Study. In: 2019 ICUFN. 2019. p. 1–4. doi:10.1109/ICUFN.2019.8806140

[33] Lic TV, Ferrero F, et al. Internet of Things terminal with Embedded Machine Learning Capabilities for Terrestrial and Space Communication Experiments. In: 2023 IEEE ATC. 2023. doi:10.1109/ATC58710.2023.10318893

[34] Ledesma O, Lamo P. Trends in LPWAN Technologies for LEO Satellite Constellations in the NewSpace Context. Electronics. 2024;13(3):579. doi:10.3390/electronics13030579

[35] Mehdi SZA, Ali AM, et al. LoRaWAN CubeSat with an Adaptive Data Rate: An Experimental Analysis of Path Loss Link Margin. Aerospace. 2023;10(1):53. doi:10.3390/aerospace10010053

[36] Fraunhofer IIS. Satellite IoT [Internet]. [cited 2025 May 19]. Available from: https://www.iis.fraunhofer.de/en/ff/kom/satkom/satellite_iot.html#147986728510053863

[37] Univ. Grenoble Alpes. Thingsat CubeSat mission [Internet]. [cited 2025 May 19]. Available from: https://gricad-gitlab.univ-grenoblealpes.fr/thingsat/public/-/blob/master/cubesat_mission/README.md

[38] SEOS Project. Introduction to Remote Sensing [Internet]. [cited 2025 May 19]. Available from: http://www.seos-project.eu

[39] Qu Z, Zhang G, et al. LEO Satellite Constellation for Internet of Things. IEEE Access. 2017;5:18391–18401. doi:10.1109/ACCESS.2017.2735988

[40] Ferrer T, Céspedes S, et al. Review and Evaluation of MAC Protocols for Satellite IoT Systems Using Nanosatellites. Sensors. 2019;19(8):1947. doi:10.3390/s19081947

[41] Fraire JA, Céspedes S, et al. Direct-To-Satellite IoT - A Survey of the State of the Art and Future Research Perspectives: Backhauling the IoT Through LEO Satellites. In: Internet of Things. Springer; 2020. p. 303–322. doi:10.1007/978-3-030-31831-4_17

[42] Ullah MA, Pasolini G. Understanding the Limits of LoRa Direct-to-Satellite: The Doppler Perspectives. IEEE Open J Commun Soc. 2023;4:1400–1411. doi:10.1109/OJCOMS.2023.3337004

[43] Zadorozhny AM, Doroshkin AA, et al. First Flight-Testing of LoRa Modulation in Satellite Radio Communications in Low-Earth Orbit. IEEE Access. 2022;10:114747–114755. doi:10.1109/ACCESS.2022.3207762

[44] TinyGS Project. GitHub Wiki [Internet]. [cited 2025 May 19]. Available from: https://github.com/G4lile0/tinyGS/wiki

[45] Huang T. Computer Vision: Evolution and Promise. CERN Yellow Reports. 1996;CERN-1996-008.21. doi:10.5170/CERN-1996-008.21

[46] Albanese A, Nardello M, Brunelli D. Automated Pest Detection With DNN on the Edge for Precision Agriculture. IEEE J Emerg Sel Top Circuits Syst. 2021;11(3):389–398. doi:10.1109/JETCAS.2021.3101740

[47] Amudhan AN, Vrajesh SR, Sudheer AP. RFSOD: a lightweight single-stage detector for real-time embedded applications to detect small-size objects. J Real-Time Image Proc. 2022;19(5):929–944. doi:10.1007/s11554-021-01170-3

[48] Bhusal S, Karkee M, Zhang Q. Apple dataset benchmark from orchard environment in modern fruiting wall. Washington State University; 2019. doi:10.7273/000001752.

[49] Häni N, Roy P, Isler V. Minne Apple: a benchmark dataset for apple detection and segmentation. IEEE Robot Autom Lett. 2020;5(2):852-8. doi:10.1109/LRA.2020.2965061.

[50] Albumentations. Bounding Boxes Augmentation [Internet]. [cited 2025 May 19]. Available from: https://albumentations.ai/docs/getting_started/bounding_boxes_augmentation/

[51] Tzutalin. LabelImg. GitHub [Internet]. 2015 [cited 2025 May 19]. Available from: https://github.com/tzutalin/labelImg

[52] OpenCV. CVAT: Annotate better with CVAT [Internet]. GitHub. [cited 2025 May 19]. Available from: https://github.com/opencv/cvat

[53] Allali A. Leaf Diseases Classification [Internet]. GitHub. [cited 2025 May 19]. Available from: https://github.com/aallali/Leaf-Diseases-Classification

[54] He L, Fang W, Zhao G. Fruit yield prediction and estimation in orchards: A state-of-the-art comprehensive review for both direct and indirect methods. Comput Electron Agric. 2022;198:106812. doi:10.1016/j.compag.2022.106812

[55] Yang B, Wang X, Xing Y, Cheng C, Jiang W, Feng Q. Modality Fusion Vision Transformer for Hyperspectral and LiDAR Data Collaborative Classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2024;17:17052–17065. doi:10.1109/JSTARS.2024.3415729.

[56] Wang Q, Yu C, Chen S, Fang W, Xiong N. Joint Adaptive Resolution Selection and Conditional Early Exiting for Efficient Video Recognition on Edge Devices. Big Data Mining and Analytics. 2024;8(3):661–677. doi:10.26599/BDMA.2024.9020093.

[57] Liu Z, Dang F, Liu X, Tong X, Zhao H, Liu K, Li K. A Multimodal Fusion Framework for Enhanced Exercise Quantification Integrating RFID and Computer Vision. Tsinghua Sci. Technol. 2025;30(8):––. doi:10.26599/TST.2025.9010107.

[58] Jia Z, Dong C, Guo K, Wu Q. The potential of LEO satellites in 6G space–air–ground enabled access networks. IEEE Open J Commun Soc. 2024;5:1117–37. doi:10.1109/OJCOMS.2024.3418860

[59] Lin Y, Feng W, Wang Y, Chen Y, Zhu Y, Zhang X, et al. Satellite-MEC integration for 6G Internet of Things: Minimal structures, advances, and prospects. arXiv. 2023. doi:10.48550/arXiv.2308.14992

[60] Turnbull O, Cevora G. Instability of computer vision models is a necessary result of the task itself. arXiv. 2023. doi:10.48550/arXiv.2310.17559

[61] Bayoudh K, Knani R, Hamdaoui F, Mtibaa A. A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis Comput. 2022;38(8):2939–70. doi:10.1007/s00371-021-02166-7

[62] Zhao C, Zhang X, Zhang Y, Liu Y. Model Compression and Acceleration for Edge AI: A Survey. Big Data Cogn Comput. 2022;8(4):94. doi:10.3390/bdcc8080094

[63] Kamilaris A, Prenafeta-Boldú FX. Deep learning in agriculture: A survey. Artif Intell Agric. 2018;1:1–11. doi:10.1016/j.aiia.2019.12.001

[64] European Commission: Directorate-General for Communications Networks, Content and Technology, Decision Etudes & Conseil, Saint-Martin L, Delesse J-P, Tual J-P, et al. Study on the economic potential of far edge computing in the future smart Internet of Things – Final study report. Luxembourg: Publications Office of the European Union; 2023. Available from: https://data.europa.eu/doi/10.2759/05608

[65] Zheng Y, Cui L. Zero-Shot Object Detection with Transformers. In: 2021 IEEE International Conference on Image Processing (ICIP); 2021 Sep 19–22; Anchorage, AK, USA. IEEE; 2021. p. 1749–53. doi:10.1109/ICIP42928.2021.9506277

[66] Lin J, Yin H, Ping W, Lu Y, Molchanov P, Tao A, Mao H, Kautz J, Shoeybi M, Han S. VILA: On Pre-training for Visual Language Models. arXiv preprint arXiv:2312.07533. 2023 Dec 12. Available from: https://doi.org/10.48550/arXiv.2312.07533

[67] Hager PA, Moons B, Cosemans S, Papistas IA, et al. 11.3 Metis AIPU: A 12nm 15TOPS/W 209.6TOPS SoC for cost- and energy-efficient inference at the edge. In: 2024 IEEE International Solid-State Circuits Conference (ISSCC); 2024 Feb 18–22; San Francisco, CA, USA. IEEE; 2024. p. 1–3. doi:10.1109/ISSCC49657.2024.10454395

[68] Wang Y-C, Xue J, Wei C, Kuo C-CJ. An overview on generative AI at scale with edge-cloud computing. IEEE Open J Commun Soc. 2023;4:1–1. doi:10.1109/OJCOMS.2023.3320646

Downloads

Published

28-10-2025

How to Cite

[1]
P. Savvidis and G. A. Papakostas, “Edge Computing for Computer Vision in IoT: Feasibility and Directions ”, EAI Endorsed Trans IoT, vol. 11, Oct. 2025.

Issue

Vol. 11 (2025): EAI Endorsed Transactions on Internet of Things

Section

Research article

License

Copyright (c) 2025 Panagiotis Savvidis, George A. Papakostas

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.