Conference paper · 2026 · Open access
Efficient AI-Driven Edge Surveillance Using Edge Computing
IEEE World Conference on Applied Intelligence and Computing (AIC), 525–530 · Published 1 August 2026 · DOI 10.1109/aic70896.2026.11717262
In brief
“Efficient AI-Driven Edge Surveillance Using Edge Computing” is a 2026 conference paper by Herman Singh Umrao and 4 co-authors, published in IEEE World Conference on Applied Intelligence and Computing (AIC). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE World Conference on Applied Intelligence and Computing (AIC).
- Citations
- 0
- References
- 10
- Authors
- 5
Abstract
Edge computing has emerged as a transformative paradigm for real-time surveillance, enabling intelligent video analytics at the network periphery while addressing the latency, bandwidth, and privacy constraints of cloud-based solutions. This paper presents the design, implementation, and evaluation of an AI-driven edge surveillance system deployed on a Raspberry Pi Zero 2W with a Pi Camera module. The system implements a two-stage detection pipeline combining lightweight frame differencing for motion pre-filtering with YOLO-based human detection via ONNX inference, reducing unnecessary inference calls while maintaining efficiency on resource-constrained hardware. Video capture is achieved by launching libcamera-vid as a subprocess with MJPEG output, and a multi-threaded architecture—a reader thread for capture and recording, a motion-triggered detection thread, and an HTTP server thread— ensures responsive performance. Continuous recording with segmented, auto-rotating MJPEG files enables efficient storage and rapid incident retrieval, and a lightweight HTTP server built on POSIX sockets serves a web dashboard for real-time streaming, camera network management, and playback. Experimental results show stable operation at 20 fps with minimal frame dropping and practical detection accuracy for residential and small-business security, all while eliminating cloud dependency, minimizing bandwidth use, and preserving privacy through fully local processing.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Umrao, H. S., Seerpu, A. B., Subramanian, G., V, U., & Singh, D. (2026). Efficient AI-Driven Edge Surveillance Using Edge Computing. IEEE World Conference on Applied Intelligence and Computing (AIC), 525–530. https://doi.org/10.1109/aic70896.2026.11717262
MLA 9
Umrao, Herman Singh, et al. “Efficient AI-Driven Edge Surveillance Using Edge Computing.” IEEE World Conference on Applied Intelligence and Computing (AIC), 2026, pp. 525–530. https://doi.org/10.1109/aic70896.2026.11717262.
Chicago
Umrao, Herman Singh, Akshaj B Seerpu, Govind Subramanian, Uday V, and Dinesh Singh. 2026. “Efficient AI-Driven Edge Surveillance Using Edge Computing.” IEEE World Conference on Applied Intelligence and Computing (AIC): 525–530. https://doi.org/10.1109/aic70896.2026.11717262.
Harvard
Umrao, H. S. et al. (2026) ‘Efficient AI-Driven Edge Surveillance Using Edge Computing’, IEEE World Conference on Applied Intelligence and Computing (AIC), pp. 525–530. doi:10.1109/aic70896.2026.11717262.
IEEE
H. S. Umrao, A. B. Seerpu, G. Subramanian, U. V, and D. Singh, “Efficient AI-Driven Edge Surveillance Using Edge Computing,” IEEE World Conference on Applied Intelligence and Computing (AIC), pp. 525–530, 2026, doi: 10.1109/aic70896.2026.11717262.
BibTeX
@inproceedings{umrao2026efficient,
title = {{Efficient AI-Driven Edge Surveillance Using Edge Computing}},
author = {Umrao, Herman Singh and Seerpu, Akshaj B and Subramanian, Govind and V, Uday and Singh, Dinesh},
booktitle = {IEEE World Conference on Applied Intelligence and Computing (AIC)},
year = {2026},
pages = {525--530},
doi = {10.1109/aic70896.2026.11717262},
url = {https://doi.org/10.1109/aic70896.2026.11717262}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- edge computing
- real-time video processing
- human detection
- YOLO
- Raspberry Pi
- motion detection
- frame difference
- lightweight inference
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Umrao, H. S., Seerpu, A. B., Subramanian, G., V, U., & Singh, D. (2026). Efficient AI-Driven Edge Surveillance Using Edge Computing. IEEE World Conference on Applied Intelligence and Computing (AIC), 525–530. https://doi.org/10.1109/aic70896.2026.11717262
How many times has this paper been cited?
0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE World Conference on Applied Intelligence and Computing (AIC): sign in and open the full text from this page.
Who wrote this paper?
Herman Singh Umrao, Akshaj B Seerpu, Govind Subramanian, Uday V, Dinesh Singh.
What is the DOI of this paper?
10.1109/aic70896.2026.11717262, permanently at https://doi.org/10.1109/aic70896.2026.11717262. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.