A Comprehensive Systematic Review of TinyML for Person Detection Systems.
Saved in:
| Title: | A Comprehensive Systematic Review of TinyML for Person Detection Systems. |
|---|---|
| Authors: | Soliman, Yehia A.1 yahia.abuelkhair@fci.helwan.edu.eg, Ghoneim, Amr S.2 amr.ghoneim@fci.helwan.edu.eg, Elkhouly, Mahmoud M.3 elkhouly@fci.helwan.edu.eg |
| Source: | IAENG International Journal of Computer Science. Nov2025, Vol. 52 Issue 11, p4074-4086. 13p. |
| Subjects: | Machine learning, Computing platforms, Benchmark problems (Computer science), Intelligent sensors, Automatic tracking, Mathematical optimization, Artificial neural networks |
| Abstract: | Tiny Machine Learning (TinyML) enables the deployment of machine learning models on ultra-low-power and memory-constrained edge devices. This capability is crucial for person detection systems in applications such as smart homes, wearable health monitors, industrial safety, and wildlife surveillance. However, deploying person detection on microcontrollers poses significant challenges due to limited computation, memory, and energy resources. This paper presents a systematic literature review (SLR) of recent research in TinyML-based person detection from 2014 to 2024. We explore lightweight neural network architectures (e. g., MobileNet, Tiny-YOLO), optimization techniques (e. g., quantization, pruning, knowledge distillation), and performance metrics, including accuracy, latency, and energy efficiency. We also assess the suitability of edge hardware platforms such as ARM Cortex-M, ESP32, STM32, Jetson Nano, and Raspberry Pi. The review identifies current trends, highlights practical constraints, and proposes future directions involving adaptive models, federated learning, and privacypreserving designs. This work serves as a reference for researchers and practitioners aiming to build efficient, scalable, and real-time TinyML-based person detection systems. [ABSTRACT FROM AUTHOR] |
| Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
