{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:04:05Z","timestamp":1774541045207,"version":"3.50.1"},"reference-count":12,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T00:00:00Z","timestamp":1756425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"FCT","award":["https:\/\/doi.org\/10.54499\/2023.15325.PEX"],"award-info":[{"award-number":["https:\/\/doi.org\/10.54499\/2023.15325.PEX"]}]},{"name":"FCT","award":["IPL\/IDI&CA2024\/CSAT-OBC_ISEL"],"award-info":[{"award-number":["IPL\/IDI&CA2024\/CSAT-OBC_ISEL"]}]},{"name":"9th edition of IDI&amp;CA","award":["https:\/\/doi.org\/10.54499\/2023.15325.PEX"],"award-info":[{"award-number":["https:\/\/doi.org\/10.54499\/2023.15325.PEX"]}]},{"name":"9th edition of IDI&amp;CA","award":["IPL\/IDI&CA2024\/CSAT-OBC_ISEL"],"award-info":[{"award-number":["IPL\/IDI&CA2024\/CSAT-OBC_ISEL"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Electronics"],"abstract":"<jats:p>Hand gesture recognition is used in human\u2013computer interaction, with multiple applications in assistive technologies, virtual reality, and smart systems. While vision-based methods are commonly employed, they are often computationally intensive, sensitive to environmental conditions, and raise privacy concerns. This work proposes a hardware\/software co-optimized system for real-time hand gesture recognition using accelerometer data, designed for a portable, low-cost platform. A Convolutional Neural Network from TinyML is implemented on a Xilinx Zynq-7000 SoC-FPGA, utilizing fixed-point arithmetic to minimize computational complexity while maintaining classification accuracy. Additionally, combined architectural optimizations, including pipelining and loop unrolling, are applied to enhance processing efficiency. The final system achieves a 62\u00d7 speedup over an unoptimized floating-point implementation while reducing power consumption, making it suitable for embedded and battery-powered applications.<\/jats:p>","DOI":"10.3390\/electronics14173457","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T12:25:57Z","timestamp":1756470357000},"page":"3457","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Design of Real-Time Gesture Recognition with Convolutional Neural Networks on a Low-End FPGA"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7060-4745","authenticated-orcid":false,"given":"Rui","family":"Policarpo Duarte","sequence":"first","affiliation":[{"name":"ISEL-IPL\/INESC-INOV-LAB, 1000-029 Lisboa, Portugal"}]},{"given":"Tiago","family":"Gon\u00e7alves","sequence":"additional","affiliation":[{"name":"IST-ULisboa\/INESC-ID, 1000-039 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9651-5043","authenticated-orcid":false,"given":"Gustavo","family":"Jacinto","sequence":"additional","affiliation":[{"name":"IST-ULisboa\/INESC-ID, 1000-039 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2970-3589","authenticated-orcid":false,"given":"Paulo","family":"Flores","sequence":"additional","affiliation":[{"name":"IST-ULisboa\/INESC-ID, 1000-039 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8556-4507","authenticated-orcid":false,"given":"M\u00e1rio","family":"V\u00e9stias","sequence":"additional","affiliation":[{"name":"ISEL-IPL\/INESC-INOV-LAB, 1000-029 Lisboa, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,29]]},"reference":[{"key":"ref_1","unstructured":"Warden, P., and Situnayake, D. (2019). TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers, O\u2019Reilly Media."},{"key":"ref_2","unstructured":"Tensorflow (2025, May 25). TensorFlow Lite. Available online: https:\/\/www.tensorflow.org\/lite\/guide."},{"key":"ref_3","unstructured":"(2008). IEEE Standard for Floating-Point Arithmetic (Standard No. IEEE Std 754-2008)."},{"key":"ref_4","unstructured":"Xilinx (2025, May 25). Vitis High-Level Synthesis User Guide (UG1399). Available online: https:\/\/docs.xilinx.com\/r\/2021.1-English\/ug1399-vitis-hls."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Tsai, Y.C., Lai, Y.H., Xu, C.H., and Ruan, S.J. (2023, January 21\u201323). FPGA-based implementation of a dynamic hand gesture recognition system. Proceedings of the IET International Conference on Engineering Technologies and Applications (ICETA 2023), Yunlin, Taiwan.","DOI":"10.1049\/icp.2023.3181"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Eggimann, M., Erb, J., Mayer, P., Magno, M., and Benini, L. (2019, January 27\u201330). Low Power Embedded Gesture Recognition Using Novel Short-Range Radar Sensors. Proceedings of the 2019 IEEE SENSORS, Montreal, QC, Canada.","DOI":"10.1109\/SENSORS43011.2019.8956617"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhou, W., Jiang, X., and Liu, Y. (2018, January 25\u201327). FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network. Proceedings of the 2018 IEEE International Conference on Cyborg and Bionic Systems (CBS), Shenzhen, China.","DOI":"10.1109\/CBS.2018.8612238"},{"key":"ref_8","unstructured":"Viswanatha, V., Ramachandra, A.C., Raghavendra, P., Prem, C.K., Viveka Simha, P.J., and Nishant, M. (2022). Implementation of Tiny Machine Learning Models on Arduino 33 BLE for Gesture and Speech Recognition. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"N\u00fa\u00f1ez-Prieto, R., G\u00f3mez, P.C., and Liu, L. (2019, January 29\u201330). A Real-Time Gesture Recognition System with FPGA Accelerated ZynqNet Classification. Proceedings of the 2019 IEEE Nordic Circuits and Systems Conference (NORCAS): NORCHIP and International Symposium of System-on-Chip (SoC), Helsinki, Finland.","DOI":"10.1109\/NORCHIP.2019.8906956"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bellotti, F., Grammatikakis, M.D., Mansour, A., Ruo Roch, M., Seepold, R., Solanas, A., and Berta, R. (2024). Real-Time Implementation of Tiny Machine Learning Models for Hand Motion Classification. Applications in Electronics Pervading Industry, Environment and Society, Springer.","DOI":"10.1007\/978-3-031-48121-5"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhou, W., Lyu, C., Jiang, X., Li, P., Chen, H., and Liu, Y.H. (2017, January 5\u20138). Real-time implementation of vision-based unmarked static hand gesture recognition with neural networks based on FPGAs. Proceedings of the 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), Macau, China.","DOI":"10.1109\/ROBIO.2017.8324552"},{"key":"ref_12","unstructured":"Raza, W. (2025, March 03). Hand Gesture Recognition Using TinyML on OpenMV. Available online: https:\/\/www.hackster.io\/wamiq-raza\/hand-gesture-recognition-using-tinyml-on-openmv-e0fb7c."}],"container-title":["Electronics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-9292\/14\/17\/3457\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:35:10Z","timestamp":1760034910000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-9292\/14\/17\/3457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,29]]},"references-count":12,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["electronics14173457"],"URL":"https:\/\/doi.org\/10.3390\/electronics14173457","relation":{},"ISSN":["2079-9292"],"issn-type":[{"value":"2079-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,29]]}}}