Abstract
Tinyml is a developing area of machine learning that, when combined with edge computing and computer vision, can produce impressive outcomes. This study will examine the notion of tinyml and how edge computing and machine learning interact and describe the benefits and drawbacks of employing this new technology as well. More importantly, a model has been presented that explains how tinyml would get around the limitations of cutting-edge computer vision. This approach used a Arduino board to recognize various boxing blows in real-time. This idea stands in stark contrast to the conventional computer vision approach, which necessitates a lot more technical know-how and data. Here a sample solution is offered to a real-world issue that tracks bodily mobility and has enormous promise in the field of healthcare. The application of tinyml to computer vision techniques rather than the use of conventional ones may bring about a new breakthrough in these domains.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abdel Magid, S., Petrini, F., Dezfouli, B.: Image classification on IoT edge devices: profiling and modeling. Clust. Comput. 23(2), 1025–1043 (2019). https://doi.org/10.1007/s10586-019-02971-9
Dutta, L., Bharali, S.: TinyML Meets IoT: A Comprehensive Survey. Internet of Things 16, 100461 (2021). https://doi.org/10.1016/j.iot.2021.100461
UAB BitFlow: Differences Between Computer Vision vs. Machine Learning (2022). https://www.linkedin.com/pulse/differences-between-computer-vision-vs-machine-learning-uab-bitflow/?trk=pulse-article_more-articles_related-content-card
Alake, R.: A Beginner’s Guide to Computer Vision - Towards Data Science. Medium (2021). https://towardsdatascience.com/a-beginners-guide-to-computer-vision-dca81b0e94b4
Sriram, G.K.: Edge computing vs. cloud computing: an overview of big data challenges and opportunities for large enterprises 04(01) (2022)
Accenture Page https://www.accenture.com/us-en/insights/cloud/edge-computing-index. Last accessed 24 February 2023
David, R., et al.: TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems. ArXiv (Cornell University). https://arxiv.org/pdf/2010.08678Author, F.: Contribution title. In: 9th International Proceedings on Proceedings, pp. 1–2. Publisher, Location (2020)
Banbury, C.R., et al.: Benchmarking TinyML Systems: Challenges and Direction. ArXiv (Cornell University) (2020). https://arxiv.org/pdf/2003.04821.pdf
Ray, P.P.: A review on TinyML: State-of-the-art and prospects. J. King Saud Univ. Comp. Info. Sci. 34(4), 1595–1623 (2021). https://doi.org/10.1016/j.jksuci.2021.11.019
Asutkar, S., Chalke, C., Shivgan, K., Tallur, S.: TinyML-enabled edge implementation of transfer learning framework for domain generalization in machine fault diagnosis. Expert Syst. Appl. 213, 119016 (2022). https://doi.org/10.1016/j.eswa.2022.119016
TensorFlow Lite. Available online: http://www.tensorflow.org/lite
Dennis, D.K., et al.: EdgeML Machine LEARNING for Resource-Constrained Edge Devices. Available online: https://github.com/Microsoft/EdgeML
X-CUBE-AI—AI Expansion Pack for STM32CubeMX—STMicroelectronics. Available online: http://www.st.com/en/embedded-software/x-cube-ai.html
Sakr, F., Bellotti, F., Berta, R., De Gloria, A.: Machine learning on mainstream microcontrollers. Sensors 20, 2638 (2020)
Alajlan, N., Ibrahim, D.M.: TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications. Micromachines 13(6), 851 (2022). https://doi.org/10.3390/mi13060851
How Artificial Intelligence Revolutionized Computer Vision: A Brief History (2021). Motion Metrics. https://www.motionmetrics.com/how-artificial-intelligence-revolutionized-computer-vision-a-brief-history/
Advantages and Disadvantages of Computer Vision - Master in Artificial Intelligence and Deep Learning: University of Alcala - Madrid. Master in Artificial Intelligence and Deep Learning: University of Alcala – Madrid (2021). https://master-artificialintelligence.com/advantages-disadvantages-computer-vision
Kitsela, V.: Computer vision system: challenges, benefits, use cases. Software Development Company - N-iX (2022). https://www.n-ix.com/computer-vision/
Understanding computer vision, its advantages, and limitations (2019). https://www.allerin.com/blog/understanding-computer-vision-its-advantages-and-limitations
Building a TinyML Application with TF Micro and SensiML. (n.d.). https://blog.tensorflow.org/2021/05/building-tinyml-application-with-tf-micro-and-sensiml.html
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sahasra, K., Jain, A., Savaridassan, P., Likhitha, P. (2024). Tiny-Ml Model for Pugilism Sport Gesture Classification and Its Potential over Computer Vision. In: R., A.U., et al. Deep Sciences for Computing and Communications. IconDeepCom 2023. Communications in Computer and Information Science, vol 2176. Springer, Cham. https://doi.org/10.1007/978-3-031-68905-5_41
Download citation
DOI: https://doi.org/10.1007/978-3-031-68905-5_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-68904-8
Online ISBN: 978-3-031-68905-5
eBook Packages: Computer ScienceComputer Science (R0)