Assistive Technology: The Role of Artificial Intelligence in Embedded Systems for Accessibility

• Francisnilto S. N. IFPI
• Larissa S. N. IFPI
• Luis Guilherme S. F. IFPI
• Maria Isabelly B. R. IFPI
• Ricardo M. S. Budaruiche IFPI
• Vanessa P. Cunha IFPI

DOI: https://doi.org/10.5753/enucompi.2025.9807

Abstract

This study explores the application of artificial intelligence (AI) in embedded systems to develop affordable assistive technologies for visually impaired individuals. We analyze models such as YOLOv3 and quantization techniques, demonstrating their efficiency in low-cost devices like the Raspberry Pi. The Blind Assistance project, based on computer vision and auditory feedback, illustrates the feasibility of these solutions. While challenges such as accuracy in dynamic environments and costs remain, the results highlight the potential of embedded AI to enhance autonomy and inclusion. Advances in algorithms and energy optimization are crucial to expanding access to these technologies.

References

Abhishek, Y., Nadeem, N., Delankawala, S., Jayakody, S., and Sumanathilaka, T. (2023). Deep learning based framework for reliable sri lankan currency authentication and counterfeit prevention. In 2023 IEEE 13th International Conference on System Engineering and Technology (ICSET), pages 84–89.

Almeida, W. d. N. (2022). Inteligência artificial em sistemas embarcados utilizando abordagem tinyml. B.S. thesis, Universidade Tecnológica Federal do Paraná.

Freitas, A. W., dos Santos, E. A. B., Pereira, L. S. M., Tortelli, S. d. P., Freitas, M. P., Teive, R. C. G., and Fernandes, A. M. R. (2023). Soluções de tecnologia assistiva baseadas em aiot - um mapeamento sistemático de literatura. Revista Brasileira de Computação Aplicada, 15(2):60–72.

Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., and Dally, W. J. (2016). Eie: Efficient inference engine on compressed deep neural network. ACM SIGARCH Computer Architecture News, 44(3):243–254.

Harzing, A.-W. (2007). Publish or perish. Available from [link]. Accessed: 30 March 2025.

Jambo, C. H. M. and da Costa, R. M. E. M. (2024). Integração de tecnologias embarcadas controladas por inteligência artificial: uma aplicação para apoiar o tratamento de fobias. In Anais Estendidos do Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 49–54.

Jouini, K., Maaloul, M. H., and Korbaa, O. (2021). Real-time, cnn-based assistive device for visually impaired people. In 2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pages 1–6.

Karthik, S. and Satish, N. (2021). Smart gloves used for blind visually impaired using wearable technology. Engineering and Scientific International Journal, 8(4):143–146.

Nguyen, X.-T.-A., Koopman, J., van Genderen, M. M., Stam, H. L., and Boon, C. J. (2022). Artificial vision: the effectiveness of the orcam in patients with advanced inherited retinal dystrophies. Acta Ophthalmologica, 100(4):e986 – e993.

Sam, M. V., Sharma, R., Chinchur, R., and Bhingardive, M. (2023). Object detection for blind people using cnn. International Research Journal of Modernization in Engineering Technology and Science, 5(4):[páginas].

Singh, P., Nayak, P., Datta, A., Sani, D., Raghav, G., and Tejpal, R. (2019). Voice control device using raspberry pi. In 2019 Amity International Conference on Artificial Intelligence (AICAI), pages 723–728.

Wang, L. and Wong, A. (2019). Enabling computer vision driven assistive devices for the visually impaired via micro-architecture design exploration. arXiv preprint arXiv:1905.07836.

World Health Organization (2019). World report on vision. Acesso em: 03 abr. 2025.