Controle de Mouse Virtual Assistivo por Movimentos da Cabeça
Resumo
Dispositivos convencionais de entrada impõem barreiras a pessoas com deficiência motora, sendo a imprecisão por microtremores involuntários um obstáculo crítico no controle assistivo por movimentos da cabeça. Propõe-se um mouse virtual preditivo integrando visão computacional (MediaPipe), classificador Random Forest e magnetismo adaptativo web. Treinado com 1.980 amostras e cinco features físicas fundamentadas na Lei de Fitts, o modelo prediz intenção de clique com 70,45% de acurácia (69,51 ± 3,20% em validação cruzada), aplicando assistência gradual condicionada à confirmação facial. Operando em hardware convencional sem GPU, a solução consolida-se como alternativa inclusiva de baixo custo.Referências
Ashtankar, H. et al. (2015). Mouse control using head movement. Journal of Advance Research in Computer Science & Engineering, 2(3):95–98.
Brasil (2015). Lei nº 13.146, de 6 de julho de 2015. Lei Brasileira de Inclusão da Pessoa com Deficiência. Legislação federal.
Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.
Fitts, P. M. (1954). The information capacity of the human motor system in controlling the amplitude of movement. Journal of Experimental Psychology, 47(6):381–391.
Google (2026). MediaPipe Face Landmarker. Disponível em: [link].
Goulart, R. F. and Buiatti, R. C. (2025). Uso da visão computacional para desenvolver mouse virtual e controlar movimentos capturados pela webcam. Revista DELOS, 18(67):e5075.
Haseeb, M. A., Kyrarini, M., Jiang, S., Ristic-Durrant, D., and Gräser, A. (2018). Head gesture-based control for assistive robots. In Proceedings of the 11th PErvasive Technologies Related to Assistive Environments Conference (PETRA ’18), pages 379–383. ACM.
Kang, M.-J., Lee, J.-K., and Kang, J.-W. (2017). Combining random forest with multiblock local binary pattern feature selection for multiclass head pose estimation. PLOS ONE, 12(7):e0180792.
Lank, E., Cheng, Y.-C. N., and Ruiz, J. (2007). Endpoint prediction using motion kinematics. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’07), pages 637–646.
MacKenzie, I. S. (1992). Fitts’ law as a research and design tool in human-computer interaction. Human–Computer Interaction, 7(1):91–139.
McGuffin, M. and Balakrishnan, R. (2002). Acquisition of expanding targets. In CHI Conference on Human Factors in Computing Systems, pages 57–64.
Sairam, U., Gowra, D. K. R., and Kopparapu, S. C. (2022). Virtual mouse using machine learning and gui automation. In 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), volume 1, pages 1112–1117. IEEE.
Santos, J. D. M. et al. (2025). Visionhead: alternativa de uso do mouse para pessoas tetraplégicas utilizando visão computacional. In Anais do LII SEMISH 2025, pages 549–560. SBC.
Soukupová, T. and Čech, J. (2016). Real-time eye blink detection using facial landmarks. In Computer Vision Winter Workshop.
Wigdor, D. and Wixon, D. (2011). Brave NUI World: Designing Natural User Interfaces for Touch and Gesture. Morgan Kaufmann.
Worden, A. et al. (1997). Making computers easier for older adults to use: area cursors and sticky icons. In Proceedings of the ACM SIGCHI Conference, pages 266–271.
Brasil (2015). Lei nº 13.146, de 6 de julho de 2015. Lei Brasileira de Inclusão da Pessoa com Deficiência. Legislação federal.
Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.
Fitts, P. M. (1954). The information capacity of the human motor system in controlling the amplitude of movement. Journal of Experimental Psychology, 47(6):381–391.
Google (2026). MediaPipe Face Landmarker. Disponível em: [link].
Goulart, R. F. and Buiatti, R. C. (2025). Uso da visão computacional para desenvolver mouse virtual e controlar movimentos capturados pela webcam. Revista DELOS, 18(67):e5075.
Haseeb, M. A., Kyrarini, M., Jiang, S., Ristic-Durrant, D., and Gräser, A. (2018). Head gesture-based control for assistive robots. In Proceedings of the 11th PErvasive Technologies Related to Assistive Environments Conference (PETRA ’18), pages 379–383. ACM.
Kang, M.-J., Lee, J.-K., and Kang, J.-W. (2017). Combining random forest with multiblock local binary pattern feature selection for multiclass head pose estimation. PLOS ONE, 12(7):e0180792.
Lank, E., Cheng, Y.-C. N., and Ruiz, J. (2007). Endpoint prediction using motion kinematics. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’07), pages 637–646.
MacKenzie, I. S. (1992). Fitts’ law as a research and design tool in human-computer interaction. Human–Computer Interaction, 7(1):91–139.
McGuffin, M. and Balakrishnan, R. (2002). Acquisition of expanding targets. In CHI Conference on Human Factors in Computing Systems, pages 57–64.
Sairam, U., Gowra, D. K. R., and Kopparapu, S. C. (2022). Virtual mouse using machine learning and gui automation. In 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), volume 1, pages 1112–1117. IEEE.
Santos, J. D. M. et al. (2025). Visionhead: alternativa de uso do mouse para pessoas tetraplégicas utilizando visão computacional. In Anais do LII SEMISH 2025, pages 549–560. SBC.
Soukupová, T. and Čech, J. (2016). Real-time eye blink detection using facial landmarks. In Computer Vision Winter Workshop.
Wigdor, D. and Wixon, D. (2011). Brave NUI World: Designing Natural User Interfaces for Touch and Gesture. Morgan Kaufmann.
Worden, A. et al. (1997). Making computers easier for older adults to use: area cursors and sticky icons. In Proceedings of the ACM SIGCHI Conference, pages 266–271.
Publicado
23/09/2026
Como Citar
PEREIRA, Nataly B.; S. FILHO, José Valentim dos.
Controle de Mouse Virtual Assistivo por Movimentos da Cabeça. In: ESCOLA REGIONAL DE COMPUTAÇÃO BAHIA, ALAGOAS E SERGIPE (ERBASE), 26. , 2026, Maragogi/AL.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 121-130.
DOI: https://doi.org/10.5753/erbase.2026.32192.
