Um Estudo de Caso da Detecção do Uso de Máscaras Faciais com Redes Neurais Convolucionais Regionais
Resumo
Com o objetivo de desenvolver soluções para Cidades Inteligentes que colaborem na mitigação da propagação de doenças, este trabalho considerou o problema de Visão Computacional de detecção do uso de máscaras faciais, o qual foi abordado com os modelos YOLOv3 e YOLOv5 em um estudo de caso com três conjuntos de dados distintos e realísticos. Os resultados experimentais destacaram o YOLOv5 Small 6 como a solução de referência com um mAP de 92,8 % em um cenário de validação com exemplos unificados. Também foi realizada uma transferência de aprendizado desse modelo com imagens do conjunto de dados AIZOO e os resultados foram comparados com soluções da literatura, em que verificou-se competitivo com as alternativas do estado da arte e com forte potencial para ser embarcado em dispositivos computacionais com recursos limitados.
Palavras-chave:
Visão Computacional, Aprendizado Profundo, Cidades Inteligentes
Referências
AIZOOTech (2022). Face mask detection. Disponível em https://github.com/AIZOOTech/FaceMaskDetection. Acesso em 18 de maio de 2022.
Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. Disponível em https://arxiv.org/abs/2004.10934. Acesso em 18 de maio de 2022.
Costa, D. G. and Peixoto, J. P. J. (2020). COVID-19 pandemic: a review of smart cities initiatives to face new outbreaks. IET Smart Cities, 2(2):64–73.
Deng, J., Guo, J., Ververas, E., Kotsia, I., and Zafeiriou, S. (2020). RetinaFace: Single-Shot Multi-Level face localisation in the wild. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE.
Du, R., Santi, P., Xiao, M., Vasilakos, A. V., and Fischione, C. (2019). The sensable city: A survey on the deployment and management for smart city monitoring. IEEE Commun. Surv. Tutor., 21(2):1533–1560.
Fan, X. and Jiang, M. (2021). Retinafacemask: A single stage face mask detector for assisting control of the covid-19 pandemic. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pages 832–837.
Fan, X., Jiang, M., and Yan, H. (2021). A deep learning based light-weight face mask detector with residual context attention and gaussian heatmap to fight against COVID-19. IEEE Access, 9:96964–96974.
Ge, S., Li, J., Ye, Q., and Luo, Z. (2017). Detecting masked faces in the wild with lle-cnns. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 426–434. Disponível em 10.1109/CVPR.2017.53. Acesso em 18 de maio de 2022.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT press.
JHU (2019). Johns Hopkins University (JHU) COVID-19 dashboard (COVID-19) pandemic. Disponível em https://coronavirus.jhu.edu/map.html. Acesso em 18 de maio de 2022.
Jocher, G., Stoken, A., Borovec, J., NanoCode012, ChristopherSTAN, Changyu, L., Laughing, tkianai, Hogan, A., lorenzomammana, yxNONG, AlexWang1900, Diaconu, L., Marc, wanghaoyang0106, ml5ah, Doug, Ingham, F., Frederik, Guilhen, Hatovix, Poznanski, J., Fang, J., Yu, L., changyu98, Wang, M., Gupta, N., Akhtar, O., PetrDvoracek, and Rai, P. (2020). ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements. Disponível em https://doi.org/10.5281/zenodo.4154370. Acesso em 18 de maio de 2022.
Khan, S., Rahmani, H., Shah, S., and Bennamoun, M. (2018). A Guide to Convolutional Neural Networks for Computer Vision. Number 1 in Synthesis Lectures on Computer Vision. Morgan & Claypool Publishers.
Kwon, S., Joshi, A. D., Lo, C.-H., Drew, D. A., Nguyen, L. H., Guo, C.-G., Ma, W., Mehta, R. S., Shebl, F. M., Warner, E. T., Astley, C. M., Merino, J., Murray, B., Wolf, J., Ourselin, S., Steves, C. J., Spector, T. D., Hart, J. E., Song, M., VoPham, T., and Chan, A. T. (2021). Association of social distancing and face mask use with risk of COVID-19. Nat. Commun., 12(1):3737.
Loey, M., Manogaran, G., Taha, M. H. N., and Khalifa, N. E. M. (2021). Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection. Sustain. Cities Soc., 65(102600):102600.
Lorenzo, A. (2020). MaskDetection at YOLO format. Disponível em https://www.kaggle.com/alexandralorenzo/maskdetection/version/6. Acesso em 18 de maio de 2022.
Mahurkar, R. R. and Gadge, N. G. (2021). Real-time covid-19 face mask detection with YOLOv4. In 2021 Second International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE.
MakeML (2020). Mask dataset. Disponível em https://makeml.app/datasets/ mask. Acesso em 18 de maio de 2022.
Nieto-Rodríguez, A., Mucientes, M., and Brea, V. M. (2015). System for medical mask detection in the operating room through facial attributes. In Pattern Recognition and Image Analysis, Lecture notes in computer science, pages 138–145. Springer International Publishing, Cham.
Nowrin, A., Afroz, S., Rahman, M. S., Mahmud, I., and Cho, Y.-Z. (2021). Comprehensive review on facemask detection techniques in the context of covid-19. IEEE Access, 9:106839–106864. Disponível em 10.1109/ACCESS.2021.3100070.
OMS (2019). Coronavirus disease (COVID-19) pandemic. Disponível em https://www.who.int/emergencies/diseases/novel-coronavirus-2019. Acesso em 18 de maio de 2022.
ONU (2018). TheWorld’s Cities in 2018, volume 1. Department of Economical and Social Affairs – Population Dynamics. Disponível em https://population.un.org/wup/Publications/. Acesso em 18 de maio de 2022.
Padilla, R., Netto, S. L., and da Silva, E. A. B. (2020). A Survey on Performance Metrics for Object-Detection Algorithms. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), pages 237–242, Niterói, Brasil.
Prather, K. A., Wang, C. C., and Schooley, R. T. (2020). Reducing transmission of SARSCoV-2. Science, 368(6498):1422–1424.
Purohit, A. (2020). Face mask dataset. Disponível em https://www.kaggle.com/aditya276/face-mask-dataset-yolo-format/version/2. Acesso em 18 de maio de 2022.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788.
Redmon, J. and Farhadi, A. (2017). Yolo9000: Better, faster, stronger. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 6517–6525, Estados Unidos.
Redmon, J. and Farhadi, A. (2018). Yolov3: An incremental improvement. Disponível em https://arxiv.org/abs/1804.02767. Acesso em 18 de maio de 2022.
Shorfuzzaman, M., Hossain, M. S., and Alhamid, M. F. (2021). Towards the sustainable development of smart cities through mass video surveillance: A response to the COVID-19 pandemic. Sustain. Cities Soc., 64(102582):102582.
Singh, S., Ahuja, U., Kumar, M., Kumar, K., and Sachdeva, M. (2021). Face mask detection using YOLOv3 and faster R-CNN models: COVID-19 environment. Multimed. Tools Appl., 80(13):1–16.
Srivastava, N., Baxi, P., Ratho, R. K., and Saxena, S. K. (2020). Global trends in epidemiology of coronavirus disease 2019 (COVID-19). In Medical Virology: From Pathogenesis to Disease Control, pages 9–21. Springer Singapore.
Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, volume 1, pages I–I. Disponível em 10. 1109/CVPR.2001.990517. Acesso em 18 de maio de 2022.
Yang, G., Feng, W., Jin, J., Lei, Q., Li, X., Gui, G., and Wang, W. (2020). Face mask recognition system with YOLOV5 based on image recognition. In 2020 IEEE 6th International Conference on Computer and Communications (ICCC). IEEE.
Yang, S., Luo, P., Loy, C. C., and Tang, X. (2016). WIDER FACE: A face detection benchmark. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE.
Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. Disponível em https://arxiv.org/abs/2004.10934. Acesso em 18 de maio de 2022.
Costa, D. G. and Peixoto, J. P. J. (2020). COVID-19 pandemic: a review of smart cities initiatives to face new outbreaks. IET Smart Cities, 2(2):64–73.
Deng, J., Guo, J., Ververas, E., Kotsia, I., and Zafeiriou, S. (2020). RetinaFace: Single-Shot Multi-Level face localisation in the wild. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE.
Du, R., Santi, P., Xiao, M., Vasilakos, A. V., and Fischione, C. (2019). The sensable city: A survey on the deployment and management for smart city monitoring. IEEE Commun. Surv. Tutor., 21(2):1533–1560.
Fan, X. and Jiang, M. (2021). Retinafacemask: A single stage face mask detector for assisting control of the covid-19 pandemic. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pages 832–837.
Fan, X., Jiang, M., and Yan, H. (2021). A deep learning based light-weight face mask detector with residual context attention and gaussian heatmap to fight against COVID-19. IEEE Access, 9:96964–96974.
Ge, S., Li, J., Ye, Q., and Luo, Z. (2017). Detecting masked faces in the wild with lle-cnns. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 426–434. Disponível em 10.1109/CVPR.2017.53. Acesso em 18 de maio de 2022.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT press.
JHU (2019). Johns Hopkins University (JHU) COVID-19 dashboard (COVID-19) pandemic. Disponível em https://coronavirus.jhu.edu/map.html. Acesso em 18 de maio de 2022.
Jocher, G., Stoken, A., Borovec, J., NanoCode012, ChristopherSTAN, Changyu, L., Laughing, tkianai, Hogan, A., lorenzomammana, yxNONG, AlexWang1900, Diaconu, L., Marc, wanghaoyang0106, ml5ah, Doug, Ingham, F., Frederik, Guilhen, Hatovix, Poznanski, J., Fang, J., Yu, L., changyu98, Wang, M., Gupta, N., Akhtar, O., PetrDvoracek, and Rai, P. (2020). ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements. Disponível em https://doi.org/10.5281/zenodo.4154370. Acesso em 18 de maio de 2022.
Khan, S., Rahmani, H., Shah, S., and Bennamoun, M. (2018). A Guide to Convolutional Neural Networks for Computer Vision. Number 1 in Synthesis Lectures on Computer Vision. Morgan & Claypool Publishers.
Kwon, S., Joshi, A. D., Lo, C.-H., Drew, D. A., Nguyen, L. H., Guo, C.-G., Ma, W., Mehta, R. S., Shebl, F. M., Warner, E. T., Astley, C. M., Merino, J., Murray, B., Wolf, J., Ourselin, S., Steves, C. J., Spector, T. D., Hart, J. E., Song, M., VoPham, T., and Chan, A. T. (2021). Association of social distancing and face mask use with risk of COVID-19. Nat. Commun., 12(1):3737.
Loey, M., Manogaran, G., Taha, M. H. N., and Khalifa, N. E. M. (2021). Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection. Sustain. Cities Soc., 65(102600):102600.
Lorenzo, A. (2020). MaskDetection at YOLO format. Disponível em https://www.kaggle.com/alexandralorenzo/maskdetection/version/6. Acesso em 18 de maio de 2022.
Mahurkar, R. R. and Gadge, N. G. (2021). Real-time covid-19 face mask detection with YOLOv4. In 2021 Second International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE.
MakeML (2020). Mask dataset. Disponível em https://makeml.app/datasets/ mask. Acesso em 18 de maio de 2022.
Nieto-Rodríguez, A., Mucientes, M., and Brea, V. M. (2015). System for medical mask detection in the operating room through facial attributes. In Pattern Recognition and Image Analysis, Lecture notes in computer science, pages 138–145. Springer International Publishing, Cham.
Nowrin, A., Afroz, S., Rahman, M. S., Mahmud, I., and Cho, Y.-Z. (2021). Comprehensive review on facemask detection techniques in the context of covid-19. IEEE Access, 9:106839–106864. Disponível em 10.1109/ACCESS.2021.3100070.
OMS (2019). Coronavirus disease (COVID-19) pandemic. Disponível em https://www.who.int/emergencies/diseases/novel-coronavirus-2019. Acesso em 18 de maio de 2022.
ONU (2018). TheWorld’s Cities in 2018, volume 1. Department of Economical and Social Affairs – Population Dynamics. Disponível em https://population.un.org/wup/Publications/. Acesso em 18 de maio de 2022.
Padilla, R., Netto, S. L., and da Silva, E. A. B. (2020). A Survey on Performance Metrics for Object-Detection Algorithms. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), pages 237–242, Niterói, Brasil.
Prather, K. A., Wang, C. C., and Schooley, R. T. (2020). Reducing transmission of SARSCoV-2. Science, 368(6498):1422–1424.
Purohit, A. (2020). Face mask dataset. Disponível em https://www.kaggle.com/aditya276/face-mask-dataset-yolo-format/version/2. Acesso em 18 de maio de 2022.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788.
Redmon, J. and Farhadi, A. (2017). Yolo9000: Better, faster, stronger. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 6517–6525, Estados Unidos.
Redmon, J. and Farhadi, A. (2018). Yolov3: An incremental improvement. Disponível em https://arxiv.org/abs/1804.02767. Acesso em 18 de maio de 2022.
Shorfuzzaman, M., Hossain, M. S., and Alhamid, M. F. (2021). Towards the sustainable development of smart cities through mass video surveillance: A response to the COVID-19 pandemic. Sustain. Cities Soc., 64(102582):102582.
Singh, S., Ahuja, U., Kumar, M., Kumar, K., and Sachdeva, M. (2021). Face mask detection using YOLOv3 and faster R-CNN models: COVID-19 environment. Multimed. Tools Appl., 80(13):1–16.
Srivastava, N., Baxi, P., Ratho, R. K., and Saxena, S. K. (2020). Global trends in epidemiology of coronavirus disease 2019 (COVID-19). In Medical Virology: From Pathogenesis to Disease Control, pages 9–21. Springer Singapore.
Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, volume 1, pages I–I. Disponível em 10. 1109/CVPR.2001.990517. Acesso em 18 de maio de 2022.
Yang, G., Feng, W., Jin, J., Lei, Q., Li, X., Gui, G., and Wang, W. (2020). Face mask recognition system with YOLOV5 based on image recognition. In 2020 IEEE 6th International Conference on Computer and Communications (ICCC). IEEE.
Yang, S., Luo, P., Loy, C. C., and Tang, X. (2016). WIDER FACE: A face detection benchmark. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE.
Publicado
31/07/2022
Como Citar
MEDEIROS, Diego Lucena de; GUEDES, Elloá B.; FIGUEIREDO, Carlos Maurício S..
Um Estudo de Caso da Detecção do Uso de Máscaras Faciais com Redes Neurais Convolucionais Regionais. In: WORKSHOP BRASILEIRO DE CIDADES INTELIGENTES (WBCI), 3. , 2022, Niterói.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 131-142.
DOI: https://doi.org/10.5753/wbci.2022.223107.
