Rastreamento e contagem de pedestre em tempo real por meio de imagens digitais
Resumo
Este trabalho apresenta o uso de dois modelos neurais trabalhando em conjunto a fim de efetuar a tarefa de detecção de pedestres, rastreamento e contagem por meio de imagens digitais. A ideia é poder mensurar a quantidade de pessoas em um determinado local. Foi utilizado uma rede de classificação para efetuar a detecção dos pedestre e repassado as coordenadas das detecções para uma rede de rastreamento, possibilitando definir sua trajetória e assim efetuar a contagem referente a entrada ou saída do pedestre de um determinado local.
Palavras-chave:
Rastreamento, Contagem de pedestre, Detecção pedestre, Redes convolucionais, Deep Learning
Referências
Xu, Zheng and Hu, Chuanping and Mei, Lin, Video structured description technology based intelligence analysis of surveillance videos for public security applications, Multimedia Tools and Applications, p. 12155-12172, V. 75, 2016. Disponível em https://link.springer.com/article/10.1007/s11042-015-3112-5
O. Sidla and Y. Lypetskyy and N. Brandle and S. Seer, Pedestrian Detection and Tracking for Counting Applications in Crowded Situations, IEEE International Conference on Video and Signal Based Surveillance, p. 70, 2006. Disponível em https://ieeexplore.ieee.org/document/4020729
A. Broggi and P. Cerri and S. Ghidoni and P. Grisleri and H. G. Jung, A New Approach to Urban Pedestrian Detection for Automatic Braking, IEEE Transactions on Intelligent Transportation Systems, p. 594-605, V. 10, 2009. Disponível em https://ieeexplore.ieee.org/document/5290131
A. Velastin and B. A. Boghossian and B. P. L. Lo and Jie Sun and M. A. Vicencio-Silva, PRISMATICA: toward ambient intelligence in public transport environments, IEEE Transactions on Systems, p. 164-182, V. 35, 2005. Disponível em https://ieeexplore.ieee.org/document/1369353
Joseph Redmon and Ali Farhadi, YOLOv3: An Incremental Improvement, CoRR, Vol. abs/1804.02767, 2018. Disponível em https://arxiv.org/abs/1804.02767
Joseph Redmon and Ali Farhadi, YOLO9000: Better, Faster, Stronger, CoRR, Vol. abs/1612.08242, 2016. Disponível em http://arxiv.org/abs/1612.08242
Joseph Redmon and Ali Farhadi, You Only Look Once: Unified, Real-Time Object Detection, CoRR, Vol. abs/1506.02640, 2016. Disponível em http://arxiv.org/abs/1506.02640
Wang, Naiyan and Yeung, Dit-Yan Learning a deep compact image representation for visual tracking.
Martin Danelljan and Gustav Hager and Fahad Shahbaz Khan and Michael Felsberg, Accurate Scale Estimation for Robust Visual Tracking, British Machine Vision Conference, 2014. Disponível em http://www.bmva.org/bmvc/2014/files/paper038.pdf
Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra Rich feature hierarchies for accurate object detection and semantic segmentation.
Dollar, Piotr and Wojek, Christian and Schiele, Bernt and Perona, Pietro. Pedestrian detection: An evaluation of the state of the art.
Wang, Naiyan and Yeung, Dit-Yan. Learning a deep compact image representation for visual tracking.
Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., & Zitnick, C. L. (2014, September). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740-755). Springer, Cham.
O. Sidla and Y. Lypetskyy and N. Brandle and S. Seer, Pedestrian Detection and Tracking for Counting Applications in Crowded Situations, IEEE International Conference on Video and Signal Based Surveillance, p. 70, 2006. Disponível em https://ieeexplore.ieee.org/document/4020729
A. Broggi and P. Cerri and S. Ghidoni and P. Grisleri and H. G. Jung, A New Approach to Urban Pedestrian Detection for Automatic Braking, IEEE Transactions on Intelligent Transportation Systems, p. 594-605, V. 10, 2009. Disponível em https://ieeexplore.ieee.org/document/5290131
A. Velastin and B. A. Boghossian and B. P. L. Lo and Jie Sun and M. A. Vicencio-Silva, PRISMATICA: toward ambient intelligence in public transport environments, IEEE Transactions on Systems, p. 164-182, V. 35, 2005. Disponível em https://ieeexplore.ieee.org/document/1369353
Joseph Redmon and Ali Farhadi, YOLOv3: An Incremental Improvement, CoRR, Vol. abs/1804.02767, 2018. Disponível em https://arxiv.org/abs/1804.02767
Joseph Redmon and Ali Farhadi, YOLO9000: Better, Faster, Stronger, CoRR, Vol. abs/1612.08242, 2016. Disponível em http://arxiv.org/abs/1612.08242
Joseph Redmon and Ali Farhadi, You Only Look Once: Unified, Real-Time Object Detection, CoRR, Vol. abs/1506.02640, 2016. Disponível em http://arxiv.org/abs/1506.02640
Wang, Naiyan and Yeung, Dit-Yan Learning a deep compact image representation for visual tracking.
Martin Danelljan and Gustav Hager and Fahad Shahbaz Khan and Michael Felsberg, Accurate Scale Estimation for Robust Visual Tracking, British Machine Vision Conference, 2014. Disponível em http://www.bmva.org/bmvc/2014/files/paper038.pdf
Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra Rich feature hierarchies for accurate object detection and semantic segmentation.
Dollar, Piotr and Wojek, Christian and Schiele, Bernt and Perona, Pietro. Pedestrian detection: An evaluation of the state of the art.
Wang, Naiyan and Yeung, Dit-Yan. Learning a deep compact image representation for visual tracking.
Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., & Zitnick, C. L. (2014, September). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740-755). Springer, Cham.
Publicado
27/11/2019
Como Citar
CORDEIRO, Alexssandro Ferreira; P. FILHO, Pedro L. ; OJEDA, Cristian A. U. ; VALIATI, Gustavo R. .
Rastreamento e contagem de pedestre em tempo real por meio de imagens digitais. In: CONGRESSO LATINO-AMERICANO DE SOFTWARE LIVRE E TECNOLOGIAS ABERTAS (LATINOWARE), 16. , 2019, Foz do Iguaçu.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 146-149.
DOI: https://doi.org/10.5753/latinoware.2019.10350.
