Avaliação de Técnicas de Detecção de Pedestres para Veículos Autônomos
Resumo
A detecção de objetos é uma das principais aplicações dentro do contexto dos Veículos Autônomos (AVs). As aplicações de detecção de pedestres compõem a camada de percepção veicular, utilizando sensores e câmeras para detectar a presença de objetos na área próxima ao AV. No entanto, as técnicas de detecção de pedestre apresentam limitações e restrições de acordo com o comportamento do cenário veicular, principalmente devido à variação das condições de iluminação e o tamanho dos pedestres. Nesse contexto, este artigo apresenta um estudo comparativo das principais técnicas de detecção de pedestre para AVs. A avaliação considera quatro tipos de técnicas de detecção, sendo eles: Faster R-CNN, SSD, YOLO e RetinaNet. Os resultados da avaliação indicam que as abordagens YOLO e Faster R-CNN obtiveram desempenho superior em termos de tempo de processamento e detecção de pedestres, apresentando uma média de detecção de 0,58 segundos por imagem.
Referências
Chai, T. and Draxler, R. R. (2014). Root mean square error (rmse) or mean absolute error (mae)?–arguments against avoiding rmse in the literature. Geoscientific model development, 7(3):1247–1250.
Dollar, P., Wojek, C., Schiele, B., and Perona, P. (2011). Pedestrian detection: An evaluation of the state of the art. IEEE transactions on pattern analysis and machine intelligence, 34(4):743–761.
Everingham, M., Van Gool, L., Williams, C. K., Winn, J., and Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International journal of computer vision.
Garlichs, K., Wegner, M., and Wolf, L. C. (2018). Realizing collective perception in the artery simulation framework. In IEEE Vehicular Networking Conference (VNC), pages 1–4. IEEE.
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2015). Rich feature hierarchies for accurate object detection and semantic segmentation. In IEEE International Conference on Computer Vision (ICCV), pages 1440–1448. arXiv.
Hussain, R. and Zeadally, S. (2018). Autonomous cars: Research results, issues and future challenges. IEEE Communications Surveys & Tutorials.
Kim, J.-a., Sung, J.-Y., and Park, S.-h. (2020). Comparison of faster-rcnn, yolo, and ssd for real-time vehicle type recognition. In 2020 IEEE international conference on consumer electronics-Asia (ICCE-Asia), pages 1–4.
Krijestorac, E., Memedi, A., Higuchi, T., Ucar, S., Altintas, O., and Cabric, D. (2020). Hybrid vehicular and cloud distributed computing: A case for cooperative perception. In IEEE Global Communications Conference (GLOBECOM), pages 1–6. IEEE.
Liang, M., Yang, B., Wang, S., and Urtasun, R. (2018). Deep continuous fusion for multisensor 3d object detection. In Proceedings of the European conference on computer vision (ECCV), pages 641–656.
Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2020). Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2):318–327.
Liu, S., Tang, J., Zhang, Z., and Gaudiot, J.-L. (2017). Computer architectures for autonomous driving. Computer, 50(8):18–25.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A. C. (2016). SSD: Single shot MultiBox detector. In Computer Vision – ECCV 2016, pages 21–37. Springer International Publishing.
Lobato, W., Mendes, P., Rosário, D., Cerqueira, E., and Villas, L. A. (2023). Redundancy mitigation mechanism for collective perception in connected and autonomous vehicles. Future Internet, 15(2):41.
maintainers, T. and contributors (2016). Torchvision: Pytorch’s computer vision library. GitHub repository.
Pendleton, S., Andersen, H., Du, X., Shen, X., Meghjani, M., Eng, Y., Rus, D., and Ang, M. (2017). Perception, planning, control, and coordination for autonomous vehicles. Machines, 5(1):6.
Rahmad, C., Asmara, R. A., Putra, D. R. H., Dharma, I., Darmono, H., and Muhiqqin, I. (2020). Comparison of viola-jones haar cascade classifier and histogram of oriented gradients (hog) for face detection. IOP Conference Series: Materials Science and Engineering, 732(1):012038.
Rasouli, A. and Tsotsos, J. K. (2020). Autonomous vehicles that interact with pedestrians: A survey of theory and practice. IEEE Transactions on Intelligent Transportation Systems, 21(3):900–918.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788. IEEE Computer Society.
Saleh, K., Hossny, M., and Nahavandi, S. (2020). Spatio-temporal densenet for real-time intent prediction of pedestrians in urban traffic environments. Neurocomputing, 386:317–324.
Tan, M. and Le, Q. V. (2021). Efficientnetv2: Smaller models and faster training.
Vora, S., Lang, A. H., Helou, B., and Beijbom, O. (2020). Pointpainting: Sequential fusion for 3d object detection. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4603–4611, Los Alamitos, CA, USA. IEEE Computer Society.
Wang, J., Liu, J., and Kato, N. (2018). Networking and communications in autonomous driving: a survey. IEEE Communications Surveys & Tutorials.
Xu, W., Zhou, H., Cheng, N., Lyu, F., Shi, W., Chen, J., and Shen, X. (2017). Internet of vehicles in big data era. IEEE/CAA Journal of Automatica Sinica, 5(1):19–35.
Yang, Q., Fu, S., Wang, H., and Fang, H. (2021). Machine-learning-enabled cooperative perception for connected autonomous vehicles: Challenges and opportunities. IEEE Network, 35(3):96–101.
Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., and Hoi, S. C. (2021). Deep learning for person re-identification: A survey and outlook. IEEE transactions on pattern analysis and machine intelligence, 44(6):2872–2893.
Dollar, P., Wojek, C., Schiele, B., and Perona, P. (2011). Pedestrian detection: An evaluation of the state of the art. IEEE transactions on pattern analysis and machine intelligence, 34(4):743–761.
Everingham, M., Van Gool, L., Williams, C. K., Winn, J., and Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International journal of computer vision.
Garlichs, K., Wegner, M., and Wolf, L. C. (2018). Realizing collective perception in the artery simulation framework. In IEEE Vehicular Networking Conference (VNC), pages 1–4. IEEE.
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2015). Rich feature hierarchies for accurate object detection and semantic segmentation. In IEEE International Conference on Computer Vision (ICCV), pages 1440–1448. arXiv.
Hussain, R. and Zeadally, S. (2018). Autonomous cars: Research results, issues and future challenges. IEEE Communications Surveys & Tutorials.
Kim, J.-a., Sung, J.-Y., and Park, S.-h. (2020). Comparison of faster-rcnn, yolo, and ssd for real-time vehicle type recognition. In 2020 IEEE international conference on consumer electronics-Asia (ICCE-Asia), pages 1–4.
Krijestorac, E., Memedi, A., Higuchi, T., Ucar, S., Altintas, O., and Cabric, D. (2020). Hybrid vehicular and cloud distributed computing: A case for cooperative perception. In IEEE Global Communications Conference (GLOBECOM), pages 1–6. IEEE.
Liang, M., Yang, B., Wang, S., and Urtasun, R. (2018). Deep continuous fusion for multisensor 3d object detection. In Proceedings of the European conference on computer vision (ECCV), pages 641–656.
Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2020). Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2):318–327.
Liu, S., Tang, J., Zhang, Z., and Gaudiot, J.-L. (2017). Computer architectures for autonomous driving. Computer, 50(8):18–25.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A. C. (2016). SSD: Single shot MultiBox detector. In Computer Vision – ECCV 2016, pages 21–37. Springer International Publishing.
Lobato, W., Mendes, P., Rosário, D., Cerqueira, E., and Villas, L. A. (2023). Redundancy mitigation mechanism for collective perception in connected and autonomous vehicles. Future Internet, 15(2):41.
maintainers, T. and contributors (2016). Torchvision: Pytorch’s computer vision library. GitHub repository.
Pendleton, S., Andersen, H., Du, X., Shen, X., Meghjani, M., Eng, Y., Rus, D., and Ang, M. (2017). Perception, planning, control, and coordination for autonomous vehicles. Machines, 5(1):6.
Rahmad, C., Asmara, R. A., Putra, D. R. H., Dharma, I., Darmono, H., and Muhiqqin, I. (2020). Comparison of viola-jones haar cascade classifier and histogram of oriented gradients (hog) for face detection. IOP Conference Series: Materials Science and Engineering, 732(1):012038.
Rasouli, A. and Tsotsos, J. K. (2020). Autonomous vehicles that interact with pedestrians: A survey of theory and practice. IEEE Transactions on Intelligent Transportation Systems, 21(3):900–918.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788. IEEE Computer Society.
Saleh, K., Hossny, M., and Nahavandi, S. (2020). Spatio-temporal densenet for real-time intent prediction of pedestrians in urban traffic environments. Neurocomputing, 386:317–324.
Tan, M. and Le, Q. V. (2021). Efficientnetv2: Smaller models and faster training.
Vora, S., Lang, A. H., Helou, B., and Beijbom, O. (2020). Pointpainting: Sequential fusion for 3d object detection. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4603–4611, Los Alamitos, CA, USA. IEEE Computer Society.
Wang, J., Liu, J., and Kato, N. (2018). Networking and communications in autonomous driving: a survey. IEEE Communications Surveys & Tutorials.
Xu, W., Zhou, H., Cheng, N., Lyu, F., Shi, W., Chen, J., and Shen, X. (2017). Internet of vehicles in big data era. IEEE/CAA Journal of Automatica Sinica, 5(1):19–35.
Yang, Q., Fu, S., Wang, H., and Fang, H. (2021). Machine-learning-enabled cooperative perception for connected autonomous vehicles: Challenges and opportunities. IEEE Network, 35(3):96–101.
Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., and Hoi, S. C. (2021). Deep learning for person re-identification: A survey and outlook. IEEE transactions on pattern analysis and machine intelligence, 44(6):2872–2893.
Publicado
06/08/2023
Como Citar
REIS, Gabriel; LOBATO, Wellington; ROSÁRIO, Denis; CERQUEIRA, Eduardo; VILLAS, Leandro A..
Avaliação de Técnicas de Detecção de Pedestres para Veículos Autônomos. In: WORKSHOP EM DESEMPENHO DE SISTEMAS COMPUTACIONAIS E DE COMUNICAÇÃO (WPERFORMANCE), 22. , 2023, João Pessoa/PB.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 61-72.
ISSN 2595-6167.
DOI: https://doi.org/10.5753/wperformance.2023.230699.
