Descarte de Quadros para Redução do Atraso na Detecção de Objetos em Vídeos
Resumo
A detecção de objetos em tempo real é um desafio comum a diferentes aplicações, de carros autônomos à vigilância. Entretanto, o processamento de vídeos em tempo real exige um alto poder computacional, tornando comum a ocorrência de atrasos. Algumas dessas aplicações podem ser sensíveis a atrasos, tendo seu funcionamento prejudicado. Assim, este artigo propõe uma comparação de quadros sequenciais por meio da utilização dos valores RGB de cada pixel. Aqueles quadros que forem julgados semelhantes não serão enviados para processamento, o que diminui significativamente o tempo de processamento. Com os experimentos deste trabalho, pode-se observar uma redução no tempo de processamento de 41,5% com uma perda de precisão inferior a 13%.Referências
Aharon, S., Louis-Dupont, Ofri Masad, Yurkova, K., Lotem Fridman, Lkdci, Khvedchenya, E., Rubin, R., Bagrov, N., Tymchenko, B., Keren, T., Zhilko, A., and Eran-Deci (2021). Super-gradients.
Ashraf, A. H., Imran, M., Qahtani, A. M., Alsufyani, A., Almutiry, O., Mahmood, A., Attique, M., and Habib, M. (2022). Weapons detection for security and video surveillance using cnn and yolo-v5s. CMC-Comput. Mater. Contin, 70:2761–2775.
Ćorović, A., Ilić, V., Ðurić, S., Marijan, M., and Pavković, B. (2018). The real-time detection of traffic participants using yolo algorithm. In 2018 26th Telecommunications Forum (TELFOR), pages 1–4. IEEE.
Cristiani, A. L., Nespolo, R. G., Maschi, L. F. C., Nakamura, L., Ueyama, J., and Meneguette, R. I. (2018). Uma nova arquitetura para classificação de tráfego de véıculos baseado em processamento de imagens. In Anais do II Workshop de Computação Urbana, Porto Alegre, RS, Brasil. SBC.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255.
Fang, W., Wang, L., and Ren, P. (2019). Tinier-yolo: A real-time object detection method for constrained environments. IEEE Access, 8:1935–1944.
Frankle, J. and Carbin, M. (2019). The lottery ticket hypothesis: Finding sparse, trainable neural networks.
Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448.
He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969.
Huang, R., Pedoeem, J., and Chen, C. (2018). Yolo-lite: a real-time object detection algorithm optimized for non-gpu computers. In 2018 IEEE international conference on big data (big data), pages 2503–2510. IEEE.
Itseez (2015). Open source computer vision library. [link].
Jocher, G., Chaurasia, A., and Qiu, J. (2023). YOLO by Ultralytics.
Lan, W., Dang, J., Wang, Y., and Wang, S. (2018). Pedestrian detection based on yolo network model. In 2018 IEEE international conference on mechatronics and automation (ICMA), pages 1547–1551. IEEE.
Lee, J. and Hwang, K.-i. (2022). Yolo with adaptive frame control for real-time object detection applications. Multimedia Tools and Applications, 81(25):36375–36396.
Liang, S., Wu, H., Zhen, L., Hua, Q., Garg, S., Kaddoum, G., Hassan, M. M., and Yu, K. (2022). Edge yolo: Real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles. IEEE Transactions on Intelligent Transportation Systems, 23(12):25345–25360.
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer.
Lu, Y., Zhang, L., and Xie, W. (2020). Yolo-compact: an efficient yolo network for single category real-time object detection. In 2020 Chinese control and decision conference (CCDC), pages 1931–1936. IEEE.
Narejo, S., Pandey, B., Esenarro Vargas, D., Rodriguez, C., and Anjum, M. R. (2021). Weapon detection using yolo v3 for smart surveillance system. Mathematical Problems in Engineering, 2021:1–9.
Nguyen, H. H., Ta, T. N., Nguyen, N. C., Pham, H. M., Nguyen, D. M., et al. (2021). Yolo based real-time human detection for smart video surveillance at the edge. In 2020 IEEE Eighth International Conference on Communications and Electronics (ICCE), pages 439–444. IEEE.
Pacheco, R. and Couto, R. (2021). Particionamento de redes neurais profundas com saídas antecipadas. In Anais Estendidos do XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 169–176, Porto Alegre, RS, Brasil. SBC.
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.
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.
Shafiee, M. J., Chywl, B., Li, F., and Wong, A. (2017a). Fast yolo: A fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943.
Shafiee, M. J., Mishra, A., and Wong, A. (2017b). Deep learning with darwin: Evolutionary synthesis of deep neural networks.
Shang, X., Ren, T., Guo, J., Zhang, H., and Chua, T.-S. (2017). Video visual relation detection. In ACM International Conference on Multimedia, Mountain View, CA USA.
Shinde, S., Kothari, A., and Gupta, V. (2018). Yolo based human action recognition and localization. Procedia computer science, 133:831–838.
Van Der Walt, S., Colbert, S. C., and Varoquaux, G. (2011). The numpy array: a structure for efficient numerical computation. Computing in science & engineering, 13(2):22–30.
Zuraimi, M. A. B. and Zaman, F. H. K. (2021). Vehicle detection and tracking using yolo and deepsort. In 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), pages 23–29. IEEE.
Ashraf, A. H., Imran, M., Qahtani, A. M., Alsufyani, A., Almutiry, O., Mahmood, A., Attique, M., and Habib, M. (2022). Weapons detection for security and video surveillance using cnn and yolo-v5s. CMC-Comput. Mater. Contin, 70:2761–2775.
Ćorović, A., Ilić, V., Ðurić, S., Marijan, M., and Pavković, B. (2018). The real-time detection of traffic participants using yolo algorithm. In 2018 26th Telecommunications Forum (TELFOR), pages 1–4. IEEE.
Cristiani, A. L., Nespolo, R. G., Maschi, L. F. C., Nakamura, L., Ueyama, J., and Meneguette, R. I. (2018). Uma nova arquitetura para classificação de tráfego de véıculos baseado em processamento de imagens. In Anais do II Workshop de Computação Urbana, Porto Alegre, RS, Brasil. SBC.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255.
Fang, W., Wang, L., and Ren, P. (2019). Tinier-yolo: A real-time object detection method for constrained environments. IEEE Access, 8:1935–1944.
Frankle, J. and Carbin, M. (2019). The lottery ticket hypothesis: Finding sparse, trainable neural networks.
Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448.
He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969.
Huang, R., Pedoeem, J., and Chen, C. (2018). Yolo-lite: a real-time object detection algorithm optimized for non-gpu computers. In 2018 IEEE international conference on big data (big data), pages 2503–2510. IEEE.
Itseez (2015). Open source computer vision library. [link].
Jocher, G., Chaurasia, A., and Qiu, J. (2023). YOLO by Ultralytics.
Lan, W., Dang, J., Wang, Y., and Wang, S. (2018). Pedestrian detection based on yolo network model. In 2018 IEEE international conference on mechatronics and automation (ICMA), pages 1547–1551. IEEE.
Lee, J. and Hwang, K.-i. (2022). Yolo with adaptive frame control for real-time object detection applications. Multimedia Tools and Applications, 81(25):36375–36396.
Liang, S., Wu, H., Zhen, L., Hua, Q., Garg, S., Kaddoum, G., Hassan, M. M., and Yu, K. (2022). Edge yolo: Real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles. IEEE Transactions on Intelligent Transportation Systems, 23(12):25345–25360.
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer.
Lu, Y., Zhang, L., and Xie, W. (2020). Yolo-compact: an efficient yolo network for single category real-time object detection. In 2020 Chinese control and decision conference (CCDC), pages 1931–1936. IEEE.
Narejo, S., Pandey, B., Esenarro Vargas, D., Rodriguez, C., and Anjum, M. R. (2021). Weapon detection using yolo v3 for smart surveillance system. Mathematical Problems in Engineering, 2021:1–9.
Nguyen, H. H., Ta, T. N., Nguyen, N. C., Pham, H. M., Nguyen, D. M., et al. (2021). Yolo based real-time human detection for smart video surveillance at the edge. In 2020 IEEE Eighth International Conference on Communications and Electronics (ICCE), pages 439–444. IEEE.
Pacheco, R. and Couto, R. (2021). Particionamento de redes neurais profundas com saídas antecipadas. In Anais Estendidos do XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 169–176, Porto Alegre, RS, Brasil. SBC.
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.
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.
Shafiee, M. J., Chywl, B., Li, F., and Wong, A. (2017a). Fast yolo: A fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943.
Shafiee, M. J., Mishra, A., and Wong, A. (2017b). Deep learning with darwin: Evolutionary synthesis of deep neural networks.
Shang, X., Ren, T., Guo, J., Zhang, H., and Chua, T.-S. (2017). Video visual relation detection. In ACM International Conference on Multimedia, Mountain View, CA USA.
Shinde, S., Kothari, A., and Gupta, V. (2018). Yolo based human action recognition and localization. Procedia computer science, 133:831–838.
Van Der Walt, S., Colbert, S. C., and Varoquaux, G. (2011). The numpy array: a structure for efficient numerical computation. Computing in science & engineering, 13(2):22–30.
Zuraimi, M. A. B. and Zaman, F. H. K. (2021). Vehicle detection and tracking using yolo and deepsort. In 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), pages 23–29. IEEE.
Publicado
20/05/2024
Como Citar
ANTUNES, Hugo; COUTO, Rodrigo S.; CRUZ, Pedro.
Descarte de Quadros para Redução do Atraso na Detecção de Objetos em Vídeos. In: WORKSHOP DE COMPUTAÇÃO URBANA (COURB), 8. , 2024, Niterói/RJ.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 57-70.
ISSN 2595-2706.
DOI: https://doi.org/10.5753/courb.2024.2887.
