Reusing TV Boxes for People Counting Applications at the Edge in Smart Cities

• Gabriel Massuyoshi Sato UNICAMP
• Gustavo P. C. P da Luz UNICAMP
• Luis Fernando Gomez Gonzalez UNICAMP
• Juliana Freitag Borin UNICAMP

DOI: https://doi.org/10.5753/courb.2024.3375

Abstract

In recent years, large quantities of illegal TV Box equipment have been confiscated in Brazil. According to news released in March of this year, it is estimated that there are around 2.5 million TV Boxes in the warehouses of the Federal Revenue Service. On the other hand, the advancement of smart cities applications based on Internet of Things (IoT) and machine learning has driven research in edge computing using hardware-constrained devices. This article presents a study on the feasibility of repurposing TV Boxes for edge computing in an application of people counting from images collected by cameras. A comparison between the performance of 2 models of TV Boxes and widely used hardware in IoT solutions during the execution of the YOLOv8 and EfficientDet deep learning models demonstrates this feasibility.

References

Artstein, R. (2017). Inter-annotator agreement. Handbook of linguistic annotation, pages 297–313.

Band, S. S., Ardabili, S., Sookhak, M., Chronopoulos, A. T., Elnaffar, S., Moslehpour, M., Csaba, M., Torok, B., Pai, H.-T., and Mosavi, A. (2022). When smart cities get smarter via machine learning: An in-depth literature review. IEEE Access, 10:60985–61015.

Collini, E., Palesi, L. A. I., Nesi, P., Pantaleo, G., and Zhao, W. (2024). Flexible thermal camera solution for smart city people detection and counting. Multimedia Tools and Applications, 83(7):20457–20485.

de Carvalho Borges, I. G. C. and Borin, J. F. (2023). Abordagens para Superar Limitações de Hardware em TV Box RK3229 para uso em IoT. Technical Report IC-PFG-23-48, Instituto de Computação, Universidade Estadual de Campinas.

Eisenstein, M. (2022). Short-circuiting the electronic-waste crisis. Nature, 611:8–10.

Gao, M., Souri, A., Zaker, M., Zhai, W., Guo, X., and Li, Q. (2024). A comprehensive analysis for crowd counting methodologies and algorithms in internet of things. Cluster Computing, (27):859–873.

Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Iandola, F. N., Moskewicz, M. W., Ashraf, K., Han, S., Dally, W. J., and Keutzer, K. (2016). Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <1mb model size. CoRR, abs/1602.07360.

Jocher, G., Chaurasia, A., and Qiu, J. (2023). Ultralytics YOLO.

Kaggle Hub Models. [link]. Acessado em 03/04/2024.

Khan, L. U., Yaqoob, I., Tran, N. H., Kazmi, S. M. A., Dang, T. N., and Hong, C. S. (2020). Edge-computing-enabled smart cities: A comprehensive survey. IEEE Internet of Things Journal, 7(10):10200–10232.

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Commun. ACM, 60(6):84–90.

Mohd Razif, M. H., Ismail, A. P., Che Abdullah, S. A., Shafie, M. A., Isa, I. S., Sulaiman, S. N., and Che Soh, Z. H. (2024). On edge crowd traffic counting system using deep learning on jetson nano for smart retail environment. Journal of Advanced Research in Applied Sciences and Engineering Technology, 42(1):1–13.

Monti, L., Tse, R., Tang, S.-K., Mirri, S., Delnevo, G., Maniezzo, V., and Salomoni, P. (2022). Edge-based transfer learning for classroom occupancy detection in a smart campus context. Sensors, 22(10).

Moreira, R., Rodrigues Moreira, L. F., Munhoz, P. L. A., Lopes, E. A., and Ruas, R. A. A. (2022). Agrolens: A low-cost and green-friendly smart farm architecture to support real-time leaf disease diagnostics. Internet of Things, 19:100570.

Morseletto, P. (2020). Targets for a circular economy. Resources, conservation and recycling, 153:104553.

Nations, U. (2015). Transforming our world: The 2030 agenda for sustainable development. New York: United Nations, Department of Economic and Social Affairs, 1:41.

Prefeitura Universitária Unicamp. [link]. Acessado em 03/04/2024.

Redmon, J. and Farhadi, A. (2018). Yolov3: An incremental improvement. CoRR, abs/1804.02767.

Ribeiro, A. F., Yoshioka, D. D. K., Ramirez, G., Silva, J. B., dos Santos, M., Souza, M. A., Cândido, M. A. S., Rodrigues, M. O., Pietrobom, V. R., and Borin, J. F. (2023). Transformação de TV Boxes piratas em computadores de baixo custo suportados por nuvem computacional. Technical Report IC-PFG-23-49, Instituto de Computação, Universidade Estadual de Campinas.

Tan, M., Pang, R., and Le, Q. V. (2020). Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10781–10790.

TensorFlow. [link]. Acessado em 05/04/2024.

TensorFlow Lite. [link]. Acessado em 05/04/2024.

TensorFlow Lite Runtime. [link]. Acessado em 05/04/2024.

Willskytt, S., Böckin, D., André, H., Ljunggren Söderman, M., and Tillman, A.-M. (2016). Framework for analysing resource-efficient solutions. In Eco-Balance Conference 2016.