People Counting Application with Crowded Scenarios: A Case Study with TV Boxes as Edge Devices
DOI:
https://doi.org/10.5753/jisa.2025.5156Keywords:
Internet of Things, Smart Cities, People Counting, Crowded Scenarios, Sustainability, TV Boxes, RepurposingAbstract
Counting people in various urban spaces using artificial intelligence enables a wide range of smart city applications, enhancing governance and improving citizens' quality of life. However, the rapid expansion of edge computing for these applications raises concerns about the growing volume of electronic waste. To address this challenge, our previous work demonstrated the feasibility of repurposing confiscated illegal TV boxes as Internet of Things (IoT) edge devices for machine learning applications, specifically for people counting using images captured by cameras. Despite promising results, experiments in crowded scenarios revealed a high Mean Absolute Error (MAE). In this work, we propose a patching technique applied to YOLOv8 models to mitigate this limitation. By employing this technique, we successfully reduced the MAE from 8.77 to 3.77 using the nano version of YOLOv8, converted to TensorFlow Lite, on a custom dataset collected at the entrance of a university restaurant. This work presents an effective solution for resource-constrained devices and promotes a sustainable approach to repurposing hardware that would otherwise contribute to electronic waste.
Downloads
References
Akyon, F. C., Altinuc, S. O., and Temizel, A. (2022). Slicing aided hyper inference and fine-tuning for small object detection. In 2022 IEEE International Conference on Image Processing (ICIP), pages 966-970. IEEE. DOI: 10.1109/icip46576.2022.9897990.
Artstein, R. (2017). Inter-annotator agreement. Handbook of linguistic annotation, pages 297-313. DOI: 10.1007/978-94-024-0881-2_11.
Badidi, E., Moumane, K., and Ghazi, F. E. (2023). Opportunities, applications, and challenges of edge-ai enabled video analytics in smart cities: A systematic review. IEEE Access, 11:80543-80572. DOI: 10.1109/ACCESS.2023.3300658.
Baldé, C. P., Kuehr, R., Yamamoto, T., McDonald, R., D’Angelo, E., Althaf, S., Bel, G., Deubzer, O., Fernandez-Cubillo, E., Forti, V., Gray, V., Herat, S., Honda, S., Iattoni, G., Khetriwal, D. S., di Cortemiglia, V. L., Lobuntsova, Y., Nnorom, I., Pralat, N., and Wagner, M. (2024). The global e-waste monitor 2024. Technical report, International Telecommunication Union (ITU) and United Nations Institute for Training and Research (UNITAR). Available online [link].
Bhatt, C., Kukreti, A., Pratap, A., and Dhondiyal, S. A. (2024). Deep learning for crowd counting: Addressing crowd density with advanced methods. In 2024 Second International Conference on Advances in Information Technology (ICAIT), volume 1, pages 1-5. IEEE. DOI: 10.1109/icait61638.2024.10690493.
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. DOI: 10.1007/s11042-023-16374-x.
da Luz, G. P., Sato, G. M., Gonzalez, L. F. G., and Borin, J. F. (2024). Smart parking with pixel-wise roi selection for vehicle detection using yolov8, yolov9, yolov10, and yolov11. arXiv preprint arXiv:2412.01983. DOI: 10.48550/arXiv.2412.01983.
da Luz, G. P., Sato, G. M., Gonzalez, L. F. G., and Borin, J. F. (2025). Repurposing of tv boxes for a circular economy in smart cities applications. Scientific Reports, 15(1):22638. DOI: 10.1038/s41598-025-97379-4.
Dwivedi, Y. K., Hughes, L., Kar, A. K., Baabdullah, A. M., Grover, P., Abbas, R., Andreini, D., Abumoghli, I., Barlette, Y., Bunker, D., Chandra Kruse, L., Constantiou, I., Davison, R. M., De’, R., Dubey, R., Fenby-Taylor, H., Gupta, B., He, W., Kodama, M., Mäntymäki, M., Metri, B., Michael, K., Olaisen, J., Panteli, N., Pekkola, S., Nishant, R., Raman, R., Rana, N. P., Rowe, F., Sarker, S., Scholtz, B., Sein, M., Shah, J. D., Teo, T. S., Tiwari, M. K., Vendelø, M. T., and Wade, M. (2022). Climate change and cop26: Are digital technologies and information management part of the problem or the solution? an editorial reflection and call to action. International Journal of Information Management, 63:102456. DOI: 10.1016/j.ijinfomgt.2021.102456.
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(1):859-873. DOI: 10.1007/s10586-023-03987-y.
Gia, B. T., Khanh, T. B. C., Trong, H. H., Doan, T. T., Do, T., Le, D.-D., and Ngo, T. D. (2024). Enhancing road object detection in fisheye cameras: An effective framework integrating sahi and hybrid inference. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7227-7235. DOI: 10.1109/cvprw63382.2024.00718.
Himeur, Y., Sayed, A. N., Alsalemi, A., Bensaali, F., and Amira, A. (2024). Edge ai for internet of energy: Challenges and perspectives. Internet of Things, 25:101035. DOI: 10.1016/j.iot.2023.101035.
Huang, S., Lu, Z., Cun, X., Yu, Y., Zhou, X., and Shen, X. (2024). Deim: Detr with improved matching for fast convergence. arXiv preprint arXiv:2412.04234. DOI: 10.48550/arxiv.2412.04234.
Jocher, G., Chaurasia, A., and Qiu, J. (2023). Ultralytics YOLO. Available online [link].
Kaggle Hub (2024). Efficientdet object detection model. [link]. Accessed in 03/03/2024.
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. DOI: 10.1007/978-3-319-10602-1_48.
Liu, S., Huang, D., and Wang, Y. (2019). Adaptive nms: Refining pedestrian detection in a crowd. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6459-6468. DOI: 10.1109/cvpr.2019.00662.
Metwaly, A., Queralta, J. P. n., Sarker, V. K., Gia, T. N., Nasir, O., and Westerlund, T. (2020). Edge computing with embedded ai: Thermal image analysis for occupancy estimation in intelligent buildings. In Proceedings of the INTelligent Embedded Systems Architectures and Applications Workshop 2019, INTESA2019, page 1–6, New York, NY, USA. Association for Computing Machinery. DOI: 10.1145/3372394.3372397.
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. DOI: 10.1016/j.iot.2022.100570.
Nations, U. (2015). Transforming our world: The 2030 agenda for sustainable development. New York: United Nations, Department of Economic and Social Affairs, 1:41. DOI: 10.1891/9780826190123.ap02.
Peng, Y., Li, H., Wu, P., Zhang, Y., Sun, X., and Wu, F. (2024). D-fine: redefine regression task in detrs as fine-grained distribution refinement. arXiv preprint arXiv:2410.13842. DOI: h10.48550/arxiv.2410.13842.
Prefeitura Universitária Unicamp (2024). Fila do restaurante em tempo real. [link]. Accessed in 04/03/2024.
Ruchika, Purwar, R. K., and Verma, S. (2022). Analytical study of yolo and its various versions in crowd counting. In Intelligent Data Communication Technologies and Internet of Things: Proceedings of ICICI 2021, pages 975-989. Springer. DOI: 10.1007/978-981-16-7610-9_71.
Sato, G., Luz, G., Gonzalez, L., and Borin, J. (2024). Reaproveitamento de tv boxes para aplicação de contagem de pessoas na borda em cidades inteligentes. In Anais do VIII Workshop de Computação Urbana, pages 197-209, Porto Alegre, RS, Brasil. SBC. DOI: 10.5753/courb.2024.3375.
Shu, F. and Shu, J. (2021). An eight-camera fall detection system using human fall pattern recognition via machine learning by a low-cost android box. Scientific reports, 11(1):2471. DOI: 10.1038/s41598-021-81115-9.
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. DOI: 10.1109/cvpr42600.2020.01079.
Tang, C., Li, W., Vishwakarma, S., Chetty, K., Julier, S., and Woodbridge, K. (2020). Occupancy detection and people counting using wifi passive radar. In 2020 IEEE Radar Conference (RadarConf20), pages 1-6. DOI: 10.1109/RadarConf2043947.2020.9266493.
TensorFlow Lite (2024). Guide for tensorflow lite. [link]. Accessed in 04/05/2024.
TensorFlow Lite Runtime (2024). Tensorflow - an end-to-end platform for machine learning. [link]. Accessed in 04/05/2024.
Verma, G., Gupta, Y., Malik, A. M., and Chapman, B. (2021). Performance evaluation of deep learning compilers for edge inference. In 2021 IEEE international parallel and distributed processing symposium workshops (IPDPSW), pages 858-865. IEEE. DOI: 10.1109/ipdpsw52791.2021.00128.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Journal of Internet Services and Applications
This work is licensed under a Creative Commons Attribution 4.0 International License.
