10 Years of Deep Learning for Vehicle Detection at a Smart Parking : What has Changed?
Resumo
Over the past decade, deep learning has transformed vehicle detection systems, particularly in smart parking applications. This work presents the evolution of a near real-time parking lot monitoring system at a university campus through multiple research and development iterations. The latest version incorporates the YOLOv11m model, converted to TensorFlow Lite, achieving a balanced accuracy of 98.65% on a dataset of 3,484 images, with an inference time of 8 seconds and updates sent to the parking totem every minute. The system integrates a Raspberry Pi 3 for edge inference, sending the number of available parking spaces to an InfluxDB database, while an ESP8266 receives this data and displays it on an LED panel at a totem. Earlier versions faced challenges such as hardware limitations, lack of documentation, and reliance on outdated deep learning models. The new version addresses these issues, improving detection accuracy, with enhanced fault tolerance, and a more robust totem structure. Additionally, a benchmark comparing 13 deep learning models for smart parking is introduced, along with software and hardware instructions for system replication.
Palavras-chave:
Smart Cities, Internet of Things, Deep Learning, Smart Parking, Urban Sensing Infrastructures
Referências
Abbas, Q., Ahmad, G., Alyas, T., Alghamdi, T., Alsaawy, Y., and Alzahrani, A. (2023). Revolutionizing urban mobility: IoT-enhanced autonomous parking solutions with transfer learning for smart cities. Sensors, 23(21), 8753.
Amato, G., Carrara, F., Falchi, F., Gennaro, C., Meghini, C., and Vairo, C. (2017). Deep learning for decentralized parking lot occupancy detection. Expert Systems with Applications, 72, 327–334.
An, R., Zhang, X., Sun, M., and Wang, G. (2024). GC-YOLOv9: Innovative smart city traffic monitoring solution. Alexandria Engineering Journal, 106, 277–287.
Assemi, B., Baker, D., and Paz, A. (2020). Searching for on-street parking: An empirical investigation of the factors influencing cruise time. Transport Policy, 97, 186–196.
Baggio, J. V., Gonzalez, L. F., and Borin, J. F. (2020). SmartParking: A smart solution using deep learning. Technical report, Instituto de Computação - UNICAMP.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1251–1258.
da Luz, G. P., Sato, G. M., Gonzalez, L. F. G., and Borin, J. F. (2024a). Smart parking with pixel-wise ROI selection for vehicle detection using YOLOv8, YOLOv9, YOLOv10, and YOLOv11. arXiv preprint arXiv:2412.01983.
da Luz, G. P. P., Sato, G. M., Gonzalez, L. F. G., and Borin, J. F. (2024b). Repurposing of TV boxes for a circular economy in smart cities applications.
de Moraes, P. A., Pisani, F., and Borin, J. F. (2024). Smart university: A pathway for advancing sustainable development goals. Internet of Things, 101246.
Doshi, Y., Shah, K., Katre, N., Sawant, V., and Correia, S. (2024). Comparison of YOLO models for object detection from parking spot images. Educational Administration: Theory and Practice, 30(4), 10401–10411.
Dowling, C., Fiez, T., Ratliff, L., and Zhang, B. (2017). How much urban traffic is searching for parking? arXiv preprint.
Greco, A., Saggese, A., Vento, M., and Vigilante, V. (2021). Vehicle detection for smart roads applications on board of smart cameras: A comparative analysis. IEEE Transactions on Intelligent Transportation Systems, 23(7), 8077–8089.
He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017). Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969.
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.
Nations, U. (2015). Transforming our world: The 2030 agenda for sustainable development. New York: United Nations, Department of Economic and Social Affairs.
Nyambal, J. and Klein, R. (2017). Automated parking space detection using convolutional neural networks. In 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech), 1–6. IEEE.
Paidi, V., Håkansson, J., Fleyeh, H., and Nyberg, R. G. (2022). CO2 emissions induced by vehicles cruising for empty parking spaces in an open parking lot. Sustainability, 14(7), 3742.
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.
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 (CVPR), 779–788.
Redmon, J. and Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767.
Rodríguez, A., Alonso, B., Moura, J. L., and dell’Olio, L. (2024). Analysis of user behavior in urban parking under different levels of information scenarios provided by smart devices or connected cars. Travel Behaviour and Society, 37, 100847.
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, 197–209, Porto Alegre, RS, Brasil. SBC.
Satyanath, G., Sahoo, J. K., and Roul, R. K. (2023). Smart parking space detection under hazy conditions using convolutional neural networks: A novel approach. Multimedia Tools and Applications, 82(10), 15415–15438.
Shoup, D. (2021). Pricing curb parking. Transportation Research Part A: Policy and Practice, 154, 399–412.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1–9.
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 (CVPR), 10781–10790.
Tian, Y., Ye, Q., and Doermann, D. (2025). YOLOv12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524.
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), 858–865. IEEE.
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., and Zhang, J. (2019). Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 107(8), 1738–1762.
Amato, G., Carrara, F., Falchi, F., Gennaro, C., Meghini, C., and Vairo, C. (2017). Deep learning for decentralized parking lot occupancy detection. Expert Systems with Applications, 72, 327–334.
An, R., Zhang, X., Sun, M., and Wang, G. (2024). GC-YOLOv9: Innovative smart city traffic monitoring solution. Alexandria Engineering Journal, 106, 277–287.
Assemi, B., Baker, D., and Paz, A. (2020). Searching for on-street parking: An empirical investigation of the factors influencing cruise time. Transport Policy, 97, 186–196.
Baggio, J. V., Gonzalez, L. F., and Borin, J. F. (2020). SmartParking: A smart solution using deep learning. Technical report, Instituto de Computação - UNICAMP.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1251–1258.
da Luz, G. P., Sato, G. M., Gonzalez, L. F. G., and Borin, J. F. (2024a). Smart parking with pixel-wise ROI selection for vehicle detection using YOLOv8, YOLOv9, YOLOv10, and YOLOv11. arXiv preprint arXiv:2412.01983.
da Luz, G. P. P., Sato, G. M., Gonzalez, L. F. G., and Borin, J. F. (2024b). Repurposing of TV boxes for a circular economy in smart cities applications.
de Moraes, P. A., Pisani, F., and Borin, J. F. (2024). Smart university: A pathway for advancing sustainable development goals. Internet of Things, 101246.
Doshi, Y., Shah, K., Katre, N., Sawant, V., and Correia, S. (2024). Comparison of YOLO models for object detection from parking spot images. Educational Administration: Theory and Practice, 30(4), 10401–10411.
Dowling, C., Fiez, T., Ratliff, L., and Zhang, B. (2017). How much urban traffic is searching for parking? arXiv preprint.
Greco, A., Saggese, A., Vento, M., and Vigilante, V. (2021). Vehicle detection for smart roads applications on board of smart cameras: A comparative analysis. IEEE Transactions on Intelligent Transportation Systems, 23(7), 8077–8089.
He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017). Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969.
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.
Nations, U. (2015). Transforming our world: The 2030 agenda for sustainable development. New York: United Nations, Department of Economic and Social Affairs.
Nyambal, J. and Klein, R. (2017). Automated parking space detection using convolutional neural networks. In 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech), 1–6. IEEE.
Paidi, V., Håkansson, J., Fleyeh, H., and Nyberg, R. G. (2022). CO2 emissions induced by vehicles cruising for empty parking spaces in an open parking lot. Sustainability, 14(7), 3742.
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.
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 (CVPR), 779–788.
Redmon, J. and Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767.
Rodríguez, A., Alonso, B., Moura, J. L., and dell’Olio, L. (2024). Analysis of user behavior in urban parking under different levels of information scenarios provided by smart devices or connected cars. Travel Behaviour and Society, 37, 100847.
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, 197–209, Porto Alegre, RS, Brasil. SBC.
Satyanath, G., Sahoo, J. K., and Roul, R. K. (2023). Smart parking space detection under hazy conditions using convolutional neural networks: A novel approach. Multimedia Tools and Applications, 82(10), 15415–15438.
Shoup, D. (2021). Pricing curb parking. Transportation Research Part A: Policy and Practice, 154, 399–412.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1–9.
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 (CVPR), 10781–10790.
Tian, Y., Ye, Q., and Doermann, D. (2025). YOLOv12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524.
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), 858–865. IEEE.
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., and Zhang, J. (2019). Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 107(8), 1738–1762.
Publicado
19/05/2025
Como Citar
DA LUZ, Gustavo P. C. P; SATO, Gabriel Massuyoshi; BANNWART, Tiago Godoi; GONZALEZ, Luis Fernando Gomez; BORIN, Juliana Freitag.
10 Years of Deep Learning for Vehicle Detection at a Smart Parking : What has Changed?. In: WORKSHOP DE COMPUTAÇÃO URBANA (COURB), 9. , 2025, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 127-140.
ISSN 2595-2706.
DOI: https://doi.org/10.5753/courb.2025.8869.
