Uma Ferramenta de Visão Computacional para Caracterização de Configurações de Eixos em Sistemas de Monitoramento de Carga
Resumo
Automatic characterization of truck axle configurations from road monitoring images can support intelligent transportation systems and fiscal enforcement by identifying inconsistencies between vehicle characteristics and declared freight information. This paper presents a computer-vision-based tool that combines YOLO-based tire detection with a geometric heuristic to automatically infer axle configurations (single, tandem, and tridem) from real-world traffic images. The tire detector was trained and evaluated on 1,520 images collected by a Brazilian public road monitoring system under challenging conditions, including variations in illumination, perspective, and partial occlusions. The complete tool was assessed on 483 monitored vehicle images, achieving an overall F1-score of 86.98% for axle configuration identification. Additionally, the tool was applied to the analysis of these images, demonstrating its ability to automatically characterize axle configurations and support statistical analyses for intelligent monitoring and tax auditing. The results indicate the potential of the proposed tool for integration into operational road monitoring systems, providing an effective mechanism for vehicle characterization and automated inspection support.
Palavras-chave:
Computer Vision, Deep Learning, YOLO, Tire Detection, Axle Identification, Intelligent Transportation Systems, Traffic Monitoring
Referências
CONTRAN – Conselho Nacional de Trânsito. 2021. Resolução CONTRAN nº 882, de 13 de dezembro de 2021. Diário Oficial da União. [link]
Daniel J. Dailey, Fritz W. Cathey, and Suree Pumrin. 2000. An Algorithm to Estimate Mean Traffic Speed Using Uncalibrated Cameras. IEEE Transactions on Intelligent Transportation Systems 1, 2 (2000), 98–107. DOI: 10.1109/6979.880967
Loveleen Gaur and Biswa Mohan Sahoo. 2022. Explainable Artificial Intelligence for Intelligent Transportation Systems: Ethics and Applications. Springer. DOI: 10.1007/978-3-031-09644-0
Byeong-Cheol Lim, Kyeong-Su Lee, and Deuk-Seon Yun. 2025. A Study on the Vehicle Classification Method Based on Panorama Image. Journal of the Korean Society of Mechanical and Aerospace Technology 27, 4 (2025), 775–780. DOI: 10.17958/ksmt.27.4.202508.775
Wuguang Lin, Haiyang Sun, Youzhang Gu, Qifeng Yu, and Yoon-Ho Cho. 2025. Vehicle Classification in Intelligent Transportation Systems: Enhanced CNN Approach and Data Set Expansion. Journal of Transportation Engineering, Part A: Systems 151, 8 (2025), 04025054. DOI: 10.1061/JTEPBS.TEENG-8751
Kaiky Maia, Ludmila Gomes, Allan Vasconcelos, Thaís Rêgo, Yuri Malheiros, Telmo Silva Filho, and Marcelo Iury. 2025. Integrating Computer Vision into CACTO: A System for Fraud Prevention and Secure Transport Monitoring. In Anais Estendidos do XXXI Simpósio Brasileiro de Sistemas Multimídia e Web (Rio de Janeiro/RJ). SBC, Porto Alegre, RS, Brasil, 123–126. DOI: 10.5753/webmedia_estendido.2025.16415
R. Pawar, S. Gujar, S. Chougule, R. Pote, D. Pandit, and Y. Dandawate. 2023. Real-Time Detection of Vehicles on South Asian Roads. In Lecture Notes in Electrical Engineering, Vol. 946. Springer, 413–427. DOI: 10.1007/978-981-19-5868-7_31
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 779–788. DOI: 10.1109/CVPR.2016.91
Yunjie Tian, Qixiang Ye, and DAVID DOERMANN. 2025. YOLOv12: Attention-Centric Real-Time Object Detectors. In Advances in Neural Information Processing Systems, D. Belgrave, C. Zhang, H. Lin, R. Pascanu, P. Koniusz, M. Ghassemi, and N. Chen (Eds.), Vol. 38. Curran Associates, Inc., 78433–78457. DOI: 10.52202/085713-2627
Daniel J. Dailey, Fritz W. Cathey, and Suree Pumrin. 2000. An Algorithm to Estimate Mean Traffic Speed Using Uncalibrated Cameras. IEEE Transactions on Intelligent Transportation Systems 1, 2 (2000), 98–107. DOI: 10.1109/6979.880967
Loveleen Gaur and Biswa Mohan Sahoo. 2022. Explainable Artificial Intelligence for Intelligent Transportation Systems: Ethics and Applications. Springer. DOI: 10.1007/978-3-031-09644-0
Byeong-Cheol Lim, Kyeong-Su Lee, and Deuk-Seon Yun. 2025. A Study on the Vehicle Classification Method Based on Panorama Image. Journal of the Korean Society of Mechanical and Aerospace Technology 27, 4 (2025), 775–780. DOI: 10.17958/ksmt.27.4.202508.775
Wuguang Lin, Haiyang Sun, Youzhang Gu, Qifeng Yu, and Yoon-Ho Cho. 2025. Vehicle Classification in Intelligent Transportation Systems: Enhanced CNN Approach and Data Set Expansion. Journal of Transportation Engineering, Part A: Systems 151, 8 (2025), 04025054. DOI: 10.1061/JTEPBS.TEENG-8751
Kaiky Maia, Ludmila Gomes, Allan Vasconcelos, Thaís Rêgo, Yuri Malheiros, Telmo Silva Filho, and Marcelo Iury. 2025. Integrating Computer Vision into CACTO: A System for Fraud Prevention and Secure Transport Monitoring. In Anais Estendidos do XXXI Simpósio Brasileiro de Sistemas Multimídia e Web (Rio de Janeiro/RJ). SBC, Porto Alegre, RS, Brasil, 123–126. DOI: 10.5753/webmedia_estendido.2025.16415
R. Pawar, S. Gujar, S. Chougule, R. Pote, D. Pandit, and Y. Dandawate. 2023. Real-Time Detection of Vehicles on South Asian Roads. In Lecture Notes in Electrical Engineering, Vol. 946. Springer, 413–427. DOI: 10.1007/978-981-19-5868-7_31
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 779–788. DOI: 10.1109/CVPR.2016.91
Yunjie Tian, Qixiang Ye, and DAVID DOERMANN. 2025. YOLOv12: Attention-Centric Real-Time Object Detectors. In Advances in Neural Information Processing Systems, D. Belgrave, C. Zhang, H. Lin, R. Pascanu, P. Koniusz, M. Ghassemi, and N. Chen (Eds.), Vol. 38. Curran Associates, Inc., 78433–78457. DOI: 10.52202/085713-2627
Publicado
27/10/2026
Como Citar
FREITAS, Herick José de; SILVEIRA, João Victor F. da; TEIXEIRA, Davi de Lacerda; REIS, Luis Gustavo Lacerda; MALHEIROS, Yuri; OLIVEIRA, Marcelo Iury S.; RÊGO, Thaís Gaudencio do.
Uma Ferramenta de Visão Computacional para Caracterização de Configurações de Eixos em Sistemas de Monitoramento de Carga. In: WORKSHOP DE FERRAMENTAS E APLICAÇÕES - SIMPÓSIO BRASILEIRO DE SISTEMAS MULTIMÍDIA E WEB (WEBMEDIA), 32. , 2026, Lavras/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 213-216.
ISSN 2596-1683.
DOI: https://doi.org/10.5753/webmedia_estendido.2026.34695.
