Integrating Computer Vision into CACTO: A System for Fraud Prevention and Secure Transport Monitoring

• Kaiky Maia UFPB
• Ludmila Gomes UFPB
• Allan Vasconcelos UFPB
• Thaís G. do Rêgo UFPB
• Yuri Malheiros UFPB
• Telmo Silva Filho University of Bristol
• Marcelo Iury UFPB

DOI: https://doi.org/10.5753/webmedia_estendido.2025.16415

Resumo

The rapid growth of freight transport in Brazil has increased the demand for intelligent tax auditing tools capable of handling high-volume, real-time data. This paper presents the integration of three computer vision modules into CACTO, a large-scale monitoring platform used by the State Treasury Secretariat of Paraíba (SEFAZPB). The modules address key inspection tasks: vehicle re-identification and multi-camera tracking, direction recognition and route monitoring, and open-truck cargo detection. By combining distributed architectures with scalable machine learning pipelines, the system enhances proactive and evidence-based auditing, supporting fiscal enforcement and reducing vulnerabilities to tax evasion.

Palavras-chave: CACTO, computer vision, vehicle re-identification, route monitoring, cargo detection, tax auditing, fraud prevention, big data

Referências

Michael Abebe Berwo, Asad Khan, Yong Fang, Hamza Fahim, Shumaila Javaid, Jabar Mahmood, Zain Ul Abideen, and M. S. Syam. 2023. Deep Learning Techniques for Vehicle Detection and Classification from Images/Videos: A Survey. Sensors 23, 10 (2023), 4832. DOI: 10.3390/s23104832

Lingxiao He, Xingyu Liao, Wu Liu, Xinchen Liu, Peng Cheng, and Tao Mei. 2020. FastReID: A Pytorch Toolbox for General Instance Re-identification. arXiv:2006.02631 [cs.CV] [link]

Youngmin Kim, Donghwa Kang, and Hyeongboo Baek. 2025. A 2-Stage Model for Vehicle Class and Orientation Detection with Photo-Realistic Image Generation. arXiv preprint arXiv:2506.01338 [cs.CV] (2025). DOI: 10.48550/arXiv.2506.01338

Xinchen Liu, Wu Liu, Huadong Ma, and Huiyuan Fu. 2016. Large-scale vehicle re-identification in urban surveillance videos. DOI: 10.1109/ICME.2016.7553002

Xinchen Liu, Wu Liu, Tao Mei, and Huadong Ma. 2016. A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance, Vol. 9906. 869–884. DOI: 10.1007/978-3-319-46475-6_53

Xinchen Liu, Wu Liu, Tao Mei, and Huadong Ma. 2017. PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance. IEEE Transactions on Multimedia PP (09 2017). DOI: 10.1109/TMM.2017.2751966

Matheus Oliveira, Lucas Fonseca, and Rodrigo Minetto. 2021. A Two-Stream Siamese Neural Network for Vehicle Re-Identification with License Plate Recognition. Master’s thesis. Universidade Tecnológica Federal do Paraná (UTFPR). [link]

Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. arXiv:1506.02640 [cs.CV] [link]

Lucas Nascimento Souza, Carla M. Medeiros, and João P. Silva. 2025. Reidentificação Veicular em Ambientes Reais Utilizando Restrições Espaço-Temporais e Aprendizado Semissupervisionado. In Anais do Simpósio Brasileiro de Computação Ubíqua e Pervasiva (SBCUP). [link]