Monitoring vehicle plate detection in Brazilian Universities
ResumoContext: With the growth of smart cities, surveillance camera systems have increased their monitoring capacity in different environments. In public Universities, monitoring requires subtle and precise alerts, in order to curb actions that may present a lack of security for the academic community. Problem: Although the detection objects in videos is possible, the high cost of acquiring, installing high-quality cameras and machines capable of executing high-precision models of customized solutions is expensive. In addition, most solutions achieve high precision in controlled environments, with high resolution still images, and focus on objects, which does not portray the reality of surveillance cameras in Universities. Solution: Faced with this problem, the objective is to build a Automatic License Plate Recognition system(ALPR) to control vehicles entering and leaving Universities. It is proposed to interoperate with camera systems in order to alert the competent authorities. Information systems theory: This work was conceived under the General Theory of Systems with regard to interoperate with already existing heterogeneous systems. Furthermore, as part of the theory of socio-technical systems, this approach aims to improve the performance of the organization, offering improvements in the productivity of the task due to the alerts of the offered approach. Method: This research is descriptive and its evaluation is done through proof of concept. Results: The artifact developed showed good performance, allowing to recognize license plates in surveillance cameras with 76.6% accuracy. Contributions and Impact in the area of information systems: Our main contribution is the artifact to detect vehicles. A secondary contribution is our dataset with Old and Mercosul Plaques versions. Such method impacts the three pilars from IS area: People, Process and Technology.
V. Ganapathy and Dennis Lui. 2008. A Malaysian Vehicle License Plate Localization and Recognition System. Journal of Systemics, Cybernetics and Informatics 6 (02 2008).
Pradeep.J. 2020. Efficient Vehicle Detection System using OCR and REST API. International Journal of Engineering Research and V9 (07 2020). https://doi.org/10.17577/IJERTV9IS070306
Kartikeya Jain, Tanupriya Choudhury, and Nirbhay Kashyap. 2017. Smart vehicle identification system using OCR. In 2017 3rd International Conference on Computational Intelligence & Communication Technology (CICT). 1–6. https://doi.org/10.1109/CIACT.2017.7977297
Rayson Laroca, Everton Cardoso, Diego Lucio, Valter Estevam, and David Menotti. 2022. On the Cross-dataset Generalization in License Plate Recognition. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. SCITEPRESS - Science and Technology Publications. https://doi.org/10.5220/0010846800003124
R. Laroca, E. Severo, L. A. Zanlorensi, L. S. Oliveira, G. R. Gonçalves, W. R. Schwartz, and D. Menotti. 2018. A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector. In International Joint Conference on Neural Networks (IJCNN). 1–10. https://doi.org/10.1109/IJCNN.2018.8489629
Rayson Laroca, Luiz A. Zanlorensi, Gabriel Resende Gonçalves, Eduardo Todt, William Robson Schwartz, and David Menotti. 2019. An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detector. CoRR abs/1909.01754 (2019). arXiv:1909.01754 http://arxiv.org/abs/1909.01754
Sérgio Montazzolli and Claudio Jung. 2017. Real-Time Brazilian License Plate Detection and Recognition Using Deep Convolutional Neural Networks. In 2017 30th SIBGRAPI. 55–62. https://doi.org/10.1109/SIBGRAPI.2017.14
Natan Moura, Daniela B. Claro, and João M. Gondim. 2021. Análise experimental para a detecção de objetos em vídeos de câmeras de vigilância: Uma abordagem para porte de arma, incêndio e pichação. In Anais Estendidos do XXVII Simpósio Brasileiro de Sistemas Multimídia e Web (Minas Gerais). SBC, Porto Alegre, RS, Brasil, 37–40. https://doi.org/10.5753/webmedia_estendido.2021.17608
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2015. You Only Look Once: Unified, Real-Time Object Detection. https://doi.org/10.48550/ARXIV.1506.02640