Motorcycle Apprehension using Deep Learning and K-Nearest Neighbor Algorithm

  • Maria Rosario T. Garcia
  • Argel A. Bandala
  • Elmer P. Dadios


Abstract — Road violations that lead to accidents and deaths are increasing significantly. There are about 1.35 million people who die every year because of road accidents, and more than half of these involve a motorcycle.  Authorities are strictly implementing traffic laws and making some innovations to capture those motorists violating laws easily.  Researchers are also doing their part to help solve the problem; indeed, their studies give a vast contribution and solve road safety issues.  However, the papers on road violations were focused more on on-road violations involving four-wheeled vehicles.

For this reason, a motorcyclist violation detection and plate recognition with e-mail notification using a Deep Learning algorithm were developed to apprehend motorcyclists violating traffic laws.  Tensorflow Object Detection API was used as a framework along with the Faster R-CNN model.   The system was developed using Anaconda Environment, Python Scripting, KNN, and MySQL Connector.  The conditions and criteria for detecting a violation are based on motorcycle detection, including motorcycle tracking.  After violation detection and plate recognition, the violation's image is sent through e-mail together with the details of the offense.

Keywords: motorcycle, machine learning, Tensorflow Object Detection Classifier, Faster R-CNN, KNN, MySQL, traffic violation


Download data is not yet available.


[1] D. L. Romero, D. M. De Barros, G. O. Belizario, and A. De Pádua Serafim, "Personality traits and risky behavior among motorcyclists: An exploratory study," PLoS One, vol. 14, no. 12, pp. 1–15, 2019.
[2] “No Contact Traffic Apprehension Policy.” [Online]. Available: [Accessed: 04-Jul-2019].
[3] G. Desai, V. Ambre, S. Jakharia, and S. Sherkhane, "Smart Road Surveillance Using Image Processing," 2018 Int. Conf. Smart City Emerg. Technol. ICSCET 2018, pp. 1–5, 2018.
[4] R. Shreyas, B. V. P. Kumar, H. B. Adithya, B. Padmaja, and M. P. Sunil, "Dynamic traffic rule violation monitoring system using automatic number plate recognition with SMS feedback," 2nd Int. Conf. Telecommun. Networks, TEL-NET 2017, vol. 2018-Janua, pp. 1–5, 2018.
[5] J. Spanhel, J. Sochor, and A. Makarov, "Detection of Traffic Violations of Road Users Based on Convolutional Neural Networks," 2018 14th Symp. Neural Networks Appl. NEUREL 2018, 2018.
[6] A. C. P. Uy, R. A. Bedruz, A. R. Quiros, A. Bandala, and E. P. Dadios, "Machine Vision for Traffic Violation Detection System through Genetic Algorithm," no. January, 2016.
[7] W. Tan, "WHO PH: Over 90% of Motorcycle Deaths Didn't Wear Helmets." [Online]. Available: [Accessed: 16-Mar-2019].
[8] J. Mistry, A. K. Misraa, M. Agarwal, A. Vyas, V. M. Chudasama, and K. P. Upla, "An automatic detection of helmeted and non-helmeted motorcyclist with license plate extraction using convolutional neural network," Proc. 7th Int. Conf. Image Process. Theory, Tools Appl. IPTA 2017, vol. 2018-Janua, pp. 1–6, 2018.
[9] K. Li, X. Zhao, J. Bian, and M. Tan, "Automatic Safety Helmet Wearing Detection," 2017 IEEE 7th Annu. Int. Conf. CYBER Technol. Autom. Control. Intell. Syst. CYBER 2017, pp. 617–622, 2018.
[10] J. Li et al., "Safety helmet wearing detection based on image processing and machine learning," 9th Int. Conf. Adv. Comput. Intell. ICACI 2017, pp. 201–205, 2017.
[11] G. Zhang, L. Lv, L. I. Dan, and M. Zhu, "The Method for Recognizing Recognition Helmet Based On Color and Shape," vol. 126, no. 5th Int. Conf. on Machinery, Materials and Computing Tech ICMMCT, pp. 1219–1223, 2017.
[12] “How to train Tensorflow models - Towards Data Science.” [Online]. Available: [Accessed: 19-Jun-2020].
[13] L. T. O. Phil., "Land Transportation and Traffic Code RA4136." 1964.
[14] Department of Transportation, "Procurement of Goods and Services for the Land Transportation Office Motor Vehicle License Plate Standardization Program," 2012.
0 Views | 0 Downloads
How to Cite
Garcia, M. R. T., Bandala, A. A., & Dadios, E. P. (2021). Motorcycle Apprehension using Deep Learning and K-Nearest Neighbor Algorithm. Asian Journal For Convergence In Technology (AJCT), 7(1), 01-06.