Increasing Efficiency in Detection of Helmet with Data Augmentation

Article Sidebar

PDF
Published: Nov 25, 2022
Keywords:
Deep learning Data augmentation Cutmix Objectdetectio

Main Article Content

Boonyakon Tongmonwit
Department of Computer Science and Information Technology, Faculty of Science, Naresuan University, Phitsanulok, 65000, Thailand
Chirayut Deepard
Department of Computer Science and Information Technology, Faculty of Science, Naresuan University, Phitsanulok, 65000, Thailand
Kreangsak Tamee
Department of Computer Science and Information Technology, Faculty of Science, Naresuan University, Phitsanulok, 65000, Thailand

Abstract

Accidents caused by the motorcycle rider do not wear helmets are an important problem. of course, it’s not just fatalities that helmets help to prevent. A helmet could help the motorcycle rider to avoid serious injuries. Therefore, the motorcycle rider should wear helmets. At present, A system to detect people not wearing helmets using Deep Learning is already have, which an effective system have to a lot of data. This research has data limitations, so there's not enough data for training. For this reason, The Data Augmentation is used to increase the amount of data. It can be concluded that use of Data Augmentation resulted in increased efficiency from 90-95% to 99.3%.

Article Details

How to Cite
Tongmonwit, B. ., Deepard, C. ., & Tamee, K. . (2022). Increasing Efficiency in Detection of Helmet with Data Augmentation. KKU Science Journal, 50(2), 93–101. Retrieved from https://ph01.tci-thaijo.org/index.php/KKUSciJ/article/view/250302
Issue
Vol. 50 No. 2 (2022): May - August 2022
Section
Research Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

References

กลุ่มสถิติการขนส่ง. (2562). รายงานการวิเคราะห์สถิติการ เกิดอุบัติเหตุจราจรทางบก รอบ 12 เดือนปีงบประมาณ 2562 (ตุลาคม 2561 – กันยายน 2562). กองแผนงานกรมการขนส่งทางบก.

ยงยุทธ ละมูลมอญ และธนาสัย สุคนธ์พันธ์. (2562). การตรวจจับหมวกนิรภัยและการใช้อาวุธปืน เพื่อเตือนภัยเหตุโจรกรรมจากภาพกล้องวงจรปิดแบบเวลาจริง. ผลงานค้นคว้าอิสระของนักศึกษาคณะสถิติประยุกต์ สถาบันบัณฑิตพัฒนาบริหารศาสตร์ ประจำปี รุ่น 2563.

Albawi, S., Mohammed, T.A., and Al-Zawi, S. (2017). Understanding of a convolutional neural network. In: 2017 International Conference on Engineering and Technology (ICET). 1-6.

Bochkovskiy, A., Wang, C.Y., and Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv: 2004.10934.

Doan, T.N., and Truong, M.T. (2020). Real-time vehicle detection and counting based on YOLO and DeepSORT. In: 2020 12th International Conference on Knowledge and Systems Engineering (KSE). 67-72.

Li, J., and Wu, Z. (2021). The application of Yolov4 and a new pedestrian clustering algorithm to implement social distance monitoring during The COVID-19 pandemic. Journal of Physics Conference Series 1865(4): 042019.

Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In: Proceeding of the IEEE conference on computer vision and pattern recognition. 779-788.

Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. 6023-6032.

Zhao, Z. Q., Zheng, P., Xu, S.T., and Wu, X. (2019). Object detection with deep learning: A review. IEEE transactions on neural networks and learning systems 30(11): 3212-3232.