Proposal Real-Time Corridor Monitoring System Based on Deep Learning Algorithm
DOI:
https://doi.org/10.52783/jns.v14.2761Keywords:
Edge Computing, Yolo, Deep Learning, Corridor Monitoring, Object DetectingAbstract
e nanosized-based carrier systems which comprise solid lipid matrix combined with liquid lipids and surfactants. Urban Air Mobility (UAM) has emerged as a next-generation transportation solution to address urbanization and traffic congestion challenges. This study proposes a secondary surveillance system based on a monocular camera to support the safe operation of UAM. The system aims to mitigate unexpected issues such as GNSS signal disruptions and 5G network failures and enhance flight safety by detecting unidentified aerial objects. The YOLOv8 object detection model was utilized to achieve high accuracy and real-time detection performance. YOLOv8 leverages an advanced backbone network and an enhanced pyramid structure to effectively detect objects of various scales, maintaining high detection performance even in complex environments and for fast-moving objects. Furthermore, its diverse versions, ranging from lightweight to high-performance models, enable a balance between efficiency and accuracy. In this study, drones were used as experimental targets, and experiments conducted within a 20m range confirmed detection rates exceeding 80%. YOLOv8's real-time processing capability and high detection rate highlight its potential as a key technology for UAM surveillance systems.
Downloads
Metrics
References
Ministry of Land, Infrastructure and Transport, "Korean Urban Air Mobility (K-UAM) Concept of Operations 1.0," Ministry of Land, Infrastructure and Transport Journal, Vol. 1, No. 1, pp. 1-100, 2023. Retrieved from https://www.molit.go.kr.
W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, “Edge computing: Vision and challenges,” IEEE Internet of Things Journal, Vol. 3, No. 5, pp. 637-646, Oct. 2016. DOI: http://dx.doi.org/10.1109/JIOT.2016.2579198.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A., “You Only Look Once: Unified, Real-Time Object Detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV: USA, pp. 779-788, June 2016. DOI: 10.1109/CVPR.2016.91.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, Vol. 86, No. 11, pp. 2278-2324, Nov. 1998. DOI: 10.1109/5.726791.
Jocher, G., Chaurasia, A., and Qiu, J., “Ultralytics YOLOv5,” [Internet]. Available: https://github.com/ultralytics/ultralytics.
Wang, C., Bochkovskiy, A., and Liao, H. Y. M., “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” [Internet]. Available: https://arxiv.org/abs/2207.02696.
Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S., “Feature Pyramid Networks for Object Detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI: USA, pp. 2117-2125, July 2017. DOI: 10.1109/CVPR.2017.106.
M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The PASCAL visual object classes (VOC) challenge,” *International Journal of Computer Vision*, Vol. 88, No. 2, pp. 303-338, June 2010. DOI: http://dx.doi.org/10.1007/s11263-009-0275-4.
Copyright© by the authors. Licensee TAETI, Taiwan. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY-NC) license (http://creativecommons.org/licenses/by/4.0/).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
