International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Fundamental Function Design of Real-Time Unmanned Monitoring System Applying YOLOv5s on NVIDIA TX2TM AI Edge Computing Platform

  • LEE, SI HYUN (Department of Information and Communication, Dong Seoul University)
  • Received : 2022.03.10
  • Accepted : 2022.03.15
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, for the purpose of designing an real-time unmanned monitoring system, the YOLOv5s (small) object detection model was applied on the NVIDIA TX2TM AI (Artificial Intelligence) edge computing platform in order to design the fundamental function of an unmanned monitoring system that can detect objects in real time. YOLOv5s was applied to the our real-time unmanned monitoring system based on the performance evaluation of object detection algorithms (for example, R-CNN, SSD, RetinaNet, and YOLOv5). In addition, the performance of the four YOLOv5 models (small, medium, large, and xlarge) was compared and evaluated. Furthermore, based on these results, the YOLOv5s model suitable for the design purpose of this paper was ported to the NVIDIA TX2TM AI edge computing system and it was confirmed that it operates normally. The real-time unmanned monitoring system designed as a result of the research can be applied to various application fields such as an security or monitoring system. Future research is to apply NMS (Non-Maximum Suppression) modification, model reconstruction, and parallel processing programming techniques using CUDA (Compute Unified Device Architecture) for the improvement of object detection speed and performance.

Keywords

Acknowledgement

This study was conducted by Dong Seoul University's intramural research grant in 2010. We would like to thank Dong Seoul University for its research support.

References

  1. https://nvidia.com
  2. Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, You Only Look Once: Unified, Real-Time Object Detection, arXiv:1506.02640v5 [cs.CV] 9 May 2016.
  3. Qihai Cai, Shangping Zhong, Kaizhi Chen, Target Detection in Rural River Image Based on Yolo V5 Model with the Cross-Switch Unit, 2021 6th International Conference on Image, Vision and Computing (ICIVC) | 978-1-6654-4368-5/21/© 2021 IEEE | DOI: 10.1109/ICIVC52351.2021.9527005
  4. Xingkui Zhu1, Shuchang Lyu1, Xu Wang 1 Qi Zhao1, TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios, ICCV 2021 open access.
  5. Ross. Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," IEEE Conf. Comput. Vision Pattern Recogn., Columbus, OH, USA, June 23-28, 2014, pp. 580-587.
  6. R. Girshick, "Fast R-CNN," IEEE Int. Conf. Comput. Vision, Santiago, Chile, Dec. 7-13, 2015, pp. 1440-1448.
  7. S. Ren et al., "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, 2017, pp. 1137-1149. https://doi.org/10.1109/TPAMI.2016.2577031
  8. J. Dai et al., "R-FCN: Object Detection via Region-based Fully Convolutional Networks," Conf. Neural Inform. Process. Syst., Barcelona, Spain, Dec. 4-6, 2016, pp. 379-387.
  9. W. Liu et al., "SSD: Single Shot MultiBox Detector," Eur. Conf. Comp. Vision, Amsterdam, Netherlands, Oct. 8- 16, 2016, pp. 21-37.
  10. Tsung Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollar, "Focal Loss for Dense Object Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, Issue 2, pp. 318-327, 2018. https://doi.org/10.1109/tpami.2018.2858826
  11. Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, and Qi Tian, "CenterNet: Keypoint Triplets for Object Detection", arXiv:1904.08189v3 [cs.CV] 19 Apr 2019.
  12. Liu Ting, Zhou Baijun, Zhao Yongsheng, and Yan Shun, Ship Detection Algorithm based on Improved YOLOv5, IEEE Xplore, 2022, Fab. 24, 2022.
  13. Wei Ding, Li Zhang, Building Detection in Remote Sensing Image Based on Improved YOLOv5, IEEE Xplore, 2022, 2.
  14. Guihui Shi, et. el, Combined Channel and Spatial Attention for YOLOv5 during Target Detection, IEEE Xplore, 2022, 2.
  15. Yaqi Guan, et. el, Design and Implementation of Safety Helmet Detection System Based on YOLOv5, 2021 2nd Asia Conference on Computers and Communications (ACCC)
  16. Guanhao Yang, et. el, Garbage Classification System with YOLOv5 Based on Image Recognition, IEEE Xplore, 2022, 2.
  17. Pallavi Udatewar, et. el, Personal Protective Equipment Kit Detection using YOLOv5 and TensorFlow, IEEE Xplore, 2021, 2.
  18. Tian-Hao Wu1, et. el, Real-Time Vehicle and Distance Detection Based on Improved YOLOv5 Network, IEEE Xplore, 2022, 2.
  19. Zhiyue Zhang, et. el, Recognition of Casting Embossed Convex and Concave Characters Based on YOLOv5 for Different Distribution Conditions, IEEE, 2021, 2.
  20. WenZe Fan, et. el, Research on Abnormal Target Detection Method in Chest Radiograph Based on YOLOv5 Algorithm, IEEE, 2021, 2.
  21. https://public.roboflow.com/
  22. https://github.com/ultralytics/YOLOv5.git