Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Research of Deep Learning-Based Multi Object Classification and Tracking for Intelligent Manager System

지능형 관제시스템을 위한 딥러닝 기반의 다중 객체 분류 및 추적에 관한 연구

  • 이준환 (극동대학교 에너지IT학과)
  • Received : 2023.05.03
  • Accepted : 2023.05.30
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, intelligent control systems are developing rapidly in various application fields, and methods for utilizing technologies such as deep learning, IoT, and cloud computing for intelligent control systems are being studied. An important technology in an intelligent control system is recognizing and tracking objects in images. However, existing multi-object tracking technology has problems in accuracy and speed. In this paper, a real-time intelligent control system was implemented using YOLO v5 and YOLO v6 based on a one-shot architecture that increases the accuracy of object tracking and enables fast and accurate tracking even when objects overlap each other or when there are many objects belonging to the same class. The experiment was evaluated by comparing YOLO v5 and YOLO v6. As a result of the experiment, the YOLO v6 model shows performance suitable for the intelligent control system.

최근 지능형 관제 시스템은 다양한 응용 분야에서 빠르게 발전하고 있으며, 딥러닝, IoT, 클라우드 컴퓨팅 등의 기술이 지능형 관제 시스템에 활용하는 방안이 연구되고 있다. 지능형 관제 시스템에서 중요한 기술은 영상에서 객체를 인식하고 추적하는 것이다. 그러나 기존의 다중 객체 추적 기술은 정확도 및 속도에서 문제점을 가지고 있다. 본 논문에서는 객체 추적의 정확성을 높이고, 객체가 서로 겹쳐있거나 동일한 클래스에 속하는 객체들이 많을 경우에도 빠르고 정확하게 추적 가능한 원샷 아키텍처 기반의 YOLO v5와 YOLO v6을 사용하여 실시간 지능형 관제시스템을 구현하였다. 실험은 YOLO v5와 YOLO v6를 비교하여 평가하였다. 실험결과 YOLO v6 모델이 지능형 관제시스템에 적합한 성능을 보여주고 있다. 실험결과 YOLO v6 모델이 지능형 관제시스템에 적합한 성능을 보여주고 있다.

Keywords

Acknowledgement

이 연구는 2022년도 극동대학교 교내연구비 지원에 의하여 수행된 것임(No. FEU2022R05).

References

  1. Ibrahim, S. W., "A comprehensive review on intelligent surveillance systems," Communications in science and technology, Vol. 1, No. 1, 2016.
  2. Kim, I. S., Choi, H. S., Yi, K. M., Choi, J. Y., & Kong, S. G., "Intelligent visual surveillance-a survey," International Journal of Control, Automation and Systems, Vol. 8, No. 5, pp. 926-939, 2010. https://doi.org/10.1007/s12555-010-0501-4
  3. Joshi, K. A., Thakore, D. G., "A survey on moving object detection and tracking in video surveillance system," International Journal of Soft Computing and Engineering, Vol. 2, No. 3, pp. 44-48, 2012.
  4. Elharrouss, O., Almaadeed, N., Al-Maadeed, S., "A review of video surveillance systems," Journal of Visual Communication and Image Representation, Vol. 77, (3),103116, May 2021.
  5. Adrian, A. I., Ismet, P., Petru, P., "An overview of intelligent surveillance systems development," 2018 International Symposium on Electronics and Telecommunications (ISETC), pp.1-6, Timisoara, Romania, Nov. 2018.
  6. Haghighat, A. K., Ravichandra-Mouli, V., Chakraborty, P., Esfandiari, Y., Arabi, S., & Sharma, A., "Applications of deep learning in intelligent transportation systems," Journal of Big Data Analytics in Transportation 2020, Vol. 2, No. 11, pp. 115-145, Aug. 2020. https://doi.org/10.1007/s42421-020-00020-1
  7. Sreenu, G., Durai, S., "Intelligent video surveillance: a review through deep learning techniques for crowd analysis," Journal of Big Data, 6(1), pp.1-27, 2019. https://doi.org/10.1186/s40537-019-0212-5
  8. Girshick, R., Donahue, J., Darrell, T., Malik, J., "Rich feature hierarchies for accurate object detection and semantic segmentation," Proceedings of the IEEE conference on computer vision and pattern recognition, pp.580-587, Columbus, USA, Sep. 2014.
  9. Girshick, R., "Fast r-cnn," Proceedings of the IEEE international conference on computer vision, pp. 1440-1448, Santiago, Chile, Dec. 2015.
  10. Ren, S., He, K., Girshick, R., Sun, J., "Faster r-cnn: Towards real-time object detection with region proposal networks," Advances in neural information processing systems, 28, pp.1-9, 2015.
  11. Redmon, J., Divvala, S., Girshick, R., Farhadi, A., "You only look once: Unified, real-time object detection," Proceedings of the IEEE conference on computer vision and pattern recognition, pp.779-788, Jun. 2016.
  12. Redmon, J., Farhadi, A., "YOLO9000: better, faster, stronger," Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263-7271, Jul. 2017.
  13. He, K., Zhang, X., Ren, S., Sun, J., "Spatial pyramid pooling in deep convolutional networks for visual recognition," IEEE transactions on pattern analysis and machine intelligence, 37, pp1904-1916, 2015. https://doi.org/10.1109/TPAMI.2015.2389824
  14. Gidaris, S., Komodakis, N., "Object detection via a multi-region and semantic segmentation-aware cnn model," Proceedings of the IEEE international conference on computer vision, pp.1134-1142, May 2015.
  15. O'Byrne, M., Sugrue, M., Kokaram, A., "Impact of Video Compression on the Performance of Object Detection Systems for Surveillance Applications," 2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance(AVSS), pp. 1-8, Madrid, Spain, Nov. 2022.
  16. Katsamenis, I., Karolou, E. E., Davradou, A., Protopapadakis, E., Doulamis, A., Doulamis, N., Kalogeras, D., "TraCon: A novel dataset for real-time traffic cones detection using deep learning," Novel & Intelligent Digital Systems: Proceedings of the 2nd International Conference (NiDS 2022), pp. 382-391, 2022.
  17. Li, C., et al., "YOLOv6: A single-stage object detection framework for industrial applications," arXiv:2209.02976, 2022.