USING THE YOLOV3 METHOD ENHANCED THE QUALITY OF OBJECT DETECTING FOR SURVEILLANCE SYSTEM, PROTECTION OF THE ISLAND FACILITIES

176 views

Authors

  • Chu Van Hoat (Corresponding Author) Institute of Military Technical Automation, Academy of Military Science and Technology
  • Vu Minh Khiem Institute of Military Technical Automation, Academy of Military Science and Technology
  • Vu Xuan Vuong Institute of Military Technical Automation, Academy of Military Science and Technology
  • Nguyen Dinh Long Institute of Military Technical Automation, Academy of Military Science and Technology

DOI:

https://doi.org/10.54939/1859-1043.j.mst.76.2021.137-143

Keywords:

Auto-detection; Security monitoring system; Yolov3.

Abstract

Improvement and modernization of the security surveillance system, protecting bases on the island is a vital duty to our military nowadays. Previously, machine learning methods have been used to construct object detectors, but the results of the experimental process in the ocean and islands did not meet the specified requirements, and the false detection rate was still high. In this paper, Yolov3 algorithm is proposed to automatically detect objects appearing in the surveillance area.

References

[1]. Kim C, Lee Y, Park J et al. "Diminishing unwanted objects based on object detection using deep learning and image inpainting," 2018 International Workshop on Advanced Image Technology (IWAIT), 2018, 1-3.

[2]. Chu V H, Vũ M K. “Xây dựng thuật toán tự động phát hiện đối tượng trên nền ảnh động cho bệ quay quét giám sát an ninh,” Tạp chí Nghiên cứu KH&CN quân sự, Số Đặc san TĐH, 04 – 2019.

[3]. Uijlings J R R, van de Sande K E A, Gevers T, et al. “Selective Search for Object Recognition,” Int J Comput Vis 104(2013), 154–171.

[4]. Girshick R. “Fast r-cnn,” Proceedings of the IEEE international conference on computer vision, 2015, 1440-1448.

[5]. Ren S, He K, Girshick R, et. al. “Faster r-cnn: Towards real-time object detection with region proposal networks,” preprint arXiv:1506.01497, 2015.

[6]. Liu W, Anguelov D, Erhan D, et al. “Ssd: Single shot multibox detector,” European conference on computer vision, 2016, 21-37.

[7]. Fu C Y, Liu W, Ranga A, et al. “Dssd: Deconvolutional single shot detector,” arXiv preprint arXiv:1701.06659, 2017.

[8]. Cui H, Yang Y, Liu M, et al. “Ship detection: an improved YOLOv3 method,” OCEANS 2019-Marseille, 2019: 1-4.

[9]. Wang Q, Shen F, Cheng L, et al. “Ship detection based on fused features and rebuilt YOLOv3 networks in optical remote-sensing images,” International Journal of Remote Sensing, 2021, 42(2): 520-536.

[10]. Russakovsky O, Deng J, Su H, et al. “Imagenet large scale visual recognition challenge,” International Journal of Computer Vision, 2015, 115(3): 211-252.

Published

12-12-2021

How to Cite

Chu Văn Hoạt, Khiêm, Vượng, and Nguyễn Đình Long. “USING THE YOLOV3 METHOD ENHANCED THE QUALITY OF OBJECT DETECTING FOR SURVEILLANCE SYSTEM, PROTECTION OF THE ISLAND FACILITIES”. Journal of Military Science and Technology, no. 76, Dec. 2021, pp. 137-43, doi:10.54939/1859-1043.j.mst.76.2021.137-143.

Issue

Section

Research Articles