DOI QR코드

DOI QR Code

Implementation of Prevention and Eradication System for Harmful Wild Animals Based on YOLO

YOLO에 기반한 유해 야생동물 피해방지 및 퇴치 시스템 구현

  • Min-Uk Chae (Graduate School of Information and Communication Engineering, Hanbat National University) ;
  • Choong-Ho Lee (Graduate School of Information and Communication Engineering, Hanbat National University)
  • 채민욱 (한밭대학교 정보통신전문대학원) ;
  • 이충호 (한밭대학교 정보통신전문대학원)
  • Received : 2022.09.04
  • Accepted : 2022.09.29
  • Published : 2022.09.30

Abstract

Every year, the number of wild animals appearing in human settlements increases, resulting in increased damage to property and human life. In particular, the damage is more severe when wild animals appear on highways or farmhouses. To solve this problem, ecological pathways and guide fences are being installed on highways. In addition, in order to solve the problem in farms, horn repelling using sensors, installing a net, and repelling by smell of excrement are being used. However, these methods are expensive and their effectiveness is not high. In this paper, we used YOLO (You Only Look Once), an AI-based image analysis method, to analyze harmful animals in real time to reduce malfunctions, and high-brightness LEDs and ultrasonic frequency speakers were used as extermination devices. The speaker outputs an audible frequency that only animals can hear, increasing the efficiency to only exterminate wild animals. The proposed system is designed using a general-purpose board so that it can be installed economically, and the detection performance is higher than that of the devices using the existing sensor.

해마다 야생동물이 인간의 거주지에 출몰하는 횟수가 증가하여 재산 및 인명 피해가 증가하고 있다. 특히, 고속도로나 농가에 야생동물이 출몰하는 경우에 그 피해가 더 심하다. 이런 문제점을 해결하기 위해 고속도로에는 생태통로와 유도펜스를 설치하였다. 또한, 농가에서도 문제를 해결하기 위해 센서를 이용한 경적 퇴치기, 그물망 설치, 배설물로 퇴치 하는 등방법을 쓰고 있으나 고가의 비용이 들며 그 효과가 높지 않다. 본 논문에서는 AI 기반 영상분석 방법인 YOLO(You Only Live Once)를 이용하여 유해동물을 실시간 분석하여 오작동을 줄였고, 퇴치장치로 고휘도 LED와 초음파 주파수 스피커를 이용였다. 스피커는 동물들만 들을 수 있는 가청주파수를 출력하여 야생동물만 퇴치하도록 효율성을 높였다. 제안하는 시스템은, 경제적으로 설치할 수 있도록 범용 보드를 사용하여 설계되어 있으며 기존의 센서를 이용한 장치들보다 감지 성능이 높다.

Keywords

References

  1. J. S. Song, G. J. Lee, and B. H. Han, "A Study on the Road-kill Decrease Effect of Mammals Followed by Installation of Highway Wild-life Fences," Korean Society of Environment and Ecology, pp. 123-125, 2009.
  2. H. K. Kweon, Y. H. Choi, M. J Kim, and J. W. Lee, "Study on the Status and Cause of the Road Kill for Wildlife Killing Reduce," Journal of Forest and Environmental Science, Vol. 24, No. 2, pp. 99-109, 2008.
  3. Ministry of Environment Korea, (2019, June). Status of Harmful Wildlife Damage. [Online]. Available: http://me.go.kr/home/web/policy_data/.
  4. T. Y. Lee, Object Detection of Road Facilities Using YOLOv3 for High Definition Map Updates, KERIS Theses & Dissertations, Vol. 34, No. 1, pp. 251-260, 2022.
  5. J. Redmon, S. Divvala, R. Girshick, A. Farhadi, "You Only Look Once: Unified, Real-time Object Detection," 2016 IEEE Conference on, pp. 779-788, 2015.
  6. A. Lee, S. Park, J. Hong, "Development of a Yolo-Based System for Prevention of Wildlife Damage," Proceedings of Conf. of 2018 KIISE, pp.1897-1899, 2018.
  7. J. S. Lee, M. G. Kim and H. I. Kim, "Camera and LiDAR Sensor Fusion for Improving Object Detection," Journal of Broadcast Engineering, Vol. 24, No. 4, pp. 580-591, 2019. https://doi.org/10.5909/JBE.2019.24.4.580
  8. C. H. Moon, "Design of an Ultrasonic Speaker with Piezoelectric Ceramic and Fabrication of its Prototypes," Proceedings of the Acoustical Society of Korea Conference, pp. 5-8, 1998.