본문 바로가기
KERD
논문KCI 등재

YOLOv8을 이용한 실시간 야생동물 로드킬 탐지 기법

A Real-Time Wildlife Roadkill Detection Approach Using YOLOv8

문지훈|김해성
한국사물인터넷학회 (The Korea Internet of Things Society)|2024.10|사물인터넷융복합논문지 (Journal of Internet of Things and Convergence)|제10권 제5호|pp. 185-196

0

조회

0

다운로드

1

인용

0

참고문헌

키워드

교통사고Object Detection야생동물객체 탐지Traffic AccidentYOLOv8Wild Animals로드킬Roadkill

초록

지속적인 도시화와 도로 개발로 인해 야생동물의 로드킬 사고가 심각한 사회적 문제로 대두되고 있다. 특히한국은 높은 도로 밀도로 인해 야생동물이 로드킬 위험에 더욱 노출되어 있다. 본 연구는 최신 객체 탐지 기술인YOLOv8 모델을 활용하여 국내 야생동물 로드킬 사고를 예방하기 위한 객체 탐지 시스템을 제안한다. Roboflow를이용해 6종의 포유류 이미지 데이터를 전처리한 후, YOLOv8 모델을 학습시켜 높은 정확도(mAP50: 0.986, mAP50-95: 0.86)를 달성하였다. 또한, YOLOv5 및 YOLOv7과의 비교 실험을 통해 YOLOv8의 우수성을 입증하였다. 본 연구는 보호색을 가진 동물들에서도 높은 탐지 성능을 보여 로드킬 사고 감소와 야생동물의 안전한 이동을 지원하며, 생태 통로 및 유도 울타리의 설계와 배치에 중요한 기초 자료를 제공한다.

Abstract

Increasing urbanization and road development have led to severe wildlife roadkill incidents, posing a significant social challenge. Especially in Korea, the high road density increases the exposure of wildlife to roadkill risks. This study proposes a wildlife object detection system using the latest object detection technology, YOLOv8, to mitigate domestic wildlife roadkill incidents. Using Roboflow for preprocessing, six mammal species were selected and the YOLOv8 model was trained, achieving high accuracy with mAP50 of 0.986 and mAP50-95 of 0.86. Comparative experiments with YOLOv5 and YOLOv7 demonstrated the superior performance of YOLOv8. The proposed system effectively detects animals even with protective coloration, contributing to the reduction of roadkill incidents and assisting in the design and placement of ecological corridors and guide fences. This research provides an important technological foundation for improving wildlife safety and maintaining ecological balance in urbanized areas.

참고문헌 (35)

  1. S. E. Lee, "Drawing of Habitat Assessment Map and Conservation Value Assessment for Environmental Friendly Road Construction", Journal of Korean Society of Environmental Engineers, 31(8), pp.611~618 (2009)
  2. J. Lee, "A Study on the Analysis of Roadkill Status and the Installation of Ecological Pathway and Guided Fences for Roadkill Prevention in Korea", The Journal of Society for e-Business Studies, 29(1), pp.17~33 (2024)
  3. X. Huang, "Constructing and optimizing urban ecological network in the context of rapid urbanization for improving landscape connectivity", Ecological Indicators, 132, pp.108319~ (2021)
  4. E. Kent, "Life in the fast lane : roadkill risk along an urban–rural gradient", Journal of Urban Ecology, 7(1), pp.juaa039~ (2021)
  5. J. Rew, "Habitat suitability estimation using a two-stage ensemble approach", Remote Sensing, 12(9), pp.1475~ (2020)
  6. J. -H. Park, "The Critical Review of the Lee Myung-Bak Government’s Green Technology Policy-From the Perspective of the Sustainable Technology Policy", ECO, 13(2), pp.99~138 (2009)
  7. D. Andersen, "Biodiversity and Transportation Infrastructure in the Republic of Korea : A Review on Impacts and Mitigation in Developing the Country", Diversity, 13(11), pp.519~ (2021)
  8. F. Lala, "Wildlife roadkill in the Tsavo Ecosystem, Kenya : identifying hotspots, potential drivers, and affected species", Heliyon, 7(3), pp.e06364~ (2021)
  9. H. K. Kweon, "Study on the Status and Cause of the Road Kill for Wildlife Killing Reduce-A Case Study of National Road in Daejeon~Seosan Section-", Journal of Forest and Environmental Science, 24(2), pp.99~109 (2008)
  10. P. Medrano-Vizcaíno, "Roadkill patterns in Latin American birds and mammals", Global Ecology and Biogeography, 31(9), pp.1756~1783 (2022)
  11. Y. Oh, "A Study on the Spatial Correlation between Roadkill and Traffic Accidents on Roads in Chungcheongnam-do", Journal of Environmental Policy and Administration, 26(2), pp.147~166 (2018)
  12. "Deer Fence Height Guide: Your Questions Answered"[URL]
  13. P. R. Armsworth, "Management costs for small protected areas and economies of scale in habitat conservation", Biological Conservation, 144(1), pp.423~429 (2011)
  14. S. -Y. Ahn, "The Mirror-based real-time dynamic projection mapping design and dynamic object detection system research", Journal of Internet of Things and Convergence, 10(2), pp.85~91 (2024)
  15. T. Heyi, "A Research on the Application of Face Recognition Algorithm Based on Convolutional Model and Transformer Model in Community Monitoring System", Journal of Internet of Things and Convergence, 9(5), pp.61~72 (2023)
  16. C. Bang, "Real-time Fall Accident Prediction using Random Forest in IoT Environment", Journal of Internet of Things and Convergence, 10(4), pp.27~33 (2024)
  17. J. Mok, "Performance Improvement of Facial Gesture-based User Interface Using MediaPipe Face Mesh", Journal of Internet of Things and Convergence, 9(6), pp.125~134 (2023)
  18. Y. Li, "Adaptive Enhancement of Low-light Video Images Algorithm Based on Visual Perception", Journal of Internet of Things and Convergence, 10(2), pp.51~60 (2024)
  19. G. Wang, "UAV-YOLOv8 : A small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios", Sensors, 23(16), pp.7190~ (2023)
  20. D.Deepa, "Pothole detection using roboflow convolutional neural networks", Proceedings of the 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS), pp.560~564 (2023)
  21. H. -J. Gwak, "Estimation of fruit number of apple tree based on YOLOv5 and regression model", Journal of IKEEE, 28(2), pp.28~35 (2024)
  22. C. -M. Lee, "A Real-time System for Judging Vehicle Loads and Overloaded using Yolo with Post-Processing Algorithm", Journal of Korean Institute of Intelligent Systems, 33(5), pp.414~422 (2023)
  23. J. M. Kang, "A Study on a Wildlife Detection and Classification Model using YOLOv5", The Journal of Korean Institute of Information Technology, 20(10), pp.21~27 (2022)
  24. L. Aziz, "Exploring Deep Learning-Based Architecture, Strategies, Applications and Current Trends in Generic Object Detection : A Comprehensive Review", IEEE Access, 8, pp.170461~170495 (2020)
  25. Y. -K. Hong, "Estimation of Populations of Moth Using Object Segmentation and an SVM Classifier", Journal of the Korea Academia-Industrial Cooperation Society, 18(11), pp.705~710 (2017)
  26. D. Park, "A Study on the Applicability of Media Videos of Deep Learning Models Related to Computer Vision", Communication Theories, 18(1), pp.111~154 (2022)
  27. J. Moon, "Object detection under the lens of privacy : A critical survey of methods, challenges, and future directions", ICT Express, 10(5), pp.1124~1144 (2024)
  28. R. Kaur, "A comprehensive review of object detection with deep learning", Digital Signal Processing, 132, pp.103812~ (2023)
  29. J. Y. Kim, "A Study on Object Detection using Restructured RetinaNet", Journal of Korea Multimedia Society, 23(12), pp.1531~1539 (2020)
  30. H. Kim, "Automated Facial Wrinkle Segmentation Scheme Using UNet++", KSII Transactions on Internet & Information Systems, 18(8) (2024)
  31. D. -H. Kim, "Design and Implementation of Real-Time Monitoring Platform for Preventing Wild Animals", The Journal of Korean Institute of Communications and Information Sciences, 46(8), pp.1294~1300 (2021)
  32. S. -M. Lee, "Wildlife Vehicle Collision in South Korea:Current Status and Factor Analysis", M.S., pp.2023
  33. Q. Liu, "Small unopened cotton boll counting by detection with MRF-YOLO in the wild", Computers and Electronics in Agriculture, 204, pp.107576~ (2023)
  34. F. Ullah, "Explainable artificial intelligence approach in combating real-time surveillance of COVID19 pandemic from CT scan and X-ray images using ensemble model", The Journal of Supercomputing, 78(17), pp.19246~19271 (2022)
  35. "The Chosun Daily"[URL]

관련 논문AI추천

YOLO에 기반한 유해 야생동물 피해방지 및 퇴치 시스템 구현이충호, 채민욱한국융합신호처리학회 · 융합신호처리학회 논문지2022 · 제23권 제3호YOLOv8 기반 딥러닝 모델을 이용한 동적 교통객체 검출 성능 비교 분석 연구류찬무, 장봉주, 정인택, 최우철, 셔흐루흐한국ITS학회 · 한국ITS학회 논문지2024 · 제23권 제6호YOLOv8 기반 차량 탐지 및 분류 시스템의 설계와 성능 평가심철준한국차세대컴퓨팅학회 · 한국차세대컴퓨팅학회 논문지2025 · 제21권 제1호A Design and Implementation of Real-time Automatic Traffic Violation Detection and Reporting System based on Edge Devices곽호영, 남정학, 선민수, 송현석, 이세종, 장은서, 정윤지한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2025 · 제30권 제5호객체탐지를 이용한 캠퍼스내 교통안전 시스템 개발이건, 양인범, 우지영, 이나영, 이민섭, 홍윤정한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2024 · 제29권 제1호기계학습 기반의 로드킬 발생 예측과 영향 요인 탐색에 대한 연구김지영, 허소진한국환경영향평가학회 · 환경영향평가2024 · 제33권 제2호

이 간행물의 다른 논문 (27건)

MediaPipe 모델을 이용한 손-얼굴 혼성 제스처 인터페이스에 관한 연구곽노윤pp. 1-11클라우드 컴퓨팅과 기계학습 기법을 이용한 주식의 기술적 분석 지표 최적화 및 주가 추세 변동 예측김훈희pp. 13-18산업용 로봇과 2D 비전을 연동한 6D 자세 추정 방법 연구장양수, 장경배pp. 19-26Research on Multi-Vehicle and Multi-Task Route Planning for Autonomous Delivery Robots in Parks노크, 민병원pp. 27-37A Study on the Effectiveness of Advanced Life Support Education and Reeducation Program Based on High-Fidelity Simulation박선영, 김지현, 양정하pp. 39-44
원문 보기