RISS 학술연구정보서비스

검색
다국어 입력

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

변환된 중국어를 복사하여 사용하시면 됩니다.

예시)
  • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
  • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
닫기
    인기검색어 순위 펼치기

    RISS 인기검색어

      검색결과 좁혀 보기

      선택해제

      오늘 본 자료

      • 오늘 본 자료가 없습니다.
      더보기
      • 무료
      • 기관 내 무료
      • 유료
      • KCI등재

        Dynamic Beehive Detection and Tracking System Based on YOLO V5 and Unmanned Aerial Vehicle

        Gao Peng,이강빈,쿠스위디얀토 루카스 위쿠,유승화,Hu Kai,Liang Gaotian,Chen Yufeng,Wang Weixing,Liao Fei,정유석,전문석,최인찬,한웅철 한국농업기계학회 2022 바이오시스템공학 Vol.47 No.4

        Purpose With urban development and improvements in human living conditions, wild beehives in densely populated areas present a threat to human safety. The traditional manual method of clear beehives may result in secondary injury to humans. Methods This paper proposes a beehive detection model based on YOLO V5 by introducing the Shufe Block V2 and depthwise separable convolution (DSC) modules to decrease the original model parameters. The model can be deployed on edge computation devices such as Raspberry 4B with good detection accuracy. The PID algorithm and dual servo motors were combined with the object detection model to track the beehive automatically. The results of experiments showed that the inference speed of the improved beehive detection model was 92.5% faster than the original YOLO V5s model, although the detection accuracy and other indicators were not signifcantly diferent. Results The accuracy of the system in this study was as high as 96% in real-time detection, and the maximum recognition distance was 2.5 m. The performance test results of the system deployed on an unmanned aerial vehicle (UAV) showed that 90% of the beehive tracking process could be completed within 2 s, positioning the object in the center of the images collected by the camera. At the same time, when the UAV was moving at random, the detection and tracking system could still follow the beehive quickly and automatically. Conclusion The detection model and tracking system established in this paper provide important support to reduce the secondary damage to the rescue workers that may occur in beehive governance.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼