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
      • Field Scene Recognition for Navigating Autonomous Agricultural Vehicle

        ( Yoshinari Morio ),( Yuta Sawada ),( Masataka Shioji ),( Motoki Tanaka ),( Katsusuke Murakami ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.1

        In this study, four agricultural vehicle navigation systems, namely, two different types of vehicle position estimation systems for self-localization of an autonomous agricultural vehicle, an obstacle detection system for safety self-driving, and an agricultural key-objects recognition system for intelligent worker assistance, were developed by using image processing system without using GNSS and LiDAR. Firstly, in the two types of vehicle position estimation systems, the position of a vehicle could be estimated by matching an input field scene image to the training scene images captured along each of targeted traveling routes. The scene images were captured by using a three-camera-type of capture system with left camera, front camera, and right camera. Secondly, in the obstacle detection system, obstacles on a road, ditches along a road, and the level difference between a traveling road and a farm field were detected by using the stereo camera built with two web camera. The obstacles, ditches, and the level difference were recognized by in real time estimating 3D ground plane. Finally, in the agricultural key-objects recognition system, key-object types(workers, trucks, containers, agricultural machines) and key-posture types(standing, squat, stoop, sitting), key-worker-direction types (front, back, left, right), and container contents amount could be recognized by using deep learning based system of YOLO. The experimental results demonstrated the potential of our systems for navigating an autonomous vehicle in agricultural fields.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼