• 제목/요약/키워드: Hot Spot Recognition

검색결과 3건 처리시간 0.019초

Hot Spot Detection of Thermal Infrared Image of Photovoltaic Power Station Based on Multi-Task Fusion

  • Xu Han;Xianhao Wang;Chong Chen;Gong Li;Changhao Piao
    • Journal of Information Processing Systems
    • /
    • 제19권6호
    • /
    • pp.791-802
    • /
    • 2023
  • The manual inspection of photovoltaic (PV) panels to meet the requirements of inspection work for large-scale PV power plants is challenging. We present a hot spot detection and positioning method to detect hot spots in batches and locate their latitudes and longitudes. First, a network based on the YOLOv3 architecture was utilized to identify hot spots. The innovation is to modify the RU_1 unit in the YOLOv3 model for hot spot detection in the far field of view and add a neural network residual unit for fusion. In addition, because of the misidentification problem in the infrared images of the solar PV panels, the DeepLab v3+ model was adopted to segment the PV panels to filter out the misidentification caused by bright spots on the ground. Finally, the latitude and longitude of the hot spot are calculated according to the geometric positioning method utilizing known information such as the drone's yaw angle, shooting height, and lens field-of-view. The experimental results indicate that the hot spot recognition rate accuracy is above 98%. When keeping the drone 25 m off the ground, the hot spot positioning error is at the decimeter level.

Peste des petits ruminants in Pakistan; past, present and future perspectives

  • Abubakar, Muhammad;Irfan, Muhammad;Manzoor, Shumaila
    • Journal of Animal Science and Technology
    • /
    • 제57권11호
    • /
    • pp.32.1-32.8
    • /
    • 2015
  • Peste des petits ruminants (PPR) is considered to be one of the main constraints to enhancing the productivity of goats and sheep in regions where it is present and becoming endemic. PPR was recognized in Pakistan in early 1990s but got importance during the Participatory Disease Surveillance (PDS) of Rinderpest Eradication Campaign. Lot of research work has been initiated during last decade towards disease epidemiology, risk factor recognition, laboratory diagnosis, vaccination and demonstration of control strategies. Although there are ongoing projects working towards the progressive control of the disease in country yet there is need to have a national level control program for PPR. Also there is need to have comprehensive social economic surveys, disease hot spot recognition and identification of role of other species in disease transmission. With combined efforts of local and national authorities and political will, there is high likelihood that this devastating disease can be controlled and eventually eradicated in near future.

열처리 장비의 Safety를 위한 딥러닝 기반 영상처리 시스템 (Image Processing System based on Deep Learning for Safety of Heat Treatment Equipment)

  • 이정훈;이로운;홍승택;김영곤
    • 한국인터넷방송통신학회논문지
    • /
    • 제20권6호
    • /
    • pp.77-83
    • /
    • 2020
  • 열처리 시설은 뿌리산업 중에서 고열에 의한 열악한 환경과 긴 근로시간 등으로 원격 IOT 시스템의 적용 범위가 확대되는 상황이다. 이러한 열처리 공정 환경에서 IOT 미들웨어는 사물인터넷 기기(센서 등)의 데이터 정보를 해석하고 관리하며 제어할 수 있는 중추적 역할이 요구된다. 그간 열처리 원격에서 제어하는 시스템은 현장 상황에 대한 전반적 감시 없이 작업자의 일괄 시스템 명령으로 운영되었다. 하지만 열처리 시설의 안전성과 정밀한 제어를 위해서는 다양한 센서 컨트롤과 주변 작업환경 인지가 필요하다. 본 논문에서 제시한 열처리 안전지원 시스템은 그에 대한 해결책으로 열화상 감지를 통해 열처리로의 작업인력 접근을 파악하고 원격에서 작업 가동 시 열처리 장비의 Safety를 위한 지원시스템을 제안하였다. 또한 일반적인 고정된 열점 감시 기반 열화상 분석보다 더욱 빠르고 정확한 인식을 위해 DNN 딥러닝 네트워크를 활용한 OPEN CV 기반 열화상 분석 시스템을 구성하였다. 이를 통해 열처리 산업에 특성화된 안전관리 지원과 향후 열처리 환경에서 범용적으로 활용 할 수 있는 시스템을 제안하고자 한다.