http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Estimation of Cloud Motion Vector Based on the Optical Flow Method to Forecast Cloud Movement
Rial Arifin,Hyunjin Lee 대한설비공학회 2019 대한설비공학회 학술발표대회논문집 Vol.2019 No.-
One important step in forecasting short-term solar irradiance is to predict the movement of clouds. The optical flow method can be used for tracking and estimating the motion of cloud using images. It assumes that a feature point maintains constant brightness across the images. The optical flow method is comprised of a process of calculating the motion between two or more images that can be used to extract the cloud motion vector (CMV) from each pixel of an image. The cloud motion is predicted by using CMV’s data from the previous cloud movements. Using Korea Meteorological Agency (KMA) satellite images, we predicted the orientations of 15 minutes ahead cloud movement and compared them to the actual cloud movement. The errors of forecast cloud movement were evaluated in terms of the mean absolute error (MAE) and the root mean square error (RMSE).