Short-time cloud picture tracking method based on optical flow method

Abstract

The invention discloses a short-time cloud picture tracking method based on an optical flow method. The method comprises: firstly, collecting real-time sky pictures through an all-sky imager, and removing irrelevant factors such as buildings in the images are removed; secondly, utilizing RBG color information of the image to separate pixels of the cloud from pixels of the sky; and finally, comparing the same cloud pixels of the two frames to obtain an edge position and a speed vector of the cloud, predicting the edge position of the cloud at the next moment, and comparing the edge position with the sun position to realize prediction. The method can achieve the recognition and prediction of the position of the cloud picture, is higher in accuracy, is high in speed, is high in universality,is good in robustness, and can be used for an irradiation intensity prediction or solar photovoltaic power output prediction system.

Description

technical field [0001] The invention relates to a short-term cloud image tracking method, in particular to a short-term cloud image tracking method based on an optical flow method. Background technique [0002] Drifting clouds can obscure the sun, causing significant fluctuations in power output from solar power systems. Predicting the position of the cloud cover provides enough time to smooth out the power output. At present, the commonly used photovoltaic power prediction methods are based on historical data for data analysis to achieve power prediction, and the time scale is basically based on the day, so the impact of cloud movement on power is directly ignored. However, traditional meteorological data such as weather forecasts can only predict data such as temperature, rainfall probability, and wind speed within a certain period of time. Predict short-term cloud position changes, and short-term cloud position prediction can only be realized through images. Therefore,...

AI Technical Summary

Problems solved by technology

However, the existing cloud image tracking method usually regards the cloud as an object with a constant shape, and tracks and predicts it by setting the center of mass, which does not conform to the law of cloud motion in reality.

Images