Method for identifying clouds and sky of sky image based on improved k-means clustering algorithm

Abstract

The invention provides a method for identifying the clouds and sky of a sky image based on an improved k-means clustering algorithm. The method comprises the steps of extracting red channel values R, green channel values G, blue channel values B from the sky image to form a red channel value R matrix, a green channel value G matrix, a blue channel value B matrix and an R / B*100 matrix, and extracting a characteristic matrix; determining an initial clustering number and an initial clustering center; based on the improved k-means clustering algorithm, clustering according to the initial clustering center, thus obtaining a new clustering center; and clustering according to the new clustering center, determining the type of an area to which each pixel point belongs according to the clustering result, and drawing a cloud and sky identification image. According to the method for identifying the clouds and sky of the sky image based on the improved k-means clustering algorithm, the extracting effect is stable; the three color components are used as a whole for clustering, and the R / B*100 column vector with high cloud and sky contrast ratio is also added, so that compared with the method of using a global threshold to perform cloud and sky identification on a gray level image only, the method for identifying the clouds and sky of the sky image based on the improved k-means clustering algorithm is greatly improved in adaptive capacity in image identification and can solve the problem of poor adaptation in the prior art.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a cloud recognition method for sky images based on an improved k-means clustering algorithm. Background technique [0002] Due to the non-renewability of conventional fossil fuels and the problems of climate change and environmental pollution caused by the use of fossil fuels, renewable energy power generation, mainly wind power and photovoltaics, has been developed. The decisive factor for solar power generation is the intensity of the ground receiving solar short-wave radiation. The shading effect of clouds is the main cause of random fluctuations in the incoming solar radiation. The short-term prediction of photovoltaic power generation cannot capture the instantaneous and large fluctuations in output power caused by the instantaneous occlusion of clouds, resulting in limited prediction accuracy. Therefore, the accuracy of cloud key feature extraction and de...

AI Technical Summary

Problems solved by technology

[0004] The invention provides a sky image cloud recognition method based on an improved k-means clustering algorithm to solve the problem of poor adaptability of the prior art

Images