Abstract: Cloud coverage has a crucial impact on photovoltaic power generation. The key point of cloud cover estimation is to correct the distortion of the all-sky image and to design the segmentation method of ground-based cloud with high accuracy. Aiming at these two problems,this paper proposes a cloud cover estimation model based on decision fusion strategy. Firstly,the fisheye distortion correction algorithm based on the perspective projection model of multi-dimensional spherical section is used to obtain multi-directional local restoration images. Secondly,the decision fusion method of the nearest neighbor restoration center is used to modify the data after multidimensional restoration image segmentation,and finally,the estimated cloud cover is obtained. Experimental results show that this method can restore the proportion relationship between cloud and sky better and improve the accuracy of cloud cover estimation.