Research and practice of a fisheye image based approach for solar orientation recognition

A solar tracking approach based on fisheye images is proposed. First, processing the (H, S, I) components, the high light areas are enhanced. Then the sun areas are recognized according to the contour, offset and magnitude of transformed areas; the sun´s azimuth and altitude angle is derived from the sun area barycentre. Experimental results show that our proposed approach can not only located the sun orientation accurately in ordinary environment, but it is also workable under occlusion and image distortion.