Shadow removal algorithm for aerial images of photovoltaic array unmanned aerial vehicle

The invention provides a shadow removal algorithm for an aerial image of a photovoltaic array unmanned aerial vehicle, and the algorithm comprises the following steps: (a) a user inputs a shadow region and a non-shadow region in a stroke indication image, and constructs a KNN classifier to classify pixels according to the shadow region and the non-shadow region; (b) setting a threshold condition by using the OTSU, and detecting a shadow; (c) sampling the shadow boundary, determining the position of each sampling line by applying a bidirectional search algorithm, and removing abnormal samplinglines according to the lengths of the sampling lines and a DBSCAN algorithm; and (d) removing shadows through shadow proportion estimation and illumination recovery to obtain a shadow-free image. Compared with a superposition method and a YCbCr channel method, it is shown that the shadow removing effect of the algorithm is better than that of other two algorithms, image information is completely reserved, and a more real