Detection of and compensation for shadows in colored urban aerial images

A new method for shadow detection in colored urban aerial images is proposed. First, a new imaging model of shadows is presented, which indicates that hue values of shadowed image areas are larger than those of these areas non-shadowed. Based on this model, a thresholding technique is employed to detect shadowed areas. After detection, the Retinex technique is applied to shadowed and non-shadowed areas individually to compensate for shadows. Experiment results show the effectiveness of the proposed method.