关键词: 图像特征匹配, 加速稳健特征, 遥感图像处理, 局部归一化, 扩展的特征描述符, Image features matching, Speed up robust features, Remote sensing image processing, Local normalization, Extended feature descriptor

Abstract: To solve the classical methods’ problems of long executing time or low accuracy, this paper proposes an extended SURF descriptor. On the method using SURF, the proposed method uses local normalization information and second-order gradient values of neighborhood regions to build a new one. Not only does this method perform as fast as SURF algorithm, but it also fully employs the image grayscale information and details. Considering the executing time and rate, experimental results presented in this paper show that the proposed method is more robust than classical methods.