Uniform Distribution of Multiple Features for Remote Sensing Optical Image Matching

Uniform distribution of selected features is one of the important factors in optical image matching. In this paper, an effective scheme is proposed to obtain a uniform distribution of the extracted features. At first, two different types of operators namely scale invariant feature transform (SIFT) and multi-scale Harris detector are employed to extract initial features from the optical images. Then, the well distributed and robust features are selected from these initial features and these are considered as final features. After that, the input optical images are matched through the feature matching process by using the selected features. The proposed scheme can obtain better distribution of matching pairs than the state-of-the-art methods. Experiments on three sets of remote sensing optical image pairs verify the performance of the developed algorithm.