A Modified SUSAN Corner Detection Algorithm Based on Adaptive Gradient Threshold for Remote Sensing Image

Abstract

Remote Sensing image registration plays an important role in image processing. The exact corner detection is vital to image registration. A modified SUSAN corner detection algorithm based on adaptive gradient threshold is presented. Ensuring the gray threshold automatically is the key of the new algorithm. First, the Traditional SUSAN principle and the new algorithm are discussed carefully. Then, testing the two methods that have been mentioned with the software of MATLAB 7.0 using the ASTER remote sensing data. Experimental result indicates that the proposed algorithm is more adaptable and has better applicable value.