Thresholding-based remote sensing image segmentation using mean absolute deviation algorithm

Abstract

Simple and effective segmentation algorithms are required for remote sensing images because of their mass data and complex texture features. An algorithm based on minimum class mean absolute deviation (MCMAD) is proposed. First, a two-dimensional (2-D) histogram is constructed by a median filter and gray process. Second, by using a diagonal projection, the 2-D histogram of remote sensing images is transformed into a one-dimensional (1-D) histogram to decrease the computational complexity. Finally, class mean absolute deviation of each threshold in the 1-D histogram is calculated and the threshold corresponding to the MCMAD is considered as the optimal segmentation threshold. To improve performance, we introduce spectral information into the MCMAD algorithm and the results of spectral bands are combined to get final segmentation results. Because most of the background used in our experiment is vegetation, we introduce a normalized difference vegetation index band into our algorithm and use the MCMAD algorithm on it. Experimental results show that our algorithms not only perform better for remote sensing images but also meet time requirements.