Superpixel Segmentation with Adaptive Nonlocal Random Walk

Abstract

In this paper, we propose a novel superpixel segmentation method using adaptive nonlocal random walk (ANRW) algorithm. There are three main steps in our image superpixel algorithm. Our method is based on the random walk model, and the seed points are produced to generate the initial superpixels by a gradient-based method in the first step. In the second step, the ANRW is proposed to get the initial superpixels by adjusting the nonlocal random walk (NRW) to be more suitable for image segmentation. In the last step, we merge these small superpixels to get the final regular and compact superpixels. The experimental results have demonstrated that our method achieves better performance than the state-of-the-art methods.