UMMS: Efficient Superpixel Segmentation Driven by a Mixture of Spatially Constrained Uniform Distribution

Abstract

A novel superpixel segmentation approach driven by uniform mixture model with spatially constrained (UMMS) is proposed. Under this algorithm, each observation, i.e. pixel is first represented as a fivedimensional vector which consists of colour in CLELAB space and position information. And then, we define a new uniform distribution through adding pixel position, so that this distribution can describe each pixel in input image. Applied weighted 1-Norm to difference between pixels and mean to control the compactness of superpixel. In addition, an effective parameter estimation scheme is introduced to reduce computational complexity. Specifically, the invariant prior probability and parameter range restrict the locality of superpixels, and the robust mean optimization technique ensures the accuracy of superpixel boundaries. Finally, each defined uniform distribution is associated with a superpixel and the proposed UMMS successfully implements superpixel segmentation. The experiments on BSDS500 dataset verify that UMMS outperforms most of the state-of-theart approaches in terms of segmentation accuracy, regularity, and rapidity.