Superpixel Segmentation using Dynamic and Iterative Spanning Forest

TL;DR

This paper introduces Dynamic ISF, a novel superpixel segmentation method that iteratively refines seed selection and edge relevance to improve segmentation accuracy, especially with fewer superpixels, outperforming existing seed-based methods.

Contribution

The paper proposes Dynamic ISF, a seed-based superpixel segmentation approach with dynamic arc-weight estimation and iterative seed refinement, enhancing segmentation quality over prior methods.

Findings

DISF reconstructs relevant edges more effectively than region merging algorithms.

DISF outperforms other seed-based superpixel methods on multiple datasets.

Dynamic arc-weight estimation improves superpixel delineation.

Abstract

As constituent parts of image objects, superpixels can improve several higher-level operations. However, image segmentation methods might have their accuracy seriously compromised for reduced numbers of superpixels. We have investigated a solution based on the Iterative Spanning Forest (ISF) framework. In this work, we present Dynamic ISF (DISF) -- a method based on the following steps. (a) It starts from an image graph and a seed set with considerably more pixels than the desired number of superpixels. (b) The seeds compete among themselves, and each seed conquers its most closely connected pixels, resulting in an image partition (spanning forest) with connected superpixels. In step (c), DISF assigns relevance values to seeds based on superpixel analysis and removes the most irrelevant ones. Steps (b) and (c) are repeated until the desired number of superpixels is reached. DISF has the chance to reconstruct relevant edges after each iteration, when compared to region merging algorithms. As compared to other seed-based superpixel methods, DISF is more likely to find relevant seeds. It also introduces dynamic arc-weight estimation in the ISF framework for more effective superpixel delineation, and we demonstrate all results on three datasets with distinct object properties.