DeepAI AI Chat
Log In Sign Up

Superpixel Segmentation using Dynamic and Iterative Spanning Forest

by   F. C. Belem, et al.
University of Campinas

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.


page 1

page 2

page 3

page 4


An Iterative Spanning Forest Framework for Superpixel Segmentation

Superpixel segmentation has become an important research problem in imag...

Efficient Multiscale Object-based Superpixel Framework

Superpixel segmentation can be used as an intermediary step in many appl...

Spanning eulerian subdigraphs in semicomplete digraphs

A digraph is eulerian if it is connected and every vertex has its in-deg...

Towards an intelligent VNS heuristic for the k-labelled spanning forest problem

In a currently ongoing project, we investigate a new possibility for sol...

A Learning-based Variable Size Part Extraction Architecture for 6D Object Pose Recovery in Depth

State-of-the-art techniques for 6D object pose recovery depend on occlus...