ISEC: Iterative over-Segmentation via Edge Clustering

02/16/2018
by   Marcelo Santos, et al.
0

Several image pattern recognition tasks rely on superpixel generation as a fundamental step. Image analysis based on superpixels facilitates domain-specific applications, also speeding up the overall processing time of the task. Recent superpixel methods have been designed to fit boundary adherence, usually regulating the size and shape of each superpixel in order to mitigate the occurrence of undersegmentation failures. Superpixel regularity and compactness sometimes imposes an excessive number of segments in the image, which ultimately decreases the efficiency of the final segmentation, specially in video segmentation. We propose here a novel method to generate superpixels, called iterative over-segmentation via edge clustering (ISEC), which addresses the over-segmentation problem from a different perspective in contrast to recent state-of-the-art approaches. ISEC iteratively clusters edges extracted from the image objects, providing adaptive superpixels in size, shape and quantity, while preserving suitable adherence to the real object boundaries. All this is achieved at a very low computational cost. Experiments show that ISEC stands out from existing methods, meeting a favorable balance between segmentation stability and accurate representation of motion discontinuities, which are features specially suitable to video segmentation.

READ FULL TEXT

page 3

page 10

page 12

page 20

page 22

page 25

research
07/21/2021

Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation

Learning segmentation from noisy labels is an important task for medical...
research
09/28/2022

Streaming Video Temporal Action Segmentation In Real Time

Temporal action segmentation (TAS) is a critical step toward long-term v...
research
06/02/2011

A Novel Image Segmentation Enhancement Technique based on Active Contour and Topological Alignments

Topological alignments and snakes are used in image processing, particul...
research
03/11/2019

Generating superpixels using deep image representations

Superpixel algorithms are a common pre-processing step for computer visi...
research
10/05/2019

Object Segmentation Tracking from Generic Video Cues

We propose a light-weight variational framework for online tracking of o...
research
04/07/2022

Efficient Multiscale Object-based Superpixel Framework

Superpixel segmentation can be used as an intermediary step in many appl...
research
10/16/2015

Multiresolution hierarchy co-clustering for semantic segmentation in sequences with small variations

This paper presents a co-clustering technique that, given a collection o...

Please sign up or login with your details

Forgot password? Click here to reset