Efficient Multiscale Object-based Superpixel Framework

04/07/2022
by   Felipe Belém, et al.
0

Superpixel segmentation can be used as an intermediary step in many applications, often to improve object delineation and reduce computer workload. However, classical methods do not incorporate information about the desired object. Deep-learning-based approaches consider object information, but their delineation performance depends on data annotation. Additionally, the computational time of object-based methods is usually much higher than desired. In this work, we propose a novel superpixel framework, named Superpixels through Iterative CLEarcutting (SICLE), which exploits object information being able to generate a multiscale segmentation on-the-fly. SICLE starts off from seed oversampling and repeats optimal connectivity-based superpixel delineation and object-based seed removal until a desired number of superpixels is reached. It generalizes recent superpixel methods, surpassing them and other state-of-the-art approaches in efficiency and effectiveness according to multiple delineation metrics.

READ FULL TEXT

page 3

page 7

page 9

page 15

research
07/08/2020

Superpixel Segmentation using Dynamic and Iterative Spanning Forest

As constituent parts of image objects, superpixels can improve several h...
research
09/16/2020

DAER to Reject Seeds with Dual-loss Additional Error Regression

Many vision tasks require side information at inference time—a seed—to f...
research
01/30/2018

An Iterative Spanning Forest Framework for Superpixel Segmentation

Superpixel segmentation has become an important research problem in imag...
research
02/04/2018

Efficient Video Object Segmentation via Network Modulation

Video object segmentation targets at segmenting a specific object throug...
research
02/16/2018

ISEC: Iterative over-Segmentation via Edge Clustering

Several image pattern recognition tasks rely on superpixel generation as...
research
07/30/2019

An Empirical Study of Propagation-based Methods for Video Object Segmentation

While propagation-based approaches have achieved state-of-the-art perfor...
research
06/07/2021

HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation

Superpixels serve as a powerful preprocessing tool in many computer visi...

Please sign up or login with your details

Forgot password? Click here to reset