Semi-supervised Segmentation Fusion of Multi-spectral and Aerial Images

TL;DR

This paper introduces a semi-supervised segmentation fusion method that combines multiple segmentation outputs using consensus and convex optimization, improving accuracy on multi-spectral and aerial images.

Contribution

It proposes a novel semi-supervised segmentation fusion algorithm that incorporates side information as constraints, enhancing segmentation performance over existing methods.

Findings

Outperforms individual segmentation algorithms on benchmark datasets

Effective in integrating multi-spectral and aerial image data

Reduces computational complexity compared to NP-hard solutions

Abstract

A Semi-supervised Segmentation Fusion algorithm is proposed using consensus and distributed learning. The aim of Unsupervised Segmentation Fusion (USF) is to achieve a consensus among different segmentation outputs obtained from different segmentation algorithms by computing an approximate solution to the NP problem with less computational complexity. Semi-supervision is incorporated in USF using a new algorithm called Semi-supervised Segmentation Fusion (SSSF). In SSSF, side information about the co-occurrence of pixels in the same or different segments is formulated as the constraints of a convex optimization problem. The results of the experiments employed on artificial and real-world benchmark multi-spectral and aerial images show that the proposed algorithms perform better than the individual state-of-the art segmentation algorithms.