CEU-Net: Ensemble Semantic Segmentation of Hyperspectral Images Using Clustering

TL;DR

CEU-Net introduces an ensemble CNN approach that leverages clustering to improve hyperspectral image segmentation, especially in complex and diverse land cover scenarios, outperforming existing methods.

Contribution

The paper presents CEU-Net, a novel ensemble model that combines spectral information from clustered pixels, enhancing segmentation accuracy without relying solely on patching.

Findings

CEU-Net outperforms state-of-the-art methods on multiple datasets.

CEU-Net achieves competitive results with and without patching.

High performance demonstrated on Botswana, KSC, and Salinas datasets.

Abstract

Most semantic segmentation approaches of Hyperspectral images (HSIs) use and require preprocessing steps in the form of patching to accurately classify diversified land cover in remotely sensed images. These approaches use patching to incorporate the rich neighborhood information in images and exploit the simplicity and segmentability of the most common HSI datasets. In contrast, most landmasses in the world consist of overlapping and diffused classes, making neighborhood information weaker than what is seen in common HSI datasets. To combat this issue and generalize the segmentation models to more complex and diverse HSI datasets, in this work, we propose our novel flagship model: Clustering Ensemble U-Net (CEU-Net). CEU-Net uses the ensemble method to combine spectral information extracted from convolutional neural network (CNN) training on a cluster of landscape pixels. Our CEU-Net model outperforms existing state-of-the-art HSI semantic segmentation methods and gets competitive performance with and without patching when compared to baseline models. We highlight CEU-Net's high performance across Botswana, KSC, and Salinas datasets compared to HybridSN and AeroRIT methods.