Deakin University
Browse

A robust rule-based ensemble framework using mean-shift segmentation for hyperspectral image classification

Download (3.67 MB)
Version 2 2024-06-04, 10:27
Version 1 2019-09-19, 08:16
journal contribution
posted on 2024-06-04, 10:27 authored by MS Roodposhti, A Lucieer, A Anees, Brett BryanBrett Bryan
This paper assesses the performance of DoTRules—a dictionary of trusted rules—as a supervised rule-based ensemble framework based on the mean-shift segmentation for hyperspectral image classification. The proposed ensemble framework consists of multiple rule sets with rules constructed based on different class frequencies and sequences of occurrences. Shannon entropy was derived for assessing the uncertainty of every rule and the subsequent filtering of unreliable rules. DoTRules is not only a transparent approach for image classification but also a tool to map rule uncertainty, where rule uncertainty assessment can be applied as an estimate of classification accuracy prior to image classification. In this research, the proposed image classification framework is implemented using three world reference hyperspectral image datasets. We found that the overall accuracy of classification using the proposed ensemble framework was superior to state-of-the-art ensemble algorithms, as well as two non-ensemble algorithms, at multiple training sample sizes. We believe DoTRules can be applied more generally to the classification of discrete data such as hyperspectral satellite imagery products.

History

Journal

Remote Sensing

Volume

11

Article number

ARTN 2057

Pagination

1 - 20

Location

Basel, Switzerland

Open access

  • Yes

eISSN

2072-4292

Language

English

Publication classification

C Journal article, C1 Refereed article in a scholarly journal

Issue

17

Publisher

MDPI