A Soft Computing Approach for Selecting and Combining Spectral Bands

TL;DR

This paper presents a soft computing method using genetic programming to automatically select and combine spectral indices from multispectral images, improving classification of tropical biomes.

Contribution

It introduces a novel GP-based framework for optimizing spectral indices for remote sensing classification tasks, outperforming traditional indices.

Findings

GP-derived indices improve classification accuracy

Superior discrimination of tropical vegetation types

Time series analysis enhances classification results

Abstract

We introduce a soft computing approach for automatically selecting and combining indices from remote sensing multispectral images that can be used for classification tasks. The proposed approach is based on a Genetic-Programming (GP) framework, a technique successfully used in a wide variety of optimization problems. Through GP, it is possible to learn indices that maximize the separability of samples from two different classes. Once the indices specialized for all the pairs of classes are obtained, they are used in pixelwise classification tasks. We used the GP-based solution to evaluate complex classification problems, such as those that are related to the discrimination of vegetation types within and between tropical biomes. Using time series defined in terms of the learned spectral indices, we show that the GP framework leads to superior results than other indices that are used to discriminate and classify tropical biomes.