A Soft Computing Approach for Selecting and Combining Spectral Bands
This work addresses classification challenges in remote sensing for tropical biome analysis, but it is incremental as it applies an existing GP framework to a specific domain.
The authors tackled the problem of selecting and combining spectral bands from remote sensing images for classification tasks, using a Genetic-Programming approach to learn indices that maximize class separability, and showed it leads to superior results in discriminating tropical biomes compared to other indices.
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.