A Concise Tiling Strategy for Preserving Spatial Context in Earth Observation Imagery

TL;DR

The paper introduces Flip-n-Slide, a novel tiling strategy for Earth observation imagery that enhances spatial context preservation and improves semantic segmentation performance, especially for underrepresented classes.

Contribution

Flip-n-Slide is a minimalistic tiling approach that creates multiple spatial views without redundancy, improving model generalization in satellite image analysis.

Findings

Outperforms previous augmentation methods across all metrics.

Increases precision for underrepresented classes by up to 15.8%.

Enhances spatial context preservation in tiling strategies.

Abstract

We propose a new tiling strategy, Flip-n-Slide, which has been developed for specific use with large Earth observation satellite images when the location of objects-of-interest (OoI) is unknown and spatial context can be necessary for class disambiguation. Flip-n-Slide is a concise and minimalistic approach that allows OoI to be represented at multiple tile positions and orientations. This strategy introduces multiple views of spatio-contextual information, without introducing redundancies into the training set. By maintaining distinct transformation permutations for each tile overlap, we enhance the generalizability of the training set without misrepresenting the true data distribution. Our experiments validate the effectiveness of Flip-n-Slide in the task of semantic segmentation, a necessary data product in geophysical studies. We find that Flip-n-Slide outperforms the previous state-of-the-art augmentation routines for tiled data in all evaluation metrics. For underrepresented classes, Flip-n-Slide increases precision by as much as 15.8%.