Recurrent Neural Networks to Correct Satellite Image Classification Maps

TL;DR

This paper introduces a recurrent neural network model that learns to iteratively refine satellite image classification maps, significantly improving their accuracy and boundary precision without manual tuning of enhancement algorithms.

Contribution

It proposes a novel RNN-based approach to directly learn the iterative enhancement process for satellite image classification maps, replacing traditional manual tuning methods.

Findings

RNN effectively learns an iterative refinement process

Significant improvement in classification map quality

Enhanced boundary accuracy in satellite images

Abstract

While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them good at recognizing but poor at localizing objects precisely. This problem is magnified in the context of aerial and satellite image labeling, where a spatially fine object outlining is of paramount importance. Different iterative enhancement algorithms have been presented in the literature to progressively improve the coarse CNN outputs, seeking to sharpen object boundaries around real image edges. However, one must carefully design, choose and tune such algorithms. Instead, our goal is to directly learn the iterative process itself. For this, we formulate a generic iterative enhancement process inspired from partial differential equations, and observe that it can be expressed as a recurrent neural network (RNN). Consequently, we train such a network from manually labeled data for our enhancement task. In a series of experiments we show that our RNN effectively learns an iterative process that significantly improves the quality of satellite image classification maps.