Runway Extraction and Improved Mapping from Space Imagery

TL;DR

This paper explores using GAN architectures for reversible translation between satellite imagery and runway maps, improving change detection, boundary emphasis, and automated map updating for disaster relief and urban planning.

Contribution

It demonstrates the effectiveness of Pix2Pix and CycleGAN architectures for runway map generation and introduces a novel sketch-to-satellite style transfer approach.

Findings

CycleGAN can generate effective runway maps without paired data.

Higher contrast palettes improve boundary clarity in generated maps.

Automated updates correct faulty runway maps based on GAN outputs.

Abstract

Change detection methods applied to monitoring key infrastructure like airport runways represent an important capability for disaster relief and urban planning. The present work identifies two generative adversarial networks (GAN) architectures that translate reversibly between plausible runway maps and satellite imagery. We illustrate the training capability using paired images (satellite-map) from the same point of view and using the Pix2Pix architecture or conditional GANs. In the absence of available pairs, we likewise show that CycleGAN architectures with four network heads (discriminator-generator pairs) can also provide effective style transfer from raw image pixels to outline or feature maps. To emphasize the runway and tarmac boundaries, we experimentally show that the traditional grey-tan map palette is not a required training input but can be augmented by higher contrast mapping palettes (red-black) for sharper runway boundaries. We preview a potentially novel use case (called "sketch2satellite") where a human roughly draws the current runway boundaries and automates the machine output of plausible satellite images. Finally, we identify examples of faulty runway maps where the published satellite and mapped runways disagree but an automated update renders the correct map using GANs.