Synthetic Data for Robust Runway Detection
This work addresses the challenge of data scarcity and robustness in critical industrial applications, such as autonomous aircraft landing, by leveraging synthetic data generation, though it is incremental in its approach to domain adaptation.
The paper tackles the problem of training deep vision models for critical applications like runway detection in autonomous landing systems, where collecting and labeling real data for all conditions is costly and difficult. They propose using synthetic images from a flight simulator combined with a few real images and a customized domain adaptation strategy, achieving accurate predictions and demonstrating robustness to adverse conditions like nighttime images not present in the real data.
Deep vision models are now mature enough to be integrated in industrial and possibly critical applications such as autonomous navigation. Yet, data collection and labeling to train such models requires too much efforts and costs for a single company or product. This drawback is more significant in critical applications, where training data must include all possible conditions including rare scenarios. In this perspective, generating synthetic images is an appealing solution, since it allows a cheap yet reliable covering of all the conditions and environments, if the impact of the synthetic-to-real distribution shift is mitigated. In this article, we consider the case of runway detection that is a critical part in autonomous landing systems developed by aircraft manufacturers. We propose an image generation approach based on a commercial flight simulator that complements a few annotated real images. By controlling the image generation and the integration of real and synthetic data, we show that standard object detection models can achieve accurate prediction. We also evaluate their robustness with respect to adverse conditions, in our case nighttime images, that were not represented in the real data, and show the interest of using a customized domain adaptation strategy.