Robust automatic crater detection at all latitudes on Mars with deep-learning

Abstract

Understanding the distribution and characteristics of impact craters on planetary surfaces is essential for unraveling geological processes and the evolution of celestial bodies. Several machine learning and AI-based approaches have been proposed to detect craters on planetary surface images automatically. However, designing a robust tool for an entire complex planet such as Mars, is still an open problem. This article presents a novel approach using the Faster Region-based Convolutional Neural Network (Faster R-CNN) for such a detection. The proposed method involves the pre-processing, training and crater detection steps, which are especially designed for robustness regarding latitude and complex geomorphological features. The objectives of this studies are to (i) be robust at all latitudes and (ii) for $\ge 1$ km diameter crater sizes. (iii) To propose an open-source and re-usable algorithm that (iv) only needs an image to run. Extensive experiments on high-resolution planetary imagery demonstrate excellent performances with an average precision ${\text{AP}}_{50}>0.82$ with an intersection over union criterion $\text{IoU}\ge 0.5$, irrespective of crater scale. For mid and high latitudes (higher than 48°north and south), performance decreases down to ${\text{AP}}_{50}\sim 0.7$, which is still better than the current state of the art. Loss of performance is mostly due to strong shadowing effects. Our results also highlight the versatility and potential of our robust model for automating the analysis of craters across different celestial bodies. The automated crater detection tool presented in this article is publicly available as open-source and holds great promise for future scientific research of space exploration missions.