Vision-Language Model for Accurate Crater Detection

TL;DR

The paper presents a crater detection method tailored for lunar missions by fine-tuning the OWLv2 Vision Transformer with Low-Rank Adaptation (LoRA) using IMPACT-derived crater annotations. It couples $CIoU$-based localization with a contrastive loss anchored to the text embedding of the word 'crater', enabling open-world, cross-modal crater detection via Hungarian assignment. Results show strong recall (up to $94\%$) but moderate precision (up to $73\%$), highlighting robust crater detection across varying illumination and geometry while acknowledging GT incompleteness and labeling noise. The approach advances lunar exploration readiness by delivering a scalable, parameter-efficient detector that generalizes to diverse lunar terrains and lighting, with future work aimed at smaller craters and segmentation-based morphology.

Abstract

The European Space Agency (ESA), driven by its ambitions on planned lunar missions with the Argonaut lander, has a profound interest in reliable crater detection, since craters pose a risk to safe lunar landings. This task is usually addressed with automated crater detection algorithms (CDA) based on deep learning techniques. It is non-trivial due to the vast amount of craters of various sizes and shapes, as well as challenging conditions such as varying illumination and rugged terrain. Therefore, we propose a deep-learning CDA based on the OWLv2 model, which is built on a Vision Transformer, that has proven highly effective in various computer vision tasks. For fine-tuning, we utilize a manually labeled dataset fom the IMPACT project, that provides crater annotations on high-resolution Lunar Reconnaissance Orbiter Camera Calibrated Data Record images. We insert trainable parameters using a parameter-efficient fine-tuning strategy with Low-Rank Adaptation, and optimize a combined loss function consisting of Complete Intersection over Union (CIoU) for localization and a contrastive loss for classification. We achieve satisfactory visual results, along with a maximum recall of 94.0% and a maximum precision of 73.1% on a test dataset from IMPACT. Our method achieves reliable crater detection across challenging lunar imaging conditions, paving the way for robust crater analysis in future lunar exploration.

Figures (7)

• Figure 1: Examples of craters for the few-shot crater detection approach.
• Figure 2: Schematic overview of the proposed crater detection method: Calibrated Data Record (CDR) images are processed by the OWLv2 Vision Transformer (ViT), where trainable LoRA parameters are inserted into the encoder. Simultaneously, the word "crater" is encoded by the frozen text Transformer and used as an anchor in the shared embedding space. The Box Head minimizes a CIoU-based loss between predicted boxes and ground truth, while the Class Head applies a contrastive loss to separate crater from non-crater embeddings utilizing the anchor vector, by adding LoRA parameters into both heads for efficient fine-tuning.
• Figure 3: Examples of poorly annotated images. Each column: top: original $2048\times 2048$ image with a yellow rectangle marking the zoomed region; bottom: cropped zoom corresponding to that rectangle. Red circles show annotated ground-truth craters.
• Figure 4: Each column: (top) Original $2048\times 2048$ image with a yellow rectangle indicating the zoomed region. (bottom) Cropped and zoomed-in region corresponding to the yellow rectangle above. The red circles indicate the annotated ground truth craters.
• Figure 5: Qualitative results on CDR images unseen during both training and validation, selected randomly. Each row consists of three tiles of size $512 \times 512$. First row: M1369716293R, second row: M1310840621L, third row: M1501897277L, fourth row: M1496678308R. Despite varying image conditions, such as incidence angles ranging from 40.2 to 85.1 degrees, an overall sufficient detection quality is achieved. In the fourth row, especially for larger craters, the bounding boxes often capture only the shadowed part of the crater, that also appear circular. Under these illumination conditions, however, even for human observers the crater contours are difficult to extract.