Vision-Language Model for Accurate Crater Detection

2026-01-12

AI Summary

This work addresses the challenge of high-precision crater detection in complex lunar surface environments characterized by varying illumination and rugged terrain. For the first time, the vision-language model OWLv2 is introduced to this task, leveraging a Vision Transformer architecture with parameter-efficient fine-tuning via Low-Rank Adaptation (LoRA). The approach jointly optimizes localization and semantic discrimination of craters across multiple scales and morphologies by integrating Complete IoU localization loss with contrastive classification loss. Evaluated on the high-resolution IMPACT dataset derived from Lunar Reconnaissance Orbiter (LRO) imagery, the proposed model achieves a maximum recall of 94.0% and a maximum precision of 73.1%, significantly enhancing robustness and generalization for crater detection in lunar landing scenarios.

Technology Category

• Computer Vision: Language and Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web search models and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• crater detection
• lunar landing
• vision-language model
• deep learning
• lunar imagery

Innovation

• Vision-Language Model
• Low-Rank Adaptation
• Complete IoU
• Parameter-Efficient Fine-Tuning
• Crater Detection