VAD4Space: Visual Anomaly Detection for Planetary Surface Imagery

2026-03-14

AI Summary

This work addresses the challenge of detecting rare geological phenomena in planetary surface imagery, where scarcity of labeled data hinders conventional supervised approaches. To this end, we propose an open-world perception framework based on visual anomaly detection (VAD) that automatically identifies anomalous features in lunar and Martian images without requiring extensive annotations. We present the first systematic evaluation of feature-driven VAD methods on real planetary imagery, introduce two publicly available benchmark datasets tailored to the Moon and Mars, and develop a lightweight, computationally efficient edge-adaptation algorithm suitable for resource-constrained orbiter and rover platforms. Experimental results demonstrate the effectiveness of our approach in identifying rare geomorphological features such as fresh impact craters, offering practical support for landing site selection, hazard avoidance, prioritized data downlink, and the discovery of novel geological processes.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Space missions generate massive volumes of high-resolution orbital and surface imagery that far exceed the capacity for manual inspection. Detecting rare phenomena is scientifically critical, yet traditional supervised learning struggles due to scarce labeled examples and closed-world assumptions that prevent discovery of genuinely novel observations. In this work, we investigate Visual Anomaly Detection (VAD) as a framework for automated discovery in planetary exploration. We present the first empirical evaluation of state-of-the-art feature-based VAD methods on real planetary imagery, encompassing both orbital lunar data and Mars rover surface imagery. To support this evaluation, we introduce two benchmarks: (i) a lunar dataset derived from Lunar Reconnaissance Orbiter Camera Narrow Angle imagery, comprising of fresh and degraded craters as anomalies alongside normal terrain; and (ii) a Mars surface dataset designed to reflect the characteristics of rover-acquired imagery. We evaluate multiple VAD approaches with a focus on computationally efficient, edge-oriented solutions suitable for onboard deployment, applicable to both orbital platforms surveying the lunar surface and surface rovers operating on Mars. Our results demonstrate that feature-based VAD methods can effectively identify rare planetary surface phenomena while remaining feasible for resource-constrained environments. By grounding anomaly detection in planetary science, this work establishes practical benchmarks and highlights the potential of open-world perception systems to support a range of mission-critical applications, including tactical planning, landing site selection, hazard detection, bandwidth-aware data prioritization, and the discovery of unanticipated geological processes.

Problem

• Visual Anomaly Detection
• Planetary Surface Imagery
• Rare Phenomena Discovery
• Open-World Perception
• Space Mission Automation

Innovation

• Visual Anomaly Detection
• Planetary Surface Imagery
• Feature-based VAD
• Onboard Deployment
• Open-world Perception